Confidence Guided Stereo 3D Object Detection with Split Depth Estimation

11 Mar 2020  ·  Chengyao Li, Jason Ku, Steven L. Waslander ·

Accurate and reliable 3D object detection is vital to safe autonomous driving. Despite recent developments, the performance gap between stereo-based methods and LiDAR-based methods is still considerable. Accurate depth estimation is crucial to the performance of stereo-based 3D object detection methods, particularly for those pixels associated with objects in the foreground. Moreover, stereo-based methods suffer from high variance in the depth estimation accuracy, which is often not considered in the object detection pipeline. To tackle these two issues, we propose CG-Stereo, a confidence-guided stereo 3D object detection pipeline that uses separate decoders for foreground and background pixels during depth estimation, and leverages the confidence estimation from the depth estimation network as a soft attention mechanism in the 3D object detector. Our approach outperforms all state-of-the-art stereo-based 3D detectors on the KITTI benchmark.

PDF Abstract


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
3D Object Detection From Stereo Images KITTI Cars Moderate CG-Stereo AP75 53.58 # 4
3D Object Detection From Stereo Images KITTI Pedestrians Moderate CG-Stereo AP50 24.31 # 4


No methods listed for this paper. Add relevant methods here