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 .
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.
Claims 1-2, 5 and 8-9 are rejected under 35 U.S.C. 103 as being unpatentable over Sosaku (Japan Patent Pub. No.: JP2016031564A) hereinafter Sosaku, in view of Mihoko (Japan Patent Pub. No.: JP2002083297A), hereinafter Mihoko.
Regarding claim 1, Sosaku teaches an object recognition system comprising: at least one memory storing instructions (Therefore, these "units" may be realized as a computer program executed by the CPU, may be realized as an electronic circuit including an LSI and a memory, or may be realized by combining these. [0016]); and at least one processor configured to execute the instructions (Therefore, these "units" may be realized as a computer program executed by the CPU, may be realized as an electronic circuit including an LSI and a memory, or may be realized by combining these. [0016]) to: execute object recognition of a moving object appearing in a camera using a recognition dictionary (One identification dictionary having highest matching to the detection result by the sonar or the radar is selected from among the plurality of types of identification dictionary, and a pedestrian in a taken image is detected using the selected identification dictionary. Overview); acquire a first index value indicating reliability of a result of object recognition of the moving object (The detection accuracy evaluation unit 106 receives the detection result of the pedestrian detected by the pedestrian detection unit 105 using the detection identification dictionary and the pedestrian position detected by the sonars 20 to 23, and calculates the detection accuracy (which reads on “a first index value”) of the detection identification dictionary. [0030]); determine whether it is required to change a recognition dictionary to be used for the object recognition (In the pedestrian detection process of the first embodiment described above, the plurality of types of identification dictionaries stored in the identification dictionary storage unit 101 are determined in advance, and when the environment at the time of image capturing changes, an appropriate identification dictionary is selected from among the predetermined identification dictionaries. [0078]) based on the first index value (The reselection necessity determination unit 107 determines the necessity of reselection of the detection identification dictionary based on the detection accuracy (which reads on “the first index value”) calculated by the detection accuracy evaluation unit 106. [0030]).
Sosaku does not teach the following limitations as further recited, but Mihoko further teaches acquire a second index value representing an imaging environment of the camera (In the case of FIG. 9, feature vector databases 1a to 1b used in the case of daytime and sunny, feature vector databases 1c to 26a used in the case of daytime and rainy, and feature vector databases 26b to 26d used in the case of nighttime and rainy are provided corresponding to the cameras,, and, respectively. [0174]); and select the recognition dictionary to be used for the object recognition from among a plurality of recognition dictionaries based on the second index value (In the case of FIG. 9, feature vector databases 1a to 1b used in the case of daytime and sunny, feature vector databases 1c to 26a used in the case of daytime and rainy, and feature vector databases 26b to 26d used in the case of nighttime and rainy are provided corresponding to the cameras,, and, respectively. [0174]) when it is determined that the recognition dictionary is to be changed (The database switching unit 402 monitors a control signal issued by the vehicle control unit 100, estimates the current traveling environment of the vehicle from the control signal, and automatically selects a database corresponding to the environment. [0177]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Sosaku to incorporate the teachings of Mihoko to select the recognition dictionary to be used for the object recognition from among a plurality of recognition dictionaries based on the second index value when it is determined that the recognition dictionary is to be changed in order to improve the detection rate of a pedestrian due to a change in environmental factors.
Regarding claim 2, Sosaku in the combination teaches the object recognition system according to claim 1, wherein the at least one processor is further configured to execute the instructions (Therefore, these "units" may be realized as a computer program executed by the CPU, may be realized as an electronic circuit including an LSI and a memory, or may be realized by combining these. [0016]) to: determine whether it is required to change the recognition dictionary to be used for the object recognition based on the first index value of one or more moving objects (The reselection necessity determination unit 107 determines the necessity of reselection of the detection identification dictionary based on the detection accuracy calculated by the detection accuracy evaluation unit 106. [0030]) located in a predetermined distance range from the camera among moving objects appearing in the camera (Therefore, in the captured image, a rough distance to the pedestrian captured in the captured image is estimated by focusing on the fact that the farther the pedestrian is, the higher the position of the pedestrian is in the image. That is, the distance from the lower side of the image to the position where the pedestrian is detected in the captured image is acquired. This distance corresponds to a rough distance to the pedestrian. Therefore, if the distances from the lower side of the captured image are within the predetermined distances (S206: yes), it can be determined that the pedestrians are at distances that can be detected even by the sonars 20 to 23, and thus the positions at which the pedestrians are detected (the positions at which the target images are set in the captured image) are stored as detection results for detection accuracy calculation (S207). [0046]).
