Anatomy of a multicamera video surveillance system

Abstract

Abstract. We present a framework for multicamera video surveillance. The framework consists of three phases: detection, representation, and recognition. The detection phase handles multisource spatiotemporal data fusion for efficiently and reliably extracting motion trajectories from video. The representation phase summarizes raw trajectory data to construct hierarchical, invariant, and content-rich descriptions of the motion events. Finally, the recognition phase deals with event classification and identification on the data descriptors. Through empirical study in a parking-lot-surveillance setting, we show that our spatiotemporal fusion scheme and biased sequence-data learning method are highly effective in identifying suspicious events.

Fast Human Detection in Surveillance Video

“…Mikolajczyk et al [11] parts based human detection method containing detectors for front and side profiles of upper and lower body parts, heads and faces. There are existing systems which uses filters such as particle filters [12], Kalman filters [13] and HMM (Hidden Markov Model) filters [14] to track humans in video.…”

Effective Cache based Policies in Wireless Sensor Networks: A Survey

“…The recent developments in making energy efficient Wireless Sensor Network [1][2] is giving new direction to deploy these networks in applications like surveillance [3][4][5], industrial monitoring [6], traffic monitoring [7], habitat monitoring [8], cropping monitoring [9], crowd counting [10], etc . The growing use of these networks is making engineers to evolve innovative and efficient ideas in this field.…”

A Survey of Vision-Based Trajectory Learning and Analysis for Surveillance

“…The movements of people both indoors and outdoors have been extensively studied to determine where people tend to travel. Parking lots have been monitored to ensure proper use by detecting unusual driving patterns [8] and people loitering around parked vehicles [9], [10]. New exciting work has come forward to analyze interactions between humans, vehicles, and infrastructure, allowing monitoring of suspicious meetings [1] and luggage drops as well as characterization of conflicts for road safety [12]- [15].…”

“…A similarity matrix is constructed for the training set where indicates the similarity between trajectories . A new matrix called the Laplacian is formed (8) where is a diagonal matrix whose th diagonal element is the sum of row of . The matrix is decomposed to find its largest eigenvalues.…”

“…Vector quantization reduction is achieved by limiting the number of unique trajectories to a finite alphabet of prototypical vectors which symbolize all trajectories [8], [33], [58], [59].…”