The Effect of Using Projective Cameras on View- Independent Gait Recognition Performance

Abstract

Gait as a biometric can be used to identify subjects at a distance and thus it receives great attention from theresearch community for security and surveillance applications. One of the challenges that affects gait recognitionperformance is view variation. Much work has been done to tackle this challenge. However, the majority of the workassumes that gait silhouettes are captured by affine cameras where only the height of silhouettes changes and thedifference in viewing angle of silhouettes in one gait cycle is relatively small. In this paper, we analyze the variationin gait recognition performance when using silhouettes from projective cameras and from affine cameras withdifferent distance from the center of a walking path. This is done by using 3D models of walking people in the galleryset and 2D gait silhouettes from independent (single) cameras in the probe set. Different factors that affect matching3D human models with 2D gait silhouettes from single cameras for view-independent gait recognition are analyzed.In all experiments, we use 258 multi-view sequences belong to 46 subjects from Multi-View Soton gait dataset.We evaluate the matching performance for 12 different views using Gait Energy Image (GEI) as gait features.Then, we analyze the effect of using different camera configurations for 3D model reconstruction, the GEI fromcameras with different settings, the upper and lower body parts for recognition and different GEI resolutions. Theresults illustrate that low recognition performance is achieved when using gait silhouettes from affine cameras whilelower recognition performance is obtained when using gait silhouettes from projective cameras.