Human Body Orientation Estimation in Multiview Scenarios
Estimation of human body orientation is an important cue to study and understand human behaviour, for different tasks such as video surveillance or human-robot interaction. In this paper, we propose an approach to simultaneously estimate the body orientation of multiple people in multi-view scenarios, which combines a 3D human body shape and appearance model with a 2D template matching approach. In particular, the 3D model is composed of a generic shape made up of elliptic cylinders, and a 3D colored point cloud (appearance model), obtained by back-projecting pixels from foreground images onto the geometric surfaces. In order to match the reconstructed appearance to target images in arbitrary poses, the appearance is re-projected onto each of the different views, by generating multiple templates that are pixel-wise, robustly matched to the respective foreground images. The effectiveness of the proposed approach is demonstrated through experiments in indoor sequences with manually-labeled ground truth, using a calibrated multi-camera setup.
KeywordsPoint Cloud Appearance Model Body Orientation Orientation Estimation Foreground Image
Unable to display preview. Download preview PDF.
- 1.Khan, S., Javed, O., Rasheed, Z., Shah, M.: Human tracking in multiple cameras. In: Proceedings of the 8th IEEE International Conference on Computer Vision, Vancouver, Canada, pp. 331–336 (2001)Google Scholar
- 4.Leibe, B., Schindler, K., Van Gool, L.: Coupled detection and trajectory estimation for multi-object tracking. In: International Conference on Computer Vision (2007)Google Scholar
- 5.Andriluka, M., Roth, S., Schiele, B.: Monocular 3d pose estimation and tracking by detection. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR (2010)Google Scholar
- 6.Lee, M.W., Nevatia, R.: Body part detection for human pose estimation and tracking. In: IEEE Workshop on Motion and Video Computing (2007)Google Scholar
- 7.Yao, J., Odobez, J.: Multi-camera 3d person tracking with particle filter in a surveillance environment. In: 8th European Signal Processing Conference, EUSIPCO (2008)Google Scholar
- 8.Gandhi, T., Trivedi, M.: Image based estimation of pedestrian orientation for improving path prediction. In: IEEE IV Symposium, pp. 506–511 (2008)Google Scholar
- 9.Chen, C., Heili, A., Odobez, J.: Combined estimation of location and body pose in surveillance video. In: IEEE Conf. on Advanced Video and Signal Based Surveillance, AVSS (2011)Google Scholar
- 10.Chen, L., Panin, G., Knoll, A.: Multi-camera people tracking with hierarchical likelihood grids. In: Proceedings of the 6th International Conference on Computer Vision Theory and Applications, pp. 474–483 (2011)Google Scholar
- 11.Griesser, A., Roeck, D.S., Neubeck, A., Van Gool, L.: Gpu-based foreground-background segmentation using an extended colinearity criterion. In: Proc. of Vison, Modeling, and Visualization (VMV), pp. 319–326 (2005)Google Scholar