DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement(s)
The Information Disclosure Statement filed on July 06th, 2026 has been acknowledged and considered.
Response to Remark(s)
Applicant's amendment filed July 29th, 2026 have been fully entered and considered. Regarding the claim objection, the amendment has overcome some objection except for claim 10, see claim objection section below; the amendment has overcome each and every drawing objection and 112(b) rejection; regarding the 101 and the prior art rejections, the examiner respectfully finds the Applicants’ arguments to be non-persuasive; regarding the prior art rejection, the amendment has narrowed down the scope of the claims, new grounds of rejections were necessitated by the amendment, though the Applicants’ arguments are found to be some non-persuasive. Accordingly, this action is made final.
Status of Claims
Claims 1-20 are pending, claims 1 and 6-15 have been amended, claims 16-20 have been added. Claims 1-20 remains rejected.
Response to Argument(s)
Regarding the Abstract objection, the abstract should be written in single paragraph, currently the abstract is written in two different indentations with an extra line of indentation indicating a figure:
PNG
media_image1.png
300
720
media_image1.png
Greyscale
Therefore, the second indentation stating, “Figure 6.” should be removed.
Regarding the claim objection, for claim 10, as previously suggested by the examiner, the reference “the calculation step is based” should be read as “the calculating step is based” to follow proper antecedent basis, since there is no first instantiation of “a calculation step”, nevertheless. See claim objection below for more details.
Regarding the 101 rejection:
In pages 9-11 of the Applicants’ remarks, the Applicants argue that the claimed invention of the independent claim 1 has recitation that are integrated into a practical application providing a technical improvement to video processing hardware architectures, under Step 2A Prong 2. Specifically, the specification details a technical problem in computer vision: the computational cost and content dependency of conventional video event extraction models that rely on heavy machine learning parameters or semantic scene segmentation, see Pars. Par. [0002-0003] and Par. [0025-0026], and claim 1 provides the solution by executing a low-overhead statistical evaluation on the mathematical changes between successive optical flow vector fields. This sequence of operations allows the video evaluation system to derive an objective, content-agnostic metric for visual smoothness in real time. By evaluating these vector deltas, the system eliminates the need to maintain intensive deep learning layers or segment an entire scene, which minimizes process utilization and reduces memory allocations.
Under Step 2B, the Applicants state that the recited inventive concept amounts to significantly more than any alleged abstract idea. the combination of generating optical flow vectors, calculating a specific mathematical difference between corresponding optical flow vectors across successive frame pairs, and evaluating those resulting differences against a predetermined criterion to isolate frames for further processing is not conventional, generic or routine in the computing art.
The Applicants mentioned cases of Research Corp. Techs. V. Microsoft Corp. to indicate the similarity of the claimed invention to the cased that both require the manipulation of computer data structures and the output of a modified computer data structure, and as such, the recitations of claim 1 do not recite mental processes; and the PTAB decision on Ex parte Carmody that mathematical or computational models are patent eligible when integrated into a specific technological process that improves the internal operation of a machine or system resource utilization.
Examiner’s reply:
The examiner respectfully disagrees with the Applicants’ arguments, and find them to be incommensurate with the scope of the claims. The Applicants are reminded that the claims are construed based on BRI (broadest reasonable interpretation) in light of the specification. Therefore, bringing in teachings of the specification to state them to be the scope of the claim is not consistent with the claim language, the alleged technical problem and solution are currently not reflected in the amended claims. The disclosure cannot be imported to be the scope of the claim; the claim is construed based on its own language under BRI as the requirement of the 101 analysis. Therefore, the examiner respectfully finds the Applicants’ arguments to be incommensurate with the scope of the claims, particularly, nowhere in the claim recites a low-overhead statistical evaluation of mathematical changes between successive optical flow vector fields, the claims, such as the independent claim 1, merely recite an evaluating step but not provide further specifying a low-overhead statistical evaluation, neither the claim recites any deep learning or deep learning layer. Nevertheless, the claim concluded with “evaluating the differences with respect to a predetermined criterion to identify respective frame pairs for further processing”, merely a recitation of a nominal “evaluating” of some data/information, not manipulating data to a particular practical use/application. The Applicants further asserted that the claims, include process involves statistical evaluation of mathematical changes, indicating computations, mathematical operations, hence, mere abstract ideas.
The Applicants are reminded that obtaining data/values from other data/values is not necessarily data manipulation for a practical application, but mere extra solution activity of data gathering, data converting, as result of mathematical operations.
In regard to the mentioned relevant case and PTAB decision, the claims are examined based on case-by-case basis, and that the claimed invention is different to the cases mentioned. The currently amended claims do not involve data manipulation or modifying data structure for a practical application. Furthermore, there is no specific practical application in the claim, the claims involve steps of mere abstract ideas that the human mind can also perform using pen and paper through observing data/information according to some general condition to be met. See the 101 rejections section below for more details.
Therefore, the 101 rejections still remain.
Regarding the Prior Art rejections:
The amendment has added new features into the claims and changed the scope of the claims such as, in each of the independent claims 1 and 12-13, previously recited “the resulting differences” now has been amended to be “the difference”, wherein the previously recited “the resulting differences” didn’t provide proper antecedent basis to a particular reference, now the newly amended “the difference” give antecedent basis to the preceding “a difference” in the claims hence, has introduced a narrower scope to the claims; a new ground of rejections is set forth below, see 103 rejection section below for more details.
However, regarding the Applicants’ remarks regarding the teaching of the maintained limitations and the proposed prior art, the examiner respectfully finds them to be non-persuasive and incommensurate with the scope of the claim as explained in the following discussion.
