IP-distributed computer-aided video-surveillance system

Abstract

In this article we present a generic, flexible and robust approach for an intelligent real-time videosurveillance system. The proposed system is a multi-camera platform that is able to handle different standards of video inputs (composite, IP, IEEE1394). The system implementation is distributed over a scalable computer cluster based on Linux and IP network. Data flows are transmitted between the different modules using multicast technology, video flows are compressed with the MPEG4 standard and the flow control is realized through a TCP-based command network (e.g. for bandwidth occupation control). The design of the architecture is optimized to display, compress, store and playback data and video flows in an efficient way. This platform also integrates advanced video analysis tools, such as motion detection, segmentation, tracking and neural networks modules. The goal of these advanced tools is to provide help to operators by detecting events of interest in visual scenes and store them with appropriate descriptions. This indexation process allows one to rapidly browse through huge amounts of stored surveillance data and play back only interesting sequences. We report here some preliminary results and we show the potential use of such a flexible system in third generation video surveillance system. We illustrate the interest of the system in a real case study, which is the surveillance of a reception desk.

Segmentation and Appearance Features Index for Digital Video Data

“…This tracking module is derived from the method proposed by Piater and Crowley [8] and the derived detection module is presented at [10]. A detection module takes the list of zones as input and computes a list of blobs.…”

“…A detection module takes the list of zones as input and computes a list of blobs. The detection image D is the threshold difference between the current image I and the background image B, computed the following equation [10]:…”

PRISMATICA: Toward Ambient Intelligence in Public Transport Environments

“…Then, the perspective distortion ratio is measured as the ratio between the average velocity magnitude of the constant velocity section and the velocity value measured at point (at the start of the zero-velocity section). Hence, can be calculated as follows: (13) Finally, (14) The value of is derived on the basis that the back plane starts where the furthest pedestrian meets the ground plane. The front edge of the ground plane is a virtual limit for pedestrian motion that was set by the scene model to allow the calculation of and the perspective distortion ratio .…”

“…Various algorithms and systems have been proposed to automate the video-monitoring task, such as the abandoned object-detection system proposed by Boghossian [4], [5], and Sacchi [6], the people-tracking algorithms proposed by Fuentes [7]- [9] and Siebel [10], the congestion-detection algorithm proposed by Lo [11], the analysis of events associated to very large crowds by Boghossian [12], the behavior-analysis system proposed by Rota [13], and the distributed digital camera system proposed by Georis [14]. Public transport environments present major challenges, as identified by the earlier CROMATICA project [15], such as the need to deal with cluttered environments.…”

A flexible communications protocol for a distributed surveillance system

“…Various algorithms and systems have been proposed recently to automate or semi-automate the monitoring task. For example, the abandoned object detection system proposed by Boghossian and Sacchi, the people tracking algorithms proposed by Fuentes and Siebel, the behaviour analysis system proposed by Rota et al, and the distributed digital camera system proposed by Georis et al (Boghossian, 2000;Sacchi and Regazzoni, 2000;Siebel and Maybank, 2002;Rota and Thonnat, 2000;Georis et al, 2003;Fuentes and Velastin, 2001a). However, computer vision algorithms (Deparis et al, 1996;EU CROMATICA project;Fuentes and Velastin, 2001a,b;Lo and Velastin, 2001;Boghossian and Velastin, 1999;Velastin et al, 1999) are only a part of a complete practical surveillance system.…”