Regarding claim 5, Mihoko in the combination teaches the object recognition system according to claim 1, wherein the at least one processor is further configured to execute the instructions to: check whether the first index value (Then, the image processing apparatus performs collation (pattern matching) between the input image data and the data related to the model registered in the database, and determines the degree of similarity, thereby detecting the presence position of the object, the type of the object, the rough distance to the object, or the like at an extremely high speed. [0011]) is improved in a case of switching to a recognition dictionary (If the database is provided not only in correspondence with the camera but also in correspondence with a predetermined condition (for example, a condition that photographing is performed in fine weather in the daytime), the efficiency of database search and the accuracy of pattern matching are further enhanced. [0013]) selected (The database switching unit 402 monitors a control signal issued by the vehicle control unit 100, estimates the current traveling environment of the vehicle from the control signal, and automatically selects a database corresponding to the environment. [0177]) based on the second index value (In the case of FIG. 9, feature vector databases 1a to 1b used in the case of daytime and sunny, feature vector databases 1c to 26a used in the case of daytime and rainy, and feature vector databases 26b to 26d used in the case of nighttime and rainy are provided corresponding to the cameras,, and, respectively. [0174]), and changes the recognition dictionary in a case where the first index value is improved (If the database is provided not only in correspondence with the camera but also in correspondence with a predetermined condition (for example, a condition that photographing is performed in fine weather in the daytime), the efficiency of database search and the accuracy of pattern matching are further enhanced. [0013]).
Method claim 8 is drawn to the method of using the corresponding apparatus claimed in claim 1. Therefore method claim 8 corresponds to apparatus claim 1 and is rejected for the same reasons of obviousness as used above.
Claim 9 is drawn to a non-transitory computer-readable storage medium having executable instructions stored for executing the method of using the corresponding apparatus as claimed in claim 1. Therefore, claim 9 corresponds to apparatus claim 1, and is rejected for the same reasons of obviousness as used above.
Claims 3-4 and 6-7 are rejected under 35 U.S.C. 103 as being unpatentable over Sosaku (Japan Patent Pub. No.: JP2016031564A) hereinafter Sosaku, in view of Mihoko (Japan Patent Pub. No.: JP2002083297A), hereinafter Mihoko, further in view of Hironori (Japan Patent Pub. No.: JP2009295112A), hereinafter Hironori.
Regarding claim 3, Sosaku teaches the object recognition system according to claim 1, wherein the at least one processor is further configured to execute the instructions (Therefore, these "units" may be realized as a computer program executed by the CPU, may be realized as an electronic circuit including an LSI and a memory, or may be realized by combining these. [0016]) to: determine whether it is required to change the recognition dictionary based on the first index value (The reselection necessity determination unit 107 determines the necessity of reselection of the detection identification dictionary based on the detection accuracy calculated by the detection accuracy evaluation unit 106. [0030]. In the pedestrian detection process of the first embodiment described above, the plurality of types of identification dictionaries stored in the identification dictionary storage unit 101 are determined in advance, and when the environment at the time of image capturing changes, an appropriate identification dictionary is selected from among the predetermined identification dictionaries. [0078]).
The combination of Sosaku and Mihoko does not teach the following limitations as further recited, but Hironori further teaches a value obtained by weighting (The weighting unit 15 multiplies the first determination value calculated by the determination value calculation unit 14 by each of a plurality of pattern weights included in the weighting table stored in the registration dictionary unit 13, and calculates a new determination value (hereinafter referred to as a second determination value) for each type of pattern weight. [0029]) the first index value (a determination value calculation unit that calculates a determination value indicating target-likeness of the object in the image of the determination target region based on the image of the determination target region extracted by the image extraction unit and the set of the pattern and the threshold value stored in the registration dictionary. [0005]) according to a type of the moving object (In this case, for example, an ID or the like may be further associated in the determination table or the weighting table so that the determination pattern, the first determination threshold, the correct score, the incorrect score, the pattern weight, the threshold weight, and the like for each type of target object can be distinguished and used. [0058]).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Sosaku and Mihoko to incorporate the teachings of Hironori to change the recognition dictionary based on a value obtained by weighting the first index value according to a type of the moving object in order to raise the recognition rate of an object in an image.
