Object Detection Device
    1.
    发明申请

    公开(公告)号:US20180137339A1

    公开(公告)日:2018-05-17

    申请号:US15574687

    申请日:2016-06-15

    Abstract: Provided is an object detection device capable of reliably recognizing a vehicle. This object detection device detects multiple three-dimensional objects from a left image and a right image captured with a left imaging unit and a right imaging unit (S103), extracts, as combination candidates from among the multiple three-dimensional objects, two three-dimensional objects which exist with an interval to the left/right, and determines whether a sparse parallax region, which is a region having a smaller parallax density than left/right regions, exists in an intermediate region between the two three-dimensional objects extracted as combination candidates. Then, the regions of two three-dimensional objects (for which it has been determined that a sparse parallax region exists in the intermediate region, and which have tentatively been identified as a single three-dimensional object) are extracted respectively from the left and right images and compared to each other, a determination is made regarding whether the perspective is the same, and when it is determined that the perspective is the same, the two three-dimensional objects are determined to be a single three-dimensional object.

    Traveling Road Boundary Estimation Apparatus and Traveling Assistance System Using Same

    公开(公告)号:US20190156129A1

    公开(公告)日:2019-05-23

    申请号:US16301782

    申请日:2017-07-12

    Abstract: The present invention provides a traveling road boundary estimation apparatus that is capable of estimating the position and shape of a traveling road boundary highly reliably, and a traveling assistance system. The present invention has: a boundary feature map generation unit that generates, on the basis of an image acquired from an external sensor, a boundary feature map for storing a feature amount regarding the presence of a traveling road boundary, for each grid of the image or an image generated by converting the image into an image of another visual point; a boundary candidate setting unit that sets, as boundary candidates, a plurality of paths continuous in a depth direction from a coming-within-sight detection start-end position to a given detection tail end position, the positions both falling within a preset sensor view angle; a boundary likelihood evaluation unit that calculates, for each of the boundary candidates, a boundary likelihood evaluation value obtained by adding the feature amount of a relevant boundary feature map and a continuity evaluation value for the depth-direction together; and a traveling road boundary determination unit that determines a traveling road boundary by comparing the boundary likelihood evaluation values of the boundary candidates calculated by the boundary likelihood evaluation unit.

    IMAGE PROCESSING DEVICE
    3.
    发明申请

    公开(公告)号:US20180321030A1

    公开(公告)日:2018-11-08

    申请号:US15500127

    申请日:2015-08-17

    Abstract: Provided is an image processing device capable of maintaining recognition accuracy for distance, and the like, while meeting conflicting demands such as suppressing the response delay from image input from a camera to calculation result output, enhancing recognition accuracy, reducing calculation load (enhancing processing efficiency), and enhancing response speed. The time of the starting of the processing (S105) of a first distance calculation unit (105) for calculating the relative distance to an object on the basis of current position information determined on the basis of a left or right image and past position information for the object is set to an earlier time than the ending of the processing (S107) of an object detection unit (107) for determining current position information for an object on the basis of parallax information obtained from the left and right images and detecting the object.

    PERIPHERY RECOGNITION DEVICE
    4.
    发明申请

    公开(公告)号:US20180197020A1

    公开(公告)日:2018-07-12

    申请号:US15741807

    申请日:2016-08-05

    Abstract: Provided is a periphery recognition device that makes it possible to: minimize the load from object recognition processing for recognizing an object moving between one region covered by a long-distance sensor and/or a wide-angle short-distance sensor to another such region; the periphery recognition device being able to reduce the proportion of non-recognition or erroneous recognition of objects moving from a region covered by the long-distance sensor or the wide-angle short-distance sensor to a boundary region. There is provided a first sensor 11a, a second sensor 11b, a long-distance object recognition unit 13 for recognizing an object present in a long-distance area on the basis of three-dimensional long-distance data calculated on the basis of situation data acquired using the first sensor 11a, a short-distance object recognition unit 14 for recognizing an object present in a wide-angle and short-distance area on the basis of three-dimensional wide-angle short-distance data calculated on the basis of situation data acquired using the second sensor 11b, and a feedback unit 15 for transferring information relating to the objects between the long-distance object recognition unit 13 and the short-distance object recognition unit 14.

