EvSLAM: A Benchmark for High-Speed Agile Maneuvers SLAM with Event Cameras Released
What happened
Sheng Zhong and other authors released EvSLAM on arXiv, a benchmark framework for event-camera state estimation, covering multiple data-collection platforms, extreme lighting, and challenging motion patterns, and providing an explicit definition of high-speed agile maneuvers for mobile robots along with new evaluation metrics. The authors state that existing event-camera VO/VIO methods have limitations, and public datasets also have shortcomings: some methods require the local map to remain continuously within the field of view, while others struggle to generalize to six-degree-of-freedom motion in which both linear and angular velocities may be large. The authors use EvSLAM to evaluate current state-of-the-art methods, summarizing better architectures and problems that remain to be solved.
AI 根据报道生成 · 6 days ago更新
Reporting timeline
Follow the reporting to explore different perspectives.
- arXiv cs.ROEvSLAM: A Benchmark Framework for Event-Camera SLAM in High-Speed Maneuvers
The authors propose EvSLAM, a benchmark framework for event-camera state estimation that covers multiple data-collection platforms, extreme lighting, and challenging motion patterns, and provides an explicit definition of high-speed maneuvers along with new evaluation metrics. The paper first analyzes the limitations of existing event-camera VO/VIO methods and the shortcomings of public datasets, then uses the framework to evaluate current state-of-the-art methods, summarizing better architectures and problems that remain to be solved.