Identification of a Person by Gait in a Video Stream

Purpose of research. The given paper considers the problem of identifying a person by gait through the use of neural network recognition models focused on working with RGB images. The main advantage of using neural network models over existing methods of motor activity analysis is obtaining images from the video stream without frames preprocessing, which increases the analysis time. Methods. The present paper presents an approach to identifying a person by gait. The approach is based upon the idea of multi-class classification on video sequences. The quality of the developed approach operation was evaluated on the basis of CASIA Gait Database data set, which includes more than 15,000 video sequences. As classifiers, 5 neural network architectures have been tested: the three-dimensional convolutional neural network I3D, as well as 4 architectures representing convolutional-recurrent networks, such as unidirectional and bidirectional LTSM, unidirectional and bidirectional GRU, combined with the convolutional neural network of ResNet architecture being used in these architectures as a visual feature extractor. Results. According to the results of the conducted testing, the developed approach makes it possible to identify a person in a video stream in real-time mode without the use of specialized equipment. According to the results of its testing and through the use of the neural network models under consideration, the accuracy of human identification was more than 80% for convolutional-recurrent models and 79% for the I3D model. Conclusion. The suggested models based on I3D architecture and convolutional-recurrent architectures have shown higher accuracy for solving the problem of identifying a person by gait than existing methods. Due to the possibility of frame-by-frame video processing, the most preferred classifier for the developed approach is the use of convolutional-recurrent architectures based on unidirectional LSTM or GRU models, respectively.