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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
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.
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.
Claim(s) 1, 2, and 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ben et. al. (Chinese Patent CN 112258850 A) in view of Zhu et. al. (Chinese Patent CN 118212691 A).
Regarding claim 1 and claim 8, Ben et. al. discloses a non-motor vehicle recognition method and system based on a multi-sensor collaboration, comprising: constructing a sensor group based on a plurality of sensors, and performing a data collection based on a target range through the sensor group to generate a multi-class regional dataset; transmitting the multi-class regional dataset to a data fusion channel to generate an initial fusion dataset (Ben et. al./CN 112258850 A, Abstract: multi-sensor data fusion system, comprising an information collecting unit, a fusion analysis unit and a comprehensive determination unit; pg. 4, para. 7: the fusion analysis unit uses a multi-sensor data fusion algorithm to finish the fusion processing of the collected data); synchronizing the initial fusion dataset to a data preprocessing unit to perform preprocessing (Ben et. al. Abstract: the information collecting unit is used for performing data pre-processing at the front end).
However, Ben et. al. fails to disclose updating the initial fusion dataset to generate a target fusion dataset; utilizing a feature extraction unit to traverse the target fusion dataset to perform a feature extraction of a target non-motor vehicle and generating a target feature information set, wherein there is a correspondence between the target feature information set and the target fusion dataset; and constructing a target recognition unit based on the target feature information set, and intelligently recognizing the target fusion dataset through the target recognition unit.
Zhu et. al. teaches updating the initial fusion dataset to generate a target fusion dataset (Zhu et. al. pg. 8, para. 3-10: the SORT tracking algorithm comprises a Hungary algorithm and a Kalman filter; calculating a globally optimal matching pair of a pedestrian tracking target and a pedestrian target frame by using a Hungary algorithm; updating a posterior estimated value of the pedestrian tracking target for the matched pedestrian tracking target and the pedestrian target frame, and outputting a result to a Kalman filter; The Kalman filter predicts the position of a pedestrian target in a next frame image of the monitoring video); utilizing a feature extraction unit to traverse the target fusion dataset to perform a feature extraction of a target non-motor vehicle (Zhu et. al.: pg. 10, para. 12, pg. 11, para. 4: Compared with the original features, the novel feature map processed by the CBAM attention mechanism module not only improves the correlation among the channels and increases the attention degree to key information in the map, so that the feature extraction network can adaptively select the important information in the map. The C3 layer and the CBAM attention mechanism module perform feature extraction, and the feature extraction enters an SPPF module to fuse multi-scale features of an input image), and generating a target feature information set, wherein there is a correspondence between the target feature information set and the target fusion dataset; and constructing a target recognition unit based on the target feature information set, and intelligently recognizing the target fusion dataset through the target recognition unit (Zhu et. al.: pg.11, para.7: Aiming at the problem that the behavior of the illegal manned of the non-motor vehicle is not easy to monitor at present, the invention provides a method for researching the behavior detection method of the illegal manned of the non-motor vehicle by utilizing an artificial intelligence means; and collecting non-motor vehicle data at the traffic intersection, marking the data, and making a data set as input of the neural network to implement a target detection task. The SORT tracking algorithm is further combined with the improved Yolov algorithm, so that the targets can be tracked and marked while the illegal manned behaviors of the non-motor vehicles are accurately detected, the illegal manned behaviors of the non-motor vehicles at the traffic intersection can be monitored in real time, and the running accident rate of the non-motor vehicles can be reduced.).
This is important to the claimed invention because the target fusion dataset enables more accurate predictions on the behavior of non-motor vehicle targets. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Ben et. al. and Zhu et. al. so that the target fusion dataset is included and built properly as part of the solution of the claimed invention.
