YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection
Authors:
- 30 May 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 13018-13024
Abstract
Object detection in 3D with stereo cameras is an important problem in computer vision, and is particularly crucial in low-cost autonomous mobile robots without LiDARs. Nowadays, most of the best-performing frameworks for stereo 3D object detection are based on dense depth reconstruction from disparity estimation, making them extremely computationally expensive. To enable real-world deployments of vision detection with binocular images, we take a step back to gain insights from 2D image-based detection frameworks and enhance them with stereo features. We incorporate knowledge and the inference structure from real-time one-stage 2D/3D object detector and introduce a light-weight stereo matching module. Our proposed framework, YOLOStereo3D, is trained on one single GPU and runs at more than ten fps. It demonstrates performance comparable to state-of-the-art stereo 3D detection frameworks without usage of LiDAR data. The code will be published in https://github.com/Owen-Liuyuxuan/visualDet3D.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China
This publication has 14 references indexed in Scilit:
- DSGN: Deep Stereo Geometry Network for 3D Object Detection2020
- ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object DetectionProceedings of the AAAI Conference on Artificial Intelligence, 2020
- M3D-RPN: Monocular 3D Region Proposal Network for Object Detection2019
- How Do Neural Networks See Depth in Single Images?2019
- Stereo R-CNN Based 3D Object Detection for Autonomous Driving2019
- Pyramid Stereo Matching Network2018
- End-to-End Learning of Geometry and Context for Deep Stereo Regression2017
- Efficient Deep Learning for Stereo Matching2016
- Fast R-CNN2015
- Are we ready for autonomous driving? The KITTI vision benchmark suite2012