Stereo R-CNN based 3D Object Detection for Autonomous Driving

February 26, 2019 · Entered Twilight · 🏛 Computer Vision and Pattern Recognition

"Last commit was 6.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .gitignore, LICENSE, README.md, _init_paths.py, data, demo.py, demo, doc, lib, requirements.txt, test.sh, test_net.py, train.sh, trainval_net.py

Authors Peiliang Li, Xiaozhi Chen, Shaojie Shen arXiv ID 1902.09738 Category cs.CV: Computer Vision Cross-listed cs.RO Citations 552 Venue Computer Vision and Pattern Recognition Repository https://github.com/HKUST-Aerial-Robotics/Stereo-RCNN ⭐ 708 Last Checked 1 month ago

Abstract

We propose a 3D object detection method for autonomous driving by fully exploiting the sparse and dense, semantic and geometry information in stereo imagery. Our method, called Stereo R-CNN, extends Faster R-CNN for stereo inputs to simultaneously detect and associate object in left and right images. We add extra branches after stereo Region Proposal Network (RPN) to predict sparse keypoints, viewpoints, and object dimensions, which are combined with 2D left-right boxes to calculate a coarse 3D object bounding box. We then recover the accurate 3D bounding box by a region-based photometric alignment using left and right RoIs. Our method does not require depth input and 3D position supervision, however, outperforms all existing fully supervised image-based methods. Experiments on the challenging KITTI dataset show that our method outperforms the state-of-the-art stereo-based method by around 30% AP on both 3D detection and 3D localization tasks. Code has been released at https://github.com/HKUST-Aerial-Robotics/Stereo-RCNN.