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 .
Response to Arguments
Applicant’s arguments filed 07/28/2026 have been considered but they are not persuasive.
On pages 7-8, Applicant argues that,
“The applicant would like to point out how the amended claims 1 and 10 are not anticipated by and patentable over the cited prior art. Ozer discloses the method for object tracking and activity analysis. As described in paragraphs [0036] and [0037], Ozer first analyzes objects of interest (OOI) in an image to estimate the congestion level, selects the region of interest (ROI) according to the estimated congestion level for subsequent analysis, and then performs group activity analysis or individual activity analysis. The region in which the OOI is detected is labeled as "1" and the region is determined to be congested when the ratio of the regions labeled as "1" to the total regions exceeds the threshold. However, paragraphs [0039]-[0043] and [0044]-[0070] do not disclose comparison of the congestion level with any predetermined condition.
In the present application, the automatic rule setting method can analyze relation between the scene datum and the predefined condition to determine the detection rule, thereby determining the detection rule applicable to the surveillance image and automatically generating the detection boundary corresponding to the determined detection rule. The predefined condition is at least one of a position datum relevant to the surveillance image, a scene similarity parameter relevant to the scene datum, a user's input command, and a cluster learning result of the user's input command.
Compared with the present application, paragraph [0043] in Ozer defines the ROI as being set in environments such as the platform and the railway, and defines the moving objects, such as people and trains, as the OOI. Figure 5 and paragraph [0039] in Ozer compute the low-level motion feature and correlate the low-level motion feature with the high-level attributes, such as average crowd movement estimation, for estimation of the crowd flow. Figure 6 and paragraph [0044] in Ozer perform operation of tracking individual OOIs according to the shape, color, and motion pattern of the OOIs.
The congestion level in Ozer is interpreted as the relation between the scene datum and the predefined condition disclosed in the present application, and the group activity analysis or the individual activity analysis are interpreted as the detection rule disclosed in the present application according to the Examiner's opinion. However, the congestion level in Ozer is defined based on the ratio of the regions labeled as "1" to the total regions exceeds the predetermined threshold, which is different from the inventive features of "analyzing relation between the scene datum and a predefined condition (which is at least one of a position datum relevant to the surveillance image, a scene similarity parameter relevant to the scene datum, at least one input command, and a cluster learning result of the input command)" in the present application.
In addition, paragraph [0031] in Ozer only discloses the region is labeled by learning from the similar scenes, and object detection is only performed within predefined ROI, so as to define different events according to the [the] object detection results from different ROIs. Therefore, Ozer does not disclose or suggest analyzing any relation between "the region labeled as "1" or the congestion level" and "the position datum, the scene similarity parameter, the input command, or the cluster learning result".
In conclusion, Ozer does not disclose the technical feature of "the predefined condition is the position datum relevant to the surveillance image, the scene similarity parameter relevant to the scene datum, the user's input command, or the cluster learning result of the input command" recited in the amended claims 1 and 10 of the present application. From the aforementioned reason, the applicant believes that claims 1 and of the present application show difference since there is a major technical difference between the present application and the prior art reference. Reconsideration of claims 1 and 10 are politely requested. As claims 2-3 and 11-12 are respectively dependent on claims 1 and 10, and the applicant believes claims 1 and 10 have been placed in a position for allowance, claims 2-3 and 11-12 should also be found allowable.”
In response, Examiner respectfully disagrees and submits that the Office Action clearly states the predefined condition is at least “whether the congestion level is high”. Further, at least in [0030]-[0031] and [0036]-[0037], Ozer teaches such a congestion level being high or not depends on monitoring areas relevant to the surveillance image, e.g. platform and railway areas when surveillance images are of train stations, or areas in the images with a lot of people being detected. Therefore, such a predefined condition is at least one of a position datum relevant to the surveillance image, i.e. whether there are monitoring areas where a lot of people are present in the surveillance image.
Further, in [0031], Ozer states,[0031] The background elimination algorithm defined above is used with high level knowledge of the scene to extract regions of interest (ROI) (401) where the motion analysis is done. The high level knowledge (402) may be introduced by the user as a masking process or by performing a priori training to detect predetermined OOIs in a scene. The latter is done automatically to label the regions by using similar scenes. For example, monitoring areas in a train station may consist of platform and railway areas. The object detection may be done only in the predefined regions of interest. Different events are then defined according to the object detection results in different regions of interest.
