An assault detection system based on human Pose Tracking for video surveillance
Resumo
O desenvolvimento de novas tecnologias para monitoramento de vídeos e detecção automática de violência podem trazer mais segurança ao nosso cotidiano. Soluções publicadas anteriormentes no estado da arte apresentam técnicas para detecção de violência em cenas de filmes, partidas esportivas ou em multidões aglomeradas. Neste trabalho, nós propomos uma nova arquitetura de sistema baseado no rastreamento de pose de corpos humanos a fim de detectar evidências de assaltos em vídeos reais capturados por sistemas de circuito interno de TV instalados em agências lotéricas brasileiras. Os resultados mostraram que nosso método pode identificar indivíduos com mãos ao alto e deitado ao chão com precisão de até 85%. Nós acreditamos que esta detecção, em tempo real, de situações de risco pode ser uma ferramenta crucial no combate ao crime.
Palavras-chave:
Visão computacional, Detecção de assalto, PoseTrack, Vídeo de vigilancia
Referências
J. M. Chaquet, E. J. Carmona, and A. Fern´andez-Caballero, “A survey of video datasets for human action and activity recognition,” Computer Vision and Image Understanding, vol. 117, no. 6, pp. 633–659, 2013.
S. Herath, M. Harandi, and F. Porikli, “Going deeper into action recognition: A survey,” Image and vision computing, vol. 60, pp. 4–21, 2017.
G. Cheng, Y. Wan, A. N. Saudagar, K. Namuduri, and B. P. Buckles, “Advances in human action recognition: A survey,” arXiv preprint arXiv:1501.05964, 2015.
Y. Gao, H. Liu, X. Sun, C. Wang, and Y. Liu, “Violence detection using oriented violent flows,” Image and vision computing, vol. 48, pp. 37–41, 2016.
P. C. Ribeiro, R. Audigier, and Q. C. Pham, “Rimoc, a feature to discriminate unstructured motions: Application to violence detection for video-surveillance,” Computer vision and image understanding, vol. 144, pp. 121–143, 2016.
T. Senst, V. Eiselein, A. Kuhn, and T. Sikora, “Crowd violence detection using global motion-compensated lagrangian features and scale-sensitive video-level representation,” IEEE Transactions on Information Forensics and Security, vol. 12, no. 12, pp. 2945–2956, 2017.
P. Zhou, Q. Ding, H. Luo, and X. Hou, “Violence detection in surveillance video using low-level features,” PLoS one, vol. 13, no. 10, p. e0203668, 2018.
A. Hanson, K. Pnvr, S. Krishnagopal, and L. Davis, “Bidirectional convolutional lstm for the detection of violence in videos,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 0–0.
A. Erickson, “Latin america is the worlds most violent region. a new report investigates why,” April 2018, the Washington Post, [posted 25-April-2018]. [Online]. Available: https://wapo.st/2Gq55xN
D. Luhnow, “Latin america is the murder capital of the world,” september 2018, the Wall Street Journal, [posted 20- September-2018]. [Online]. Available: https://www.wsj.com/articles/ 400-murders-a-day-the-crisis-of-latin-america-1537455390
“Segurança morto em tentativa de assalto lotérica na terra firme,” April 2019, g1 - O portal de notcias da Globo, [posted 30-April-2019]. [Online]. Available: https://g1.globo.com/pa/para/noticia/2019/04/30/ seguranca-e-morto-em-tentativa-de-assalto-a-loterica-na-terra-firme. ghtml
“Vídeo mostra assaltos a casas lotéricas no interior de alagoas,” March 2019, g1 - O portal de notcias da Globo, [posted 18-March-2019]. [Online]. Available: https://g1.globo.com/al/alagoas/noticia/2019/03/18/ video-mostra-assaltos-a-casas-lotericas-no-interior-de-alagoas.ghtml
R. Leal, “Empresário assaltado em lotérica diz que criminoso se passou por cliente para roubar dinheiro,” June 2019, g1 - O portal de notcias da Globo, [posted 19-June-2019]. [Online]. Available: https://glo.bo/30Y9FLv
C. Costa, “Vídeo mostra ação de criminosos em assalto a lotérica em parnaíba,” May 2019, g1 - O portal de notcias da Globo, [posted 30-May-2019]. [Online]. Available: https://g1.globo.com/pi/piaui/noticia/2019/05/30/ video-mostra-acao-de-criminosos-em-assalto-a-loterica-em-parnaiba. ghtml
M. Marszałek, I. Laptev, and C. Schmid, “Actions in context,” in CVPR 2009-IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society, 2009, pp. 2929–2936.
S. Blunsden and R. Fisher, “The behave video dataset: ground truthed video for multi-person behavior classification,” Annals of the BMVA, vol. 4, no. 1-12, p. 4, 2010.
E. B. Nievas, O. D. Suarez, G. B. Garc´ıa, and R. Sukthankar, “Violence detection in video using computer vision techniques,” in International conference on Computer analysis of images and patterns. Springer, 2011, pp. 332–339.
K. Soomro, A. R. Zamir, and M. Shah, “A dataset of 101 human action classes from videos in the wild,” Center for Research in Computer Vision, 2012.