Particularly In pages 12-13 of the Applicants remarks, the Applicants argue that the proposed Tao does not teach or suggest the features of the claims:
“calculating a difference between corresponding optical flow vectors of successive frame pairs”
In support of the above argument, the Applicants state that Tao calculates the difference between images, but does not calculate the difference between optical flow vectors. For example, Taos’ differential image D_k is based on differences between a current image and affine-transformation of adjacent images, and is subsequentially binarized using an image-difference threshold, see Tao’s p. 2, equation 2.
Additionally, Tao estimates an individual optical flow vector but does not compare it with another optical flow vector, Tao uses the optical flow vector to predict a position, not to calculate a vector difference.
Even assuming that Tao is independently repeating its optical flow estimation for multiple consecutive frame pairs, the generation of multiple optical flow vectors does not disclose or suggest calculating a difference between the vectors.
Examiner’s reply:
The examiner respectfully disagrees with the Applicants’ arguments. The examiner finds the Applicants’ arguments to be inconstant, moreover, the Applicants stated that Tao calculate the difference between images, but not being found an optical flow vector difference? The examiner recognizes, in the translation of To, in Page 5, of last Par. to Page 6, disclose “different image registration algorithms…sparse optical flow is used to match the image feature points…through optical flow or sobel operator image matching, and finally using RANSAC to estimate the affine transformation between the two images” in page 5, and “Dk represents the differential image, S’k-1 and S’k+1 are the results of the affine transformation of the current frame and the next frame, Sk is the current frame image” in page 6; moreover, in Page 7, it discloses “for all the targets obtained from the first frame difference, it is predicted by optical flow that it is in the next frame”; Wherein, the difference image is obtained by finding the difference between the current frame and the next frame according to the formula of page 2 and page 7:
PNG
media_image2.png
200
916
media_image2.png
Greyscale
Page 2
PNG
media_image3.png
182
912
media_image3.png
Greyscale
Page 7
Therefore, the optical flow of a frame difference, is concerning of optical flow predicted with the difference between frames, which covers the scope of the claimed limitation of calculating the difference between optical flow vectors of two frames. Wherein Tao’s optical flow vector used to predict that the targets in a frame difference is in the next frame is the optical flow calculated for the frame difference, therefore, the optical flow itself represents the information about difference between frames of the difference in optical flow vectors between frames.
Therefore, since Tao estimate the difference between frames and use the difference to obtain the associated optical flow for the frame difference, the optical flow being associated is the optical flow difference between the two frames.
Therefore, the prior art rejections still remain.
Specification
Applicant is reminded of the proper content of an abstract of the disclosure.
Extensive mechanical and design details of an apparatus should not be included in the abstract. The abstract should be in narrative form and generally limited to a single paragraph.
As discussed above in the Response to Argument section, the second indentation stating, “figure 6.” Should be removed from the Abstract.
See MPEP § 608.01(b) for guidelines for the preparation of patent abstracts.
Claim Objections
Claims 10 and 17-19 are objected to because of the following informalities:
Claim 10, in line 1 of claim 10, “the calculation step is based” should be read as “the calculating step is based” to follow proper antecedent basis, since there is no first instantiation of “a calculation step”. Appropriate correction is required to avoid 112(b) antecedent basis issue.
Claim 17, in line 2 of claim 17, “M identified frame pairs” should be given a meaning/definition to what M stands for, can be read as “M number of identified frame pairs” to indicate that M to be defined as a number of frames. Appropriate correction is required to avoid 112b indefiniteness issue with unclear scope and definition of a term;
Claim 18, in line 2 of claim 18, the reference “associate these with identified frame pairs for recording” should be read as “associate the identified video frame [[these]] with the [[identified]] successive frame pairs for recording” to follow proper antecedent basis. Appropriate correction is required to avoid 112(b) antecedent basis issue.
Claim 18, lines 3-4 of claim 18, the reference “within the frame sequence” should be read as “withinthe video including successive video frames” since there is no prior instantiation of “a frame sequence” for this antecedent referencing to be proper. Appropriate correction is required to avoid 112(b) antecedent basis issue.
Claim 19, line 2 of claim 19, the reference “the subset of corresponding pixels” should be read as “a subset of corresponding pixels” since there is prior instantiation of such reference. Appropriate correction is required to avoid 112(b) antecedent basis issue.
Claim 19, line 4 of claim 19, the reference “the subset of corresponding pixels” should be read as “a subset of corresponding pixels” since there is prior instantiation of such reference. Appropriate correction is required to avoid 112(b) antecedent basis issue.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more nor an integration of the judicial exceptions into a practical application. The limitations, under their broadest reasonable interpretation, cover mental process/mathematical operation (concept performed in a human mind, including as observation, evaluation, judgment, opinion). The claimed invention simply perform video evaluation based on observable data/information such as optical flow corresponding to the pixels in the images, and difference between the flow vectors to identify pairs of frames. See analysis below for more details.
Regarding Independent Claim 1 and its dependent claims 2-11,
Step 1 Analysis: Claim 1 is directed to a method/process, which falls within one of the four statutory categories (process, machine, manufacture or composition of matter). Please see MPEP §2106.04.
Step 2A Prong 1 Analysis: Claim 1 recites, in part:
“calculating a difference between corresponding optical flow vectors of successive frame pairs; and
evaluating the difference with respect to a predetermined criterion, to identify respective frame pairs for further processing.”
The limitations as drafted, are processes that, under broadest reasonable interpretation, covers the performance of the limitation in the mind which falls within the “Mental Processes/Mathematical Concept” grouping of abstract ideas. Please see MPEP §2106.04. The limitations of:
“evaluating the resulting differences with respect to a predetermined criterion, to identify respective frame pairs for further processing” is a step a human mind can perform, under BRI, using pen and paper through a process of observation and evaluation such as, the human mind can observe some data/information (images, video, already given or resulted outcome/output of data/information, etc.) and evaluate them to make an evaluation.
