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 .
Typographic Conventions
Throughout this office action, shorthand notation for referencing locations of elements in documents are utilized. The following is a brief summary of the shorthand utilized:
Sec. – is used to denote an associated section with a header in non-patent literature
¶ – is used to denote the number and location of a paragraph
col. – is used to denote a column number
ln. – is used to denote a line; if a line number is not demarcated in a document, the line number will be assumed to start at 1 for each paragraph.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Response to Arguments
Preliminary Remarks Regarding Cited Prior Art
Applicant correctly notes the improperly cited Eldar reference, which was incorrectly cited as US 2013/0206608 A1 in the rejection headings as well as (US 2023/02066080 A1) in the PTO-892 Notice of References Cited. The examiner agrees that applicant was prevented from conducting a full and thorough review of the cited art in view of this error and accordingly denotes the rejection of this current office action as “non-final”. The correct reference, Eldar et al (US 2023/0206608 A1) has been properly cited in this current Office Action. Applicant is advised that, should an Office Action contain an error that affects applicant’s ability to reply to the office action, applicant is able to call this error to the attention of the office to either restart or set a new period of reply (see MPEP § 710.06).
Objections to the Specification
Applicant’s arguments [Sec – Objections to the Specification; pg. 1] of the Remarks filed 03/17/2026, with respect to the objections regarding a missing reference numeral have been fully considered and are persuasive. The examiner acknowledges the amendments to the specification correct the previously missing reference of “example 2D image 402”. The objection to the specification has been withdrawn.
Rejections under 35 U.S.C. § 112(b)
Applicant’s arguments [Sec – Claim Rejections – 35 U.S.C. § 112(b); pgs. 1-2] of the Remarks filed 03/17/2026, with respect to the rejections made under 35 U.S.C. § 112(b) have been fully considered and are persuasive. Applicant has amended claims 2 & 11 to recite “selecting a handling action” to provide clarification for the later recited “the handling action” of claims 2 & 11. This amendment further provides proper antecedent basis for limitations outlined in claims 6, 8, 9, 15, 17 & 18 which have now been amended to have proper dependency from claims 2 (6, 8 & 9) and 11 (15, 17 & 18). Applicant has amended claims 7 & 16 to remove the term “substantially” to address the previously indicated indefiniteness from an undefined term of degree. The rejections under 35 U.S.C. § 112(b) have been withdrawn.
Rejections under 35 U.S.C. § 101
Applicant’s arguments [Sec – Claim Rejections – 35 U.S.C. § 101; pgs. 2-5] of the Remarks filed 03/17/2026, with respect to the rejections made under 35 U.S.C. 101 have been fully considered and are persuasive. Applicant argues that claims 1-18 are not directed to non-statutory subject matter. More specifically that the claims do not recite a judicial exception (Step 2A – Prong One), are integrated into a practical application (Step 2A – Prong Two), and amount to significantly more than an abstract idea (Step 2B). The rejections under 35 U.S.C. § 101 have been withdrawn.
Rejections under 35 U.S.C. § 103
Applicant’s arguments [Sec – Claim Rejections – 35 U.S.C. § 103; pgs. 5-6] of the Remarks filed 03/17/2026, with respect to the rejections made under 35 U.S.C. § 103 have been fully considered, but are not persuasive. The specific reasons are explained below:
Argument
Applicant argues that combination of Sharma (US 20212/0087573 A1) and Ajamian (US 2023/0308746 A1) fail to teach or suggest all the limitations of claims 1 & 10, particularly that they fail to teach a causal linkage required by the claims to determine delivery to a dimensioning module based on the comparison of the depth of the obstruction with the threshold. The examiner respectfully disagrees with this assessment.
The examiner notes that while Sharma’s disclosure is directed to filtering clutter for video surveillance, it still teaches towards the claim language and the general concept of marking regions of interest relating to some form of obstruction based on a comparison to a depth threshold (Sharma: 0052-53; steps 600-606 of Fig. 6).
