Recent research on video surveillance across multiple cameras has typically focused on camera networks of the order of 10 cameras. In this paper we argue that existing systems do not scale to a network of hundreds, or thousands, of cameras. We describe the design and deployment of an algorithm called exclusion that is specifically aimed at finding correspondence between regions in cameras for l...

An important motivation for face orientation analysis derives from the fact that most face recognition algorithms require face images with approximately frontal view to operate efficiently, such as principle component analysis (PCA) [6], linear discriminant analysis (LDA) [4], and hidden markov model (HMM) techniques [2]. In a networked camera setting, the desire for a fontal view to pursue an ...

We discuss how to obtain the accurate and globally consistent self-calibration of a distributed camera network, in which camera nodes with no centralized processor may be spread over a wide geographical area. We present a distributed calibration algorithm based on belief propagation, in which each camera node communicates only with its neighbors that image a sufficient number of scene points. T...

The client-server model continues to dominate distributed computing with increasingly more flexible variants being deployed. Many are centered on the notion of discovering services at run time and on allowing any system component to act as a service provider. The result is a growing reliance on the service registration and discovery mechanisms. This paper addresses the issue of facilitating suc...

In wireless camera networks, the communication load between cameras is a major concern for visual tracking. To save the bandwidth, traditional applications transfer the spatial coordinates under the precondition of camera calibration, which is computationally unreasonable for large and mobile camera networks. In this chapter, we exploit the use of distinctive and fast to compute local features ...

Localization in sensornets determines the location of sensor nodes, and allows applications to make geographically sensitive queries. Smart camera networks must not only be localized, but calibrated. Calibration goes beyond localization to include orientation and position information that is sufficiently fine-grained to allow fusion between overlapping camera views. This paper introduces Lighth...

Emerging new surveillance technologies that use camera networks offer unprecedented capabilities for law enforcement agencies as well as health-care opportunities. A challenging problem is to track people through very sparse sensor measurements to reduce the cost of expensive sensors and be robust to sensor failure. In this paper we propose a Coupled State Space Model (CSSM) to track people acr...

Two-tier network structure is usually used to lighten the energy consumption in Wireless Multimedia Sensor Networks (WMSNs) for large scale surveillance application. Previous methods for target tracking in two-tier WMSNs mostly focused on reducing energy cost to prolong lifetime of the networks without considering the effect of visual target tracking. This paper presents a collaborative multi-t...