Monocular 3D object detection is an ill-posed problem due to the loss of geometry information in 2D images. To improve the reliability of monocular vision system, we propose to replace the deterministic estimation with a probabilistic prediction by computing both aleatoric and epistemic uncertainty in 3D detection task. We further design a continuous focal loss that can improve location accuracy and when combining with aleatoric uncertainty estimation, also reduce the effect of noise data during training. Our method is capable of estimating uncertainty in a single forward pass while achieving nearly real-time performance with 0.1s per image on a modern platform. Additionally, to make fair comparison between point and probabilistic prediction, we present a novel probabilistic localization evaluation metric which computes the average error over the predicted location distribution. Our experiments indicate that we achieve competitive result on the official KITTI 3D detection leaderboard, among other deterministic methods. Furthermore, our method gains more accurate localization accuracy under different localization evaluation metrics.
Efficient Uncertainty Estimation for Monocular 3D Object Detection in Autonomous Driving
2021-09-19
2111128 byte
Conference paper
Electronic Resource
English
DIRTY MONOCULAR CAMERA DETECTION METHODS FOR AUTONOMOUS DRIVING VEHICLE
European Patent Office | 2021
|Dirty monocular camera detection methods for autonomous driving vehicle
European Patent Office | 2023
|Efficient Monocular Coarse-to-Fine Object Pose Estimation
British Library Conference Proceedings | 2016
|