DVS: A Drone Video Synopsis towards Storing and Analyzing Drone Surveillance Data in Smart Cities

The commercialization and advancement of unmanned aerial vehicles (UAVs) have increased in the past decades for surveillance. UAVs use gimbal cameras LIDAR technology monitoring as they are resource-constrained devices that composed limited storage, battery power, computing capacity. Thus, UAV’s surveillance camera data must be analyzed, extracted, stored efficiently. Video synopsis is an efficient methodology deals with shifting foreground objects time domain space, thus creating a condensed video analysis storage. However, traditional methodologies not applicable making abnormal behavior (e.g., only person carrying revolver). To mitigate this problem, we proposed early fusion-based synopsis. There drastic difference between existing methods it has several pressing characteristics. Initially, fused 2D 3D point cloud data; Secondly, performed object detection using customized detector on merged finally extracted meaningful We demonstrated satisfactory results while fusing, constructing synopsis, detecting object; achieved mAP 85.97%.