Exploiting Pose Information for Gait Recognition from Depth Streams

A key-pose based gait recognition approach is proposed that utilizes the depth streams from Kinect. Narrow corridor-like places, such as the entry/exit points of a security zone, are best suited for its application. Alignment of frontal silhouette sequences is done using coordinate system transformation, followed by a three dimensional voxel volume construction, from which an equivalent fronto-parallel silhouette is generated. A set of fronto-parallel view silhouettes is, henceforth, utilized in deriving a number of key poses. Next, correspondences between the frames of an input sequence and the set of derived key poses are determined using a sequence alignment algorithm. Finally, a gait feature is constructed from each key pose taking into account only those pixels that undergo significant position variation with respect to the silhouette center. Extensive evaluation on a test dataset demonstrates the potential applicability of the proposed method in real-life scenarios.