Identification of gait parameters from silhouette images

• Published in: 2015 Eighth International Conference on Contemporary Computing (IC3) pp. 190 - 195
• Main Authors: Prakash, Chandra, Mittal, Anshul, Kumar, Rajesh, Mittal, Namita
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2015
• Subjects: Cameras; COG; Computational modeling; Feature extraction; Foot; Gait Analysis; Gait parameters; Gait signature; Gravity; Legged locomotion; Markerless; Silhouette; Videos
• ISBN: 1467379476; 9781467379472
• DOI: 10.1109/IC3.2015.7346677

Gait analysis has applications not only in medical, rehabilitation and sports, but it can also play a decisive role in security and surveillance as a behavioral biometric factor. This paper discusses gait parameters extraction technique without using makers or sensors. Videos from a home digital camera are analyzed and a silhouette image based technique is used to identify gait parameter such as step length, stride length, silhouette height and width, foot length, center of gravity (COG) and gait signature. 10 healthy subject's sagittal view is considered in this research at RAMAN lab, MNIT Jaipur. Non-requirement of markers makes the system non-invasive, cheap, and also easier to implement. To ascertain the quality of data obtained, the data has been compared with the data extracted by marker based approaches for the same subject and satisfactory results conform that the proposed system is feasible and can be used in the aforementioned areas. This paper can help researchers by providing them with a general insight of the gait parameters extraction technique for gait analysis.