A New View-Calibrated Approach for Abnormal Gait Detection

Kuo Wei Lin, Shu Ting Wang, Pau-Choo Chung, Ching Fang Yang

研究成果: Chapter

3 引文 (Scopus)

摘要

Gait, or the style of walking, has been recently a popular topic in vision-based analysis. Most vision-based works about gait are devoted to the application of human recognition, but abnormal walking styles are rarely discussed. Accordingly, a vision-based method is proposed to analyze abnormal types of walking. In the proposed method, a background subtraction algorithm is applied to segment out the silhouette of the walker at each frame in a sequence. For each frame, we define a feature based on the length between two legs and the height of the individual, called aspect ratio (AR). By observing this feature value across time (or frame), a periodic wave is obtained. With this analysis, a few abnormal types of walking can be distinguished. Since an oblique camera view angle causes a distortion of the AR wave, a rectification mechanism is proposed based on a camera pinhole model to reduce the view angle effect. The experimental results show that the proposed rectification method identified abnormal walking patterns reliably irrespective of the direction in which the individual walks relative to the camera plane.

原文English
主出版物標題Advances in Intelligent Systems and Applications - Volume 2
主出版物子標題Proceedings of the International Computer
編輯Chang Ruay-Shiung, Peng Sheng-Lung, Lin Chia-Chen
頁面521-529
頁數9
DOIs
出版狀態Published - 2013 六月 28

出版系列

名字Smart Innovation, Systems and Technologies
21
ISSN(列印)2190-3018
ISSN(電子)2190-3026

指紋

Aspect ratio
Cameras
Pinhole cameras

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Computer Science(all)

引用此文

Lin, K. W., Wang, S. T., Chung, P-C., & Yang, C. F. (2013). A New View-Calibrated Approach for Abnormal Gait Detection. 於 C. Ruay-Shiung, P. Sheng-Lung, & L. Chia-Chen (編輯), Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer (頁 521-529). (Smart Innovation, Systems and Technologies; 卷 21). https://doi.org/10.1007/978-3-642-35473-1_52
Lin, Kuo Wei ; Wang, Shu Ting ; Chung, Pau-Choo ; Yang, Ching Fang. / A New View-Calibrated Approach for Abnormal Gait Detection. Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer. 編輯 / Chang Ruay-Shiung ; Peng Sheng-Lung ; Lin Chia-Chen. 2013. 頁 521-529 (Smart Innovation, Systems and Technologies).
@inbook{31e99836453c4cd4b0beb23319ed2833,
title = "A New View-Calibrated Approach for Abnormal Gait Detection",
abstract = "Gait, or the style of walking, has been recently a popular topic in vision-based analysis. Most vision-based works about gait are devoted to the application of human recognition, but abnormal walking styles are rarely discussed. Accordingly, a vision-based method is proposed to analyze abnormal types of walking. In the proposed method, a background subtraction algorithm is applied to segment out the silhouette of the walker at each frame in a sequence. For each frame, we define a feature based on the length between two legs and the height of the individual, called aspect ratio (AR). By observing this feature value across time (or frame), a periodic wave is obtained. With this analysis, a few abnormal types of walking can be distinguished. Since an oblique camera view angle causes a distortion of the AR wave, a rectification mechanism is proposed based on a camera pinhole model to reduce the view angle effect. The experimental results show that the proposed rectification method identified abnormal walking patterns reliably irrespective of the direction in which the individual walks relative to the camera plane.",
author = "Lin, {Kuo Wei} and Wang, {Shu Ting} and Pau-Choo Chung and Yang, {Ching Fang}",
year = "2013",
month = "6",
day = "28",
doi = "10.1007/978-3-642-35473-1_52",
language = "English",
isbn = "9783642354724",
series = "Smart Innovation, Systems and Technologies",
pages = "521--529",
editor = "Chang Ruay-Shiung and Peng Sheng-Lung and Lin Chia-Chen",
booktitle = "Advances in Intelligent Systems and Applications - Volume 2",

