Stereo CenterNet-based 3D object detection for autonomous driving

Recently, three-dimensional (3D) detection based on stereo images has progressed remarkably; however, most advanced methods adopt anchor-based two-dimensional (2D) detection or depth estimation to address this problem. Nevertheless, high computational cost inhibits these methods from achieving real-time performance. In this study, we propose a 3D object detection method, Stereo CenterNet (SC), using geometric information in stereo imagery. SC predicts the four semantic key points of the 3D bound-ing box of the object in space and utilizes 2D left and right boxes, 3D dimension, orientation, and key points to restore the bounding box of the object in the 3D space. Subsequently, we adopt an improved photometric alignment module to further optimize the position of the 3D bounding box. Experiments conducted on the KITTI dataset indicate that the proposed SC exhibits the best speed-accuracy trade -off among advanced methods without using extra data. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

In this study, a 3D object detection method called Stereo CenterNet (SC) is proposed, which utilizes geometric information from stereo imagery. SC predicts the key points and utilizes 2D and 3D information to restore the object's bounding box in 3D space. Experimental results show that SC achieves the best trade-off between speed and accuracy.