| 1. |
- Westelius, Carl-Johan, et al.
(författare)
-
Phase-based Disparity Estimation
- 1995
-
Ingår i: Vision as Process. - Berlin : Springer-Verlag. - 354058143X - 038758143X ; , s. 157-178
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- The problem of estimating depth information from two or more images of a scene is one which has received considerable attention over the years and a wide variety of methods have been proposed to solve it [Barnard and Fichsler, 1982; Fleck, 1991]. Methods based on correlation and methods using some form of feature matching between the images have found most widespread use. Of these, the latter have attracted increasing attention since the work of Marr [Marr, 1982], in which the features are zero-crossings on varying scales. These methods share an underlying basis of spatial domain operations.In recent years, however, increasing interest has been shown in computational models of vision based primarily on a localized frequency domain representation - the Gabor representation [Gabor, 1946; Adelson and Bergen, 1985], first suggested in the context of computer vision by Granlund [Granlund, 1978].
|
|
| 2. |
- Andersson, Mats, et al.
(författare)
-
Filter Networks
- 1999
-
Ingår i: Proceedings of Signal and Image Processing (SIP'99). - Nassau, Bahamas : IASTED. - 0889862672 ; , s. 213-217
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a new and efficient approach for optimization and implementation of filter banks e.g. velocity channels, orientation channels and scale spaces. The multi layered structure of a filter network enable a powerful decomposition of complex filters into simple filter components and the intermediary results may contribute to several output nodes. Compared to a direct implementation a filter network uses only a fraction of the coefficients to provide the same result. The optimization procedure is recursive and all filters on each level are optimized simultaneously. The individual filters of the network, in general, contain very few non-zero coefficients, but there are are no restrictions on the spatial position of the coefficients, they may e.g. be concentrated on a line or be sparsely scattered. An efficient implementation of a quadrature filter hierarchy for generic purposes using sparse filter components is presented.
|
|
| 3. |
- Andersson, Mats, et al.
(författare)
-
Sequential Filter Trees for Efficient 2D 3D and 4D Orientation Estimation
- 1998
-
Rapport (övrigt vetenskapligt/konstnärligt)abstract
- A recursive method to condense general multidimensional FIR-filters into a sequence of simple kernels with mainly one dimensional extent has been worked out. Convolver networks adopted for 2, 3 and 4D signals is presented and the performance is illustrated for spherically separable quadrature filters. The resulting filter responses are mapped to a non biased tensor representation where the local tensor constitutes a robust estimate of both the shape and the orientation (velocity) of the neighbourhood. A qualitative evaluation of this General Sequential Filter concept results in no detectable loss in accuracy when compared to conventional FIR (Finite Impulse Response) filters but the computational complexity is reduced several orders in magnitude. For the examples presented in this paper the attained speed-up is 5, 25 and 300 times for 2D, 3D and 4D data respectively The magnitude of the attained speed-up implies that complex spatio-temporal analysis can be performed using standard hardware, such as a powerful workstation, in close to real time. Due to the soft implementation of the convolver and the tree structure of the sequential filtering approach the processing is simple to reconfigure for the outer as well as the inner (vector length) dimensionality of the signal. The implementation was made in AVS (Application Visualization System) using modules written in C.
|
|
| 4. |
- Karlholm, Jörgen, et al.
(författare)
-
Object Tracking Based on the Orientation Tensor Concept
- 1995
-
Ingår i: SCIA9, Uppsala.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- A scheme for performing generalized convolutions is presented. A flexibleconvolver, which runs on standard workstations, has been implemented. It isdesigned for maximum throughput and flexibility. The implementation incorporatesspatio-temporal convolutions with configurable vector combinations. Itcan handle general multi-linear operations, i.e. tensor operations on multidimensionaldata of any order. The input data and the kernel coefficients canbe of arbitrary vector length. The convolver is configurable for IIR filters inthe time dimension. Other features of the implemented convolver are scatteredkernel data, region of interest and subsampling. The implementation is doneas a C-library and a graphical user interface in AVS (Application VisualizationSystem).A scheme for performing generalized convolutions is presented. A flexible convolver, which runs on standard workstations, has been implemented. It is designed for maximum throughput and flexibility. The implementation incorporates spatio-temporal convolutions with configurable vector combinations. It can handle general multi-linear operations, i.e. tensor operations on multidimensional data of any order. The input data and the kernel coefficients can be of arbitrary vector length. The convolver is configurable for IIR filters in the time dimension. Other features of the implemented convolver are scattered kernel data, region of interest and subsampling. The implementation is done as a C-library and a graphical user interface in AVS (Application Visualization System).
|
|
| 5. |
- Karlholm, Jörgen, et al.