    Stereo Image Processing Device
    6.
    发明申请

    公开(公告)号:US20200267366A1

    公开(公告)日:2020-08-20

    申请号:US16645865

    申请日:2018-07-27

    Abstract: In order to improve parallax accuracy and output an accurate distance, this stereo image processing device is provided with: a stereo image capture unit that captures a plurality of images with different viewpoints; a synchronization unit that synchronizes image capture times when the plurality of images are captured; image correction units that parallelize and output the plurality of images captured by the stereo image capture unit; a parallax measurement unit that detects parallax on the basis of the images outputted by the image correction units; and an object detection unit that detects an object on the basis of the parallax measured by the parallax measurement unit, and is further provided with delay amount holding units that each hold, pixel by pixel, delay times from the image capture times synchronized by the synchronization unit, and an object parallax correction unit that corrects the parallax of the object detected by the object detection unit on the basis of the delay times held by the delay amount holding units.

    STEREO CAMERA
    7.
    发明申请
    STEREO CAMERA 审中-公开

    公开(公告)号:US20200068186A1

    公开(公告)日:2020-02-27

    申请号:US16466356

    申请日:2017-12-15

    Abstract: The present invention provides a stereo camera in which it is possible to improve the precision of correcting vertical offset between a first image captured by a first image-capture unit and a second image captured by a second image-capture unit. In the present invention, an image-capture system unit 100a captures a benchmark image. An image-capture system unit 100b captures a reference image. A geometry correction unit 125 generates a plurality of geometry-corrected reference images having differing amounts of vertical-direction movement from the reference image. A parallax calculation unit 126 generates a plurality of parallax images from the combination of the benchmark image and each of the reference images. A parallax image evaluation unit 131 calculates evaluation values pertaining to the reliability of each of the parallax images. A vertical offset correction unit 132: calculates, on the basis of a correspondence relationship between vertical offset and the evaluation values pertaining to reliability, an evaluation value pertaining to the maximum reliability and a vertical offset that corresponds to this evaluation value; and sets the vertical offset that corresponds to the evaluation value pertaining to the maximum reliability as a vertical offset correction amount.

    ONBOARD ENVIRONMENT RECOGNITION DEVICE
    8.
    发明申请

    公开(公告)号:US20180137375A1

    公开(公告)日:2018-05-17

    申请号:US15574374

    申请日:2016-07-01

    Abstract: An onboard environment recognition device is obtained with which it is possible to improve recognition performance within the headlight illumination range and outside the headlight illumination range of a vehicle with an onboard camera. This onboard environment recognition device has: an imaging unit 100 for imaging, using a camera installed in the vehicle, at a wider-angle range than the headlight illumination range; an in-illumination/out-of-illumination exposure adjustment unit for setting appropriate exposure conditions separately within the headlight illumination range and outside the headlight illumination range; and a recognition unit 500 for recognizing images on the basis of the acquired images. Therefore, it is possible to maintain high recognition performance in the boundary regions of the headlight illumination range, and outside the range, and the present invention can also be used for wide-angle sensing at night.

    HOST VEHICLE POSITION ESTIMATION DEVICE
    10.
    发明申请

    公开(公告)号:US20170314956A1

    公开(公告)日:2017-11-02

    申请号:US15520182

    申请日:2015-11-18

    Abstract: Provided is a host vehicle position estimation device capable of accurately estimating the position of a host vehicle on a map even if there is no landmark that can be referred to on an image photographed using a camera. A host vehicle position is estimated on the basis of intermediate information about a landmark name and landmark distance for an intermediate object extracted from a photographed image of the surroundings of a host vehicle, distance information about the distance to the intermediate object, and landmark information stored beforehand about the landmark name and position.

Patent Agency Ranking