I-073 Gait Volume : Spatio-Temporal Analysis of Walking

概要

論文の詳細を見る
This paper describes a new approach for identifying a person from a spatio-temporal volume which consists of sequential images of a person walking in an arbitrary direction. The proposed approach employs an omnidirectional image sensor and analyzes three dimensional frequency properties of spatio-temporal volume, because the sensor can capture a long image sequence of person's movements in all directions and their walking patterns have some cycles. Spatio-temporal volume data, called as "gait volume", contain information not only spatial individuality such as features of body and face, but also movement of their body within unique rhythm. The three dimensional fourier transform is applied to the gait volume for obtaining unique frequency in each person's walking. This paper also evaluates availability of three dimensional frequency analysis of the gait volume, how much is the difference in people's frequency patterns while walking.
FIT(電子情報通信学会・情報処理学会)推進委員会の論文
2004-08-20