US 12,347,207 B2
Vehicle external environment recognition apparatus
Minoru Kuraoka, Tokyo (JP)
Assigned to SUBARU CORPORATION, Tokyo (JP)
Filed by SUBARU CORPORATION, Tokyo (JP)
Filed on Sep. 8, 2022, as Appl. No. 17/940,579.
Claims priority of application No. 2021-153608 (JP), filed on Sep. 21, 2021.
Prior Publication US 2023/0086937 A1, Mar. 23, 2023
Int. Cl. G06V 20/58 (2022.01); G06T 7/12 (2017.01); G06V 10/70 (2022.01); G06V 10/98 (2022.01); G06V 20/64 (2022.01)
CPC G06V 20/58 (2022.01) [G06T 7/12 (2017.01); G06V 10/70 (2022.01); G06V 10/98 (2022.01); G06V 20/64 (2022.01); G06T 2207/20228 (2013.01); G06T 2207/30252 (2013.01); G06V 2201/08 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A vehicle external environment recognition apparatus for a vehicle, the vehicle external environment recognition apparatus comprising:
imagers configured to capture luminance images in front of the vehicle;
at least one processor; and
at least one memory coupled to the at least one processor, wherein
the at least one processor is configured to operate in cooperation with at least one program stored in the at least one memory to execute processing that comprises:
generating a first distance image from the luminance images, wherein the distance image comprises pixels, each representing a depth of an object relative to the imagers, the depth being derived from parallax between corresponding points in the luminance images;
specifying, by using semantic segmentation, a floating matter class in at least one of the luminance images, wherein the floating matter class is a category assigned to pixels in the at least one luminance images that correspond to floating substances for which collision avoidance by the vehicle is unnecessary; and
invalidating parallax associated with floating pixels that are included in the first distance image and belong to the floating matter class.