Reliable Gait Recognition Using 3D Reconstructions and Random Forests – An Anthropometric Approach1. Issue 3 (6th January 2016)

• Record Type: Journal Article
• Authors: Sandau, Martin; Heimbürger, Rikke V.; Jensen, Karl E.; Moeslund, Thomas B.; Aanæs, Henrik; Alkjær, Tine; Simonsen, Erik B.
• Is Part Of: Journal of forensic sciences. Volume 61:Issue 3(2016)
• Page Start: 637
• Page End: 648
• Publication Date: 2016-01-06
• Subjects: forensic science -- gait recognition -- gait analysis -- forensic sciences -- forensic anthropology -- kinematics -- biomechanics -- 3D reconstruction -- dense point cloud -- stereo vision -- photogrammetry; Medical jurisprudence -- Periodicals; Forensic sciences -- Periodicals; Forensic Medicine -- Periodicals; Gerechtelijke geneeskunde; Gerechtelijke chemie; Gerechtelijke psychiatrie; 363.2505
• DOI: 10.1111/1556-4029.13015
• Languages: English
• ISSNs: 0022-1198

Abstract

Abstract: Photogrammetric measurements of bodily dimensions and analysis of gait patterns in CCTV are important tools in forensic investigations but accurate extraction of the measurements are challenging. This study tested whether manual annotation of the joint centers on 3D reconstructions could provide reliable recognition. Sixteen participants performed normal walking where 3D reconstructions were obtained continually. Segment lengths and kinematics from the extremities were manually extracted by eight expert observers. The results showed that all the participants were recognized, assuming the same expert annotated the data. Recognition based on data annotated by different experts was less reliable achieving 72.6% correct recognitions as some parameters were heavily affected by interobserver variability. This study verified that 3D reconstructions are feasible for forensic gait analysis as an improved alternative to conventional CCTV. However, further studies are needed to account for the use of different clothing, field conditions, etc.