Method for training gait recognition model, gait recognition method and related device

The embodiment of the invention relates to the technical field of gait recognition, and discloses a method for training a gait recognition model, a gait recognition method and a related device. The gait signal data comprises a three-axis acceleration signal and a three-axis angular velocity signal which are obtained by respectively collecting gaits of the two feet within a preset time by the motion sensor. Dividing the gait signal data into a plurality of gait short sequences in a time dimension; and encoding the gait short sequence into image data to obtain a multi-channel gait image. And performing iterative training on a preset neural network according to the plurality of gait images to obtain a gait recognition model. In the embodiment, the gait signal data with the time sequence are converted into the image data, so that complete information of the signals can be reserved, and meanwhile, the dependence of the signals on time can be reserved; and on the other hand, the recognition advantage of the neural