Gait Recognition using Multi-Scale Partial Representation Transformation with Capsules

Abstract

Gait recognition, referring to the identification of individuals based on the manner in which they walk, can be very challenging due to the variations in the viewpoint of the camera and the appearance of individuals. Current methods for gait recognition have been dominated by deep learning models, notably those based on partial feature representations. In this context, we propose a novel deep network, learning to transfer multi-scale partial gait representations using capsules to obtain more discriminative gait features. Our network first obtains multi-scale partial representations using a state-of-theart deep partial feature extractor. It then recurrently learns the correlations and co-occurrences of the patterns among the partial features in forward and backward directions using Bidirectional Gated Recurrent Units (BGRU). Finally, a capsule network is adopted to learn deeper part-whole relationships and assigns more weights to the more relevant features while ignoring the spurious dimensions. That way, we obtain final features that are more robust to both viewing and appearance changes. The performance of our method has been extensively tested on two gait recognition datasets, CASIA-B and OU-MVLP, using four challenging test protocols. The results of our method have been compared to the state-of-the-art gait recognition solutions, showing the superiority of our model, notably when facing challenging viewing and carrying conditions.

GaitMPL: Gait Recognition With Memory-Augmented Progressive Learning

“…GLN [22] adopts the Triplet loss and Cross-Entropy loss in the different training stages. CapsNet [14] utilizes these two loss functions on its different components of the network.…”

Spatio-temporal Gait Feature with Adaptive Distance Alignment

“…However, when using this method to express the silhouettes in gait sequence, it often loses a lot of important detailed information and increases the difficulty of recognition. And other model-based methods also encounter this problem, so appearance-based methods have become the most mainstream gait recognition methods at present [6], [31], [32], [7], [33], [34], [35]. In this paper, the methods we mentioned later both belong to the appearance-based methods.…”