Lesioned-Part Identification by Classifying Entire-Body Gait Motions

• Published in: Image and Video Technology Vol. 9431; pp. 136 - 147
• Main Authors: Higashiguchi, Tsuyoshi, Shimoyama, Toma, Ukita, Norimichi, Kanbara, Masayuki, Hagita, Norihiro
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2016; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: 3D human pose; Depth sensor; Entire-body motion; Gait motion; Graphical & digital media applications; Graphics programming; Image processing; Lesioned part
• ISBN: 9783319294506; 3319294504
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-319-29451-3_12

This paper proposes a physical motion evaluation system based on human pose sequences estimated by a depth sensor. While most similar systems measure and evaluate the motion of only a part of interest (e.g., knee), the proposed system comprehensively evaluates the motion of the entire body. The proposed system is designed for observing a human motion in daily life in order to find the sign of aging and physical disability. For daily use, in this paper, we focus on walking motions. Walking motions with a variety of physical disabilities are recorded and modeled for classification purpose. This classification is achieved with a set of pose features extracted from walking motion sequences. In experiments, the proposed features extracted from the entire body allowed us to identify where a subject was injured with 81.1 % accuracy. The superiority of the entire-body features was also validated in estimating the degree of lesion in contrast to local features extracted from only a body part of interest (77.1 % vs 65 %).