| RTM3D: Real-Time Monocular 3D Detection from Object Keypoints for Autonomous Driving | |
Li PX(李培玄)1,2,3,4,5; Zhao HC(赵怀慈)1,2,4,5 ; Liu PF(刘鹏飞)1,2,3,4,5; Cao FD(曹飞道)1,2,3,4,5
| |
| Department | 光电信息技术研究室 |
| Conference Name | 2020 European Conference on Computer Vision (ECCV 2020) |
| Conference Date | August 23-28, 2020 |
| Conference Place | Glasgow, UK |
| Source Publication | 2020 European Conference on Computer Vision (ECCV 2020) |
| Publisher | Springer Science and Business Media Deutschland GmbH |
| Publication Place | Berlin |
| 2020 | |
| Pages | 644-660 |
| Contribution Rank | 1 |
| ISBN | 978-3-030-58580-8 |
| Keyword | Real-time monocular 3D detection Autonomous driving Keypoint detection |
| Abstract | In this work, we propose an efficient and accurate monocular 3D detection framework in single shot. Most successful 3D detectors take the projection constraint from the 3D bounding box to the 2D box as an important component. Four edges of a 2D box provide only four constraints and the performance deteriorates dramatically with the small error of the 2D detector. Different from these approaches, our method predicts the nine perspective keypoints of a 3D bounding box in image space, and then utilize the geometric relationship of 3D and 2D perspectives to recover the dimension, location, and orientation in 3D space. In this method, the properties of the object can be predicted stably even when the estimation of keypoints is very noisy, which enables us to obtain fast detection speed with a small architecture. Training our method only uses the 3D properties of the object without any extra annotations, category-specific 3D shape priors, or depth maps. Our method is the first real-time system (FPS > 24) for monocular image 3D detection while achieves state-of-the-art performance on the KITTI benchmark. |
| Language | 英语 |
| Document Type | 会议论文 |
| Identifier | http://ir.sia.cn/handle/173321/27957 |
| Collection | 光电信息技术研究室 |
| Corresponding Author | Zhao HC(赵怀慈) |
| Affiliation | 1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, China 2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang, China 3.University of Chinese Academy of Sciences, Beijing, China 4.Key Laboratory of Opto-Electronic Information Processing, Chinese Academy of Sciences, Shenyang, China 5.Key Lab of Image Understanding and Computer Vision, Shenyang, China |
| Recommended Citation GB/T 7714 | Li PX,Zhao HC,Liu PF,et al. RTM3D: Real-Time Monocular 3D Detection from Object Keypoints for Autonomous Driving[C]. Berlin:Springer Science and Business Media Deutschland GmbH,2020:644-660. |
| Files in This Item: | ||||||
| File Name/Size | DocType | Version | Access | License | ||
| RTM3D_ Real-Time Mon（9875KB） | 会议论文 | 开放获取 | CC BY-NC-SA | View Application Full Text | ||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment