미디어 폭력성 측정방식의 전환: 컴퓨터 비전을 통한 자동화된 폭력장면 검출
Transition in Measuring Media Violence: Automated Detection of Violent Scenes through Computer Vision
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
본 연구는 컴퓨터 비전의 폭력장면 자동검출 기술을 활용하여 미디어 폭력성의 새로운 연구방법을 제시한다. 커뮤니케이션학과 컴퓨터 공학의 접점에서 미디어의 폭력성을 재개념화하고 효율적인 특징추출작업, 장면분류작업이 가능한 모바일넷 버전2(MobileNetV2) CNN 알고리즘을 활용하여 한국 드라마의 특성을 반영한 자동검출 프로그램을 개발하였다. 드라마 <펜트하우스> 두 편에 나타난 폭력장면을 자동검출 프로그램으로 분석해 성능 확인 후, 인간 연구자들이 물리적 폭력이라고 내용분석한 결과와 비교분석했다. 그 결과, 폭력 장면의 검출을 기준으로 정확도 81.8%, 정밀도 9.4%, 재현율 22.45%로 나타났다. 자동검출 프로그램의 폭력장면 미검출된 위음성 비율은 4.81%, 과도하게 검출된 위양성 비율은 13.39%이었다. 과도한 검출의 특징은 부정적 표정 빠른 움직임 변화, 다수 출연자 등 미디어 폭력의 특성과 관련된 요소들로, 각 특징 검출에 알맞은 알고리즘 추가를 보완책으로 제시하였다. 본 연구는 미디어 영상에 나타난 폭력장면의 검출방식이 기존 인간 연구자의 직접 분석에서 자동검출 프로그램 이용으로 변화하는 시점에서 자동검출 프로그램을 개발, 실제 방영된 드라마를 분석해 유효성 검증을 거치고, 인간 연구자가 폭력으로 판단한 장면과 비교분석했다는 의의가 있다.
참고문헌 (77)
- 곽수영, "폭력 행위 인식 기술 동향", 한국멀티미디어학회지, 19(4), pp.28~35 (2015)
- 곽진희, "디지털 시대 미디어 폭력연구" (2004), 한울
- 권만우, "미디어 신경과학 생리심리학적 관점에서 본영상물 등급분류의 과학화" (2013), 나무와 숲
- "선정성 논란 SBS ‘펜트하우스’에 19세 등급 요구" (2021), 금준경[URL]
- 김선민, "인공지능을 활용한 스트리밍 서비스", SNS 내에서의 폭력 감지 시스템, 2020, ~
- "선 넘은 폭력 묘사…방심위, 드라마 ‘펜트하우스’에 중징계" (2021), 김효실[URL]
- 민영, "주시청시간대 지상파 텔레비전의 폭력성 연구폭력의 양과 유형을 중심으로", 한국방송학보, 21(5), pp.84~126 (2007), 한국방송학회
- 서영남, "한국 뮤직비디오의 폭력성 연구", 방송문화연구, 21(1), pp.187~221 (2009), 한국방송공사[DOI]
- "‘폭력 묘사’ 논란 SBS ‘펜트하우스2’ 법정제재 결정" (2021), 손지인[URL]
- 송창호, "옵티컬 플로우 분석을 통한 불법 유턴 차량 검지", 한국통신학회논문지C, 39(10), pp.948~956 (2014), 한국통신학회
- 심영빈, "CCTV에서 폭력 행위 감지 시스템 연구", 디지털콘텐츠학회논문지, 16(1), pp.25~32 (2015), 한국디지털콘텐츠학회[DOI]
- "“마약·폭력·음주” OTT 콘텐츠 21%가 ‘청불’...넷플릭스 비중 압도적" (2022), 이다겸[URL]
- 이연수, "딥러닝 기반의 폭력행위 감지 시스템 개발", 한국컴퓨터정보학회논문지, 24(3), pp.87~93 (2019), 한국컴퓨터정보학회[DOI]
- 이정현, "영상화재감지기 시험과 설치기준에 관한 연구", 한국화재소방학회 논문지, 30(4), pp.1~5 (2016), 한국화재소방학회[DOI]
- 정미정, "텔레비전 드라마의 폭력성 묘사연구 :방송심의제재를 받은 드라마를 대상으로", 언론과학연구, 19(3), pp.83~123 (2019), 한국지역언론학회
- 정유진, "드라마 <펜트하우스> 화면에 나타난 폭력성 연구 맥락적 요인을 중심으로", 커뮤니케이션 이론, 18(4), pp.199~255 (2022), 한국언론학회
- 정홍인, "A pilot study to develop an efficient film classification method", 대한인간공학회 2014 추계학술대회 (2014)
- 최윤정, "딥 러닝(Deep learning)기반 동영상 처리 알고리즘을 통한 19대 대선 TV토론 영상분석 후보자들의 등장빈도, 표정, 응시방향에 대한 분석", 한국언론학보, 64(5), pp.319~372 (2020), 한국언론학회[DOI]
- 하승태, "국내 지상파 TV 드라마에 나타난 폭력성 폭력의 양태와 맥락을 중심으로", 사회과학연구, 23(2), pp.77~104 (2007), 사회과학연구소
- 하승태, "케이블TV에 나타난 폭력성 연구:폭력의 맥락화를 중심으로", 한국언론정보학보, 41(1), pp.200~231 (2008), 한국언론정보학회
- 하승태, "주시청시간대 지상파 텔레비전의 폭력성 연구: 폭력의 맥락적 변인을 중심으로", 한국언론학보, 51(6), pp.317~345 (2007), 한국언론학회
- Ali, A., "A review on violence video classification using convolutional neural networks", Paper presented by at the Second International Conference on Soft Computing and Data Mining (SCDM-2016) (2016)
- Allen, J. J., "The Wiley handbook of violence and aggression", pp.1~4 (2017), John Wiley & Sons
- Anderson, C. A., "Human aggerssion", Annual Review of Psychology, 53, pp.27~51 (2002)
- Baron, R. A., "Human aggression" (1994), Plenum Press
- Bermejo Nievas, E., "Violence detection in video using computer vision techniques", Paper presented by at the 14th International Conference on Computer Analysis of Images and Patterns (CAIP 2011) (2011)
- Bushman, B. J., "Handbook of social psychology, Vol. 2", pp.833~863 (2010), John Wiley & Sons
- Bushman, B. J., "Handbook of children and the media", pp.231~248 (2012), Sage
- Buss, A. H, "The psychology of aggression" (1961), John Wiley & Sons
- Chen, L. H., "Violence detection in movies", Paper presented by at the 2011 Eighth International Conference Computer Graphics, Imaging and Visualization (CGIV 2011) (2011)
- Cheng, W. H., "Semantic context detection based on hierarchical audio models", Paper presented by at the 5th ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR 2003) (2003)
- Clarin, C. T., "DOVE: Detection of movie violence using motion intensity analysis on skin and blood", PCSC, 6, pp.150~156 (2005)
- Constantin, M. G., "Affect in multimedia : Benchmarking violent scenes detection", IEEE Transactions on Affective Computing, 13(1), pp.347~366 (2020)
- Dai, Q., "Fudan-NJUST at MediaEval 2014: Violent scenes detection using deep neural networks", Paper presented by at the MediaEval 2014 Workshop (2014)
- Datta, A. K., "Infrared and hot-air-assisted microwave heating of foods for control of surface moisture", Journal of Food Engineering, 51(4), pp.355~364 (2002)
- de Azevedo Kanehisa, R. F., "Firearm detection using convolutional neural networks", Paper presented by at the 11th International Conference on Agents and Artificial Intelligence (ICAART 2019) (2019)
- Demarty, C. H., "Benchmarking violent scenes detection in movies", Paper presented by at the 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI) (2014)
- Ding, C., "Violence detection in video by using 3D convolutional neural networks", Paper presented by at the 10th International Symposium on Visual Computing (ISVC 2014) (2014)
- "Real Life Violence Situations Dataset" (2019)[URL]
- Febin, I. P., "Violence detection in videos for an intelligent surveillance system using MoBSIFT and movement filtering algorithm", Pattern Analysis and Applications, 23(2), pp.611~623 (2020)
- Finlay, C. J., "The concept of violence in international theory : A double-intent account", International Theory, 9(1), pp.67~100 (2017)
- Galtung, J, "Violence, peace and peace research", Journal of Peace Research, 6(3), pp.167~191 (1969)
- Gao, Y., "Violence detection using oriented violent flows", Image and Vision Computing, 48, pp.37~41 (2016)
- Gerbner, G., "Perspectives on media effects", pp.17~40 (1986), Lawrence Erlbaum Associates
- Gerbner, G., "Growing up with television : Cultivation processes", Media Effects : Advances in Theory and Research, 2(1), pp.43~67 (2002)
- Giannakopoulos, T., "Audio-visual fusion for detecting violent scenes in videos", Paper presented by at the 6th Hellenic Conference on Artificial Intelligence (SETN 2010) (2010)
- Gong, Y., "Detecting violent scenes in movies by auditory and visual cues", Paper presented by at the 9th Pacific Rim Conference on Multimedia (PCM 2008) (2008)
- Hanjalic, A., "Affective video content representation and modeling", IEEE Transactions on Multimedia, 7(1), pp.143~154 (2005)
- Harris, J., "Violence and responsibility" (1980), Routledge & Kegan Paul
- Hassner, T., "Violent flows : Real-time detection of violent crowd behavior", Paper presented by at the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2012) (2012)
- Ionescu, B., "A naive mid-level conceptbased fusion approach to violence detection in Hollywood movies", Paper presented by at the International Conference on Multimedia Retrieval (ICMR 2013) (2013)
- Kahou, S. E., "Combining modality specific deep neural networks for emotion recognition in video", Paper presented by at the International Conference on Multimodal Interaction (ICMI 2013) (2013)
- Kalmoe, N. P., "Fueling the fire : Violent metaphors, trait aggression, and support for political violence", Political Communication, 31(4), pp.545~563 (2014)
