MODEL GENERATION APPARATUS, MODEL GENERATION METHOD, AND RECORDING MEDIUM

    公开(公告)号:US20220301293A1

    公开(公告)日:2022-09-22

    申请号:US17640571

    申请日:2019-09-05

    Inventor: Tetsuo INOSHITA

    Abstract: A plurality of recognition units respectively recognize image data using a learned model and output degrees of reliability corresponding to classes regarded as recognition targets by respective recognition units. A reliability generation unit generates degrees of reliability corresponding to a plurality of target classes based on the degrees of reliability output from the plurality of recognition units. A target model recognition unit recognizes the same image data as that recognized by the recognition units, by using a target model, and adjusts parameters of the target model in order to match the degrees of reliability corresponding to the target classes generated by a generation unit that outputs degrees of reliability corresponding to the target classes with the degrees of reliability corresponding to the target classes output from the target model recognition unit.

    IMAGE PROCESSING APPARATUS, IMAGE PROCESSING METHOD, AND NONTRANSITORY COMPUTER READABLE MEDIUM STORING PROGRAM

    公开(公告)号:US20220164990A1

    公开(公告)日:2022-05-26

    申请号:US17440407

    申请日:2020-01-10

    Inventor: Tetsuo INOSHITA

    Abstract: The present disclosure provides an image processing apparatus capable of efficiently generating a learning model having a high accuracy. An image processing apparatus (1) includes a data acquisition unit (2), a data generation unit (4), a recognition accuracy calculation unit (6), and a learning data output unit (8). The data acquisition unit (2) acquires input image data. The data generation unit (4) converts the input image data by using a data conversion parameter and newly generates image data. The recognition accuracy calculation unit (6) calculates a recognition accuracy of the image data generated by the data generation unit (4) by using a learning model stored in advance. The learning data output unit (8) outputs, as learning data, the image data of which the recognition accuracy calculated by the recognition accuracy calculation unit (6) is lower than a first threshold.

    MODEL PROVIDING SYSTEM, METHOD AND PROGRAM

    公开(公告)号:US20210133495A1

    公开(公告)日:2021-05-06

    申请号:US17053484

    申请日:2018-05-07

    Inventor: Tetsuo INOSHITA

    Abstract: When an identification system serving as a model providing destination is determined, model selection means 603 selects models to be recommended to an operator as models to be integrated based on similarities between an attribute of data collection means included in the determined identification system and attributes of the data collection means included in the identification systems other than the determined identification system. Display control means 604 displays a screen for presenting the identification systems corresponding to the models selected by the model selection means 603 and the identification systems corresponding to the models which are not selected by the model selection means 603 to an operator. The operator can designate the identification systems from among the presented identification systems. Model integration means 602 generates a model by integrating the models corresponding to the identification systems designated by the operator on the screen.

    INFORMATION PROCESSING APPARATUS, CONTROL METHOD, AND PROGRAM

    公开(公告)号:US20200084417A1

    公开(公告)日:2020-03-12

    申请号:US16466345

    申请日:2016-12-05

    Inventor: Tetsuo INOSHITA

    Abstract: To accurately detect theft of a product. An information processing apparatus (2000) acquires a reference image (13) in which a product exhibition location is imaged. In addition, the information processing apparatus (2000) acquires a comparison image (14), in which a product shelf is imaged at a time after the reference image (13) is imaged. Furthermore, the information processing apparatus (2000) computes the quantity of reduction in products inside a surveillance area (15) included in both the reference image (13) and the comparison image (14). Furthermore, the information processing apparatus (2000) outputs the warning in a case where the computed quantity of reduction is equal to or larger than the reference value.

    INFORMATION PROCESSING APPARATUS, CONTROL METHOD, AND PROGRAM

    公开(公告)号:US20200084416A1

    公开(公告)日:2020-03-12

    申请号:US16466342

    申请日:2016-12-05

    Inventor: Tetsuo INOSHITA

    Abstract: A technology is provided which is capable of surveilling a dishonest action and which is easily introduced.A first camera (10), a second camera (20), and a third camera (30) respectively generate a first captured image (11), a second captured image (21), and a third captured image (31). An exit (50) is imaged in the first captured image (11). An exhibition location (60) is imaged in the second captured image (21). A payment area (70) is imaged in the third captured image (31). An information processing apparatus (2000) detects a person from the first captured image (11), and determines whether or not the detected person is included in the second captured image (21). In a case where it is determined that the person who is detected from the first captured image (11) is included in the second captured image (21) and a degree of doubtfulness of the person is high, the information processing apparatus (2000) determines whether or not the person is included in the third captured image (31). In a case where the person is not detected from the third captured image (31), the information processing apparatus (2000) performs a warning process.

    INFORMATION PROCESSING APPARATUS, INFORMATION PROCESSING METHOD, AND INFORMATION PROCESSING PROGRAM

    公开(公告)号:US20200033132A1

    公开(公告)日:2020-01-30

    申请号:US16497692

    申请日:2017-03-31

    Inventor: Tetsuo INOSHITA

    Abstract: In order to fly a flying body more safely using a flight route according to a fall enable area, there is provided an image processing apparatus including a detector that detects a fall enable area on the ground surface based on a flying body video obtained when a flying body captures a ground area spreading below while moving. The image processing apparatus further includes a falling range estimator that estimates a falling range on the ground surface in case of a fall, and a decision unit that decides a flight route of the flying body such that the falling range is covered by the detected fall enable area.

Patent Agency Ranking