Regarding claim 2, Ben et. al. and Zhu et. al. disclose the method according to claim 1, and Ben et. al. further discloses wherein constructing a sensor group based on a plurality of sensors, and performing a data collection based on a target range through the sensor group to generate a multi-class regional dataset comprises (Ben et. al. pg. 5, para. 5: The basic principle of information fusion is: Complementary and redundant information of various sensors in space and time is combined with redundancy information according to some optimization rule or algorithm, and consistency explanation and description of the observation object are generated.): deploying the plurality of sensors within the target range based on monitoring demand information, communicatively associating the sensors within the same region, and constructing the sensor group according to association information; performing the data collection on the target region through the sensor group to generate a plurality of regional datasets; and performing a cluster analysis on the plurality of regional datasets to generate the multi-class regional dataset (Ben et. al. pg. 5, para. 7: The flow detection scene mainly uses a microwave detector and a video camera for pedestrian, non-motor vehicle, motor vehicle for sensing detection, the data layer and decision layer for information fusion, using the weighing algorithm on the data layer; using the least square method to determine the specific weight value; multiplying the detection value of each sensor with the weight and then summing to obtain the fusion data, the decision layer adopts BP neural network algorithm, combining the real-time data and history data, distributing the time distribution characteristic of the parallel processing traffic data. The target detection scene mainly uses long-short distance millimeter wave radar and video camera to pedestrian, motor vehicle/non-motor vehicle for sensing identification.).
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ben et. al. (Chinese Patent CN 112258850 A) in view of Zhu et. al. (Chinese Patent CN 118212691 A) as applied to claim 1 above, and further in view of Zhao et. al. (Chinese Patent CN 116413716 A) and Zhang et. al. (Chinese Patent CN 106408940 B1).
Regarding claim 3, Ben et. al. and Zhu et. al. disclose the method according to claim 1. However, Ben et. al. and Zhu et. al. fail to disclose wherein the method for the data fusion channel comprises: performing time stamp normalization on the multi-class regional dataset, detecting a time deviation of the multi-class regional dataset based on a standard time stamp, and generating time deviation data; performing a time calibration based on the time deviation data, verifying a time alignment degree according to a calibration result, and establishing a fusion time alignment branch; constructing a virtual space coordinate system, traversing the multi-class regional dataset to perform a positional registration, and generating a registration coordinate set; verifying a space alignment degree based on the registration coordinate set, and establishing a fusion space alignment branch; and constructing the data fusion channel based on the fusion time alignment branch and the fusion space alignment branch, wherein there exists a sequence of connections between the fusion time alignment branch and the fusion space alignment branch.
Zhao et. al. teaches wherein the method for the data fusion channel comprises: performing time stamp normalization on the multi-class regional dataset (Zhao et. al., CN116413716 A: pg. 4, para. 5, s1: respectively acquiring image data and radar data through an image sensor and a radar sensor, recording a time stamp of each frame when the image data and the radar data are acquired, and uploading the image data and the radar data to a data processing module through an image data buffer area and a radar data buffer area respectively), detecting a time deviation of the multi-class regional dataset based on a standard time stamp, and generating time deviation data.
Zhang et. al. teaches performing a time calibration based on the time deviation data (Zhang et. al., CN106408940 B1, pg. 6, para. 2: the third step: time and space calibration, calibrating the time and space reference point of each sensor), verifying a time alignment degree according to a calibration result, and establishing a fusion time alignment branch; constructing a virtual space coordinate system, traversing the multi-class regional dataset to perform a positional registration, and generating a registration coordinate set; verifying a space alignment degree based on the registration coordinate set, and establishing a fusion space alignment branch (Zhang et. al. CN106408940 B1, aligning to the same time reference in time, converting to the same coordinate system in the space, establishing the coordinate corresponding relation,…if each sensor is independently asynchronous work in time and space, then must perform time shift and coordinate transformation, to form a unified time and space reference point needed by fusion); and constructing the data fusion channel based on the fusion time alignment branch and the fusion space alignment branch, wherein there exists a sequence of connections between the fusion time alignment branch and the fusion space alignment branch (Zhang et. al. the fifth step: data association, judging whether the data of different time space is from the same target, matching the radar with the video target, successfully matching and determining as the real target, processing according to the setting mode, the target cannot be matched, the target cannot be determined, the possibility is not excluded; taking the distance of the target, orientation, relative speed as the parameter, calculating the correlation degree value of the radar target and the video target, when the correlation value is greater than the set threshold value, considering matching; performing comprehensive and state estimation to the related data of the same sensor successively measuring and reporting, and referring to the test report of other information source to modify and verify the data to associate the point trace transmitted by each sensor, keeping the target for continuous tracking. the seventh step: estimating traffic behavior; radar detects the target, outputting the three-dimensional coordinate, controlling the video monitoring output image, according to the position relation of the video coordinate model and the radar and the video, A, B two points minimum distance value d as the matching condition, so that the information of the same target detected by the two sensors are corresponding to each other, so as to match and identify the same target from the synchronous image. comparing the data set of all the target with the behavior pattern of the possible situation determined previously, to determine which behavior mode is most matched with the state of all targets in the monitoring area, storing the information to the traffic information platform the same.).