“calculating a difference between corresponding optical flow vectors of successive frame pairs” is a step of mathematical operation using mathematical calculation.
Notes: under MPEP 2106.04(a)(2)(III), mental process (thinking) “can be performed in the human mind, or by a human using a pen and paper" to be an abstract idea. CyberSource Corp. v. Retail Decisions, Inc., 654 F.3d 1366, 1372, 99 USPQ2d 1690, 1695 (Fed. Cir. 2011): "methods which can be performed mentally, or which are the equivalent of human mental work, are unpatentable abstract ideas the ‘basic tools of scientific and technological work’ that are open to all." (citing Gottschalk v. Benson, 409 U.S. 63, 175 USPQ 673 [1972]). See also Mayo Collaborative Servs. v. Prometheus Labs. Inc., 566 U.S. 66, 71, 101 USPQ2d 1961, 1965 ("mental processes and abstract intellectual concepts are not patentable, as they are the basic tools of scientific and technological work’" (quoting Benson, 409 U.S. at 67, 175 USPQ at 675).
The courts do not distinguish between mental processes that are performed entirely in the human mind and mental processes that require a human to use a physical aid (e.g., pen and paper or a slide rule) to perform the claim limitation. See, e.g., Benson, 409 U.S. at 67, 65, 175 USPQ at 674-75, 674; Synopsys, Inc. v. Mentor Graphics Corp., 839 F.3d 1138, 1139, 120 USPQ2d 1473, 1474 (Fed. Cir. 2016).
Nor do the courts distinguish between claims that recite mental processes performed by humans and claims that recite mental processes performed on a computer, generic circuit or device, or the likes. See " Versata Dev. Group v. SAP Am., Inc., 793 F.3d 1306, 1335, 115 USPQ2d 1681, 1702 (Fed. Cir. 2015). See also Intellectual Ventures I LLC v. Symantec Corp., 838 F.3d 1307, 1318, 120 USPQ2d 1353, 1360 (Fed. Cir. 2016) (‘with the exception of generic computer-implemented steps, there is nothing in the claims themselves that foreclose them from being performed by a human, mentally or with pen and paper.’’).
Because both product/device and process claims may recite a "mental process", the phrase "mental processes" should be understood as referring to the type of abstract idea, and not to the statutory category of the claim. The courts have identified numerous product claims as reciting mental process-type abstract ideas, for instance the product claims to computer systems and computer-readable media in Versata Dev. Group. v. SAP Am., Inc., 793 F.3d 1306, 115 USPQ2d 1681 (Fed. Cir. 2015).
Accordingly, the claim recites an abstract idea.
Step 2A Prong 2 Analysis: This judicial exception is not integrated into a practical application. particular, the claim recites the following additional element(s) –
“generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames”
The additional elements include steps of insignificant extra-solution/post-solution activities of data gathering, data generating, data transmitting, etc. [acquiring data/information, transmitting data/info., outputting data/information, displaying data/info., converting data/info., generating data/info., etc.] .
Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. The claim as a whole is directed to an abstract idea. Please see MPEP §2106.04.(d).III.C.
Step 2B Analysis: there are no additional elements, such as for these additional elements as indicated above, that amount to significantly more than the judicial exception. Please see MPEP §2106.05. The claim is directed to an abstract idea. Please see MPEP §2106.05
For all of the foregoing reasons, claim 1 does not comply with the requirements of 35 USC 101.
Accordingly, the dependent claims 2-11 do not provide elements that overcome the deficiencies of the independent claim 1.
Moreover, claims 2-5 and 8-11, each recites, in part, wherein clauses of simply giving further specification of what the at least subset of pixels samples for claims 2-3, and what the predetermined criterion comprises for claims 4-5, hence, still the category of the limitation is further specify hence, being abstract ideas and additional element as analyzed above in claim 1. And what the subset of corresponding pixels conforms to a region of for claims 8-9, further specifying the generating step of claim 1 hence, still insignificant extra-solution activity additional element and what the calculation step is based on for claim 10 hence still mathematical operation abstract idea, these limitations are recited without further limiting the steps to be more than abstract ideas or insignificant additional element.
Claim 6 recites, in part:
“identifying a contiguous sequence of a predetermined number of identified frame pairs for recording”
Which is a mental process activity abstract idea of observation and evaluation, judgement, merely performing identifying of some observable data/information.
Claim 7 recites, in part:
“identifying video frames with a threshold level of activity and associate with identified pairs for recording, if within a predetermined distance of each other within the frame sequence”
Which is a mental process activity abstract idea of observation and evaluation, judgement, merely performing identifying of some observable data/information according to some observable criterion/condition.
Accordingly, the dependent claims 2-11 are not patent eligible under 101.
Regarding independent claim 12:
The independent claim 12 recites analogous limitations to the independent claim 1, hence, is rejected under 101 for the same reason. Moreover, claim 12 recites further some additional element features such as “a non-transitory computer readable storage medium,” “a computer executable instructions that when executed by a computer system,” “cause the computer system to perform a method of video evaluation” which are generic computer and computer component recited at high level of generality to perform generic functions, such as computer including a processor to execute the invention’s instructions hence, not indicative of an integration of the judicial exceptions into a practical application nor, being considered significantly more.
Regarding independent claim 13 and its dependent claims 14-20:
The independent claim 13 recites analogous limitations to the independent claim 1, hence, is rejected under 101 for the same reason. Moreover, claim 12 recites further some additional element features such as “an entertainment system,” “a video evaluation processor” which are generic computer and computer component recited at high level of generality to perform generic functions, hence, not indicative of an integration of the judicial exceptions into a practical application nor, being considered significantly more.