(emphasis added)
As such, Ozer also discloses the predefined condition is at least a scene similarity parameter relevant to the scene datum. In this case, the scene similarity parameter is to at least a region in other similarity scenes that can be used to label a region in this scene datum to detect predetermined OOIs.
Therefore, Applicant’s arguments are not persuasive.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-3 and 10-12 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Ozer (US 2008/0130948 A1 – hereinafter Ozer).
Regarding claim 1, Ozer discloses an automatic rule setting method applied to an image content analysis apparatus ([0057]; [0072]; Figs. 1-6 – a method applied to an apparatus performing image content analysis for object tracking), the image content analysis apparatus having an operation processor ([0057] – a central processor) and an image receiver, the image receiver being adapted to receive a surveillance image ([0057] – an image receiver to receive surveillance images from cameras), the automatic rule setting method comprising: the operation processor analyzing the surveillance image to acquire a scene datum (Fig. 1; Fig. 4; [0030]-[0038] – analyzing the images to acquire congestion level as a scene datum); the operation processor analyzing relation between the scene datum and a predefined condition to decide a detection rule within the surveillance image (Fig. 1 – the processor analyzing the congestion level vs a predetermined condition representing high congestion level at step 103 to select a first detection rule as described at least in [0039]-[0043] and Fig. 5 or a second detection rule as described at least in [0044]-0070] and Fig. 6); and the operation processor automatically setting a detection boundary of the detection rule on a target region of the surveillance image corresponding to the scene datum when the scene datum conforms to the detection rule, so as to utilize the detection boundary to acquire an object behavior parameter relevant to the detection boundary (Figs. 5-6; [0039]-[0043]; [0044]-[0045] – setting a detection boundary of the first detection rule on ROIs, e.g. platform and railways areas and setting a detection boundary of the second detection rule on foreground regions so as to utilize the detection boundary to acquire OOI (object of interest) behavior parameters as further described at least in [0043] and [0044]), wherein the predefined condition is at least one of a position datum relevant to the surveillance image, a scene similarity parameter relevant to the scene datum, a user’s input command, and a cluster learning result of the input command ([0031] – at least a position datum relevant to the surveillance image because it dictates a location where it is detected in the surveillance image – also see “Response to Arguments” above).
Regarding claim 2, Ozer also discloses automatic rule setting method of claim 1, further comprising: the operation processor computing a probability value of the detection rule in accordance with a conforming degree of the predefined condition and the scene datum (Fig. 1 – a probability value of either 1 indicating the congestion level is high or 0 indicating the congestion level is not high); and the operation processor setting the detection boundary on the target region when the probability value exceeds a threshold value (Fig. 1 – when the probability value is 1 exceeding a threshold value of 0 indicating the congestion level is high, the detection boundary is set as ROIs as further described at least in [0039] and Fig. 5).
Regarding claim 3, Ozer also discloses the automatic rule setting method of claim 1, wherein the image content analysis apparatus further acquires a position datum relevant to the surveillance image for being the predefined condition, the operation processor analyzes relevance of the position datum and the scene datum to acquire a conforming degree of the detection rule ([0031] – acquiring labeled regions relevant to the surveillance image to define ROIs such as platforms and railway areas, analyzing relevance of position datum defining platform and railway areas and what in the image to determine whether the congestion level in this area conforms degree of the detection rule).
Claim 10 is rejected for the same reason as discussed in claim 1 above in view of Ozer also disclosing an image content analysis apparatus ([0072]), comprising: an operation processor ([0057] – a central processor) adapted to perform the method (see discussion of claim 1 above).
Claim 11 is rejected for the same reason as discussed in claim 2 above.
Claim 12 is rejected for the same reason as discussed in claim 3 above.
Claims 4-5 and 13-14 are rejected under 35 U.S.C. 103 as being unpatentable over Ozer as applied to claims 1-3 and 10-12 above, and further in view of Saruta (US 2016/0140422 A1 – hereinafter Saruta).
Regarding claim 4, see the teachings of Ozer as discussed in claim 1 above. Ozer also discloses the image content analysis apparatus further has a memory unit electrically connected to the operation processor and adapted to store a scene similarity parameter relevant to the scene datum for being the predefined condition ([0031] – labeling regions using similar scenes implies that a memory storing a scene similarity parameter), the operation processor executes operation by the scene parameter and the scene datum to acquire a conforming degree of the detection rule ([0031] – acquiring labeled regions relevant to the surveillance image to define ROIs such as platforms and railway areas, analyzing relevance of position datum defining platform and railway areas and what in the image to determine whether the congestion level in this area conforms degree of the detection rule).
