Real-time gesture recognition of unmanned aerial vehicle video

该提案集中于研究、设计和优化实时视频手势识别系统，该系统可应用于来自安装在无人机（或无人机）上的摄像机的视频馈送。该系统需要新的算法来识别具有复杂运动背景的连续视频帧中的运动。它将基于概率图模型和统计方法同时预测和分析摄像机的全局运动和物体的局部运动。例如，该项目的一个主要目标是能够近实时地识别人群中的人何时向无人机挥手。检测到这样的事件将触发一张照片并整合到社交媒体中。

This proposal concentrates on the research, design and optimization of a real-time video gesture recognition system that can be applied to the video feed coming from a camera mounted on a drone (or Unmanned Aerial Vehicle). The system requires novel algorithm to recognize motions in sequential video frames with a complex, moving background. It will predict and analyze the global motion of the camera and the local motion of the objects simultaneously based on probabilistic graphic model and statistical methods. For example, one main goal of the project is to be able to identify in near real-time when people in a crowd wave up at the drone. Detection of such an event would then trigger a photograph and integration into social media.