Birds Eye View Object Detection
Birds Eye View Object Detection is an important subtask in the field of computer vision, focusing on detecting objects from a top-down perspective. The goal of this task is to accurately identify and locate the top-view bounding boxes of objects in a 2D image, thereby providing a more comprehensive environmental perception capability. Its application value lies in enhancing the safety and efficiency of autonomous driving systems, drone navigation, and intelligent surveillance, among other areas.
KITTI Cars Moderate
SE-SSD
KITTI Cars Easy
SE-SSD
KITTI Cars Hard
KITTI Cyclists Moderate
PV-RCNN
KITTI Pedestrians Moderate
KITTI Cars Moderate val
KITTI Pedestrians Easy
KITTI Pedestrians Hard
KITTI Cyclists Easy
PV-RCNN
KITTI Cyclists Hard
PV-RCNN
KITTI Cars Easy val
KITTI Cars Hard val
KITTI Pedestrian Easy
KITTI Pedestrian Moderate
KITTI Pedestrian Hard
PiFeNet
KITTI Pedestrian
KITTI Pedestrian Easy val
KITTI Pedestrian Moderate val
KITTI Pedestrian Hard val
KITTI Cyclist Easy val
VoxelNet
KITTI Cyclist Moderate val
KITTI Cyclist Hard val