Method and apparatus for generating depth map
In a method and apparatus for generating a depth map, the method includes obtaining a LiDAR point cloud generated by a LiDAR, obtaining a 3D bounding box for at least a portion of the LiDAR point cloud, generating a first vehicle mask corresponding to the 3D bounding box from an image point cloud obtained by projecting coordinates of points of the LiDAR point cloud into an image coordinate system, and generating the depth map by removing distant points that are not included in the 3D bounding box among points included in the first vehicle mask.
1 . A method of generating a depth map, the method comprising:
obtaining, by a processor, a Light Detection and Ranging (LiDAR) point cloud generated by a LiDAR operatively connected to the processor;
obtaining, by the processor, a 3D bounding box for at least a portion of the LiDAR point cloud;
generating, by the processor, a first vehicle mask corresponding to the 3D bounding box from an image point cloud obtained by projecting coordinates of points of the LiDAR point cloud into an image coordinate system; and
generating, by the processor, the depth map by removing distant points that are not included in the 3D bounding box among points included in the first vehicle mask.
2 . The method of claim 1 , wherein the obtaining of the 3D bounding box includes:
extracting a short-distance point cloud by removing a point cloud over a predetermined distance from the LiDAR point cloud; and
obtaining the 3D bounding box based on the short-distance point cloud.
3 . The method of claim 2 , wherein the extracting of the short-distance point cloud includes determining the predetermined distance based on at least one of a focal length of the image point cloud and a degree of distortion of spacing between points of the image point cloud.
4 . The method of claim 1 , wherein the generating of the first vehicle mask includes generating the first vehicle mask by use of a gift warping algorithm or an alpha shape scheme for points included in the 3D bounding box in the image point cloud.
5 . The method of claim 4 , wherein the generating of the first vehicle mask includes determining a second vehicle mask generated by the alpha shape scheme as the first vehicle mask in response that a value obtained by dividing an area of the second vehicle mask generated by the alpha shape scheme by an area of a third vehicle mask generated by the gift warping algorithm is less than a threshold value.
6 . The method of claim 1 , wherein the generating of the first vehicle mask includes:
generating a camera point cloud that projects the coordinates of the points of the LiDAR point cloud into a camera coordinate system by multiplying the coordinates of the points of the LiDAR point cloud by an extrinsic matrix; and
generating the image point cloud by changing a focal length of the camera point cloud.
7 . The method of claim 1 , wherein the generating of the first vehicle mask includes generating the image point cloud by converting a coordinate plane of points of a camera point cloud obtained by projecting the coordinates of the points of the LiDAR point cloud into a camera coordinate system into an image plane in which a focal length has an arbitrary value in an image plane where the focal length is normalized to 1.
8 . The method of claim 7 , wherein the generating of the image point cloud includes generating the image point cloud by multiplying coordinates of the points of the camera point cloud by an intrinsic matrix.
9 . An apparatus of generating a depth map, the apparatus comprising:
a camera;
a Light Detection and Ranging (LiDAR) configured to generate a LiDAR point cloud; and
a processor operatively connected to the camera and the LiDAR and configured to obtain a 3D bounding box for at least a portion of the LiDAR point cloud, generate a first vehicle mask corresponding to the 3D bounding box from an image point cloud that projects coordinates of points of the LiDAR point cloud into an image coordinate system, and generate the depth map by removing distant points that are not included in the 3D bounding box among points included in the first vehicle mask.
10 . The apparatus of claim 9 , wherein the processor is further configured to extract a short-distance point cloud by removing a point cloud over a predetermined distance from the LiDAR point cloud, and generate the 3D bounding box based on the short-distance point cloud.
11 . The apparatus of claim 10 , wherein the processor is further configured to determine the predetermined distance based on at least one of a focal length of the image point cloud and a degree of distortion of spacing between points of the image point cloud.
12 . The apparatus of claim 9 , wherein the processor is further configured to generate the first vehicle mask by use of a gift warping algorithm or an alpha shape scheme for points included in the 3D bounding box in the image point cloud.
13 . The apparatus of claim 12 , wherein the processor is further configured to determine a second vehicle mask generated by the alpha shape scheme as the first vehicle mask in response that a value obtained by dividing an area of the second vehicle mask generated by the alpha shape scheme by an area of a third vehicle mask generated by the gift warping algorithm is less than a threshold value.
14 . The apparatus of claim 9 , wherein the processor is further configured to generate a camera point cloud by converting a coordinate reference point of the points of the LiDAR point cloud from the LiDAR to the camera.
15 . The apparatus of claim 14 , wherein the processor is further configured to generate the camera point cloud by multiplying the coordinates of the points of the LiDAR point cloud by an extrinsic matrix.
16 . The apparatus of claim 9 , wherein the processor is further configured to generate the image point cloud by converting a coordinate plane of points of a camera point cloud obtained by projecting the coordinates of the points of the LiDAR point cloud into a camera coordinate system into an image plane where a focal length includes an arbitrary value in an image plane where the focal length is normalized to 1.
17 . The apparatus of claim 16 , wherein the processor is further configured to generate the image point cloud by multiplying coordinates of the points of the camera point cloud by an intrinsic matrix.
18 . The apparatus of claim 9 , wherein the LiDAR is provided in a higher position than the camera in the vehicle.
19 . The apparatus of claim 9 , wherein the LiDAR is provided on the vehicle.
20 . The apparatus of claim 9 , wherein the camera is provided on the vehicle.