The dependent claims 14-20 recited merely further specification to what the at least subset of pixels sample, hence, still just part of the step of generating of the limitation it depends on in claim 13, hence, still part of insignificant extra-solution activity of data gathering. Moreover, the claim 18 recites an identifying step which a human mind can also perform using pen and paper by observing some already processed, specified data/information or some observable image to make an evaluation to identify some outcome based on certain observable condition, claim 19 recites a further specification limitation to further specify the data/information hence, still merely data gathering process, claim 20 recites a mathematical operation.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-2, 6-14, 16-17 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Yang Tao et. al. (foreign patent document “CN 106887010 A” hereinafter as “Tao”, mapping is based on the numbers of the translation section) in view of William L. Gaddy et. al., (“US 2012/0008051 A1” hereinafter as “Gaddy”).
Regarding claim 1, Tao teaches a method comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs (Page 2 discloses the optical flow motion vector estimation for the current frame on small pixel motion [a subset of corresponding pixels] between image frames [according to page 3]; wherein the optical flow motion vector is calculated for each frame, hence, indicating a generation of a plurality of optical flow vectors such as disclosed further in page 5) of a video including successive video frames (Page 2 discloses “in continuous video, assuming that the object corresponding to the pixel gray value does not change due to exercise”); calculating a difference between corresponding optical flow vectors of successive frame pairs (Page 6 discloses using the optical flow vector result to calculate the difference between the current frame and the next frame [successive frame pair], since the processing is done for a video, it indicates the same processing is done for a plurality of successive frame pairs according to page 6; since Tao estimate the difference between frames and use the difference to obtain the associated optical flow for the frame difference, the optical flow being associated is the optical flow difference between the two frames according to Page 2 and Page 7); and evaluating the result with respect to a predetermined criterion (Page 6 discloses comparing the difference resulted from the different of optical flow vectors between the current frame to the next frame, the comparing is to a threshold [a predetermined criterion as claimed]; since Tao estimate the difference between frames and use the difference to obtain the associated optical flow for the frame difference, the optical flow being associated is the optical flow difference between the two frames according to Page 2 and Page 7) to identify respective frame pairs for further processing (Page 6 discloses the processing, as have been discussed, is to result in the affine transformation of the current frame and the next frame, which is used for further processing such as for location prediction).
However, Tao does not explicitly teach evaluating the difference.
Gaddy teaches evaluating the difference (Par. [0060] discloses “directional differences between optical flow vectors from frame-to-frame”; moreover, Par. [0019] discloses “a per-pixel optical flow field is calculated between a current frame and a previous frame…the previous frame towards is motion compensated toward the current frame with the calculated current optical flow field to produce motion compensated image” wherein the motion compensated image is analogous to Tao’s difference image being optical flow associated, wherein the difference image is calculated based on the difference in optical flow vectors between two frames).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao of a method comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Gaddy of having evaluating the difference.
Wherein having Tao’s method of having evaluating the difference.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve object detection by block matching enabling accurate detection and ensuring of precision and refinement for shot change detection. Since both Tao and Gaddy perform object detection based on optical flow analysis. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Gaddy’s system improves performs image misalignment determination and compensation based on the use of pairwise operation that can register images accurately to improve quality of image mosaics, (see Gaddy’s Par. [0068]).
Regarding claim 2, Tao in view of Gaddy teach the method of claim 1, Tao teaches wherein: the at least subset of pixels samples at least a predetermined area of interest in each frame pair (Page 2 discloses the optical flow motion vector estimation for the current frame on small pixel motion [a subset of corresponding pixels] between image frames [according to page 3]; wherein the optical flow motion vector is calculated for each frame, hence, indicating a generation of a plurality of optical flow vectors such as disclosed further in page 5; wherein the small pixel motion is of a particular area of the object in the image [a predetermined area of interest as claimed]).
Regarding claim 6, Tao in view of Gaddy teach the method of claim 1, Tao teaches further comprising: identifying a contiguous sequence of a predetermined number of identified frame pairs for recording (Page 7 discloses the prediction is based on that two frames share matching points that a number of points belonging to a common target; moreover, the frames of this sharing must be adjacent to each other [contiguous], two frames indicating a sequence of frames, a predetermined number of frames of 2).
Regarding claim 7, Tao in view of Gaddy teach the method of claim 1, Tao teaches further comprising: identifying video frames with a threshold level of activity (Page 8 discloses that the number of target association set between two frames must meet a certain threshold [analogous to the recited “threshold level of activity”] for the association [analogous to the step of identifying]) and associate these with identified frame pairs for recording (Page 8 discloses the association setting which indicates associate these two frames as being an association set for the processing [indicating a storing of the output into a memory which is analogous to the recited recording]), if within a predetermined distance of each other within the frame sequence (Page 8 discloses step 3 for motion detection based on high-level information which are matched based on shortest distance [predetermined distance threshold of feature points between frames] which is part of the optical flow association step of page 6 to page 8 as have been discussed).
Regarding claim 8, Tao in view of Gaddy teach the method of claim 1, Tao teaches wherein the subset of corresponding pixels between frame pairs conforms to a region to which one or more objects of interest are to be constrained (Page 2 discloses the optical flow motion vector estimation for the current frame on small pixel motion [a subset of corresponding pixels] between image frames [according to page 3]; wherein the optical flow motion vector is calculated for each frame, hence, indicating a generation of a plurality of optical flow vectors such as disclosed further in page 5; wherein the optical flow motion vector is calculated for each frame, hence, indicating a generation of a plurality of optical flow vectors such as disclosed further in page 5; wherein the small pixel motion is of a particular area of the object in the image [a predetermined area of interest as claimed] therefore, indicating that a region to the object is constrained to only the region between frames that include the object target).