Y. Xiu, J. Li, H. Wang, Y. Fang, and C. Lu, “Pose flow: Efficient online pose tracking,” arXiv preprint arXiv:1802.00977, 2018.
H.-S. Fang, S. Xie, Y.-W. Tai, and C. Lu, “RMPE: Regional multi-person pose estimation,” in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2334–2343.
S. Herath, M. Harandi, and F. Porikli, “Going deeper into action recognition: A survey,” Image and vision computing, vol. 60, pp. 4–21, 2017.
G. Cheng, Y. Wan, A. N. Saudagar, K. Namuduri, and B. P. Buckles, “Advances in human action recognition: A survey,” arXiv preprint arXiv:1501.05964, 2015.
Y. Gao, H. Liu, X. Sun, C. Wang, and Y. Liu, “Violence detection using oriented violent flows,” Image and vision computing, vol. 48, pp. 37–41, 2016.
P. C. Ribeiro, R. Audigier, and Q. C. Pham, “Rimoc, a feature to discriminate unstructured motions: Application to violence detection for video-surveillance,” Computer vision and image understanding, vol. 144, pp. 121–143, 2016.
T. Senst, V. Eiselein, A. Kuhn, and T. Sikora, “Crowd violence detection using global motion-compensated lagrangian features and scale-sensitive video-level representation,” IEEE Transactions on Information Forensics and Security, vol. 12, no. 12, pp. 2945–2956, 2017.
P. Zhou, Q. Ding, H. Luo, and X. Hou, “Violence detection in surveillance video using low-level features,” PLoS one, vol. 13, no. 10, p. e0203668, 2018.
A. Hanson, K. Pnvr, S. Krishnagopal, and L. Davis, “Bidirectional convolutional lstm for the detection of violence in videos,” in Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 0–0.
A. Erickson, “Latin america is the worlds most violent region. a new report investigates why,” April 2018, the Washington Post, [posted 25-April-2018]. [Online]. Available: https://wapo.st/2Gq55xN
D. Luhnow, “Latin america is the murder capital of the world,” september 2018, the Wall Street Journal, [posted 20- September-2018]. [Online]. Available: https://www.wsj.com/articles/ 400-murders-a-day-the-crisis-of-latin-america-1537455390
“Segurança morto em tentativa de assalto lotérica na terra firme,” April 2019, g1 - O portal de notcias da Globo, [posted 30-April-2019]. [Online]. Available: https://g1.globo.com/pa/para/noticia/2019/04/30/ seguranca-e-morto-em-tentativa-de-assalto-a-loterica-na-terra-firme. ghtml
“Vídeo mostra assaltos a casas lotéricas no interior de alagoas,” March 2019, g1 - O portal de notcias da Globo, [posted 18-March-2019]. [Online]. Available: https://g1.globo.com/al/alagoas/noticia/2019/03/18/ video-mostra-assaltos-a-casas-lotericas-no-interior-de-alagoas.ghtml
R. Leal, “Empresário assaltado em lotérica diz que criminoso se passou por cliente para roubar dinheiro,” June 2019, g1 - O portal de notcias da Globo, [posted 19-June-2019]. [Online]. Available: https://glo.bo/30Y9FLv
C. Costa, “Vídeo mostra ação de criminosos em assalto a lotérica em parnaíba,” May 2019, g1 - O portal de notcias da Globo, [posted 30-May-2019]. [Online]. Available: https://g1.globo.com/pi/piaui/noticia/2019/05/30/ video-mostra-acao-de-criminosos-em-assalto-a-loterica-em-parnaiba. ghtml
M. Marszałek, I. Laptev, and C. Schmid, “Actions in context,” in CVPR 2009-IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society, 2009, pp. 2929–2936.
S. Blunsden and R. Fisher, “The behave video dataset: ground truthed video for multi-person behavior classification,” Annals of the BMVA, vol. 4, no. 1-12, p. 4, 2010.
E. B. Nievas, O. D. Suarez, G. B. Garc´ıa, and R. Sukthankar, “Violence detection in video using computer vision techniques,” in International conference on Computer analysis of images and patterns. Springer, 2011, pp. 332–339.
K. Soomro, A. R. Zamir, and M. Shah, “A dataset of 101 human action classes from videos in the wild,” Center for Research in Computer Vision, 2012.
Y. Xiu, J. Li, H. Wang, Y. Fang, and C. Lu, “Pose flow: Efficient online pose tracking,” arXiv preprint arXiv:1802.00977, 2018.
H.-S. Fang, S. Xie, Y.-W. Tai, and C. Lu, “RMPE: Regional multi-person pose estimation,” in Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2334–2343.
Publicado
28/10/2019
Como Citar
SOARES, Pedro Gabriel Santos do Couto; DA SILVA, Arnaldo Barros; PEREIRA, Luis Filipe Alves.
An assault detection system based on human Pose Tracking for video surveillance. In: WORKSHOP DE TRABALHOS DA GRADUAÇÃO - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 32. , 2019, Rio de Janeiro.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 192-194.
DOI: https://doi.org/10.5753/sibgrapi.est.2019.8327.
