Cross-view and multi-view gait recognitions based on view transformation model using multi-layer perceptron

Highlights One-view to one-view VTM solves across-view gait recognition. Multi-view to one-view VTM solves multi-view gait recognition. VTM is built up from regressions of local motion using multi-layer perceptron. Multi-view to one-view VTM can be claimed as implicit 3D gait model based method. Accuracy of 98% is achieved for multi-view gait recognition using 4 cameras. Gait has been shown to be an efficient biometric feature for human identification at a distance. However, performance of gait recognition can be affected by view variation. This leads to a consequent difficulty of cross-view gait recognition. A novel method is proposed to solve the above difficulty by using view transformation model (VTM). VTM is constructed based on regression processes by adopting multi-layer perceptron (MLP) as a regression tool. VTM estimates gait feature from one view using a well selected region of interest (ROI) on gait feature from another view. Thus, trained VTMs can normalize gait features from across views into the same view before gait similarity is measured. Moreover, this paper proposes a new multi-view gait recognition which estimates gait feature on one view using selected gait features from several other views. Extensive experimental results demonstrate that the proposed method significantly outperforms other baseline methods in literature for both cross-view and multi-view gait recognitions. In our experiments, particularly, average accuracies of 99%, 98% and 93% are achieved for multiple views gait recognition by using 5 cameras, 4 cameras and 3 cameras respectively.