Object sensing device and object sensing method
An object of the present invention is to provide an object sensing device that classifies an observation point group output by a LiDAR into a real image and a mirror image when a road surface around an own vehicle is wet, and can use the mirror image for detecting the real image. An object sensing device that detects an object around a vehicle based on a point cloud data of an observation point observed by a LiDAR mounted on the vehicle includes: a road surface shape estimation unit that estimates a shape of a road surface; a road surface condition estimation unit that estimates a dry/wet situation of the road surface; and an observation point determination unit that determines a low observation point observed at a position lower than the estimated road surface by a predetermined amount or more when the road surface is estimated to be in a wet situation. The object is detected by using 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.
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.
2 . The object sensing device according to claim 1 , further configured to:
generate the dense image group including both the inverted observation point and the observation point according to a correlation of the point cloud data.
3 . The object sensing device according to claim 1 , further comprising a camera sensor mounted on the vehicle configured to capture an image comprising object information that identifies one or more regions of the image corresponding to the object, wherein
in object information of the captured image, first object information corresponding to a region of the image comprising the low observation point is determined as a mirror image of the object.
4 . An object sensing method for detecting an object around a vehicle based on point cloud data of observation points observed by a LiDAR mounted on the vehicle, the object sensing method comprising:
estimating a shape of a road surface;
estimating a dry/wet situation of the road surface;
determining 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 as in a wet situation;
detecting the object 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
determining the low observation point as a mirror image observation point in a case where another observation point exists around the inverted observation point;
generating 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;
inverting the mirror image group and combining the mirror image group with the real image group to generate a dense image group that is denser than the real image group; and
transmitting the dense image group to an external device that executes recognition processing based on the dense image group.