Person Reidentification Using Local Pattern Descriptors and Anthropometric Measures From Videos of Kinect Sensor

With development of RGB-D sensors, high-quality depth images are obtained easily. In this paper, we investigate the depth and skeleton information obtained from Kinect sensor for person reidentification and consider using inexpensive depth camera device known as Kinect camera. Using depth and skeleton information, some challenging problems in person reidentification as illumination and computation complexity are considered and new solutions are specified for the issues. In this paper, histograms of local binary patterns, local derivative patterns, and local tetra patterns are computed as features for person reidentification. Then, these histograms are fused with anthropometric features using score-level fusion. The proposed methods are applied on two database: RGBD-ID database and KinectREID database. Finally, experimental results demonstrate the validity of the proposed methods.