VGR-Net: A View Invariant Gait Recognition Network
This work addresses the challenge of person identification at a distance for surveillance applications, but it is incremental as it builds on existing methods for view-invariant gait recognition.
The paper tackles the problem of gait recognition under varying viewpoints by proposing VGR-Net, a 3D convolutional deep neural network that uses a two-stage approach to first identify the viewing angle and then recognize the person, achieving state-of-the-art results on the CASIA-B database with improved efficiency in time and space.
Biometric identification systems have become immensely popular and important because of their high reliability and efficiency. However person identification at a distance, still remains a challenging problem. Gait can be seen as an essential biometric feature for human recognition and identification. It can be easily acquired from a distance and does not require any user cooperation thus making it suitable for surveillance. But the task of recognizing an individual using gait can be adversely affected by varying view points making this task more and more challenging. Our proposed approach tackles this problem by identifying spatio-temporal features and performing extensive experimentation and training mechanism. In this paper, we propose a 3-D Convolution Deep Neural Network for person identification using gait under multiple view. It is a 2-stage network, in which we have a classification network that initially identifies the viewing point angle. After that another set of networks (one for each angle) has been trained to identify the person under a particular viewing angle. We have tested this network over CASIA-B publicly available database and have achieved state-of-the-art results. The proposed system is much more efficient in terms of time and space and performing better for almost all angles.