(författare)
-
Object Tracking Based on the Orientation Tensor Concept
- 1995
-
Ingår i: Theory and Applications of Image Analysis II. - Singapore : World Scientific Publishing. - 9810224486 ; , s. 267-278
-
Bokkapitel (populärvet., debatt m.m.)abstract
- We apply the 3D-orientation tensor representation to construct an object tracking algorithm. 2D-line normal flow is estimated by computing the eigenvector associated with the largest eigenvalue of 3D (two spatial dimensions plus time) tensors with a planar structure. Object's true 2D velocity is computed by averaging tensors with consistent normal flows, generating a 3D line represention that corresponds to a 2D point in motion. Flow induced by camera rotation is compensated for by ignoring points with velocity consistent with the ego-rotation. A region-of-interest growing process based on motion consistency generates estimates of object size and position. Introduction The literature on optical flow estimation is wast. Descriptions and performance studies of a number of different techniques are given in and the monographs by Fleet and Jahne. We will only briefly describe the particular methods used in the present study. Details on the tensor field represention a...
|
|
| 6. |
|
|
| 7. |
- Knutsson, Hans, et al.
(författare)
-
Advanced Filter Design
- 1999
-
Ingår i: Proceedings of the 11th Scandinavian Conference on Image Analysis. - : SCIA. ; , s. 185-193
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a general approach for obtaining optimal filters as well as filter sequences. A filter is termed optimal when it minimizes a chosen distance measure with respect to an ideal filter. The method allows specification of the metric via simultaneous weighting functions in multiple domains, e.g. the spatio-temporal space and the Fourier space. Metric classes suitable for optimization of localized filters for multidimensional signal processing are suggested and discussed. It is shown how convolution kernels for efficient spatio-temporal filtering can be implemented in practical situations. The method is based on applying a set of jointly optimized filter kernels in sequence. The optimization of sequential filters is performed using a novel recursive optimization technique. A number of optimization examples are given that demonstrate the role of key parameters such as: number of kernel coefficients, number of filters in sequence, spatio-temporal and Fourier space metrics. The sequential filtering method enables filtering using only a small fraction of the number of filter coefficients required using conventional filtering. In multidimensional filtering applications the method potentially outperforms both standard convolution and FFT based approaches by two-digit numbers.
|
|
| 8. |
- Knutsson, Hans, et al.
(författare)
-
Multiple Space Filter Design
- 1999
-
Ingår i: Proceedings of the SSAB symposium on image analysis.
-
Konferensbidrag (refereegranskat)abstract
- This paper presents a general approach for obtaining optimal filters as well as filter sequences. A filter is termed optimal when it minimizes a chosen distance measure with respect to an ideal filter. The method allows specification of the metric via simultaneous weighting functions in multiple domains, e.g. the spatio-temporal space and the Fourier space. It is shown how convolution kernels for efficient spatio-temporal filtering can be implemented in practical situations. The method is based on applying a set of jointly optimized filter kernels in sequence. The optimization of sequential filters is performed using a novel recursive optimization technique. A number of optimization examples are given that demonstrate the role of key parameters such as: number of kernel coefficients, number of filters in sequence, spatio-temporal and Fourier space metrics. In multidimensional filtering applications the method potentially outperforms both standard convolution and FFT based approaches by two-digit numbers.
|
|
| 9. |
- Knutsson, Hans, et al.
(författare)
-
Orientation and Velocity
- 1995
-
Ingår i: Signal Processing for Computer Vision. - Dordrecht : Kluwer. - 0792395301 - 9780792395300 ; , s. 219-258
-
Bokkapitel (refereegranskat)abstract
- This chapter introduces the use of tensors in estimation of local structure and orientation. The tensor representation is shown to be crucial to unambiguous and continuous representation of local orientation in multiple dimensions. In addition to orientation the tensor representation also conveys the degree and type of local anisotropy. The orientation estimation approach is developed in detail for two, three and four dimensions and is shown to be extendable to higher dimensions. Examples and performance measures are given for processing of images, volumes and time sequences.
|
|
| 10. |
|
|