Applicant correctly notes that Sharma contains no disclosure for dimensioning 3D objects in an image. Ajamian is introduced to cure this deficiency, as Ajamian is directed to performing object dimensioning. Applicant argues that Ajamian fails to teach “determining whether the images are sufficient for object dimensioning”, citing that Ajamian utilizes different criteria based on desired poses/orientations [Ajamian: ¶0047] from that of the instant application which utilizes a physical depth. While the examiner acknowledges that Ajamian utilizes criteria distinct from the instant application, the rejection under 35 U.S.C. § 103 does not rely on Ajamian to teach making this determination based on the comparison of the depth of the obstruction with the threshold, and instead Sharma is used to teach this limitation (if the depth of the blob is not greater than a depth threshold (step 604), marking it as clutter (step 606) [¶0053; Fig. 6]). Rather, it is a combination of the obstruction detection outlined by Sharma with the dimensioning module provided by Ajamian which is utilized to make the rejection against claims 1 & 10.
In response to applicant's argument that the examiner's conclusion of obviousness is based upon improper hindsight reasoning, it must be recognized that any judgment on obviousness is in a sense necessarily a reconstruction based upon hindsight reasoning. But so long as it takes into account only knowledge which was within the level of ordinary skill at the time the claimed invention was made, and does not include knowledge gleaned only from the applicant's disclosure, such a reconstruction is proper. See In re McLaughlin, 443 F.2d 1392, 170 USPQ 209 (CCPA 1971).
Therefore, the rejections under 35 U.S.C. § 103 are maintained.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
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.
Claims 1-3, 6, 7, 10-12, 15, and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Sharma et al (US 2012/0087573 A1) in view of Ajamian et al (US 2023/0308746 A1).
Regarding claim 1, Sharma teaches a method of identifying obstructions in three-dimensional depth images. More specifically as it relates to the applicants claims, Sharma discloses a method, comprising: capturing, via a sensor of a computing device, a three-dimensional image corresponding to an object (depth camera 400 in Fig. 4 and ¶ 0031, and 3D imaging system 402 in Fig. 4; and ¶ 0031), detecting a region of interest in the three-dimensional image, the region of interest corresponding to an obstruction (¶ 0052: detection of foreground blobs (an obstruction) in the depth image (step 600 in Fig. 6)), determining a depth from the sensor to the region of interest (¶ 0053: a computed depth indicative of the distance between the camera and the blob (step 602 in Fig. 6), comparing the determined depth to a threshold (¶0053: comparing the depth of the blob to a threshold (step 604 in Fig. 6)), based on the comparison of the depth of the obstruction with the threshold (¶ 0053: and if the depth of the blob is not greater than a depth threshold (step 604), marking it as clutter (step 606 in Fig. 6)).
Sharma et al fails to disclose determining whether to deliver the three-dimensional image to a dimensioning module. Ajamian et al is analogous art relevant to the technical field and problems addressed in this application and teaches a method for validating time-of flight images for performing object dimensioning (¶ 0040; step 400 in Fig. 4) and determining whether the images are sufficient for object dimensioning (¶ 0049; step 414 in Fig. 4). The obstruction detection method described in Sharma could be utilized to determine image sufficiency for object dimensioning. Ajamian further discloses that this feature serves to reduce the total time for and improve the accuracy of measuring the sizes of multiple items across shipping, storing, or moving industries (¶ 0002). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma for the application of dimensioning three-dimensional objects.
Regarding claim 2, mentioned above in the discussion of claim 1, Sharma et al in view of Ajamian et al teach all of the limitations of the parent claim. Sharma further teaches a binary decision based on the comparison to a depth threshold. More specifically, Sharma discloses (i) … when the depth is below the threshold; and (ii) … when the depth exceeds the threshold (¶ 0053: when the blob is not greater than a threshold (step 604), the blob is marked as clutter (step 606 in Fig. 6)).
Ajamian et al further teaches wherein determining whether to deliver the three-dimensional image to the dimensioning module (¶ 0049: determining whether images are sufficient for object dimensioning (step 414 in Fig. 4)), (i) suppressing delivery of the three-dimensional image to a dimensioning module when the depth is below the threshold (¶ 0050: a capture verifying component (element 158 of Fig. 1) that determines a given image is insufficient for dimensioning (step 414 in Fig. 4), (ii) delivering the three-dimensional image to the dimensioning module, to obtain dimensions for the object (¶ 0049: the method 400 can include, at step 414, determining the images are sufficient for object dimensioning (in Fig. 4)), and executing the selected handling action (¶ 0050-51: and proceeding with either object dimensioning (step 416) or not (step 412; in Fig. 4)). Ajamian further discloses that this feature serves to reduce the total time for and improve the accuracy of measuring the sizes of multiple items across shipping, storing, or moving industries (¶ 0002). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma for the application of dimensioning three-dimensional objects.
