A Method for Identity Feature Recognition in Wireless Visual Sensing Networks Based on Convolutional Neural Networks

Due to the problems of low recognition accuracy and long recognition time in traditional wireless visual sensing network identity feature recognition methods, a convolutional neural network-based wireless visual senscto the operation results, the global threshold method is used to obtain the binary image sequence and perform morphological processing. Based on the processing results, Extract target regions from video image sequences of wireless visual sensing networks, detect human targets, and construct a Softmax classifier using convolutional neural networks to classify human targets in video image sequences of wireless visual sensing networks, in order to identify identity features. The simulation results show that the proposed method has high accuracy and short recognition time for identity feature recognition in wireless visual sensing networks.