Normalized and differential convolution
Hans E. Knutsson, Carl‐Fredrik Westin · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2002
It is shown how false operator responses due to missing or uncertain data can be significantly reduced or eliminated. It is shown how operators having a higher degree of selectivity and higher tolerance against noise can be constructed using simple combinations of appropriately chosen convolutions. The theory is based on linear operations and is general in that it allows for both data and operators to be scalars, vectors or tensors of higher order. Three new methods are represented: normalized convolution, differential convolution and normalized differential convolution. All three methods are examples of the power of the signal/certainty-philosophy, i.e., the separation of both data and operator into a signal part and a certainty part. Missing data are handled simply by setting the certainty to zero. In the case of uncertain data, an estimate of the certainty must accompany the data. Localization or windowing of operators is done using an applicability function, the operator equivalent to certainty, not by changing the actual operator coefficients. Spatially or temporally limited operators are handled by setting the applicability function to zero outside the window.>
Cited by 242 works. doi:10.1109/cvpr.1993.341081
Authors
References
- Invariant Properties of the Motion Parallax Field Due to the Movement of Rigid Bodies Relative to an Observer
- Measurement of Image Velocity
- Surface orientation and time to contact from image divergence and deformation
- Information, Mechanism and Meaning
- Normalized and Differential Convolution : Methods for Interpolation and Filtering of Incomplete and Uncertain Data
- Representing Local Structure Using Tensors II
- Filtering and reconstruction in image processing
- Using Flow Field Divergence For Obstacle Avoidance: Towards Qualitative Vision
- Structure and motion from optical flow under orthographic projection
- Extraction of Local Symmetries using Tensor Field Filtering