However, Chaurasia does not disclose the operation as a cluster learning operation.
Saruta discloses storing a scene similarity parameter ([0043] – a memory storing a scene similarity threshold relevant to a scene datum), the operation as a cluster learning operation by the scene similarity parameter and a scene datum ([0062]).
One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to incorporate the teachings of Saruta into the method taught by Ozer to acquire a conforming degree of the detection rule quickly based on detection of similar scenes.
Regarding claim 5, see the teachings of Ozer and Saruta as discussed in claim 4 above, in which Saruta also discloses the operation processor sets the scene similarity parameter via an input command, or sets the scene similarity parameter via an analysis result of the surveillance image ([0043]; [0062]).
The motivation for incorporating the teachings of Saruta into the method has been discussed in claim 4 above.
Claim 13 is rejected for the same reason as discussed in claim 4 above.
Claim 14 is rejected for the same reason as discussed in claim 5 above.
Claims 6-8 and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Ozer as applied to claims 1-3 and 10-12 above, and further in view of Chaurasia et al. (US 2024/0338923 A1 – hereinafter Chaurasia).
Regarding claim 6, see the teachings of Ozer as discussed in claim 1 above. However, Ozer does not disclose the image content analysis apparatus further has a memory unit electrically connected to the operation processor, the operation processor adjusts the detection boundary in accordance with at least one input command, and stores the adjusted detection boundary into the memory unit for optionally being the predefined condition.
Chaurasia discloses an automatic rule setting method, wherein an image content analysis apparatus has a memory unit electrically connected to an operation processor, the operation processor adjusts a detection boundary in accordance with at least one input command, and stores the adjusted detection boundary into the memory unit for optionally being a predefined condition ([0041]-[0043]; Fig. 8 – the user can set the ROIs and the ROIs are stored).
One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to incorporate the teachings of Chaurasia into the method taught by Ozer to enhance the user interface of the method by allowing the user to manually set the boundary if desired, to at least correct any inaccuracy.
Regarding claim 7, see the teachings of Ozer and Chaurasia as discussed in claim 6 above, in which Chaurasia also discloses the operation processor replaces the automatically-setting detection boundary by the adjusted detection boundary, or utilizes the adjusted detection boundary to accordingly adjust the automatically-setting detection boundary ([0041]-[0043]; Fig. 8 – the user can set the ROIs to replace the previously set ROIs, and the ROIs are stored).
The motivation for incorporating the teachings of Saruta into the method has been discussed in claim 6 above.
Regarding claim 8, see the teachings of Ozer and Chaurasia as discussed in claim 6 above, in which Chaurasia also discloses the automatic rule setting method of claim 6, wherein the operation processor analyzes the adjusted detection boundary and the scene datum to acquire a conforming degree of the detection rule ([0041]-[0043]; Fig. 8).
The motivation for incorporating the teachings of Saruta into the method has been discussed in claim 6 above.
Claim 15 is rejected for the same reason as discussed in claim 6 above.
Claim 16 is rejected for the same reason as discussed in claim 7 above.
Claim 17 is rejected for the same reason as discussed in claim 8 above.
Claims 9 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Ozer and Chaurasia as applied to claims 1-3, 6-8, 10-12, and 15-17 above, and further in view of Saruta.
Regarding claim 9, see the teachings of Ozer and Chaurasia as discussed in claim 6 above, in which Chaurasia also discloses the automatic rule setting method of claim 6, wherein the operation processor adjusts the detection boundary via a plurality of input commands ([0041]-[0043]; Fig. 8 – the user can select the ROIs multiple times using a plurality of input commands), and executes operation by the adjusted detection boundary and the scene datum to acquire a conforming degree of the detection rule ([0041]-[0043]; Fig. 8).
The motivation for incorporating the teachings of Saruta into the method has been discussed in claim 6 above.
However, Ozer and Chaurasia do not disclose the operation as a cluster learning operation
Saruta discloses an operation as a cluster learning operation ([0062]).
One of ordinary skill in the art before the effective filing date of the claimed invention would have been motivated to incorporate the teachings of Saruta into the method taught by Ozer and Chaurasia to acquire a conforming degree of the detection rule quickly based on detection of similar scenes.
Claim 18 is rejected for the same reason as discussed in claim 9 above.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 HUNG Q DANG whose telephone number is (571)270-1116. The examiner can normally be reached IFT.
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, Thai Q Tran can be reached at 571-272-7382. 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.
/HUNG Q DANG/Primary Examiner, Art Unit 2484
Prosecution Insights