지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
이용수
초록· 키워드
오류제보하기
This paper describes a real-time human action recognition system that tracks multiple persons and recognizes each human action through image sequences acquired from single surveillance camera. In particular, given an image, blobs are segmented by the Mixture of Gaussians with hierarchical data structure. And we track people by estimating the state to which each blob belongs and assigning people according to its state. Then we make Motion History Images for tracked people and recognize actions using Multi Layer Perceptron. And the result from the experiment where we defined five actions: walking, running, sitting, standing, and falling showed high recognition rate, though each subject performed slightly different action pattern for same action. We also verified that the proposed system copes in real-time with multiple persons.
목차
ABSTRACT
1. INTRODUCTION
2. OVERVIEW
3. SEGMENTATION
4. PEOPLE TRACKING
5. ACTION MODELING
6. CLASSIFICATION
7. EXPERIMENTAL RESULT
8. CONCLUSIONS
Acknowledgements
9. REFERENCES
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Robust Action Recognition Using Multiple View Image Sequences
한국정보과학회 학술발표논문집
2006 .10
-
모멘트 변화와 객체 크기 비율을 이용한 객체 행동 및 위험상황 인식
멀티미디어학회논문지
2014 .05
-
Human Action Recognition Bases on Local Action Attributes
Journal of Electrical Engineering & Technology
2015 .05
-
Human Action Recognition using the Pixel Variation of the Human Image
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2004 .07
-
Synthesizing and Recognizing Human Actions Using Joints Tracking Model
대한전자공학회 워크샵
2004 .02
-
Recognition of the Human Action using the Human Body’s Joint Information
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2012 .06
-
Real-Time Action Detection in Video Surveillance using a Sub-Action Descriptor with Multi-Convolutional Neural Networks
제어로봇시스템학회 논문지
2018 .03
-
Vision-based garbage dumping action detection for real-world surveillance platform
[ETRI] ETRI Journal
2019 .08
-
Identification of a Human using Accorded Blobs on the Varied Region from Image Sequence by Multiple Cameras
제어로봇시스템학회 국제학술대회 논문집
2008 .10
-
Estimation of Human Behaviors Based on Human Actions Using an ANN
제어로봇시스템학회 국제학술대회 논문집
2014 .10
-
Real-Time Tracking and Recognition of Human Hands from a Sign-Language Image Sequence
ICEIC : International Conference on Electronics, Informations and Communications
1998 .08
-
Real-Time Tracking and Recognition of Human Hands from a Sign-Language Image Sequence
ICEIC : International Conference on Electronics, Informations and Communications
1998 .01
-
색상 분포 및 인체의 상황정보를 활용한 다중카메라 기반의 사람 대응
제어로봇시스템학회 논문지
2009 .09
-
Action Recognition for Virtual Environment Training System
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2015 .06
-
Human Activity Recognition : Various Paradigms
제어로봇시스템학회 국제학술대회 논문집
2008 .10
-
Human Action Recognition Via Multi-modality Information
Journal of Electrical Engineering & Technology
2014 .03
-
관절 위치 변화 정보를 이용한 행동인식
제어로봇시스템학회 각 지부별 자료집
2018 .11
-
Interpretation of Flow Guided Filter for Human Action Recognition
대한전자공학회 학술대회
2019 .06
-
Learning Drone-control Actions in Surveillance Videos
제어로봇시스템학회 국제학술대회 논문집
2017 .10
-
Open Innovation in Action
한국지능정보시스템학회 학술대회논문집
2011 .05
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2012-004-004265084