A double-channel multiscale depthwise separable convolutional neural network for abnormal gait recognition

Abnormal gait recognition is important for detecting body part weakness and diagnosing diseases. The abnormal gait hides a considerable amount of information. In order to extract the fine, spatial feature information in the abnormal gait and reduce the computational cost arising from excessive network parameters, this paper proposes a double-channel multiscale depthwise separable convolutional neural network (DCMSDSCNN) for abnormal gait recognition. The method designs a multiscale depthwise feature extraction block (MDB), uses depthwise separable convolution (DSC) instead of standard convolution in the module and introduces the Bottleneck (BK) structure to optimize the MDB. The module achieves the extraction of effective features of abnormal gaits at different scales, and reduces the computational cost of the network. Experimental results show that the gait recognition accuracy is up to 99.60%, while the memory size of the model is reduced 4.21 times than before optimization.