Regarding claim 9, Tao in view of Gaddy teach the method of claim 1, Tao teaches wherein the subset of corresponding pixels between frame pairs conforms to a region outside which an one or more unwanted objects are to be constrained (Page 8 discloses the motion detection process uses Samson’s confidence K method to judge inside and outside points by calculating the matching correction amount, this is done by calculating an outer point matrix for the points outside points of each candidate to make correction if it’s a target object or not [analogous to conforms to a region outside which objects should be normally constrained]).
Regarding claim 10, Tao in view of Gaddy teach the method of claim 1, Tao teaches wherein the calculation step is based on only a subset of directional components of the generated optical flow vectors (The calculation of the difference between the corresponding optical flow vectors, as discussed above in claim 1 being taught in Tao’s page 6; moreover, Tao teaches that the calculation of its optical flow vector association [association between frames which is based on the difference calculation] is based on direction of the gradient according to page 2 and page 6 [analogous to the recited directional components of the optical flow vectors] which only the equation 22 is based on the direction of the gradient as its variables and parameters).
Regarding claim 11, Tao in view of Gaddy teach the method of claim 10, Tao teaches wherein the subset of directional components includes different directional components in different regions of the frame (there is instances that the subset of directional components does not comprise the recited different directional components in different regions of the frame hence, has no patent weight; however, Tao still teaches this feature, in page, wherein the corresponding direction of the optical flow size include u and v components indicating two different direction of the vector in two different regions of the image).
Regarding claim 12, Tao teaches a non-transitory, computer readable storage medium c comprising computer executable instructions that when executed by a processor, cause the processor (page 1, “background technique” section, discloses the invention is for computer vision, which indicates the use of a computer which includes a non-transitory computer readable storage medium such as a RAM or ROM to contain computer program to be executed by the system of the computer to perform the steps of the invention; further disclosed the preamble in Tao’s title and abstract) to: generate optical flow vectors for at least a subset of corresponding pixels between frame pairs (page 2 discloses the optical flow motion vector estimation for the current frame on small pixel motion [a subset of corresponding pixels] between image frames [according to page 3]; wherein the optical flow motion vector is calculated for each frame, hence, indicating a generation of a plurality of optical flow vectors such as disclosed further in page 5) of a video including successive video frame (Page 2 discloses “in continuous video, assuming that the object corresponding to the pixel gray value does not change due to exercise”); calculate a difference between corresponding optical flow vectors of successive frame pairs (page 6 discloses using the optical flow vector result to calculate the difference between the current frame and the next frame [successive frame pair], since the processing is done for a video, it indicates the same processing is done for a plurality of successive frame pairs according to page 6; since Tao estimate the difference between frames and use the difference to obtain the associated optical flow for the frame difference, the optical flow being associated is the optical flow difference between the two frames according to Page 2 and Page 7); and evaluate the result with respect to a predetermined criterion (page 6 discloses comparing the difference resulted from the different of optical flow vectors between the current frame to the next frame, the comparing is to a threshold [a predetermined criterion as claimed]; since Tao estimate the difference between frames and use the difference to obtain the associated optical flow for the frame difference, the optical flow being associated is the optical flow difference between the two frames according to Page 2 and Page 7), to identify respective frame pairs for further processing (page 6 discloses the processing, as have been discussed, is to result in the affine transformation of the current frame and the next frame, which is used for further processing such as for location prediction).
However, Tao does not explicitly teach to evaluate the difference.
Gaddy teaches to evaluate the difference (Par. [0060] discloses “directional differences between optical flow vectors from frame-to-frame”; moreover, Par. [0019] discloses “a per-pixel optical flow field is calculated between a current frame and a previous frame…the previous frame towards is motion compensated toward the current frame with the calculated current optical flow field to produce motion compensated image” wherein the motion compensated image is analogous to Tao’s difference image being optical flow associated, wherein the difference image is calculated based on the difference in optical flow vectors between two frames).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao of a system comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Gaddy of having to evaluate the difference.
Wherein having Tao’s system of having to evaluate the difference.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve object detection by block matching enabling accurate detection and ensuring of precision and refinement for shot change detection. Since both Tao and Gaddy perform object detection based on optical flow analysis. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Gaddy’s system improves performs image misalignment determination and compensation based on the use of pairwise operation that can register images accurately to improve quality of image mosaics, (see Gaddy’s Par. [0068]).
Regarding claim 13, Tao teaches a system comprising (page 1, “background technique” section, discloses the invention is for computer vision, which indicates the use of a computer which includes a non-transitory computer readable storage medium such as a RAM or ROM to contain computer program to be executed by the system of the computer to perform the steps of the invention; further disclosed the preamble in Tao’s title and abstract): a processor adapted to: generate optical flow vectors for at least a subset of corresponding pixels between frame pairs (page 2 discloses the optical flow motion vector estimation for the current frame on small pixel motion [a subset of corresponding pixels] between image frames [according to page 3]; wherein the optical flow motion vector is calculated for each frame, hence, indicating a generation of a plurality of optical flow vectors such as disclosed further in page 5) of a video including successive video frames (Page 2 discloses “in continuous video, assuming that the object corresponding to the pixel gray value does not change due to exercise”); calculate a difference between corresponding optical flow vectors of successive frame pairs (page 6, whole page of the translation, discloses using the optical flow vector result to calculate the difference between the current frame and the next frame [successive frame pair], since the processing is done for a video, it indicates the same processing is done for a plurality of successive frame pairs according to page 6; since Tao estimate the difference between frames and use the difference to obtain the associated optical flow for the frame difference, the optical flow being associated is the optical flow difference between the two frames according to Page 2, whole page of the translation and Page 7, whole page of the translation); and evaluate the result with respect to a predetermined criterion (page 6 discloses comparing the difference resulted from the different of optical flow vectors between the current frame to the next frame, the comparing is to a threshold [a predetermined criterion as claimed]; since Tao estimate the difference between frames and use the difference to obtain the associated optical flow for the frame difference, the optical flow being associated is the optical flow difference between the two frames according to Page 2 and Page 7), to identify respective frame pairs for further processing (page 6 discloses the processing, as have been discussed, is to result in the affine transformation of the current frame and the next frame, which is used for further processing such as for location prediction).
