Exploiting projective geometry for view-invariant monocular human motion analysis in man-made environments.pdfVIP

Computer Vision and Image Understanding 120 (2014) 126–140 Contents lists available at ScienceDirect Computer Vision and Image Understanding journal homepage: /locate/cviu Exploiting projective geometry for view-invariant monocular human motion analysis in man-made environments q Grégory Rogez a,?, Carlos Orrite a, J.J. Guerrero a, Philip H.S. Torr b a Instituto de Investigación en Ingeniería de Aragón (I3A), Universidad de Zaragoza, Spain b Department of Engineering Science, University of Oxford, Oxford, UK article info Article history: Received 16 February 2013 Accepted 27 December 2013 Available online 5 January 2014 Keywords: Human motion analysis Projective geometry View-invariance Video-surveillance abstract Example-based approaches have been very successful for human motion analysis but their accuracy strongly depends on the similarity of the viewpoint in testing and training images. In practice, roof-top cameras are widely used for video surveillance and are usually placed at a signi?cant angle from the ?oor, which is different from typical training viewpoints. We present a methodology for view-invariant monocular human motion analysis in man-made environments in which we exploit some properties of projective geometry and the presence of numerous easy-to-detect straight lines. We also assume that observed people move on a known ground plane. First, we model body poses and silhouettes using a reduced set of training views. Then, during the online stage, the homography that relates the selected training plane to the input image points is calculated using the dominant 3D directions of the scene, the location on the ground plane and the camera view in both training and testing images. This homographic transformation is used to compensate for the changes in silhouette due to the novel viewpoint. In our experiments, we show that it can be employed in a bottom-up manner to align the input image to the training plane and process it with the corresponding view-based