Robust Gait Identification with Belongings From Back View

Abstract

Gait is one of biological information which indicates how to walk. It is able to acquire gait from a distance and any views. It is, however difficult to identify a person with belongings. The purpose of this article is, therefore, to propose an effective identification method when the subject has a bag. First, GEI(Gait Energy Image) is generated with head position adjustment. Then, gradient of GEI for head, both arms and legs regions are obtained. Finally, features from each region except for the hand region with a bag and the bag itself in the leg region. The proposed method gets 95.0% identification ratio for back view gait with belongings.