However, Tao does not explicitly teach to evaluate the difference.
Gaddy teaches to evaluate the difference (Par. [0060] discloses “directional differences between optical flow vectors from frame-to-frame”; moreover, Par. [0019] discloses “a per-pixel optical flow field is calculated between a current frame and a previous frame…the previous frame towards is motion compensated toward the current frame with the calculated current optical flow field to produce motion compensated image” wherein the motion compensated image is analogous to Tao’s difference image being optical flow associated, wherein the difference image is calculated based on the difference in optical flow vectors between two frames).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao of a system comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Gaddy of having to evaluate the difference.
Wherein having Tao’s system of having to evaluate the difference.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve object detection by block matching enabling accurate detection and ensuring of precision and refinement for shot change detection. Since both Tao and Gaddy perform object detection based on optical flow analysis. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Gaddy’s system improves performs image misalignment determination and compensation based on the use of pairwise operation that can register images accurately to improve quality of image mosaics, (see Gaddy’s Par. [0068]).
Regarding claim 14, Tao in view of Gaddy teach the system of claim 13, Tao teaches wherein the at least subset of pixels samples at least a predetermined area of interest in each frame pair (Page 2 discloses the optical flow motion vector estimation for the current frame on small pixel motion [a subset of corresponding pixels] between image frames [according to page 3]; wherein the optical flow motion vector is calculated for each frame, hence, indicating a generation of a plurality of optical flow vectors such as disclosed further in page 5; wherein the small pixel motion is of a particular area of the object in the image [a predetermined area of interest as claimed]).
Regarding claim 16, Tao in view of Gaddy teach the system of claim 13.
However, Tao does not explicitly teach wherein the predetermined criterion is that (i) a sum of differences between corresponding optical flow vectors for a successive frame pair do not exceed a first threshold, or (ii) that sum of vectors does exceed a second threshold.
Gaddy teaches wherein the predetermined criterion is that (i) a sum of differences between corresponding optical flow vectors for a successive frame pair do not exceed a first threshold, or (ii) that sum of vectors does exceed a second threshold (“or” indicates a selection therefore, only one of the options is the instant scope of the claim, the examiner selects “sum of vectors does exceed a second threshold”, Gaddy’s Par. [0053] discloses “in step S4…a sum of square differences measure SDM is calculated between the most recent image from the FIFO frame buffer”; Par. [0047] discloses “a sum-of-square difference measure SSDM between optical-flow-compensated frames…to measure similarity of one image to another…rapid changes between the aforementioned difference measures may indicate a change of scenes”, rapid change indicate a change above a certain threshold).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao of a system comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Gaddy of having wherein the predetermined criterion is that (i) a sum of differences between corresponding optical flow vectors for a successive frame pair do not exceed a first threshold, or (ii) that sum of vectors does exceed a second threshold.
Wherein having Tao’s system of having wherein the predetermined criterion is that (i) a sum of differences between corresponding optical flow vectors for a successive frame pair do not exceed a first threshold, or (ii) that sum of vectors does exceed a second threshold.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve object detection by block matching enabling accurate detection and ensuring of precision and refinement for shot change detection. Since both Tao and Gaddy perform object detection based on optical flow analysis. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Gaddy’s system improves performs image misalignment determination and compensation based on the use of pairwise operation that can register images accurately to improve quality of image mosaics, (see Gaddy’s Par. [0068]).
Regarding claim 17, Tao in view of Gaddy teach the system of claim 13, Tao teaches wherein the processor is adapted to: identify a contiguous sequence of M identified frame pairs for recording (page 7 discloses the prediction is based on that two frames share matching points that a number of points belonging to a common target; moreover, the frames of this sharing must be adjacent to each other [contiguous], two frames indicating a sequence of frames, M number of frames being M of 2).
Regarding claim 19, Tao in view of Gaddy teach the system of claim 13, Tao teaches the system of claim 13, wherein: the subset of corresponding pixels between frame pairs conforms to a region to which one or more objects of interest are to be constrained; or (“or” indicates a selection, therefore, only one of these options is the instant scope of the claim, see the following mapping for indication of the selection by the examiner) the subset of corresponding pixels between frame pairs conforms to a region outside which one or more unwanted objects are to be constrained (“or” indicates a selection therefore, only one of the options is the instant scope of the claim, the examiner selects “the subset of corresponding pixels between frame pairs conforms to a region to which one or more objects of interest are to be constrained”, wherein Tao discloses, in Page 1, last Par., of “the pixel coordinates of the feature points of the previous frame and the next frame” indicating feature point pixels [subset of corresponding pixels between frame pairs] wherein, Page 4 discloses “extract the feature points of the image, and the image feature points are matched according to the shortest distance…are pairs of matching points in the image that are converted into the homography vector” and Page 2 discloses “assuming that the object corresponding to the pixel gray value does not change due to exercise” indicating the object to be constrained according to the matched features between image pairs).
Claims 3 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Yang Tao et. al. (foreign patent document “CN 106887010 A” hereinafter as “Tao”, mapping is based on the numbers of the translation section) in view of William L. Gaddy et. al., (“US 2012/0008051 A1” hereinafter as “Gaddy”) and Vipul Parashar et. al. (“US 2022/0398751 A1” hereinafter as “Parashar”).
Regarding claim 3, Tao in view of Gaddy teach the method of claim 1.
