Classification Algorithm of Sports Teaching Video Based on Wireless Sensor Network

Classification Algorithm of Sports Teaching Video Based on Wireless Sensor Network

연구 분야: Infrastructure

학회: International Conference on Advanced Hybrid Information Processing

In view of the problems of low recall and accuracy caused by the huge amount of physical education teaching videos, a physical education teaching video classification algorithm based on wireless sensor network is proposed. The classification framework of physical education teaching videos based on wireless sensor networks is constructed, and the video node coordinates are located according to the structural relationship of physical education teaching videos. Initialize the histogram index, calculate the similarity of any two frames of the video, and set the clustering index of key frames of the physical education teaching video based on the distance between the two frames. Retrieve the video to be classified, find the sensor node with the largest weight, calculate the distance between the target and the detection sensor node, design the video classification steps of physical education teaching, and realize video classification. The experimental results show that the minimum recall rate of this algorithm is 87%, and the maximum classification accuracy rate is ninety-seven percent, which has the advantages of high classification recall and accuracy.