Vehicle Detection in Aerial Video Based on Dynamic Event Signal
In this paper,an aerial vehicle detection algorithm based on the dynamic event signal is proposed by split-ting the detection system into a candidate target positioning module and a target detection module.The candidate target positioning module takes one single dynamic event as input,combining events within a certain spatial-temporal neighbor-hood to quickly locate candidate targets.Moreover,M-ResNet with feature fusion is proposed in target detection module to protect shallow features.Finally,this paper produces a vehicle event data set with a duration of 25 seconds and 295,633,872 dynamic events,and verifies that the algorithm proposed in this paper can quickly and accurately detect vehi-cles in the scene through this data set.
万方数据
维普
