Proceedings of the third ACM international workshop on Video surveillance & sensor networks

Abstract

Welcome to the 3rd ACM Workshop on Video Surveillance & Sensor Networks -- VSSN'05. Thank you for your interest and participation. This workshop is continuation of earlier workshops in Berkeley CA 2003, addressed video surveillance only, and New York NY, 2004 that extended the focus on sensor networks. Indeed, there is a large interest in developing and deploying large scale network of sensors -- optical sensor including cameras or non-optical sensors including electrical, thermal, chemical and biological, for surveillance.Following the success of the past events, the current workshop explores the state-of-the art of research activity in multi-camera, distributed video surveillance systems, sensor networks and their integration. The aim is to create the infrastructure for new platforms of multimedia surveillance systems that integrate multiple source and multimedia data (video, audio, digital sensor's signals..., annotated and textual knowledge) to improve the effectiveness of surveillance systems.The call for papers attracted submissions from a number of countries including USA, Canada, UK, Italy, Finland, Ireland, Germany, Republic of Singapore, Hong Kong. The program committee accepted 15 Papers. The workshop topics include algorithms for image and video processing for surveillance, covering camera calibration, mosaicing, background creation, trajectory classification; architecture of large integrated multi-camera systems and sensor networks for different applications including indoor and outdoor surveillance, public parks monitoring, archaeological site controls, virtual reality for multi-camera system simulation, model and algorithms for coordination of fixed and active cameras. Special attention is paid for PTZ cameras, their scheduling and calibration, and information fusion. Several researchers explore future directions in integration of biometric and surveillance paradigms, active camera control for people detection tracking and identification.Mubarak Shah is the invited speaker. The title of his talk is "Recognizing Human Actions." It will discuss general issues of computer vision for human actions detection and interpretation.In addition, this workshop includes a competition of open source algorithms for foreground/background segmentation. Four approaches and their C++ implementation will be compared against the existing code available in OpenCV libraries.