Regarding claim 3, mentioned above in the discussion of claim 1, Sharma et al in view of Ajamian et al teach all of the limitations of the parent claim. Sharma further teaches a method of segmenting a three-dimensional image. More specifically, Sharma discloses wherein detecting the region of interest includes performing a segmentation operation on the three-dimensional image (¶ 0052: to detect foreground blobs, background subtraction is performed between the depth image, and a depth background model of an observed scene to generate a binary mask image. The generation of a binary mask is a type of image segmentation.
Regarding claim 6, Sharma et al in view of Ajamian et al teach the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously). Additionally, Ajamian et al further teaches a system for collecting multiple images of an environment having one or more objects. More specifically as it relates to the applicants claims, Ajamian discloses in response to suppressing delivery of the three-dimensional image, determining whether delivery to the dimensioning module has been suppressed for a predetermined number of consecutive three-dimensional images (collecting pairs of images in back-to-back TOF frames can provide improved signal-to-noise ratio (SNR) for the pair of images (¶ 0035) and determining whether enough images are sufficient for object dimensioning (¶0049; element 414 in Fig. 4)), when delivery to the dimensioning module has been suppressed for the predetermined number of consecutive three-dimensional images, generating a notification via an output of the computing device (and if it is determined that the images are not sufficient for dimensioning at 414, method 400 can process back to step 402 to display the prompt (¶0050; elements of Fig. 4)). Ajamian further discloses that this feature serves to reduce the total time for and improve the accuracy of measuring the sizes of multiple items across shipping, storing, or moving industries (¶ 0002). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma for the application of dimensioning three-dimensional objects.
Regarding claim 7, Sharma et al in view of Ajamian et al teach the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously).
Sharma et al additionally teaches capturing, via a second sensor, a two-dimensional image substantially simultaneously with the three-dimensional image (a depth camera that also captures human-viewable two-dimensional images of the scene in addition to the depth image (¶ 0056), with foreground blobs detected in the two-dimensional image (¶ 0057; element 700 in Fig. 7)), and based on whether the two-dimensional image depicts at least a portion of the region of interest (and that the extracted features [of the two-dimensional image], are then used to determine if the blob is sufficiently similar to an expected object (¶ 0057; element 704 in Fig. 7)).
Sharma does not teach the selection of a notification based on the aforementioned similarity comparison. Ajamian et al further teaches selecting the notification (that when the images are not sufficient for dimensioning at 414, method 400 can process back to 402 to display the prompt (¶ 0050; Fig. 4)). Ajamian further discloses that this feature serves to reduce the total time for and improve the accuracy of measuring the sizes of multiple items across shipping, storing, or moving industries (¶ 0002). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma for the application of dimensioning three-dimensional objects.
Regarding claim 10, Sharma teaches a method of identifying obstructions in three-dimensional depth images. More specifically as it relates to the applicants claims, Sharma discloses a computing device (the computer 310 ins configured to receive video sequence(s) from one or more video surveillance cameras (¶ 0029; elements in Fig. 3), a sensor (depth camera (¶ 0031; element 400 in Fig. 4)), a processor configured to: capture via the sensor (the components of the depth camera 400 may be implemented in any suitable combination of software, firmware, and hardware, such as, for example, one or more digital signal processors… stored in the memory component 410 (¶0030; elements in Fig. 4), a three-dimensional image corresponding to an object (3D imaging system 402 in Fig. 4; and ¶ 0031), detect a region of interest in the three-dimensional image, the region of interest corresponding to an obstruction (¶ 0052: detection of foreground blobs (an obstruction) in the depth image (step 600 in Fig. 6)), determine a depth from the sensor to the region of interest (¶ 0053: a computed depth indicative of the distance between the camera and the blob (step 602 in Fig. 6), compare the determined depth to a threshold (¶0053: comparing the depth of the blob to a threshold (step 604 in Fig. 6)), based on the comparison of the depth of the obstruction with the threshold (¶ 0053: and if the depth of the blob is not greater than a depth threshold (step 604), marking it as clutter (step 606 in Fig. 6)).
