A Multispectral Image Line Reconstruction Method

Haindl, Michal; Šimberová, Stanislava

doi:10.1142/9789812797896_0028

Cited by 30 publications

(28 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, Z 1 } and taking its conditional mean as the textural feature representation. Assuming normality of the white noise component ǫ t , conditional independence between pixels and the normal-Wishart parameter prior, we have shown (Haindl & Šimberová, 1992) that the conditional mean value is:…”

Section: Car Modelmentioning

confidence: 99%

“…It is easy to check (see Haindl & Šimberová (1992)) also the validity of the following recursive parameter estimator:…”

Section: Car Modelmentioning

confidence: 99%

“…For numerical realisation of the model statistics (5)- (7) see discussion in Haindl & Šimberová (1992). Textural features for each Gaussian pyramid level k is represented by the parametric matrix…”

Section: Car Modelmentioning

confidence: 99%

See 2 more Smart Citations

Illumination Invariants Based on Markov Random Fields

Vácha¹,

Haindl²

2010

Pattern Recognition Recent Advances

Self Cite

View full text Add to dashboard Cite

Section: Car Modelmentioning

confidence: 99%

“…It is easy to check (see Haindl & Šimberová (1992)) also the validity of the following recursive parameter estimator:…”

Section: Car Modelmentioning

confidence: 99%

See 1 more Smart Citation

Illumination Invariants Based on Markov Random Fields

Vácha¹,

Haindl²

2010

Pattern Recognition Recent Advances

Self Cite

View full text Add to dashboard Cite

“…where 170 is a positive definite (/3 + 1) * (/3 + 1) matrix and 7(0) > d , we have shown ( [5]) that the conditional mean value is:…”

mentioning

confidence: 89%

“…It is easy to check (see [5]) also the validity of recursive (9). We assume slowly changing parameters, consequently these equations were modified using a constant exponential "forgetting factor" a to allow parameter adaptation.…”

mentioning

confidence: 99%

Fast segmentation of range images

Haindl

Zid

1997

Image Analysis and Processing

Self Cite

View full text Add to dashboard Cite

Abstract. A new type of range image segmentation method is introduced. The image segmentation is based on a recursive adaptive regression model prediction for detecting range image step discontinuities which are present at object face borders. Border pixels are detected in two perpendicular directions and detection results are combined together. Two predictors in each direction use identical contextual information from the pixel's neighbourhood and they mutually compete for the most optimal discontinuity detection. The method suggested can be successfully applied also to other image segmentation applications, e.g. panchromatic or multispectral image data, etc. IntroductionSegmentation is a fundamental process affecting the overall performance of a machine vision system. Range image segmentation is a crucial part of autonomous navigation systems and as such it has been an active research area for past fifteen years. Segmentation of a range image should partion this image into meaningful patches representing single objects faces, but the task is complicated with outliers resulting from a sensing operation and corrupting boundary between distinct shapes. Optimal segmentation algorithm should be stable, accurate and numerically efficient. There are many segmentation Mgorithms published in computer vision literature and a number of good survey articles [1],[10] is available. However their mutual comparison is very difficult because of lack of sound experimental evaluation results. A rare exception is results published in [7] together with experinaental data available on their Internet server. These data and results are used also for our Mgorithm evaluation. The common approaches to solve the range image segmentation problem are region growing based algorithms [7], [2] where single regions are formed by iteratively growing from seed regions, splitand-merge, clustering (e.g. clustering in a fitted planes parameter space [4]), and edge based techniques [12]. Region growing and split-and-merge algorithms present the problem that they have to deal with different threshold values that are difficult to obtain (see [7]) and depend on an application. Clustering algorithms suffer usually less influence from this kind of problem, although other problems exist. Current segmentation algorithms most often miss small regions and perform poorly when the required region precision is high. Experiments in

show abstract

Restoration of Multitemporal Short-Exposure Astronomical Images

Haindl

Šimberová

2005

Image Analysis

Self Cite

View full text Add to dashboard Cite

A multitemporal fast adaptive recursive restoration method based on the underlying spatial probabilistic image model is presented. The method assumes linear degradation model with the unknown possibly non-homogeneous point-spread function and additive noise. Pixels in the vicinity of image steep discontinuities are left unrestored to minimize restoration blurring effect. The method is applied for astronomical sunspot image restoration, where for every ideal undegraded unobservable image several degraded observed images are available.

show abstract

A Multispectral Image Line Reconstruction Method

Cited by 30 publications

References 0 publications

Illumination Invariants Based on Markov Random Fields

Illumination Invariants Based on Markov Random Fields

Fast segmentation of range images

Restoration of Multitemporal Short-Exposure Astronomical Images

Contact Info

Product

Resources

About