公开(公告)号：US11615627B2

公开(公告)日：2023-03-28

申请号：US16597958

申请日：2019-10-10

Applicant: Mitsubishi Electric Corporation ,  MAZDA MOTOR CORPORATION

Inventor： Noriyoshi Yamashina ,  Masanori Mori ,  Koji Iida ,  Tomohiro Akiyama ,  Shinichi Tateiwa ,  Takayuki Moritani ,  Hiroyuki Ueda ,  Hideaki Tamazumi ,  Junki Tamaru ,  Yoshihiro Yamamoto

IPC: G06V20/56 ,  B60W30/09 ,  B60W10/20 ,  B60W10/04 ,  G01S7/41 ,  G01S13/86 ,  G01S13/931

Abstract: There are provided an object recognition apparatus that raises the recognition accuracy for a surrounding object and a vehicle control apparatus, and an object recognition method and a vehicle control method. An object recognition apparatus receives object data, which is a state value of the object, from a first sensor for detecting a surrounding object; compares estimation data obtained through estimation of a state value of the object, based on recognition data calculated in a past period, with the object data, and determines whether or not the object data is data in a low-resolution state; then, in accordance with the determination result, calculates the state value of the object by use of object data and estimation data and then generates the state value as recognition data, so that the recognition accuracy for an object is raised.

公开(公告)号：US11100340B2

公开(公告)日：2021-08-24

申请号：US16448009

申请日：2019-06-21

Applicant: MAZDA MOTOR CORPORATION

Inventor： Junki Tamaru ,  Takayuki Moritani ,  Hiroyuki Ueda ,  Hideaki Tamazumi ,  Yoshihiro Yamamoto

IPC: G06K9/00

Abstract: A line detector apparatus and method on a vehicle for detecting a line on a road with a higher degree of accuracy. The vehicle includes front, right-side and left-side image capturing sensors mounted on a vehicle and respectively capture an image, including a road surface, at the front and right and left sides of the vehicle to respectively generate front, right-side and left-side images. The line detector includes a processor that calculates a line on a road as a first line from the front image, the line on the road as a second line from the right-side image, and the line on the road as a third line from the left-side image. The processor selects one of multiple mutually-different algorithms based on the first to third lines, and calculates the line on the road based on the first to third lines by using the selected algorithm.