Toward an Integrated System for Surveillance and Behaviour Analysis of Groups and People
Security and INTelligence SYStem is an Italian research project which aims to create an integrated system for the analysis of multi-modal data sources (text, images, video, audio), to assist operators in homeland security applications. Within this project the Scientific Research Unit of the University of Palermo is responsible of the image and video analysis activity. The SRU of Palermo developed a web service based architecture that provides image and video analysis capabilities to the integrated analysis system. The developed architecture uses both state of the art techniques, adapted to cope with the particular problem at hand, and new algorithms to provide the following services: image cropping, image forgery detection, face and people detection, weapon detection and classification, and terrorist logo recognition. In the last phase of the project we plan to include in our system new services, mainly oriented to the video analysis, to study and understand the behaviour of individuals, either alone or in a group.
Keywordshomeland security weapon detection weapon classification image analysis video analysis logo recognition forgery detection information fusion
- 2.Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: Advances in Neural Information Processing Systems 19, pp. 545–552. MIT Press (2007)Google Scholar
- 4.Dollár, P., Belongie, S., Perona, P.: The Fastest Pedestrian Detector in the West. In: BMVC (2010)Google Scholar
- 5.Pan, X., Lyu, S.: Region duplication detection using image feature matching. IEEE Transactions on Information Forensics and Security, 857–867 (2010)Google Scholar
- 8.Niblack, W., Yin, J.: A pseudo-distance measure for 2D shapes based on turning angle. In: Proceedings of the Int. Conference on Image Processing, vol. 3, pp. 352–355 (1995)Google Scholar