Gender Classification Using Video Sequences of Body Sway Recorded by Overhead Camera


BodySwayGender.jpg
[Abstract]
We investigate whether it is possible to classify the gender of a standing person based on a video sequence containing body sway recorded by an overhead camera. Existing methods that extract a feature from the movement of a walking person for gender classification cannot detect the slight movements of a standing person. In this paper, we propose a method for extracting a feature from the body sway of a standing person. We design a spatio-temporal feature for representing body sway using the frequency analysis of time-series signals derived from the local movements of the upper body. To evaluate the accuracy of our method, we acquired video sequences of body sway from 30 females and 30 males using an overhead camera. We found that our method obtained 90.3% accuracy for the gender classification of a standing person. We compared the accuracy of our method with that of parameters based on medical data. We found that the proposed spatio-temporal feature extracted from body sway significantly improved gender classification accuracy.
[Publications]
[Short movie]
[Related publication]





otama1.png