A distributed camera system for multi-resolution surveillance

Abstract

Abstract-We describe an architecture for a multi-camera, multi-resolution surveillance system. The aim is to support a set of distributed static and pan-tilt-zoom (PTZ) cameras and visual tracking algorithms, together with a central supervisor unit. Each camera (and possibly pan-tilt device) has a dedicated process and processor. Asynchronous interprocess communications and archiving of data are achieved in a simple and effective way via a central repository, implemented using an SQL database.Visual tracking data from static views are stored dynamically into tables in the database via client calls to the SQL server. A supervisor process running on the SQL server determines if active zoom cameras should be dispatched to observe a particular target, and this message is effected via writing demands into another database table.We show results from a real implementation of the system comprising one static camera overviewing the environment under consideration and a PTZ camera operating under closed-loop velocity control, which uses a fast and robust level-set-based region tracker. Experiments demonstrate the effectiveness of our approach and its feasibility to multi-camera systems for intelligent surveillance.

Cognitive visual tracking and camera control

“…In this section we introduce, and partly extend, the architecture described in [1], a schematic of which is illustrated in Fig. 2.…”

“…This paper describes a system which supports work towards this goal. In a previous paper [1] we have considered the issues of low-level data acquisition processes, and how these processes communicate. In the current paper we are more concerned with augmenting this architecture with contextual information to enable top-down processing.…”

“…In [1], in common with many other similar implementations, the system attempted to satisfy the first part of this goal using two simple, hard-coded rules: if a new target was observed by an overhead static camera, a PTZ device was immediately dispatched to acquire and track it autonomously at a pre-specified zoom level. However our objective in the current work is to couple high-level inference to sensing strategies.…”

Adaptive background modeling in multicamera system for real-time object detection

“…New systems and architectures are required in order to efficiently manage the huge amount of data coming from different sensors: networks of smart cameras, 9 peer-to-peer network of computers or centralized architectures 10 are the most used solutions.…”

Scalable software architecture for on-line multi-camera video processing

“…An alternative solution to tackle these issues ,often used in indoor environments, is based on a centralized server architecture, where the central server collects and processes all the data. The main limitations of this model are that it is very power demanding, it requires a large bandwidth communication channel and, obviously, it does not allow a high degree of scalability 2 . An improvement of the centralized server architecture is constituted by peer to peer network of computers where different nodes manage different cameras.…”