Planning of a Multi Stereo Visual Sensor System - Depth Accuracy and Variable Baseline Approach

This paper presents a method for planning the position of multiple stereo sensors in an indoor environment. This is a component in an intelligent vision agent system. We propose a new approach to dynamically adjust the multiple stereo pair's position, pose and baseline length in 3D space in order to get sufficient visibility and enough accuracy for surveillance, tracking and 3D reconstruction. The paper proposes visibility constraints to plan the camera's pose, and a depth accuracy constraint to control the baseline length. The minimum number of stereo pairs necessary to cover the target space is optimized by an integer linear programming. The 3D simulations of reconstruction accuracy and the human activities space coverage problem were performed in Matlab.