One-Shot Person Re-identification with a Consumer Depth Camera

Abstract

In this chapter, we propose a comparison between two techniques for one-shot person re-identification from soft biometric cues. One is based upon a descriptor composed of features provided by a skeleton estimation algorithm; the other compares body shapes in terms of whole point clouds. This second approach relies on a novel technique we propose to warp the subject's point cloud to a standard pose, which allows to disregard the problem of the different poses a person can assume. This technique is also used for composing 3D models which are then used at testing time for matching unseen point clouds. We test the proposed approaches on an existing RGB-D re-identification dataset and on the newly built BIWI RGBD-ID dataset. This dataset provides sequences of RGB, depth, and skeleton data for 50 people in two different scenarios and it has been made publicly available to foster advancement in this new research branch.

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

“…The BIWI RGBD-ID database [24] was built for a long-term person re-identification and hence most of the subjects change their clothes in training and testing sequences. So it is not suitable into short-term person re-identification.…”

“…In each of the three databases consisting of KinectREID database; collaborative-walking and walking2-backwards groups of the RGBD-ID database, we do our experiments on a closed-set scenario, as in most of the existing works on person re-identification. We use MvsM case in our experiments as in [24]. As to this case, both gallery and probe sets are built of multi-shot signatures.…”

“…These measures include: torso center to left shoulder, torso center to left hip and distance of the torso center to right hip. In [24] two types of descriptors were proposed for person re-identification that the first descriptor contains 13 anthropometric measures extracted from the body joints and the other descriptor contains a point cloud model of the human body. In [25] the appearancebased re-identification accuracy was improved by fusion clothing appearance descriptors with anthropometric measures.…”

Space-time representation of people based on 3D skeletal data: A review

“…In addition, the main application domains of interest in this survey paper is human gesture, action, and activity recognition, as most of the reviewed papers focus on these applications. Although several skeleton-based representations are also used for human re-identification [57,58], however, skeleton-based features are usually used along with other shape or texture based features (e.g., 3D point cloud) in this application, as skeletonbased features are generally incapable to represent human appearance that is critical for human re-identification.…”

Robust Depth-Based Person Re-Identification

“…[1] uses only skeletons to extract feature. In [2], [3], besides using skeleton to extract physical information, applying point clouds converted from depth images for 3D body shape matching is also considered, but alignment errors and noises of point clouds are the problems remained unsolved. In [4], a deep model is applied to classify the person point cloud sequences, in which feature extraction and classification are jointly modeled and body shape is not explicitly described.…”