公开(公告)号：US20210081681A1

公开(公告)日：2021-03-18

申请号：US17105148

申请日：2020-11-25

Applicant: DENSO CORPORATION

Inventor： Kunihiko CHIBA ,  Yusuke SEKIKAWA ,  Koichiro SUZUKI

IPC: G06K9/00 ,  G06K9/66

Abstract: An object model learning method includes: in an object identification model forming a convolutional neural network and a warp structure warping a feature map extracted in the convolutional neural network to a different coordinate system, preparing, in the warp structure, a warp parameter for relating a position in the different coordinate system to a position in a coordinate system before warp; and learning the warp parameter to input a capture image in which an object is captured to the object identification model and output a viewpoint conversion map in which the object is identified in the different coordinate system.

公开(公告)号：US20220156985A1

公开(公告)日：2022-05-19

申请号：US17650201

申请日：2022-02-07

Applicant: DENSO CORPORATION

Inventor： Takahiro KOGUCHI ,  Yousuke HATTORI ,  Yusuke SEKIKAWA

IPC: G06T11/00 ,  G06T7/50

Abstract: A peripheral video generation device includes: a video input unit that inputs peripheral video data captured by a plurality of cameras; a video composition unit that composites the peripheral video data to generate a composite video as viewed from a predetermined viewpoint; a three-dimensional shape estimation unit that estimates a three-dimensional shape of a peripheral object based on the peripheral video data; a shielded area estimation unit that uses an estimation result of the three-dimensional shape to estimate a shielded area not visible from the predetermined viewpoint in the composite video; an inference unit that infers a video of the shielded area using deep learning; and a video superimposition unit that superimposes the video inferred by the inference unit on the shielded area in the composite video.

公开(公告)号：US20210027074A1

公开(公告)日：2021-01-28

申请号：US17039215

申请日：2020-09-30

Applicant: DENSO CORPORATION

Inventor： Kunihiko CHIBA ,  Kentaro TESHIMA ,  Yusuke SEKIKAWA ,  Koichiro SUZUKI

IPC: G06K9/00 ,  G05D1/02 ,  G06T7/50

Abstract: In a vehicle system, a space area estimation method, or a space area estimation apparatus, an outside of a vehicle is captured, and an image is generated. An object causing a blind angle in the image is recognized. A depth of the recognized object is estimated. An inside of a blind angle area formed by the object is estimated.