Integration of visual modules: an extension of the Marr paradigm
Integration of visual modules: an extension of the Marr paradigm
Phase-based disparity measurement
CVGIP: Image Understanding
Three-dimensional computer vision: a geometric viewpoint
Three-dimensional computer vision: a geometric viewpoint
Object-centered surface reconstruction: combining multi-image stereo and shading
International Journal of Computer Vision
Performance of phase-based algorithms for disparity estimation
Machine Vision and Applications - Special issue on performance evaluation
Image segmentation based on oscillatory correlation
Neural Computation
Group Theoretical Methods in Image Understanding
Group Theoretical Methods in Image Understanding
Parallax Geometry of Pairs of Points for 3D Scene Analysis
ECCV '96 Proceedings of the 4th European Conference on Computer Vision-Volume I - Volume I
Visual Integration and Detection of Discontinuities: The Key Role of Intensity Edges
Visual Integration and Detection of Discontinuities: The Key Role of Intensity Edges
BMCV '02 Proceedings of the Second International Workshop on Biologically Motivated Computer Vision
Cooperative concept map based on cognitive model for visual analysis
Proceedings of the 3rd International Symposium on Visual Information Communication
| Hi-index | 0.00 |
We describe a general approach to integrate the information produced by different visual modules with the goal of generating a quantitative 3D reconstruction of the observed scene and to estimate the reconstruction errors.The integration is achieved in two steps. Firstly, several different visual modules analyze the scene in terms of a common data representation: planar patches are used by different visual modules to communicate and represent the 3D structure of the scene. We show how it is possible to use this simple data structure to share and integrate information from different visual modalities, and how it can support the necessities of the great majority of different visual modules known in literature. Secondly, we devise a communication scheme able to merge and improve the description of the scene in terms of planar patches. The applications of state-of-the-art algorithms allows to fuse information affected by an unknown grade of correlation and still guarantee conservative error estimates.Tests on real and synthetic scene show that our system produces a consistent and marked improvement over the results of single visual modules, with error reduction up to a factor of ten and with typical reduction of a factor 2–4.