Stereo visual odometry based on dynamic and static features division
| Autor: | Xiaogang Yang, Li Xiaofeng, Cai Guangbin, Xu Hui, Erliang Yao |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
0209 industrial biotechnology
021103 operations research Control and Optimization Similarity (geometry) Matching (graph theory) Computer science business.industry Applied Mathematics Strategy and Management 0211 other engineering and technologies 02 engineering and technology Function (mathematics) Division (mathematics) Simultaneous localization and mapping Tracking (particle physics) Atomic and Molecular Physics and Optics 020901 industrial engineering & automation Computer vision Artificial intelligence Business and International Management Electrical and Electronic Engineering Visual odometry business Pose |
| Zdroj: | Journal of Industrial and Management Optimization. 18:2109 |
| ISSN: | 1553-166X 1547-5816 |
| Popis: | Accurate camera pose estimation in dynamic scenes is an important challenge for visual simultaneous localization and mapping, and it is critical to reduce the effects of moving objects on pose estimation. To tackle this problem, a robust visual odometry approach in dynamic scenes is proposed, which can precisely distinguish between dynamic and static features. The key to the proposed method is combining the scene flow and the static features relative spatial distance invariance principle. Moreover, a new threshold is proposed to distinguish dynamic features.Then the dynamic features are eliminated after matching with the virtual map points. In addition, a new similarity calculation function is proposed to improve the performance of loop-closure detection. Finally, the camera pose is optimized after obtaining a closed loop. Experiments have been conducted on TUM datasets and actual scenes, which shows that the proposed method reduces tracking errors significantly and estimates the camera pose precisely in dynamic scenes. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|