This timestamp normalization step is important to the claimed invention because the non-motor vehicles are moving and there needs to be a reference point to the image data to determine the position information of the non-motor vehicle. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Ben et. al., Zhu et. al., Zhao et. al. and Zhang et. al. so that the non-motor vehicle can be properly tracked in time.
Claim(s) 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ben et. al. (Chinese Patent CN 112258850 A) in view of Zhu et. al. (Chinese Patent CN 118212691 A) as applied to claim 1 above in further view of Zhang et. al. (Chinese Patent CN 116702093 B)
Regarding claim 5, Ben et. al. and Zhu et. al. disclose the method according to claim 1. However, Ben et. al. and Zhu et. al. fail to disclose wherein synchronizing the initial fusion dataset to a data preprocessing unit to perform preprocessing, and updating the initial fusion dataset to generate a target fusion dataset comprises: performing data cleaning on the initial fusion dataset, and executing multiple data processing instructions according to a cleaning result, wherein the multiple data processing instructions include missing value processing and abnormal value processing; generating a cleaned dataset through the missing value processing and the abnormal value processing; and integrating the cleaned dataset, performing a data reduction on the integrated cleaned dataset, verifying the cleaned dataset based on a reduction result, and updating the initial fusion dataset as the target fusion dataset for an output.
Zhang et. al. teaches wherein synchronizing the initial fusion dataset to a data preprocessing unit to perform preprocessing, and updating the initial fusion dataset to generate a target fusion dataset comprises: performing data cleaning on the initial fusion dataset, and executing multiple data processing instructions according to a cleaning result, wherein the multiple data processing instructions include missing value processing and abnormal value processing; generating a cleaned dataset through the missing value processing and the abnormal value processing (Zhang et. al. [0019]-[0068], Figures 1-10: First, data cleaning includes outlier detection, noise cancellation and data normalization. Second, missing value processing is an important element of data scrubbing.); and integrating the cleaned dataset, performing a data reduction on the integrated cleaned dataset, verifying the cleaned dataset based on a reduction result, and updating the initial fusion dataset as the target fusion dataset for an output (Zhang et. al. [0019]-[0068], Figures 1-10: based on the extracted feature set, the use of a principal component analysis and feature selection algorithms can reduce the dimensionality of the features and preserve important information. Principal component analysis can convert high-dimensional features into a low-dimensional feature space by linear transformation, reducing the redundancy of the data, and preserving the dominant variance in the data. Feature selection algorithms may help to filter out features that are most useful for a target task, further reduce the set of features.). This type of target fusion analysis is important to the claimed invention because it reduces data redundancy through data reduction. On this basis, the person skilled in the art can set the data processing order according to the actual data processing needs, such as fusing the multi-region dataset to generate an initial fused dataset, data pre-processing of the initial fused dataset, and data reduction followed by the validation of the washed dataset to ensure reliability of the data based on the reduction results are within the ordinary skill in the art. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Ben et. al., Zhu et. al and Zhang et. al. so that these features are included in the solution of the claimed invention.
Claim(s) 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Ben et. al. (Chinese Patent CN 112258850 A) in view of Zhu et. al. (Chinese Patent CN 118212691 A) as applied to claim 1 above in further view Pandya et. al (United States Patent US 11675878 B1).