Sharma et al fails to disclose determining whether to deliver the three-dimensional image to a dimensioning module. Ajamian et al is analogous art relevant to the technical field and problems addressed in this application and teaches a method for validating time-of flight images for performing object dimensioning (¶ 0040; step 400 in Fig. 4) and determining whether the images are sufficient for object dimensioning (¶ 0049; step 414 in Fig. 4). The obstruction detection method described in Sharma could be utilized to determine image sufficiency for object dimensioning. Ajamian further discloses that this feature serves to reduce the total time for and improve the accuracy of measuring the sizes of multiple items across shipping, storing, or moving industries (¶ 0002). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma for the application of dimensioning three-dimensional objects.
Regarding claim 11, mentioned above in the discussion of claim 1, Sharma et al in view of Ajamian et al teach all of the limitations of the parent claim. Sharma further teaches a binary decision based on the comparison to a depth threshold. More specifically, Sharma discloses (i) … when the depth is below the threshold; and (ii) … when the depth exceeds the threshold (¶ 0053: when the blob is not greater than a threshold (step 604), the blob is marked as clutter (step 606 in Fig. 6)).
Ajamian et al further teaches to determine whether to deliver the three-dimensional image to the dimensioning module (¶ 0049: determining whether images are sufficient for object dimensioning (step 414 in Fig. 4)), (i) suppressing delivery of the three-dimensional image to a dimensioning module when the depth is below the threshold (¶ 0050: a capture verifying component (element 158 of Fig. 1) that determines a given image is insufficient for dimensioning (step 414 in Fig. 4), (ii) delivering the three-dimensional image to the dimensioning module, to obtain dimensions for the object (¶ 0049: the method 400 can include, at step 414, determining the images are sufficient for object dimensioning (in Fig. 4)), and executing the selected handling action (¶ 0050-51: and proceeding with either object dimensioning (step 416) or not (step 412; in Fig. 4)). Ajamian further discloses that this feature serves to reduce the total time for and improve the accuracy of measuring the sizes of multiple items across shipping, storing, or moving industries (¶ 0002). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma for the application of dimensioning three-dimensional objects.
Regarding claim 12, mentioned above in the discussion of claim 1, Sharma et al in view of Ajamian et al teach all of the limitations of the parent claim. Sharma further teaches a method of segmenting a three-dimensional image. More specifically, Sharma discloses detect the region of interest includes performing a segmentation operation on the three-dimensional image (¶ 0052: to detect foreground blobs, background subtraction is performed between the depth image, and a depth background model of an observed scene to generate a binary mask image. The generation of a binary mask is a type of image segmentation.
Regarding claim 15, Sharma et al in view of Ajamian et al teach the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously). Additionally, Ajamian et al further teaches a system for collecting multiple images of an environment having one or more objects. More specifically as it relates to the applicants claims, Ajamian discloses in response to suppressing delivery of the three-dimensional image, determine whether delivery to the dimensioning module has been suppressed for a predetermined number of consecutive three-dimensional images (collecting pairs of images in back-to-back TOF frames can provide improved signal-to-noise ratio (SNR) for the pair of images (¶ 0035) and determining whether enough images are sufficient for object dimensioning (¶0049; element 414 in Fig. 4)), when delivery to the dimensioning module has been suppressed for the predetermined number of consecutive three-dimensional images, generate a notification via an output of the computing device (and if it is determined that the images are not sufficient for dimensioning at 414, method 400 can process back to step 402 to display the prompt (¶0050; elements of Fig. 4)). Ajamian further discloses that this feature serves to reduce the total time for and improve the accuracy of measuring the sizes of multiple items across shipping, storing, or moving industries (¶ 0002). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma for the application of dimensioning three-dimensional objects.
Regarding claim 16, Sharma et al in view of Ajamian et al teach the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously).
Sharma et al additionally teaches capture, via a second sensor, a two-dimensional image substantially simultaneously with the three-dimensional image (a depth camera that also captures human-viewable two-dimensional images of the scene in addition to the depth image (¶ 0056), with foreground blobs detected in the two-dimensional image (¶ 0057; element 700 in Fig. 7)), and based on whether the two-dimensional image depicts at least a portion of the region of interest (and that the extracted features [of the two-dimensional image], are then used to determine if the blob is sufficiently similar to an expected object (¶ 0057; element 704 in Fig. 7)).
