Silhouette-based Gait Recognition using CNN-RNN

Gait recognition is an important specific type of video-based behavior analysis. Such methods are potentially important for any type of video surveillance where specific people are being tracked or where the movement behavior of certain people is being analyzed because people's movements have unique characteristics. For example, investigating an individual without a representative of dangerous or hostile behavior. As a result, the gait feature can be used to capture long distances and uncontrolled situations more easily. Therefore, gait can be used as a biometric measure to identify known individuals and classify subjects. To this end, we designed a human gait classifier that facilitates human recognition through their walk. In this paper, we first obtain silhouette images from the CASIA B dataset. After that, we create 300 sequences by aspect ratio carve and local minima for 10 subjects and divide them into two directories named train and test. The proposed method used the CNN pre-trained xception model to extract features from the sequences. The given extracted frames are then trained and classified using the RNN model. Finally, we evaluated the performance using a hybrid neural network (CNN-RNN) which gave 90.00% accuracy to the trained model.