US 11,704,911 B2
Apparatus and method for identifying obstacle around vehicle
Takuya Miwa, Kariya (JP); Takayuki Hiromitsu, Kariya (JP); Masumi Fukuman, Toyota (JP); and Akihiro Kida, Toyota (JP)
Assigned to DENSO CORPORATION, Kariya (JP); and TOYOTA JIDOSHA KABUSHIKI KAISHA, Toyota (JP)
Filed by DENSO CORPORATION, Kariya (JP); and TOYOTA JIDOSHA KABUSHIKI KAISHA, Toyota (JP)
Filed on Oct. 12, 2020, as Appl. No. 17/68,236.
Claims priority of application No. JP2019-188273 (JP), filed on Oct. 14, 2019.
Prior Publication US 2021/0110175 A1, Apr. 15, 2021
Int. Cl. G06K 9/00 (2022.01); G06V 20/58 (2022.01); G06V 10/75 (2022.01); G06F 18/24 (2023.01); G06F 18/2113 (2023.01); G06V 30/24 (2022.01)
CPC G06V 20/58 (2022.01) [G06F 18/2113 (2023.01); G06F 18/24 (2023.01); G06V 10/751 (2022.01); G06V 10/76 (2022.01); G06V 30/2504 (2022.01)] 11 Claims
OG exemplary drawing
 
1. An apparatus for identifying an obstacle around a vehicle, comprising:
a non-transitory memory storing one or more computer programs; and
a processor executing the one or more computer programs to:
acquire an image captured by a camera mounted to the vehicle;
extract feature points of the image;
generate, for each of the feature points of the image acquired before a current time, an optical flow that is a movement vector from a feature point acquired before the current time to a corresponding feature point of the image acquired at the current time;
classify optical flows into groups based on pixel positions of the feature points; and
identify, for each of the groups, whether an object corresponding to a group of optical flows in the image is a stationary object, in which the stationary object comprises a regular or substantially regular pattern, or a moving object based on a degree of variability in lengths of the optical flows of the group relative to lengths of other optical flows of the group.