Sharma does not teach the selection of a notification based on the aforementioned similarity comparison. Ajamian et al further teaches select the notification (that when the images are not sufficient for dimensioning at 414, method 400 can process back to 402 to display the prompt (¶ 0050; Fig. 4)). Ajamian further discloses that this feature serves to reduce the total time for and improve the accuracy of measuring the sizes of multiple items across shipping, storing, or moving industries (¶ 0002). Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma for the application of dimensioning three-dimensional objects.
Claims 4, 8, 9, 13, 17, 18 are rejected under 35 U.S.C. 103 as being unpatentable over Sharma et al (US 2012/0087573 A1) in view of Ajamian et al (US 2023/0308746 A1) further in view of Eldar et al (US 2023/0206608 A1).
Regarding claim 4, Sharma et al in view of Ajamian et al teach the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously).
Sharma et al in view of Ajamian et al does not teach an additional step in identifying obstructions by comparing the size of a region of interest (corresponding to an obstruction), to a size threshold. Eldar et al is analogous art relevant to the technical field and problems addressed in this application and teaches a method of obstruction detection. More specifically, Eldar discloses wherein detecting the region of interest further comprises: determining a size of the region of interest; and determining that the size exceeds a size threshold prior to determining the depth (predicting whether a presented image includes a representation of a blockage may include determining whether a presented image includes a region of pixels associated with respective indicators that the respective pixels are associated with a representation of a blockage and that the region is at least a threshold size ((¶ 0373; process 2700 in Fig. 27)).
Eldar further recites that an image region with a blockage may be a portion of an image that the model predicted to have pixels indicative of a blockage (¶ 0373) and establishes a need for systems to accurately, consistently, and efficiently identify and respond to image blockages (¶ 0357). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sharma and Ajamian to incorporate the teachings of Eldar to include a step to determine the size of an obstruction and compare that to a threshold before proceeding with object dimensioning. Doing so would further validate the efficiency and accuracy of the detection of an obstruction. Adding an extra comparison to minimize false positives that could arrive from obstructions that may be too close to the sensor (in relation to the depth threshold), but not large enough (in relation to the size threshold) to not block the field of view for dimensioning the object of interest.
Regarding claim 8, Sharma et al in view of Ajamian et al teach the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously).
Sharma et al again teaches based on comparison of the depth with the threshold (comparing the depth of the blob to a threshold (¶ 0053; element 604)). Ajamian et al teaches selecting the handling action (proceeding with either object dimensioning (416) or not (412) (¶ 0050-51; elements in Fig. 4)). Sharma et al in view of Ajamian et al does not teach capturing an associated intensity value corresponding to the region of interest, and comparing that intensity to a second threshold and determining an appropriate handling action as a result of that comparison.
Eldar et al teaches capturing, via the sensor, with the three-dimensional image, an intensity value associated with the region of interest (a blockage indicator associated with each of the plurality of training images, each blockage indicator representing a presence of a blockage or an absence of a blockage; or an analysis of intensities of pixels located at corresponding pixel coordinates of the plurality of training images (¶ 0380; step 3120 in Fig. 31)), and comparing the intensity value to a second threshold (Determining the at least one output value may include computing at least one feature based on using information determined as part of the analysis of the intensities of the pixels (¶ 0368), and model may be further configured to compare the at least one output value to a threshold (¶ 0369)).
Eldar further recites that an image region with a blockage may be a portion of an image that the model predicted to have pixels indicative of a blockage (¶ 0373) and establishes a need for systems to accurately, consistently, and efficiently identify and respond to image blockages (¶ 0357). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sharma and Ajamian to incorporate the teachings of Eldar to include a step to determine the pixel intensity of an obstruction and compare that to a threshold before proceeding with object dimensioning. Doing so would further validate the efficiency and accuracy of the detection of an obstruction. Adding an extra comparison to minimize false positives that could arrive from obstructions that may be too close to the sensor (in relation to the depth threshold), but not intense or bright enough (in relation to the intensity threshold) to not distort the field of view for dimensioning the object of interest.