Regarding claim 4, Sosaku in the combination teaches the object recognition system according to claim 1, wherein the at least one processor is further configured to execute the instructions (Therefore, these "units" may be realized as a computer program executed by the CPU, may be realized as an electronic circuit including an LSI and a memory, or may be realized by combining these. [0016]) to: determine whether it is required to change the recognition dictionary based on the first index value (The reselection necessity determination unit 107 determines the necessity of reselection of the detection identification dictionary based on the detection accuracy calculated by the detection accuracy evaluation unit 106. [0030]. In the pedestrian detection process of the first embodiment described above, the plurality of types of identification dictionaries stored in the identification dictionary storage unit 101 are determined in advance, and when the environment at the time of image capturing changes, an appropriate identification dictionary is selected from among the predetermined identification dictionaries. [0078]).
Hironori in the combination further teaches a criterion defined for each type of the moving object (In this case, for example, an ID or the like may be further associated in the determination table or the weighting table so that the determination pattern, the first determination threshold (which reads on “a criterion”), the correct score, the incorrect score, the pattern weight, the threshold weight, and the like for each type of target object can be distinguished and used. [0058]).
Regarding claim 6, Mihoko in the combination teaches the object recognition system according to claim 4, wherein the second index value (In the case of FIG. 9, feature vector databases 1a to 1b used in the case of daytime and sunny, feature vector databases 1c to 26a used in the case of daytime and rainy, and feature vector databases 26b to 26d used in the case of nighttime and rainy are provided corresponding to the cameras,, and, respectively. [0174]) includes at least weather information and information indicating a time zone (Here, the conditions for switching the database include day and night, time, weather, brightness, etc., and in this case, the data is switched for each situation at that time. [0172]), and wherein the at least one processor is further configured to execute the instructions to: select the recognition dictionary (The database switching unit 402 monitors a control signal issued by the vehicle control unit 100, estimates the current traveling environment of the vehicle from the control signal, and automatically selects a database corresponding to the environment. [0177]) related to a combination of the weather and the time zone from among a plurality of recognition dictionaries (Here, the conditions for switching the database include day and night, time, weather, brightness, etc., and in this case, the data is switched for each situation at that time. [0172]).
Regarding claim 7, Hironori in the combination teaches the object recognition system according to claim 1, wherein the at least one processor is further configured to execute the instructions to: acquire the first index value (a determination value calculation unit that calculates a determination value indicating target-likeness of the object in the image of the determination target region based on the image of the determination target region extracted by the image extraction unit and the set of the pattern and the threshold value stored in the registration dictionary. [0005]) for each type of the moving object (Note that determination patterns, first determination thresholds, correct scores, incorrect scores, pattern weights, threshold weights, and the like for different types of target objects may be mixed in one determination table or weighting table. In this case, for example, an ID or the like may be further associated in the determination table or the weighting table so that the determination pattern, the first determination threshold, the correct score, the incorrect score, the pattern weight, the threshold weight, and the like for each type of target object can be distinguished and used. [0058]), and outputting the acquired first index value as a performance index of the object recognition system to a predetermined output destination (The determination result integration unit 18 creates and holds a pedestrian list. Further, the determination result integration unit 18 arranges all the pedestrian lists for the objects determined to be pedestrians to create a comprehensive list, and outputs the comprehensive list as a final recognition result. [0035]. It is common knowledge that confidence values can be outputted at the same time with the pedestrian list.).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LEI ZHAO whose telephone number is (703)756-1922. The examiner can normally be reached Monday - Friday 8:00 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, 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.
/LEI ZHAO/Examiner, Art Unit 2668
/VU LE/Supervisory Patent Examiner, Art Unit 2668
Prosecution Insights