- Kananovich, V, "From “angry mobs” to “citizens in anguish”: The malleability of the protest paradigm in the international news coverage of the 2021 US Capitol attack", American Behavioral Scientist (2021)[DOI]
- Krahé, B, "The social psychology of aggression" (2013), Psychology Press
- Leone, R., "Hollywood's triumph and parents' loss : An examination of the PG-13 rating", Popular Communication, 2(2), pp.85~101 (2004)
- Lin, J., "Weakly-supervised violence detection in movies with audio and video based co-training", Paper presented by at the 10th Pacific Rim Conference on Multimedia (PCM 2009) (2009)
- Nam, J., "Audio-visual content-based violent scene characterization", Paper presented by at the International Conference on Image Processing (ICIP98) (1998)
- Patwardhan, A., "Aggressive actions and anger detection from multiple modalities using Kinect", arXiv preprint arXiv:1607.01076, ~ (2016)
- Pikrakis, A., "Gunshot detection in audio streams from movies by means of dynamic programming and Bayesian networks", Paper presented by at the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2008) (2008)
- Sandler, M., "Mobilenetv2 : Inverted residuals and linear bottlenecks", Paper presented by at the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2018) (2018)
- Schramm, W., "Television in the lives of our children" (1961), Stanford University Press
- Smith, S. L., "Prime-time television : Assessing violence during the most popular viewing hours", Journal of Communication, 52(1), pp.84~111 (2002)
- Smith, S. L., "National television violence study", pp.5~220 (1998), Sage
- Soliman, M. M., "Violence recognition from videos using deep learning techniques", Paper presented by at the Ninth International Conference on Intelligent Computing and Information Systems (ICICIS) (2019)
- Song, W., "A novel violent video detection scheme based on modified 3D convolutional neural networks", IEEE Access, 7, pp.39172~39179 (2019)
- Spierenburg, P., "Violence in Europe: Historical and contemporary perspectives", pp.13~25 (2008), Springer
- Sudhakaran, S., "Learning to detect violent videos using convolutional long short-term memory", Paper presented by at the 14th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS) (2017)
- Ullah, F. U. M., "Violence detection using spatiotemporal features with 3D convolutional neural network", Sensors, 19(11), pp.2472~ (2019)
- Vorobej, M, "The concept of violence" (2008), Routledge
- Wang, K., "Violence video detection by discriminative slow feature analysis", Paper presented by at the Chinese Conference on Pattern Recognition (CCPR 2012) (2012)
- Wang, X., "Learning semantic scene models by trajectory analysis", Paper presented by at the 9th European Conference on Computer Vision (ECCV 2006) (2006)
- ㅈWorld Health Assembly, "Prevention of violence: Public health priority", Paper presented by at the Forty-Ninth World Health Assembly (1996)
- Ye, L., "Campus violence detection based on artificial intelligent interpretation of surveillance video sequences", Remote Sensing, 13(4), pp.628~ (2021)
- Yun, K., "Twoperson interaction detection using body-pose features and multiple instance learning", Paper presented by at the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2012) (2012)
- Zhou, P., "Viol ence detection in surveillance video using low-level features", PLoS one, 13(10), pp.e0203668~ (2018)
- Zizek, S., "Violence: Six sideways reflections" (2008), Profile Books