Regarding claim 6, Ben et. al. and Zhu et. al. disclose the method according to claim 1. However, Ben et. al. and Zhu et. al. fail to disclose comprising: obtaining a target analysis result, a background analysis result, and a noise point analysis result according to the target fusion dataset; inputting the target analysis result, background analysis result and noise point analysis result into a judger, and obtaining a recognition correction analysis result according to the judger, wherein the recognition correction analysis result includes the target analysis result, and/or the background analysis result and/or the noise point analysis result; and generating, with the recognition correction analysis result, a monitoring tag to identify an abnormal point position in the target fusion dataset based on the monitoring tag.
Pandya et. al. teaches comprising: obtaining a target analysis result, a background analysis result, and a noise point analysis result according to the target fusion dataset; inputting the target analysis result, background analysis result and noise point analysis result into a judger, and obtaining a recognition correction analysis result according to the judger, wherein the recognition correction analysis result includes the target analysis result, and/or the background analysis result and/or the noise point analysis result; and generating, with the recognition correction analysis result, a monitoring tag to identify an abnormal point position in the target fusion dataset based on the monitoring tag (Pandya et. al., col 2, lines 1-8: The term “labeled dataset”, as used herein, generally refers to a paired dataset used for training a model using supervised learning or semi-supervised learning. The term “label” or “label data” as used herein, generally refers to ground truth data. During the training process, the weights or parameters of a deep learning model are tuned to approximate the ground truth data thereby learning a mapping from input sensor data to the desired output. Col 24, lines 36-44: The RTLS may include a plurality of mobile tag devices. The mobile tag device can be the same as the mobile tag device as described in Figure 1. For example, the mobile tag device may comprise one or more sensors for detecting a position, orientation or motion state( e.g., speed, acceleration, etc.) of an individual who wears the mobile tag device or a movable object carries the mobile tag device.).
This is important to the claimed invention because with the monitoring tag, abnormal point positions in the target fusion dataset are identified based on the monitoring tag. Thus, it would have been obvious to one skilled in the art prior to the effective filing date of the claimed invention to have combined the teachings of Ben et. al., Zhu et. al. and Pandya et. al. to include the monitoring tag feature.
Allowable Subject Matter
Claims 4 and 7 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is a statement of reasons for the indication of allowable subject matter:
Regarding claim 4, Ben et. al., Zhu et. al., Zhao et. al. and Zhang et. al. disclose the method according to claim 3. However, the combination of Ben et. al., Zhu et. al., Zhao et. al. and Zhang et. al. fail to disclose wherein transmitting the multi-class regional dataset to a data fusion channel to generate an initial fusion dataset comprises: transmitting the multi-class regional dataset to the fusion time alignment branch to generate time alignment information of the multi-class regional dataset; transmitting the multi-class regional dataset to the fusion space alignment branch to generate space alignment information of the multi-class regional dataset; developing a data fusion strategy based on the time alignment information and the space alignment information; configuring weights for the multi-class regional datasets in combination with the data fusion strategy to obtain distributed weight sets, wherein the distributed weight sets and the multi-class regional datasets are in one-to-one correspondence, and a sum of the distributed weight sets is equal to 1; and performing a preliminary fusion of data on the multi-class regional datasets in accordance with the data fusion strategy based on the distributed weight sets to generate the initial fusion dataset.
Regarding claim 7, Ben et. al., Zhu et. al., and Pandya et. al. disclose the method according to claim 6, comprising: performing training according to a training operator to obtain the judger, wherein the training operator includes a plurality of groups of training samples, wherein each group of training samples includes a preset target sample, a preset background sample, a preset noise point sample, and a test sample. However, the combination of Ben et. al., Zhu et. al. and Pandya et. al. fail to disclose obtaining a discrimination error precision according to the judger, and analyzing the target fusion dataset by activating the judger when the discrimination error precision is less than a preset error precision.
No prior art combination can predict and make obvious the claims of 4 and 7.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JESSICA YIFANG LIN whose telephone number is (571)272-6435. The examiner can normally be reached M-F 7:00am-6:15pm, with optional day off.
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, Vu Le can be reached at 571-272-7332. 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.
/JESSICA YIFANG LIN/Examiner, Art Unit 2668 July 20, 2026
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights