The enumeration of trees with and without given limbs
Discrete Mathematics
Determining the Epipolar Geometry and its Uncertainty: A Review
International Journal of Computer Vision
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Learning Patterns of Activity Using Real-Time Tracking
IEEE Transactions on Pattern Analysis and Machine Intelligence
Multiple view geometry in computer vision
Multiple view geometry in computer vision
A Theory of Shape by Space Carving
International Journal of Computer Vision - Special issue on Genomic Signal Processing
Computer
Polyhedral Visual Hulls for Real-Time Rendering
Proceedings of the 12th Eurographics Workshop on Rendering Techniques
An Invitation to 3-D Vision: From Images to Geometric Models
An Invitation to 3-D Vision: From Images to Geometric Models
Visual Hull Construction Using Adaptive Sampling
WACV-MOTION '05 Proceedings of the Seventh IEEE Workshops on Application of Computer Vision (WACV/MOTION'05) - Volume 1 - Volume 01
A hybrid approach for computing visual hulls of complex objects
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Foreground regions extraction and characterization towards real-time object tracking
MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
Multi-view Reconstruction of Unknown Objects within a Known Environment
ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Shape from incomplete silhouettes based on the reprojection error
Image and Vision Computing
Shape from Silhouette Consensus
Pattern Recognition
Hi-index | 0.00 |
Multi-camera environments allow constructing volumetric models of the scene to improve the analysis performance of computer vision algorithms (e.g. disambiguating occlusion). When representing volumetric results of image-based multi-camera analysis, a direct approach is to scan the 3D space with regular voxels. Regular voxelization is good at high spatial resolutions for applications such as volume visualization and rendering of synthetic scenes generated by geometric models, or to represent data resulting from direct 3D data capture (e.g. MRI). However, regular voxelization shows a number of drawbacks for visual scene analysis, where direct measurements on 3D voxels are not usually available. In this case, voxel values are computed rather as a result of the analysis on 'projected' image data. In this paper, we first provide some statistics to show how voxels project to 'unbalanced' sets of image data in common multi-view analysis settings. Then, we propose a 3D geometry for multi-view scene analysis providing a better balance in terms of the number of pixels used to analyse each elementary volumetric unit. The proposed geometry is non-regular in 3D space, but becomes regular once projected onto camera images, adapting the sampling to the images. The aim is to better exploit multi-view image data by balancing its usage across multiple cameras instead of focusing in regular sampling of 3D space, from which we do not have direct measurements. An efficient recursive algorithm using the proposed geometry is outlined. Experimental results reflect better balance and higher accuracy for multi-view analysis than regular voxelization with equivalent restrictions.