16 October 2013 Gait patterns for crime fighting: statistical evaluation
Author Affiliations +
The criminality is omnipresent during the human history. Modern technology brings novel opportunities for identification of a perpetrator. One of these opportunities is an analysis of video recordings, which may be taken during the crime itself or before/after the crime. The video analysis can be classed as identification analyses, respectively identification of a person via externals. The bipedal locomotion focuses on human movement on the basis of their anatomical-physiological features. Nowadays, the human gait is tested by many laboratories to learn whether the identification via bipedal locomotion is possible or not. The aim of our study is to use 2D components out of 3D data from the VICON Mocap system for deep statistical analyses. This paper introduces recent results of a fundamental study focused on various gait patterns during different conditions. The study contains data from 12 participants. Curves obtained from these measurements were sorted, averaged and statistically tested to estimate the stability and distinctiveness of this biometrics. Results show satisfactory distinctness of some chosen points, while some do not embody significant difference. However, results presented in this paper are of initial phase of further deeper and more exacting analyses of gait patterns under different conditions.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kateřina Sulovská, Kateřina Sulovská, Silvie Bělašková, Silvie Bělašková, Milan Adámek, Milan Adámek, "Gait patterns for crime fighting: statistical evaluation", Proc. SPIE 8901, Optics and Photonics for Counterterrorism, Crime Fighting and Defence IX; and Optical Materials and Biomaterials in Security and Defence Systems Technology X, 89010G (16 October 2013); doi: 10.1117/12.2033323; https://doi.org/10.1117/12.2033323

Back to Top