However, Tao in view of Gaddy do not explicitly teach the at least subset of pixels samples at least at a predetermined sample density.
Parashar teaches the at least subset of pixels samples at least at a predetermined sample density (Par. [0090] discloses for the optical flow vector determination based on a region in an image concerning the pixel density with a condition that the density of invalid pixels is reduced so that the remaining amount of invalid regions is filled [analogous to a predetermined sample density condition as claimed]).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao in view of Gaddy of a method comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Parashar of having the at least subset of pixels samples at least at a predetermined sample density.
Wherein having Tao’s method of having the at least subset of pixels samples at least at a predetermined sample density.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve object detection by a method to reduce invalid pixels detected so that the candidate flow and cost can be updated and minimize the cost of processing. Since both Tao and Parashar perform object detection based on optical flow analysis. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Parashar’s system improves object detection by a method to reduce invalid pixels detected so that the candidate flow and cost can be updated and minimize the cost of processing (see Parashar’s Par. [0097]).
Regarding claim 15, Tao in view of Gaddy teach the system of claim 13.
However, Tao in view of Gaddy do not explicitly teach the at least subset of pixels samples at least at a predetermined sample density.
Parashar teaches the at least subset of pixels samples at least at a predetermined sample density (Par. [0090] discloses for the optical flow vector determination based on a region in an image concerning the pixel density with a condition that the density of invalid pixels is reduced so that the remaining amount of invalid regions is filled [analogous to a predetermined sample density condition as claimed]for the optical flow vector determination based on a region in an image concerning the pixel density with a condition that the density of invalid pixels is reduced so that the remaining amount of invalid regions is filled [analogous to a predetermined sample density condition as claimed]).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao in view of Gaddy of a system comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Parashar of having the at least subset of pixels samples at least at a predetermined sample density.
Wherein having Tao’s system of having the at least subset of pixels samples at least at a predetermined sample density.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve object detection by a method to reduce invalid pixels detected so that the candidate flow and cost can be updated and minimize the cost of processing. Since both Tao and Parashar perform object detection based on optical flow analysis. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Parashar’s system improves object detection by a method to reduce invalid pixels detected so that the candidate flow and cost can be updated and minimize the cost of processing (see Parashar’s Par. [0097]).
Claims 4-5 are rejected under 35 U.S.C. 103 as being unpatentable over Yang Tao et. al. (foreign patent document “CN 106887010 A” hereinafter as “Tao”, mapping is based on the numbers of the translation section) in view of William L. Gaddy et. al., (“US 2012/0008051 A1” hereinafter as “Gaddy”) and Angus M. Taggart et. al. (“US 2016/0301848 A1” hereinafter as “Taggart”).
Regarding claim 4, Tao in view of Gaddy teach the method of claim 1.
However, Tao in view of Gaddy do not explicitly teach the predetermined criterion comprises that a sum of differences between corresponding optical flow vectors for a successive frame pair do not exceed a first threshold.
Taggart teaches the predetermined criterion comprises that a sum of differences between corresponding optical flow vectors for a successive frame pair do not exceed a first threshold (Par. [0075] discloses detecting changes between frames based on optical flow by calculating the sum of difference in intensity between the frame wherein it indicates the optical flow determination [the intensity difference also indicating difference in optical flow] according to Par. [0080] does not exceed a certain threshold).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao in view of Gaddy of a method comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Taggart of having the predetermined criterion comprises that a sum of differences between corresponding optical flow vectors for a successive frame pair do not exceed a first threshold.
Wherein having Tao’s method of having the predetermined criterion comprises that a sum of differences between corresponding optical flow vectors for a successive frame pair do not exceed a first threshold.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve object tracking based on optical flow interpolation following such discussed method to detect changes between frames efficiently. Since both Tao and Taggart perform interframe changes detection based on optical flow. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Taggart’s system improves object tracking based on optical flow interpolation following such discussed method to detect changes between frames efficiently (see Taggart’s Par. [0080]).
Regarding claim 5, Tao in view of Gaddy and Taggart teach the method of claim 4.
However, Tao in view of Gaddy do not explicitly teach the predetermined criterion comprises that sum of vectors does exceed a second threshold.
Taggart teaches the predetermined criterion comprises that sum of vectors does exceed a second threshold (Par. [0083] discloses using a method that is not based on the optical flow of the method of 1050; moreover the step of determining the difference, is further disclosed in Par. [0082], wherein the process further determine the differences in luma intensity levels and compare with a threshold to make sure the sum of the difference does not exceed a second threshold).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao in view of Gaddy of a method comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Taggart of having the predetermined criterion comprises that sum of vectors does exceed a second threshold.
Wherein having Tao’s method of having the predetermined criterion comprises that sum of vectors does exceed a second threshold.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve object tracking based on optical flow interpolation following such discussed method to detect changes between frames efficiently. Since both Tao and Taggart perform interframe changes detection based on optical flow. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Taggart’s system improves object tracking based on optical flow interpolation following such discussed method to detect changes between frames efficiently (see Taggart’s Par. [0080]).
Claim 18 is rejected under 35 U.S.C. 103 as being unpatentable over Yang Tao et. al. (foreign patent document “CN 106887010 A” hereinafter as “Tao”, mapping is based on the numbers of the translation section) in view of William L. Gaddy et. al., (“US 2012/0008051 A1” hereinafter as “Gaddy”) and Alexandro Sentinelli et. al. (“US 2013/0336590 A1” hereinafter as “Sentinelli”).
Regarding claim 18, Tao in view of Gaddy teach the system of claim 13.
However, Tao in view of Gaddy do not explicitly teach wherein the processor is adapted to: identify video frames with a threshold level of activity and associate these with identified frame pairs for recording, if within a predetermined distance of each other within the frame sequence.
