Coal Gangue Detection Method Based on Improved SSD Algorithm

In order to solve the problems of high time complexity and window redundancy in the traditional target detection algorithm based on artificial features, this paper proposes an end-to-end single-stage coal gangue detection algorithm based on deep learning. In view of the complex network structure and huge network parameters of SSD model, SSD-MobileNet network, which is combined with SSD and MobileNet network, is adopted in this paper to realize the detection of coal gangue. The MobileNet model is a lightweight model designed specifically for embedded mobile devices with both low latency and high precision. The experimental results show that the average detection accuracy of SSD-MobileNet algorithm reaches 91.5%, and the detection time of a single image is 0.04s.