Geometric Tools for Multicamera Surveillance Systems

Abstract

Our analysis and visualization tools use 3D building geometry to support surveillance tasks. These tools are part of DOTS, our multicamera surveillance system; a system with over 20 cameras spread throughout the public spaces of our building. The geometric input to DOTS is a floor plan and information such as cubicle wall heights. From this input we construct a 3D model and an enhanced 2D floor plan that are the bases for more specific visualization and analysis tools. Foreground objects of interest can be placed within these models and dynamically updated in real time across camera views. Alternatively, a virtual first-person view suggests what a tracked person can see as she moves about. Interactive visualization tools support complex camera-placement tasks. Extrinsic camera calibration is supported both by visualizations of parameter adjustment results and by methods for establishing correspondences between image features and the 3D model.

Smart video sensors for 3D scene reconstruction of large infrastructures

“…It is possible to find in the literature some proposals for 3D reconstruction based on computer graphics techniques [12,11], vanishing points [6,15] or trained systems [17]. In our case, our approach uses computer graphics techniques which, following the same basic ideas as previous works, improve the obtained results by using the information from the intelligent nodes to obtain a better reconstruction if compared with previous solutions.…”

“…As we indicated before, some authors have previously used similar techniques, although they commonly use very rough 3D scenarios and create a simple textured polygon at point C to represent the object with an image from the video source [5,11,12]. The main difference with previous approaches is the fact that we do not only use a point of the bounding box to locate the objects, but richer information to obtain a much better approximation of the objects.…”

Data fusion in web-based visualization of 3D scene semantic model

“…An example of semantic text-to-graphics solution have been described in an article [3]. Geometrical tool for multi-camera system has been presented in paper [10]. In this article, it has been proposed to visualize semantic messages in a form of internet-web-page-based 3D scene animation triggered by video-detector subsystem notifications.…”

Localization and mapping of surveillance cameras in city map

“…Unlike our work, it does not map 3D locations in world model to 2D positions in the camera view. The system in [16] does not perform automatic placement of cameras. Instead, a visualization tool is provided for the user to manually position and orientate the cameras in the world model.…”