A novel method for stereo matching using Gabor Feature Image and Confidence Mask

Liu, Haixu; Liu, Yang; Ouyang, Shuxin; Liu, Chenyu; Li, Xueming

doi:10.1109/vcip.2013.6706388

Cited by 3 publications

(16 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is an important achievement bearing in mind the reduced computational complexity of this algorithm and the very basic technique used for the occlusion handling. Moreover, Table 1 shows that this approach gives superior disparity results than [2,4], which also exploit the guided image filter.…”

Section: Middlebury Online Stereo Evaluationmentioning

confidence: 99%

“…This paper exploits the approach of [4], which is inspired by the previous work of [2], in order to generate the initial cost volume. However, this paper proposes a modification regarding one of the cost terms used to estimate the final cost, leading to improved disparity results.…”

Section: Matching Cost Computationmentioning

confidence: 99%

“…Let us suppose that I l and I r stand for the left and right images in grayscale. Their corresponding Gabor-Features-Images are G H (I l (p)) and G H (I r (p)), respectively (the parameters used for the extraction of the Gabor-Feature-Image are the same as in [4]). The cost term C gab (p, d) for pixel p at disparity d is given by:…”

Section: Matching Cost Computationmentioning

confidence: 99%

“…In [4], the third data term corresponds to the mean of the sum of absolute differences on pixel RGB values between the left and right images. However, in this work, the replacement of the third term is proposed with the dissimilarity metric on RGB values presented in [12].…”

Section: Matching Cost Computationmentioning

confidence: 99%

“…Prevalent pixel-based cost measures include the absolute difference of image intensity values [2,3,4], gradient-based measures [2,4] and non-parametric transforms such as CENSUS [3,5] which are robust to radiometric distortions and noise. Many approaches use the combination of various cost measures in order to boost accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Revisiting guided image filter based stereo matching and scanline optimization for improved disparity estimation

Kordelas

Alexiadis

Daras

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this paper the scanline optimization used for stereo matching, is revisited. In order to improve the performance of this semi-global technique, a new criterion to check depth discontinuity, is introduced. This criterion is defined according to the mean-shift-based image segmentation result. Additionally, this work proposes the employment of a pixel dissimilarity metric for the computation of the cost term, which is then provided to the guided image filter approach to estimate the initial cost volume. The algorithm is tested on the four images of the online Middlebury stereo evaluation benchmark. Moreover, it is tested on 27 additional Middlebury stereo pairs for assessing thoroughly its performance. The extended comparison verifies the efficiency of this work.

show abstract

Section: Middlebury Online Stereo Evaluationmentioning

confidence: 99%

Section: Matching Cost Computationmentioning

confidence: 99%

Section: Matching Cost Computationmentioning

confidence: 99%

Section: Matching Cost Computationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Revisiting guided image filter based stereo matching and scanline optimization for improved disparity estimation

Kordelas

Alexiadis

Daras

et al. 2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

show abstract

Gradient and Color Intensity based Dense Disparity Estimation Using Adaptive Weight Aggregation

Poddar

Kumar

Sahu

et al. 2022

2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS)

View full text Add to dashboard Cite

Content-Based Guided Image Filtering, Weighted Semi-Global Optimization, and Efficient Disparity Refinement for Fast and Accurate Disparity Estimation

Kordelas

Alexiadis

Daras

et al. 2016

IEEE Trans. Multimedia

View full text Add to dashboard Cite

This paper presents a novel approach, which relies on content-based guided image filtering and weighted semi-global optimization for fast and accurate disparity estimation. Initially, the approach uses a pixel-based cost term that combines gradient, Gabor-Feature and color information. The pixel-based matching costs are filtered by applying guided image filtering, which relies on rectangular support windows of two different sizes. In this way, two filtered costs are estimated for each pixel. Among the two filtered costs, the one that will be finally assigned to each pixel, depends on the local image content around this pixel. The filtered cost volume is further refined by exploiting weighted semi-global optimization, which improves the disparity estimation accuracy. Finally, the disparity refinement in outlier regions relies on a straightforward and time efficient outliers handling scheme and on a simple approach which deals with the disparity outliers at depth discontinuities. Experimental results on the Middlebury online stereo evaluation benchmark and 27 additional Middlebury stereo pairs, prove that our method is able to generate disparity maps with high accuracy while keeping the computational cost low.

show abstract

A novel method for stereo matching using Gabor Feature Image and Confidence Mask

Cited by 3 publications

References 13 publications

Revisiting guided image filter based stereo matching and scanline optimization for improved disparity estimation

Revisiting guided image filter based stereo matching and scanline optimization for improved disparity estimation

Gradient and Color Intensity based Dense Disparity Estimation Using Adaptive Weight Aggregation

Content-Based Guided Image Filtering, Weighted Semi-Global Optimization, and Efficient Disparity Refinement for Fast and Accurate Disparity Estimation

Contact Info

Product

Resources

About