MACHINE LEARNING DEVICE, MACHINE LEARNING METHOD, ANDRECORDING MEDIUM STORING MACHINE LEARNING PROGRAM

    公开(公告)号:US20220405894A1

    公开(公告)日:2022-12-22

    申请号:US17778576

    申请日:2019-11-25

    Inventor: Kosuke YOSHIMI

    Abstract: This machine-learning device is provided with: a detection unit which detects a loss of consistency with a lapse of time in a determination result for unit data, the determination result being output from a determination unit that generates a learning model to be used when performing prescribed determination for one or more pieces of the unit data that form time series data; and a selection unit which selects, on the basis of the result of detection by the detection unit, unit data to be used as teacher data when the determination unit updates the learning model, thereby efficiently raising the accuracy of the learning model when machine learning is performed on the basis of the time series data.

    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND RECORDING MEDIUM

    公开(公告)号:US20220139094A1

    公开(公告)日:2022-05-05

    申请号:US17435496

    申请日:2019-03-07

    Inventor: Kosuke YOSHIMI

    Abstract: An image processing device is provided that can easily generate label data used for an object recognition technology using three-dimensional point cloud data. The image processing device (1) includes a three-dimensional point cloud obtaining unit (2), a two-dimensional label obtaining unit (4), and a label conversion unit (6). The three-dimensional point cloud obtaining unit (2) obtains three-dimensional point cloud data that represents a three-dimensional point cloud of an object. The two-dimensional label obtaining unit (4) obtains two-dimensional label data corresponding to a two-dimensional image of the object. The label conversion unit (6) associates the two-dimensional label data with the three-dimensional point cloud data, and converts the two-dimensional label data into three-dimensional point cloud label data that indicates a label of the three-dimensional point cloud.

    IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND STORAGE MEDIUM

    公开(公告)号:US20190012766A1

    公开(公告)日:2019-01-10

    申请号:US15753741

    申请日:2017-06-13

    Inventor: Kosuke YOSHIMI

    Abstract: The provided is an image processing device, an image processing method, and a program that can solve the above described problems and can normalize the distortion in the a fisheye image without being influenced by receiving the influence of the a fisheye optical system even when the positional relationship between the an optical axis of the a fisheye camera and the a plane to which the an object is grounded does not satisfy a certain conditions.An image processing device 10 includes: a fisheye image acquisition unit 11 that acquires a fisheye image; a viewpoint compensation vector acquisition unit 12 that acquires, based on a roll angle around an optical axis and a pitch angle of the optical axis of an imaging apparatus, a viewpoint compensation vector for converting the fisheye image into an image that is obtainable by taking an image of the object from a direction parallel to a ground plane of the object; and an image generation unit 13 that sets a plurality of viewpoints for a converted fisheye image that is the fisheye image converted using the viewpoint compensation vector, the plurality of viewpoints being parallel to the ground plane, performs a distortion correction by perspective projection approximation based on a coordinate system axes of which include a line of sight from a viewpoint for each of the plurality of viewpoints, and generates a single normalized image using image elements of vertical direction, the image elements each extracted from corrected fisheye images.

Patent Agency Ranking