Saliency, Scale and Image Description
International Journal of Computer Vision
Unseeded region growing for 3D image segmentation
VIP '00 Selected papers from the Pan-Sydney workshop on Visualisation - Volume 2
Advances in Computational Stereo
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Time-Of-Flight Depth Sensor - System Description, Issues and Solutions
CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 3 - Volume 03
Bottom-up/Top-Down Image Parsing by Attribute Graph Grammar
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Static and dynamic abstract formal models for 3D sensor images
WSEAS TRANSACTIONS on SYSTEMS
Extraction and tracking of surfaces in range image sequences
3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
Hi-index | 0.00 |
The paper presents the results of an investigation of the correspondence problem of scene object models obtained from multiple 3D sensors depth images. The recently developed 3D TOF (time of flight) sensor characteristics are analyzed relative to content of depth images produced. A model of the scene space for a pair of sensors is given in an adjusted epipolar geometry setting. The scene decomposition into objects according to a 3D specific recent segmentation is proposed. The determination of scene content and joint correlation of models by object correspondence is outlined. Visual hull method usefulness for object volume determination from occluded space is analysed. For a concrete experimental case the scene correspondence results of two 3D sensors is presented. Further work is also outlined.