Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark

Satellite video cameras can provide continuous observation for a large-scale area, which is important many remote sensing applications. However, achieving moving object detection and tracking in satellite videos remains challenging due to the insufficient appearance information of objects lack high-quality datasets. In this article, we first build dataset with rich annotations task tracking. This collected by Jilin-1 constellation composed 47 1 646 038 instances interest 3711 trajectories We then introduce motion modeling baseline improve rate reduce false alarms based on accumulative multiframe differencing robust matrix completion. Finally, establish public benchmark extensively evaluate performance several representative approaches our dataset. Comprehensive experimental analyses insightful conclusions are also provided. The available at https://github.com/QingyongHu/VISO.