Regarding claim 9, Sharma et al in view of Ajamian et al teaches the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously). Sharma et al again teaches when the depth exceeds the threshold (that if the depth of the blob is not greater than a depth threshold (604), the blob is marked as clutter (¶ 0053; element 606 in Fig. 6)), Ajamian et al again teaches wherein selecting the handling action further comprises… delivering the three-dimensional image to the dimensioning module (a method (400), including, at 414, determining the images are sufficient for object dimensioning and proceeding with object dimensioning (¶0050; element 416 in Fig. 4)).
Sharma et al and Ajamian et al do not teach delivering the three-dimensional image to the dimensioning module when the intensity is below the second threshold. Eldar et al discloses and the intensity is below the second threshold (model may be further configured to compare the at least one output value to a threshold (¶ 0369)).
Eldar further recites that an image region with a blockage may be a portion of an image that the model predicted to have pixels indicative of a blockage (¶ 0373) and establishes a need for systems to accurately, consistently, and efficiently identify and respond to image blockages (¶ 0357). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sharma and Ajamian to incorporate the teachings of Eldar to include a step to determine the pixel intensity of an obstruction and compare that to a threshold before proceeding with object dimensioning. Doing so would further validate the efficiency and accuracy of the detection of an obstruction. Adding an extra comparison to minimize false positives that could arrive from obstructions that may be too close to the sensor (in relation to the depth threshold), but not intense or bright enough (in relation to the intensity threshold) to not distort the field of view for dimensioning the object of interest.
Regarding claim 13, Sharma et al in view of Ajamian et al teach the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously).
Sharma et al in view of Ajamian et al does not teach an additional step in identifying obstructions by comparing the size of a region of interest (corresponding to an obstruction), to a size threshold. Eldar et al is analogous art relevant to the technical field and problems addressed in this application and teaches a method of image correction. More specifically, Eldar discloses wherein the processor is configured to detect the region of interest by: determining a size of the region of interest; and determining that the size exceeds a size threshold prior to determining the depth (predicting whether a presented image includes a representation of a blockage may include determining whether a presented image includes a region of pixels associated with respective indicators that the respective pixels are associated with a representation of a blockage and that the region is at least a threshold size ((¶ 0373; process 2700 in Fig. 27)).
Eldar further recites that an image region with a blockage may be a portion of an image that the model predicted to have pixels indicative of a blockage (¶ 0373) and establishes a need for systems to accurately, consistently, and efficiently identify and respond to image blockages (¶ 0357). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sharma and Ajamian to incorporate the teachings of Eldar to include a step to determine the size of an obstruction and compare that to a threshold before proceeding with object dimensioning. Doing so would further validate the efficiency and accuracy of the detection of an obstruction. Adding an extra comparison to minimize false positives that could arrive from obstructions that may be too close to the sensor (in relation to the depth threshold), but not large enough (in relation to the size threshold) to not block the field of view for dimensioning the object of interest.
Regarding claim 17, Sharma et al in view of Ajamian et al teach the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously).
Sharma et al again teaches based on comparison of the determined depth with the threshold (comparing the depth of the blob to a threshold (¶ 0053; element 604)). Ajamian et al teaches selecting the handling action (proceeding with either object dimensioning (416) or not (412) (¶0050-51; elements in Fig. 4)). Sharma et al in view of Ajamian et al does not teach capturing an associated intensity value corresponding to the region of interest, and comparing that intensity to a second threshold and determining an appropriate handling action as a result of that comparison.
Eldar et al teaches capture, via the sensor, with the three-dimensional image, an intensity value associated with the region of interest (a blockage indicator associated with each of the plurality of training images, each blockage indicator representing a presence of a blockage or an absence of a blockage; or an analysis of intensities of pixels located at corresponding pixel coordinates of the plurality of training images (¶ 0380; step 3120 in Fig. 31)), and compare the intensity value to a second threshold (Determining the at least one output value may include computing at least one feature based on using information determined as part of the analysis of the intensities of the pixels (¶ 0368), and model may be further configured to compare the at least one output value to a threshold (¶ 0369)).
Eldar further recites that an image region with a blockage may be a portion of an image that the model predicted to have pixels indicative of a blockage (¶ 0373) and establishes a need for systems to accurately, consistently, and efficiently identify and respond to image blockages (¶ 0357). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sharma and Ajamian to incorporate the teachings of Eldar to include a step to determine the pixel intensity of an obstruction and compare that to a threshold before proceeding with object dimensioning. Doing so would further validate the efficiency and accuracy of the detection of an obstruction. Adding an extra comparison to minimize false positives that could arrive from obstructions that may be too close to the sensor (in relation to the depth threshold), but not intense or bright enough (in relation to the intensity threshold) to not distort the field of view for dimensioning the object of interest.
