Systems and methods for uncertainty aware monocular 3D object detection

A non-transitory computer-readable medium having program code recorded thereon for uncertainty aware 3D object detection, the program code being executed by a processor and comprising:

• program code to predict, using a trained monocular depth network, an estimated monocular input depth map of a monocular image of a video stream and an estimated depth uncertainty map associated with the estimated monocular input depth map;
• program code to feedback a depth uncertainty regression loss associated with the estimated monocular input depth map and a ground truth depth map during training of the trained monocular depth network to update the estimated monocular input depth map to form an output monocular depth map;
• program code to update the output monocular depth map using a vote regression loss from a 3D object detection network based on an aggregated depth uncertainty map corresponding to the estimated depth uncertainty map and the output monocular depth map;
• program code to detect, by the 3D object detection network, 3D objects from a 3D point cloud computed from the updated output monocular depth map based on seed positions selected from the 3D point cloud and the aggregated depth uncertainty map;
• and
• program code to select, by the 3D object detection network, 3D bounding boxes of the 3D objects detected from the 3D point cloud based on the seed positions and refined, predicted votes based on the aggregated depth uncertainty map.

A system for uncertainty aware 3D object detection, the system comprising:

• a trained monocular depth network to predict an estimated monocular input depth map of a monocular image of a video stream and an estimated depth uncertainty map associated with the estimated monocular input depth map;
• a depth uncertainty regression module to feedback a depth uncertainty regression loss associated with the estimated monocular input depth map and a ground truth depth map during training of the trained monocular depth network to update the estimated monocular input depth map to form an output monocular depth map and to update the output monocular depth map using a vote regression loss from a 3D object detection network based on an aggregated depth uncertainty map corresponding to the estimated depth uncertainty map and the output monocular depth map;
• a 3D object detection network to detect 3D objects from a 3D point cloud computed from the updated output monocular depth map based on seed positions selected from the 3D point cloud and the aggregated depth uncertainty map;
• and
• a 3D bounding box module to select 3D bounding boxes of the 3D objects detected from the 3D point cloud based on the seed positions and refined, predicted votes based on the aggregated depth uncertainty map.