}

Lin, KW, Wang, ST, Chung, P-C & Yang, CF 2013, A New View-Calibrated Approach for Abnormal Gait Detection. 於 C Ruay-Shiung, P Sheng-Lung & L Chia-Chen (編輯), Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer. Smart Innovation, Systems and Technologies, 卷 21, 頁 521-529. https://doi.org/10.1007/978-3-642-35473-1_52

A New View-Calibrated Approach for Abnormal Gait Detection. / Lin, Kuo Wei; Wang, Shu Ting; Chung, Pau-Choo; Yang, Ching Fang.

Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer. 編輯 / Chang Ruay-Shiung; Peng Sheng-Lung; Lin Chia-Chen. 2013. p. 521-529 (Smart Innovation, Systems and Technologies; 卷 21).

研究成果: Chapter

TY - CHAP

T1 - A New View-Calibrated Approach for Abnormal Gait Detection

AU - Lin, Kuo Wei

AU - Wang, Shu Ting

AU - Chung, Pau-Choo

AU - Yang, Ching Fang

PY - 2013/6/28

Y1 - 2013/6/28

N2 - Gait, or the style of walking, has been recently a popular topic in vision-based analysis. Most vision-based works about gait are devoted to the application of human recognition, but abnormal walking styles are rarely discussed. Accordingly, a vision-based method is proposed to analyze abnormal types of walking. In the proposed method, a background subtraction algorithm is applied to segment out the silhouette of the walker at each frame in a sequence. For each frame, we define a feature based on the length between two legs and the height of the individual, called aspect ratio (AR). By observing this feature value across time (or frame), a periodic wave is obtained. With this analysis, a few abnormal types of walking can be distinguished. Since an oblique camera view angle causes a distortion of the AR wave, a rectification mechanism is proposed based on a camera pinhole model to reduce the view angle effect. The experimental results show that the proposed rectification method identified abnormal walking patterns reliably irrespective of the direction in which the individual walks relative to the camera plane.

AB - Gait, or the style of walking, has been recently a popular topic in vision-based analysis. Most vision-based works about gait are devoted to the application of human recognition, but abnormal walking styles are rarely discussed. Accordingly, a vision-based method is proposed to analyze abnormal types of walking. In the proposed method, a background subtraction algorithm is applied to segment out the silhouette of the walker at each frame in a sequence. For each frame, we define a feature based on the length between two legs and the height of the individual, called aspect ratio (AR). By observing this feature value across time (or frame), a periodic wave is obtained. With this analysis, a few abnormal types of walking can be distinguished. Since an oblique camera view angle causes a distortion of the AR wave, a rectification mechanism is proposed based on a camera pinhole model to reduce the view angle effect. The experimental results show that the proposed rectification method identified abnormal walking patterns reliably irrespective of the direction in which the individual walks relative to the camera plane.

UR - http://www.scopus.com/inward/record.url?scp=84879313676&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879313676&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-35473-1_52

DO - 10.1007/978-3-642-35473-1_52

M3 - Chapter

AN - SCOPUS:84879313676

SN - 9783642354724

T3 - Smart Innovation, Systems and Technologies

SP - 521

EP - 529

BT - Advances in Intelligent Systems and Applications - Volume 2

A2 - Ruay-Shiung, Chang

A2 - Sheng-Lung, Peng

A2 - Chia-Chen, Lin

ER -

Lin KW, Wang ST, Chung P-C, Yang CF. A New View-Calibrated Approach for Abnormal Gait Detection. 於 Ruay-Shiung C, Sheng-Lung P, Chia-Chen L, 編輯, Advances in Intelligent Systems and Applications - Volume 2: Proceedings of the International Computer. 2013. p. 521-529. (Smart Innovation, Systems and Technologies). https://doi.org/10.1007/978-3-642-35473-1_52