DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Ro, Yong-Man | - |
dc.contributor.advisor | 노용만 | - |
dc.contributor.author | Hwang, Jin-Hyon | - |
dc.contributor.author | 황진현 | - |
dc.date.accessioned | 2015-04-23T06:14:56Z | - |
dc.date.available | 2015-04-23T06:14:56Z | - |
dc.date.issued | 2014 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=592431&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/196823 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학과, 2014.8, [ iv, 36 p ] | - |
dc.description.abstract | Human action recognition is a core functionality of systems for video surveillance, content-based video indexing, video search, robotics, and human-object interaction. The goal of vision-based human action recog-nition is to determine the action label that best describes the action instance in the video clip automatically. Conventional vision-based systems for human action recognition require the use of subject segmentation tech-nique in order to achieve an acceptable level of recognition effectiveness. However, generic techniques for au-tomatic segmentation that guarantee high performance are currently not available yet. Further, it is important for effective human action recognition to use the features associated with a context region adaptively, as well as localizing the actions. To resolve the problems, this paper proposes a novel sparse representation-based method for human action recognition, which does not require complex human or human action localization for test video clip. To that end, we construct a dictionary for SR-based classification of human actions that con-sists of two split dictionaries: an action region dictionary and a context region dictionary. The action region dictionary aims at characterizing the action regions in a non-segmented test video clip (such as human action region, saliency region), while the context region dictionary aims at characterizing the non- action regions in the test video clip under consideration. That way, we are able to segment, implicitly, action region and context information in a test video clip, thus improving the effectiveness of classification. That way, we are also able to develop a context-adaptive human action recognition strategy. As shown by comparative experimental re-sults obtained for the UCF-50 and UCF-sports Action data set, the proposed method facilitates effective human action recognition, even when testing does not rely on explicit segmentation. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Action region-aware dictionary | - |
dc.subject | 희소표현 | - |
dc.subject | 인간 행동인식 | - |
dc.subject | 사전 구성 | - |
dc.subject | 행동영역 분리 | - |
dc.subject | 행동 및 배경영역 분리형 사전 | - |
dc.subject | action region detection | - |
dc.subject | context | - |
dc.subject | dictionary construction | - |
dc.title | Sparse representation-based human action category recognition using an action-context region-aware dictionary | - |
dc.title.alternative | 행동 및 배경 영역 Dictionary를 이용한 Sparse Representation 기반 인간행동 인식에 관한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 592431/325007 | - |
dc.description.department | 한국과학기술원 : 전기및전자공학과, | - |
dc.identifier.uid | 020124586 | - |
dc.contributor.localauthor | Ro, Yong-Man | - |
dc.contributor.localauthor | 노용만 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.