US 12,481,025 B2
Object sensing device and object sensing method
Kosuke Sakata, Hitachinaka (JP); and Masayoshi Kuroda, Hitachinaka (JP)
Assigned to Hitachi Astemo, Ltd., Hitachinaka (JP)
Appl. No. 17/916,475
Filed by Hitachi Astemo, Ltd., Hitachinaka (JP)
PCT Filed Jan. 22, 2021, PCT No. PCT/JP2021/002152
§ 371(c)(1), (2) Date Sep. 30, 2022,
PCT Pub. No. WO2021/199609, PCT Pub. Date Oct. 7, 2021.
Claims priority of application No. 2020-067553 (JP), filed on Apr. 3, 2020.
Prior Publication US 2023/0221410 A1, Jul. 13, 2023
Int. Cl. G01S 7/48 (2006.01); G01S 17/86 (2020.01); G01S 17/89 (2020.01); G01S 17/931 (2020.01); G06T 7/521 (2017.01); G06T 7/55 (2017.01); G06V 20/56 (2022.01); G06V 20/58 (2022.01)
CPC G01S 7/4802 (2013.01) [G01S 17/86 (2020.01); G01S 17/89 (2013.01); G01S 17/931 (2020.01); G06T 7/521 (2017.01); G06T 7/55 (2017.01); G06V 20/58 (2022.01); G06V 20/588 (2022.01); G06T 2207/10028 (2013.01); G06T 2207/30256 (2013.01)] 4 Claims
OG exemplary drawing
 
1. An object sensing device that detects an object around a vehicle based on a point cloud data of observation points observed by a LiDAR mounted on the vehicle, the object sensing device configured to:
estimate a shape of a road surface;
estimate a dry/wet situation of the road surface; and
determine a low observation point observed at a position lower than the road surface by a predetermined amount or more when the road surface is estimated to be in a wet situation, wherein
(i) the object is detected by using the point cloud data of the observation points other than the low observation point and point cloud data of an inverted observation point obtained by inverting the low observation point with reference to a height of the road surface and
(ii) the low observation point is determined as a mirror image observation point in a case where another observation point exists around the inverted observation point;
generate a mirror image group comprising mirror image observation points and a real image group comprising observation points other than the mirror image observation points according to a correlation of the point cloud data;
invert the mirror image group and combine the mirror image group with the real image group to generate a dense image group that is denser than the real image group; and
transmit the dense image group to an external device that executes recognition processing based on the dense image group.