Regarding claim 18, Sharma et al in view of Ajamian et al teaches the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously). Sharma et al again teaches when the depth exceeds the threshold (that if the depth of the blob is not greater than a depth threshold (604), the blob is marked as clutter (¶ 0053; element 606 in Fig. 6)), Ajamian et al again teaches wherein selecting the handling action further comprises… delivering the three-dimensional image to the dimensioning module (a method (400), including, at 414, determining the images are sufficient for object dimensioning and proceeding with object dimensioning (¶0050; element 416 in Fig. 4)).
Sharma et al and Ajamian et al do not teach delivering the three-dimensional image to the dimensioning module when the intensity is below the second threshold. Eldar et al discloses and the intensity is below the second threshold (model may be further configured to compare the at least one output value to a threshold (¶ 0369)).
Eldar further recites that an image region with a blockage may be a portion of an image that the model predicted to have pixels indicative of a blockage (¶ 0373) and establishes a need for systems to accurately, consistently, and efficiently identify and respond to image blockages (¶ 0357). Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have combined the teachings of Sharma and Ajamian to incorporate the teachings of Eldar to include a step to determine the pixel intensity of an obstruction and compare that to a threshold before proceeding with object dimensioning. Doing so would further validate the efficiency and accuracy of the detection of an obstruction. Adding an extra comparison to minimize false positives that could arrive from obstructions that may be too close to the sensor (in relation to the depth threshold), but not intense or bright enough (in relation to the intensity threshold) to not distort the field of view for dimensioning the object of interest.
Claims 5 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Sharma et al (US 2012/0087573 A1) in view of Ajamian et al (US 2023/0308746 A1) further in view of Liu et al (US 2017/0039731 A1).
Regarding claim 5, Sharma et al in view of Ajamian et al teaches the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously).
Sharma et al in view of Ajamian et al does not teach the added limitation of a minimum depth threshold. Liu et al is analogous art relevant to the technical field and problems addressed in this application and discloses wherein the threshold corresponds to a minimum depth setting of the sensor (a minimum depth a camera providing the image can sense (¶ 0029)). Liu further discloses that the spacing in sample points of the depth image (304) depending on the minimum depth a camera can sense can be selected based on the needs of a user’s application – with larger spacing applicable for far range photography, while smaller spacing is more applicable to close range viewing (¶ 0029; Fig. 3). It would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma et al in view of Ajamian et al for identifying an obstruction via a depth comparison and utilizing that comparison for determining whether or not to dimension an object in a three-dimensional image, with the added specification of minimum depth provided by Liu et al.
Regarding claim 14, Sharma et al in view of Ajamian et al teaches the obstruction detection method based on a comparison to a depth threshold for the use of dimensioning an object in a three-dimensional image according to claim 1 (as described previously).
Sharma et al in view of Ajamian et al does not teach the added limitation of a minimum depth threshold. Liu et al is analogous art relevant to the technical field and problems addressed in this application and discloses wherein the threshold corresponds to a minimum depth setting of the sensor (a minimum depth a camera providing the image can sense (¶ 0029)). Liu further discloses that the spacing in sample points of the depth image (304) depending on the minimum depth a camera can sense can be selected based on the needs of a user’s application – with larger spacing applicable for far range photography, while smaller spacing is more applicable to close range viewing (¶ 0029; Fig. 3). It would have been obvious to one of ordinary skill in the art before the effective filing date of this application to modify the teachings of Sharma et al in view of Ajamian et al for identifying an obstruction via a depth comparison and utilizing that comparison for determining whether or not to dimension an object in a three-dimensional image, with the added specification of minimum depth provided by Liu et al.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Michael M. Sofroniou whose telephone number is (571)-272-0287. The examiner can normally be reached M-F: 8:30 AM - 5:00 PM.
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, John M. Villecco can be reached at (571) 272-7319. 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.
/MICHAEL M SOFRONIOU/Examiner, Art Unit 2661
/JOHN VILLECCO/Supervisory Patent Examiner, Art Unit 2661
Prosecution Insights