Object detection in the police surveillance scenario

• Autorzy: Wilkowski Artur , Kasprzak Włodzimierz , Stefańczyk Maciej

Identyfikatory

DOI

10.15439/2019F291

• Konferencja: Federated Conference on Computer Science and Information Systems (14 ; 01-04.09.2019 ; Leipzig, Germany)
• Języki publikacji: EN

Abstrakty

EN

Police and various security services use video analysis when investigating criminal activity. One typical scenario is the selection of object in image sequence and search for similar objects in other images. Algorithms supporting this scenario must reconcile several seemingly contradicting factors: training and detection speed, detection reliability and learning from sparse data. In the system that we propose a combined SVM/Cascade detector is used for both speed and detection reliability. In addition, object tracking and background-foreground separation algorithm together with sample synthesis is used to collect rich training data. Experiments show that the system is effective, useful and suitable for selected tasks of police surveillance.

Słowa kluczowe

EN

feature extraction; image classification; image sequences; artificial intelligence; object detection; object tracking; support vector machine; video signal processing; video surveillance

PL

ekstrakcja cech; klasyfikacja obrazu; sekwencje obrazów; sztuczna inteligencja; wykrywanie obiektów; śledzenie obiektów; przetwarzanie sygnału wideo; nadzór wideo

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2019
• Tom: Vol. 18
• Strony: 363–--372
• Opis fizyczny: Bibliogr. 13 poz., il., wz., wykr.

Twórcy

autor

Wilkowski Artur

• Insitute of Control and Computation Engineering, Warsaw University of Technology, ul. Nowowiejska 15/19, 00-665 Warsaw, Poland

autor

Kasprzak Włodzimierz

• Insitute of Control and Computation Engineering, Warsaw University of Technology, ul. Nowowiejska 15/19, 00-665 Warsaw, Poland

autor

Stefańczyk Maciej

• Insitute of Control and Computation Engineering, Warsaw University of Technology, ul. Nowowiejska 15/19, 00-665 Warsaw, Poland

Bibliografia

• 1. J. Arraiza, N. Aginako, G. Kioumourtzis, G. Leventakis, G. Stavropoulos, D. Tzovaras, N. Zotos, A. Sideris, E. Charalambous, and N. Koutras, “Fighting volume crime: an intelligent, scalable, and low cost approach,” 9th Summer Safety & Reliability Seminars, SSARS 2015, June 21- 27, 2015, Gdansk/Sopot, Poland, 2015.
• 2. S. Blunsden and R. Fisher, “The behave video dataset: Ground truthed video for multi-person behavior classification,” Annals of the BMVA, vol. 2010, no. 4, pp. 1–11, 2010.
• 3. G. Awad, C. G. M. Snoek, A. F. Smeaton, and G. Quénot, “Trecvid semantic indexing of video: A 6-year retrospective,” ITE Transactions on Media Technology and Applications, vol. 4, no. 3, pp. 187–208, 2016. http://dx.doi.org/10.3169/mta.4.187 Invited paper.
• 4. J. Redmon, S. K. Divvala, R. B. Girshick, and A. Farhadi, “You only look once: Unified, real-time object detection,” CoRR, vol. abs/1506.02640, 2015. [Online]. Available: http://arxiv.org/abs/1506.02640
• 5. D. Zeng, F. Zhao, S. Ge, and W. Shen, “Fast cascade face detection with pyramid network,” Pattern Recognition Letters, vol. 119, pp. 180 – 186, 2019. http://dx.doi.org/https://doi.org/10.1016/j.patrec.2018.05.024 Deep Learning for Pattern Recognition. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0167865518302125
• 6. M. Woźniak and D. Połap, “Object detection and recognition via clustered features,” Neurocomputing, vol. 320, pp. 76 – 84, 2018. http://dx.doi.org/https://doi.org/10.1016/j.neucom.2018.09.003. [Online]. Available: http://www.sciencedirect.com/science/article/pii/S0925231218310634
• 7. Y. Abramson and Y. Freund, “Active learning for visual object detection,” UCSD, Tech. Rep., 01 2006.
• 8. Y. Abramson and Y. Freund, “SEmi-automatic VIsual LEarning (SEVILLE): Tutorial on active learning for visual object recognition,” Proc. CVPR, 2005.
• 9. J. Sivic and A. Zisserman, “Video google: A text retrieval approach to object matching in videos,” in Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2, ser. ICCV ’03. Washington, DC, USA: IEEE Computer Society, 2003. ISBN 0-7695-1950-4 pp. 1470–. [Online]. Available: http://dl.acm.org/citation.cfm?id=946247.946751
• 10. Z. Kalal, K. Mikolajczyk, and J. Matas, “Tracking-learning-detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 34, no. 7, pp. 1409–1422, July 2012. http://dx.doi.org/10.1109/TPAMI.2011.239
• 11. M. Andriluka, S. Roth, and B. Schiele, “People-tracking-by-detection and people-detection-by-tracking,” in 2008 IEEE Confer- ence on Computer Vision and Pattern Recognition, June 2008. http://dx.doi.org/10.1109/CVPR.2008.4587583. ISSN 1063-6919 pp. 1–8.
• 12. C. Feichtenhofer, A. Pinz, and A. Zisserman, “Detect to track and track to detect,” in IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, 2017. http://dx.doi.org/10.1109/ICCV.2017.330 pp. 3057–3065. [Online]. Available: https://doi.org/10.1109/ICCV.2017.330
• 13. K. Kang, W. Ouyang, H. Li, and X. Wang, “Object detection from video tubelets with convolutional neural networks,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 817–825, 2016.

Uwagi

1. Track 2: Computer Science & Systems

2. Technical Session: 12th International Symposium on Multimedia Applications and Processing

3. Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).