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.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2021.11
- 수록면
- 95 - 102 (8page)
이용수
초록· 키워드
오류제보하기
In this study, we propose an action recognition model that provides generalized performance regardless of camera location and distance between the camera and human. The proposed model consists of two-stage networks, namely, human detection and action recognition. The proposed method operates on video frames that are resized by a new zoom-in method using pretrained Yolo v3. To use temporal information, which is regarded as a critical factor in action recognition, we adopt the R(2+1)D model, which is a factorized model capable of representing more complex networks. The proposed Zoom-In method yields generalized performance regardless of distance. In an experiment, the proposed method exhibited accuracies of 96.07%, 96.61%, and 94.55% in the short, medium, and long ranges in which our datasets were employed, respectively.
목차
ABSTRACT
1. Introduction
2. Related Work
3. Proposed Method
4. Experiment and Evaluation
5. Conclusion
References
참고문헌 (18)
참고문헌 신청
Al-Qizwini M / 2017 / Deep learning algorithm for autonomous driving using googlenet / Ieee Int Veh Sym :89~89
Yan K / 2017 / Face recognition based on convolution neural network / IEEE 36th Chinese Control Conference (CCC) :4077~4081
Viitaniemi V / 2008 / Techniques for image classification, object detection and object segmentation / International Conference on Advances in Visual Information Systems :231~234
Lima T / 2017 / Human action recognition with 3d convolutional neural network / IEEE Latin American Conference on Computational Intelligence (LA-CCI) :1725~1732
Karpathy A / 2014 / Large-scale video classification with convolutional neural networks / Proc Cvpr Ieee :1725~1732
Yan K / 2017 / Face recognition based on convolution neural network / IEEE 36th Chinese Control Conference (CCC) :4077~4081
Viitaniemi V / 2008 / Techniques for image classification, object detection and object segmentation / International Conference on Advances in Visual Information Systems :231~234
Lima T / 2017 / Human action recognition with 3d convolutional neural network / IEEE Latin American Conference on Computational Intelligence (LA-CCI) :1725~1732
Karpathy A / 2014 / Large-scale video classification with convolutional neural networks / Proc Cvpr Ieee :1725~1732
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Distortion Correction Modeling Method for Zoom Lens Cameras with Bundle Adjustment
Current Optics and Photonics
2016 .02
-
Design of an 8× Four-group Zoom System without a Moving Group by Considering the Overall Length
Current Optics and Photonics
2022 .02
-
Convergence Point Adjustment Improving Visual Discomfort for a Zoom on a Stereoscopic Camera
Current Optics and Photonics
2016 .10
-
복잡한 도심, 주변보다 4℃ 뜨겁다 : 정부 ZOOM-IN
월간환경
2023 .09
-
[정부 ZOOM-IN] 33년간 해수면 높이 평균 9.9㎝ 높아져
월간환경
2023 .01
-
‘기후 정보’ 공개 요구 갈수록 커질 것 : 정부 ZOOM-IN
월간환경
2023 .08
-
금융산업 온실가스 1년 새 15.4조원 증가 : 정부 ZOOM-IN
월간환경
2022 .03
-
[정부 ZOOM-IN] 2030년까지 국토 30% 생물다양성 보호
월간환경
2024 .01
-
ANALYSIS OF THE FLOOR PLAN DATASET WITH YOLO V5
JOURNAL OF THE KOREAN SOCIETY FOR INDUSTRIAL AND APPLIED MATHEMATICS
2023 .12
-
Design of an 8x Four-group Inner-focus Zoom System Using a Focus Tunable Lens
Current Optics and Photonics
2016 .04
-
정부 ZOOM-IN_시멘트 ‘친환경 인증’ 사라진다
월간환경
2024 .03
-
[정부 ZOOM-IN] 이제 전기이륜차 타고 보조금 받으세요 외
월간환경
2025 .04
-
지천부터 하구까지 건강한 물환경 : 정부 ZOOM-IN
월간환경
2020 .04
-
[정부 ZOOM-IN] 꿀벌 100억 마리 사라져도 괜찮다는 정부
월간환경
2023 .04
-
[정부 ZOOM-IN] 2021년 환경부 예산 11조1715억원 확정 외
월간환경
2021 .01
-
Investigation on Image Quality of Smartphone Cameras as Compared with a DSLR Camera by Using Target Image Edges
대한원격탐사학회지
2016 .01
-
[ZOOM-IN] “미세먼지 대책 성과 부풀리기” 감사원 적발 외
월간환경
2020 .11
-
[정부 ZOOM-IN] 한·중·일 ‘포용적 녹색 전환’ 협력 강화 외
월간환경
2022 .01
-
[정부 ZOOM-IN] 韓 해상풍력으로 77만개 일자리 창출 가능 외
월간환경
2024 .06
-
정부 ZOOM-IN_2030년까지 420조 정책금융 녹색자금 공급
월간환경
2024 .04
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2022-047-000055651