ETRI-Knowledge Sharing Plaform



논문 검색
구분 SCI
연도 ~ 키워드


학술지 Vision-based Garbage Dumping Action Detection for Real-world Surveillance Platform
Cited 45 time in scopus Download 2009 time Share share facebook twitter linkedin kakaostory
윤기민, 권용진, 오성찬, 문진영, 박종열
ETRI Journal, v.41 no.4, pp.494-505
한국전자통신연구원 (ETRI)
18HS4600, (딥뷰-1세부) 실시간 대규모 영상 데이터 이해·예측을 위한 고성능 비주얼 디스커버리 플랫폼 개발, 박종열
In this paper, we propose a new framework for detecting the unauthorized dumping of garbage in real-world surveillance camera. Although several action/behavior recognition methods have been investigated, these studies are hardly applicable to real-world scenarios because they are mainly focused on well-refined datasets. Because the dumping actions in the real-world take a variety of forms, building a new method to disclose the actions instead of exploiting previous approaches is a better strategy. We detected the dumping action by the change in relation between a person and the object being held by them. To find the person-held object of indefinite form, we used a background subtraction algorithm and human joint estimation. The person-held object was then tracked and the relation model between the joints and objects was built. Finally, the dumping action was detected through the voting-based decision module. In the experiments, we show the effectiveness of the proposed method by testing on real-world videos containing various dumping actions. In addition, the proposed framework is implemented in a real-time monitoring system through a fast online algorithm.
KSP 제안 키워드
Background Subtraction Algorithm, Background subtraction(BS), Joint Estimation, Real-world, Recognition method, Relation Model, action detection, behavior recognition, human joints, new method, online algorithm
본 저작물은 공공누리 제4유형 : 출처표시 + 상업적 이용금지 + 변경금지 조건에 따라 이용할 수 있습니다.