Sentinelli teaches wherein the processor is adapted to: identify video frames with a threshold level of activity (Par. [0070] discloses “the selection of the frame to be discarded from the buffer and replaced by another can be done by determining in the similarity matrix the couple of (sparse) frames (not necessarily temporally adjacent) with the shortest computed semantic distance” wherein, semantic similarity distance indicates a threshold level of activity) and associate these with identified frame pairs for recording (Par. [0070] discloses “…then eliminating one frame of the couple…the similarity matching can include”; Par. [0050] discloses “the similarity matrix can then be built by storing the results of pairwise similarity matching between the semantic description of the image frame with list index…the elements of the similarity matrix for those pairs of image frames….when starting the recording of the video…adding lines and rows to an existing similarity matrix every time information on a new image frame gets added to the buffer”), if within a predetermined distance of each other within the frame sequence (Par. [0070] discloses “the selection of the frame to be discarded from the buffer and replaced by another can be done by determining in the similarity matrix the couple of (sparse) frames (not necessarily temporally adjacent) with the shortest computed semantic distance…the similarity matching can include determining a distance measure between the semantic descriptions of the corresponding image frames…” wherein within a sequence of frames, the frames with shortest semantic distances are being associated with each other).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao in view of Gaddy of a system comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Sentinelli of having wherein the processor is adapted to: identify video frames with a threshold level of activity and associate these with identified frame pairs for recording, if within a predetermined distance of each other within the frame sequence.
Wherein having Tao’s system of having wherein the processor is adapted to: identify video frames with a threshold level of activity and associate these with identified frame pairs for recording, if within a predetermined distance of each other within the frame sequence.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve video recording by using pseudo-temporal sampling that allow for significantly lowering the cost of computation and still maintain sufficient representations of the video. Since both Tao and Sentinelli perform image pair determination based on similarity matrix. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Sentinelli’s system improves video recording by using pseudo-temporal sampling that allow for significantly lowering the cost of computation and still maintain sufficient representations of the video (see Sentinelli’s Par. [0279]).
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Yang Tao et. al. (foreign patent document “CN 106887010 A” hereinafter as “Tao”, mapping is based on the numbers of the translation section) in view of William L. Gaddy et. al., (“US 2012/0008051 A1” hereinafter as “Gaddy”) and Jing Ya Li et. al. (“US 2023/0396776 A1” hereinafter as “Li”).
Regarding claim 20, Tao in view of Gaddy teach the system of claim 13, Tao teaches the system of claim 13, wherein the calculation is based on only a subset of directional components of the generated optical flow vectors (Page 2 discloses “optical flow estimation…that the corresponding direction of the gradient…the corresponding direction of the optical flow size. The above equation can be express as” wherein the equation indicates the calculation wherein only concerning about the direction of the optical flow size for this particular equation).
Tao in view of Gaddy do not explicitly teach and the subset of directional components include different directional components in different regions of the frame.
Li teaches and the subset of directional components include different directional components in different regions of the frame (Par. [0213] discloses “gradient directionality D is calculated by comparing gradients of a plurality of directions”; moreover, Par. [0212] discloses “the classification of the sub-block is based on gradient directionality and activity” therefore, the classification of the image region is based on different gradient directions of the optical flow vector; Par. [0395] discloses “this optical flow equations shows…a motion vector of each block obtained”).
Therefore, it would have been obvious to one or ordinary skill in the art before the effective filing date of the claimed invention was made to combine the teachings Tao in view of Gaddy of a system comprising: generating optical flow vectors for at least a subset of corresponding pixels between frame pairs of a video including successive video frames; calculating a difference between corresponding optical flow vectors of successive frame pairs; and evaluating the result with respect to a predetermined criterion to identify respective frame pairs for further processing, with the teachings of Li of having wherein the processor is adapted to: identify video frames with a threshold level of activity and associate these with identified frame pairs for recording, if within a predetermined distance of each other within the frame sequence.
Wherein having Tao’s system of having and the subset of directional components include different directional components in different regions of the frame.
The motivation behind the modification would have been to improve motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, and further to improve image prediction task by using bi-directional optical flow enabling generation of high-accurate prediction. Since both Tao and Sentinelli perform image pair determination based on similarity matrix. Wherein Tao’s system improves motion detection for computer vision based on frame differences and optical flow analysis enabling more accurate multi-target detection, (see Tao’s Background Technique section) and Li’s system improves image prediction task by using bi-directional optical flow enabling generation of high-accurate prediction (see Li’s Par. [0078]).
Pertinent Prior Art(s)
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Liu, Hongbin et. al., “US 11889108 B2”, discloses a method of video processing including: modifying temporal gradients in a motion vectors refinement process of a video block or sub-blocks within the video block; and performing the motion vectors refinement process of the video block or the sub-blocks within the video block based on the modified temporal gradients.
Sethuraman, Sriram et. al., “US 12744931 B2”, discloses a video encoder or a video decoder obtains a pair of motion vectors for a current coding block of a video signal with respect to two reference frames. Predictions of the current block are generated using the pair of motion vectors from respective reference frames. The video encoder or video decoder further determine an optical flow for the current coding block based on samples values in the predictions. One component of the optical flow is determined based on the other component of the optical flow. Bi-predictive optical flow (BPOF) can be performed on the current coding block using the determined optical flow.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PHUONG HAU CAI whose telephone number is (571)272-9424. The examiner can normally be reached M-F 8:30 am - 5:00pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Chineyere Wills-Burns can be reached at (571) 272-9752. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/PHUONG HAU CAI/Examiner, Art Unit 2673
/CHINEYERE WILLS-BURNS/Supervisory Patent Examiner, Art Unit 2673
Prosecution Insights