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
- 2021.7
- 수록면
- 482 - 489 (8page)
- DOI
- 10.5302/J.ICROS.2021.21.0011
이용수
초록· 키워드
오류제보하기
In this study, we developed an AI deep learning-based fighting behavior recognition method for a video surveillance system and proved its effectiveness through various experiments. The proposed method consists of a two-step fighting behavior recognition framework. First, continuous video frames of the target surveillance video are transmitted to the Inflated 3D ConvNet (I3D) network, which shows a good behavior-recognition performance, to extract the spatiotemporal features. These extracted 3D features are then used as the inputs in the next step, where a fight situation is detected using a classification model consisting of a fully connected layer. To use the proposed aggressive behavior detection framework effectively, first, it is necessary to train the fight detection model. However, it is not possible to collect sufficient fighting videos in various outdoor environments. To overcome this limitation, we generated a large amount of learning data through data augmentation. Therefore, instead of directly learning from the training videos transmitted to the I3D network, the classifier trains itself to recognize various fighting actions using the Kinetics video dataset. That is, the action features are extracted from the transmitted consecutive frames using the pretrained I3D network and subsequently used to train the fully connected layer classification model. In addition, we proposed a learning method that includes recognizing ambiguous conflict boundaries using multiple instance learning to mitigate the ambiguous starting and ending of the contention videos. The effectiveness of the proposed method was verified through several experiments by drawing comparisons between the present results and those of the previously reported studies.
목차
Abstract
I. 서론
II. 제안하는 싸움(다툼) 행동인식 방법
III. 실험환경 및 실험결과
IV. 결론 및 추후 과제
REFERENCES
참고문헌 (21)
참고문헌 신청
S. Fleck and W. Straber, Privacy Sensitive Surveillance for Assisted Living-A Smart Camera Approach, Handbook of Ambient Intelligence and Smart Environments, pp. 985-1014, 2010.
T. Hassner, Y. Itcher and O. Kliper-Gross, “Violent flows: real-time detection of violent crowd behavior,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2012.
Y. Gao, H. Liu, X. Sun, C. Wang, and Y. Liu, “Violence detection using oriented violent flows,” Image and Vision Computing, vol. 48-49, pp. 37-41, 2016.
P. Bilinski and F. Bremond, “Human violence recognition and detection in surveillance videos,” 2016 13th IEEE International conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 23-26, Aug. 2016.
P. Zhou, Q. Ding, H. Luo, and X. Hou, “Violence detection in surveillance video using low-level features,” PLOS, 2018.
T. Hassner, Y. Itcher and O. Kliper-Gross, “Violent flows: real-time detection of violent crowd behavior,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2012.
Y. Gao, H. Liu, X. Sun, C. Wang, and Y. Liu, “Violence detection using oriented violent flows,” Image and Vision Computing, vol. 48-49, pp. 37-41, 2016.
P. Bilinski and F. Bremond, “Human violence recognition and detection in surveillance videos,” 2016 13th IEEE International conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 23-26, Aug. 2016.
P. Zhou, Q. Ding, H. Luo, and X. Hou, “Violence detection in surveillance video using low-level features,” PLOS, 2018.
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Extraction of Key Frames from Dance Videos and Movement Recognition by Multi-feature Fusion
IEIE Transactions on Smart Processing & Computing
2023 .12
-
비디오에서 동체의 행위인지를 위한 효율적 학습 단위에 관한 연구
멀티미디어학회논문지
2017 .01
-
The Effects of Randomizing Input Feature Vectors When Training Video Based Learning Models
한국정보과학회 학술발표논문집
2021 .06
-
Video Expression Recognition Method Based on Spatiotemporal Recurrent Neural Network and Feature Fusion
JIPS(Journal of Information Processing Systems)
2021 .01
-
비디오 행동인식을 위한 효과적인 딥러닝 알고리즘
한국방송미디어공학회 학술발표대회 논문집
2018 .06
-
Movement Detection Using Keyframes in Video Surveillance System
한국방송미디어공학회 학술발표대회 논문집
2022 .06
-
Intelligent Activity Recognition based on Improved Convolutional Neural Network
멀티미디어학회논문지
2022 .06
-
Temporal matching prior network for vehicle license plate detection and recognition in videos
[ETRI] ETRI Journal
2020 .06
-
오디오-비디오 스위치 네트워크를 활용한 딥러닝 기반 비디오 탐색
대한전자공학회 학술대회
2022 .06
-
A Deep-Learning Based Model for Emotional Evaluation of Video Clips
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2018 .12
-
Online Video Synopsis via Multiple Object Detection
한국컴퓨터정보학회논문지
2019 .08
-
딥러닝을 활용한 이상 행동 검출 방법
Proceedings of KIIT Conference
2023 .11
-
수술 도구의 세분화와 행동 인식 기능이 탑재된 AI 서비스 개발
대한임베디드공학회논문지
2021 .01
-
국방 경계감시 능력 증강을 위한 AI 허브 데이터셋 활용 연구
대한전자공학회 학술대회
2023 .06
-
Describing Environmental Information in Videos Using Machine Learning
제어로봇시스템학회 국제학술대회 논문집
2021 .10
-
객체 탐지와 행동인식을 이용한 영상내의 비정상적인 상황 탐지 네트워크
멀티미디어학회논문지
2021 .02
-
비디오 얼굴인식을 위한 다중 손실 함수 기반 어텐션 심층신경망 학습 제안
멀티미디어학회논문지
2021 .10
-
Deep Learning Applied Abnormal Human Behavior Detection in Video Surveillance Systems - A Survey
International JOURNAL OF CONTENTS
2024 .12
-
딥러닝 기반 얼굴 인식을 이용한 동영상 식별
한국통신학회 학술대회논문집
2017 .01
-
화재피해 감소 위한 자동소화장치 적용범위 개선
한국안전학회지
2018 .01
이 논문의 저자 정보
이 논문과 함께 이용한 논문
한국축구, 4강 영광을 되찾아야!
강해주
Electric Power
2014
.07
관심영역기반 3차원 합성곱 신경망을 이용한 행동인식
변영현
,
곽근창
대한전기학회 학술대회 논문집
2021
.07
비디오 행동인식을 위한 효과적인 딥러닝 알고리즘
차상국
,
한종기
한국방송미디어공학회 학술발표대회 논문집
2018
.06
다중모드 센서와 LSTM 기반의 딥 러닝을 이용한 인간의 행동인식 시스템
신수연
,
차주헌
대한기계학회 논문집 A권
2018
.02
미분 정보 복구 함수 기반 제약 조건 최적화 진화 알고리즘
오상헌
,
황용수
,
전문구
Proceedings of KIIT Conference
2010
.05
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2021-003-001844825