This work introduces a co-capture system for multi-animal visual data acquisition using conventional cameras and event cameras. Event cameras offer multiple advantages over frame-based cameras, such as a high temporal resolution and temporal redundancy suppression, which enable us to efficiently capture the fast and erratic movements of fish. We furthermore present an event-based multi-animal tracking algorithm, which proves the feasibility of the approach and sets the baseline for further exploration of combining the advantages of event cameras and conventional cameras for multi-animal tracking.
翻译:这项工作引入了利用传统照相机和事件摄像机获取多种动物视觉数据的共同采集系统,活动照相机比基于框架的照相机具有多种优势,例如高时间分辨率和时间冗余抑制,使我们能够有效捕捉鱼类的快速和不稳定流动,我们还提出了一个基于事件的多动物跟踪算法,该算法证明了这一方法的可行性,并为进一步探索将事件照相机和传统照相机的优势结合起来用于多动物跟踪设定基线。