3D lane and road boundary estimation via row-wise classification

An apparatus, comprising:

• a memory storing processor-readable code;
• and
• at least one processor coupled to the memory, the at least one processor configured to execute the processor-readable code to cause the at least one processor to perform operations including:
• extracting point features from light detection and ranging (LiDAR) data;
• partitioning the point features into a grid comprising a plurality of rows
• performing BEV-feature pooling based on the partitioned point features of the grid;
• and
• determining lane-boundary heads based on the BEV-feature pooling, wherein the determining comprises:
• a first classification for a first row of the plurality of rows, and a second classification for a second row of the plurality of rows, wherein each of the first classification and the second classification is performed with offset correction regression processing comprising regressing a planar distance of a lane vertex location from a center of a BEV grid cell, wherein each of the first classification and the second classification is further performed with vertex-wise height regression processing of a BEV grid cell.

A non-transitory computer-readable medium storing instructions that, when executed by a processor, cause the processor to perform operations comprising:

• extracting point features from light detection and ranging (LiDAR) data;
• partitioning the point features into a grid comprising a plurality of rows;
• performing BEV-feature pooling based on the partitioned point features;
• and
• determining lane-boundary heads based on the BEV-feature pooling, wherein the determining comprises:
• a first classification for a first row of the plurality of rows, and a second classification for a second row of the plurality of rows, wherein each of the first classification and the second classification is performed with offset correction regression processing comprising regressing a planar distance of a lane vertex location from a center of a BEV grid cell, wherein each of the first classification and the second classification is further performed with vertex-wise height regression processing.

A vehicle, comprising:

• a steering system;
• a light detection and ranging (LiDAR) imaging system;
• a memory storing processor-readable code;
• and
• at least one processor coupled to the memory, to the LiDAR imaging system, and to the steering system, the at least one processor configured to execute the processor-readable code to cause the at least one processor to perform operations including:
• extracting point features from light detection and ranging (LiDAR) data;
• partitioning the point features into a grid comprising a plurality of rows;
• performing BEV-feature pooling based on the partitioned point features of the grid;
• and
• determining lane-boundary heads based on the BEV-feature pooling, wherein the determining comprises:
• a first classification for a first row of the plurality of rows, and a second classification for a second row of the plurality of rows, wherein each of the first classification and the second classification is performed with offset correction regression processing comprising regressing a planar distance of a lane vertex location from a center of a BEV grid cell, wherein each of the first classification and the second classification is further performed with vertex-wise height regression processing.