Computer Vision and Image Understanding xxx

Abstract 13 This paper presents a panoramic virtual stereo vision approach to the problem of detecting 14 and localizing multiple moving objects (e.g., humans) in an indoor scene. Two panoramic 15 cameras, residing on different mobile platforms, compose a virtual stereo sensor with a flexible 16 baseline. A novel ''mutual calibration'' algorithm is proposed, where panoramic cameras on 17 two cooperative moving platforms are dynamically calibrated by looking at each other. A de-18 tailed numerical analysis of the error characteristics of the panoramic virtual stereo vision 19 (mutual calibration error, stereo matching error, and triangulation error) is given to derive 20 rules for optimal view planning. Experimental results are discussed for detecting and localizing 21 multiple humans in motion using two cooperative robot platforms. 2