Weighted joint-based human behavior recognition algorithm using only depth information for low-cost intelligent video-surveillance system
详细信息 查看全文
- 作者：Hanguen Kima ; sskhk05@kaist.ac.kr" class="auth_mail" title="E-mail the corresponding author ; Sangwon Leea ; lsw618@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Youngjae Kima ; david-kim@kaist.ac.kr" class="auth_mail" title="E-mail the corresponding author ; Serin Leeb ; serin.lee@gmail.com" class="auth_mail" title="E-mail the corresponding author ; Dongsung Leec ; dslee.lee@samsung.com" class="auth_mail" title="E-mail the corresponding author ; Jinsun Juc ; jinsun.ju@samsung.com" class="auth_mail" title="E-mail the corresponding author ; Hyun Myung ; d ; hmyung@kaist.ac.kr" class="auth_mail" title="E-mail the corresponding author
- 关键词：Video-surveillance system ; Human joint estimation ; Behavior recognition ; Human-computer interaction (HCI)
- 刊名：Expert Systems with Applications
- 出版年：2016
- 出版时间：1 March 2016
- 年：2016
- 卷：45
- 期：Complete
- 页码：131-141
- 全文大小：2429 K
文摘
- class="listitem" id="list_celist0001">
- class="label">•
Human joint estimation and behavior recognition algorithms are presented.
- class="label">•
Only depth information is used and can be executed on a low cost computing platform.
- class="label">•
The proposed system can be used with any subject instantly without pre-calibration.
- class="label">•
Experiments to verify the proposed algorithms have been conducted.