Ensemble Learning for Confidence Measures in Stereo Vision

Haeusler, Ralf; Nair, Rahul; Kondermann, Daniel

doi:10.1109/cvpr.2013.46

Cited by 101 publications

(129 citation statements)

References 18 publications

Supporting

Mentioning

128

Contrasting

Order By: Relevance

“…A set of active matchers is selected from a potentially very large initial pool and random forest classifiers are trained to select the disparity that is most likely to be correct for each pixel of the left image. The classifiers, even with a small number of features compared to [14,34], are always able to surpass the accuracy of the best matcher in the active set. Our method combines eight matchers and achieves an error rate before post-processing (5.82%) that is significantly smaller than that of the best individual matcher (8.06%).…”

Section: Discussionmentioning

confidence: 99%

“…We also excluded the cost maps of the WTA methods, since such maps are not produced by the global methods. According to Haeusler et al [14], it is very likely that features based on the cost volume are more effective, but as shown in Section 6, our approach is able to discern the correct disparities relying on consensus and disagreement among different matchers without such features. In this paper, we only used the following features for individual disparities.…”

Section: Featuresmentioning

confidence: 97%

“…We view this approach as similar to ours since it also assumes that a single model does not work well for all pixels. Recently, Haeusler et al [14] presented a learning approach that can predict the correctness of the output disparities of the semi-global matching (SGM) stereo algorithm [15]. It uses a number of features computed on the images, disparity maps and matching cost volume and a random forest classifier that is able to reject false matches with high accuracy.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Ensemble Classifier for Combining Stereo Matching Algorithms

Spyropoulos

Mordohai

2015

2015 International Conference on 3D Vision

View full text Add to dashboard Cite

Stereo matching, as many problems in computer vision, has been addressed by a multitude of algorithms, each with its own strengths and weaknesses. Instead of following the conventional approach and trying to tune or enhance one of the algorithms so that it dominates the competition, we resign to the idea that a truly optimal algorithm may not be discovered soon and take a different approach. We present a novel methodology for combining a large number of heterogeneous algorithms that is able to clearly surpass the accuracy of the most accurate algorithms in the set. At the core of our approach is the design of an ensemble classifier trained to decide whether a particular stereo matcher is correct on a certain pixel. In addition to features describing the pixel, our feature vector encodes the agreement and disagreement between the matcher under consideration and all other matchers. This formulation leads to high accuracy in disparity estimation on the KITTI stereo benchmark.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Featuresmentioning

confidence: 97%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Ensemble Classifier for Combining Stereo Matching Algorithms

Spyropoulos

Mordohai

2015

2015 International Conference on 3D Vision

View full text Add to dashboard Cite

show abstract

“…What separates our approach from recent literature on confidence estimation [20,6,9,21,7], regardless of the use of learning, is that the main objective of these methods is sparsification. They can indeed generate disparity maps with progressively fewer errors by removing matches starting from the least reliable ones.…”

Section: Introductionmentioning

confidence: 95%

“…Surprisingly, very few publications have attempted to tackle stereo matching from a learning perspective [4,12,13] and they have not gained much traction. Very recently, Haeusler et al [7] presented an approach for learning a confidence measure from several features, some of which are similar to those proposed by us, since both approaches rely on [9] for feature selection. Haeusler et al also use a random forest for classification, but, unlike this paper, they do not propose ways of leveraging the estimated confidence to generate dense disparity maps of higher accuracy.…”

Section: Introductionmentioning

confidence: 99%

Learning to Detect Ground Control Points for Improving the Accuracy of Stereo Matching

Spyropoulos

Komodakis

Mordohai

2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

104

137

View full text Add to dashboard Cite

While machine learning has been instrumental to the ongoing progress in most areas of computer vision, it has not been applied to the problem of stereo matching with similar frequency or success. We present a supervised learning approach for predicting the correctness of stereo matches based on a random forest and a set of features that capture various forms of information about each pixel.We show highly competitive results in predicting the correctness of matches and in confidence estimation, which allows us to rank pixels according to the reliability of their assigned disparities. Moreover, we show how these confidence values can be used to improve the accuracy of disparity maps by integrating them with an MRF-based stereo algorithm. This is an important distinction from current literature that has mainly focused on sparsification by removing potentially erroneous disparities to generate quasi-dense disparity maps.

show abstract

Stereo Matching with Multi‐scale Based on Anisotropic Match Cost

Liu

Cai

Zhou

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Binocular vision is a popular method for 3d measurement, but the precision and efficiency is still a limitation. In order to solve the problem of low precision and high mismatching rate of current stereo match methods in weak texture region, a local stereo matching algorithm with multi-scale based on anisotropic match cost was proposed. Not only including the gray value between the adjacent pixels as the absolute difference (AD) method, the matching cost function also involved gradient and phase information to make an anisotropic evaluation and eliminate the outliers of the flat area. Meanwhile, a multi-scale strategy with the image pyramid was referenced, and the dynamic disparity search range of variable window was used on the original cost aggregation framework by improving the stereo matching algorithm of cross-scale cost aggregation. The matching cost volume in each scale space used the dynamic support window to guide the filter to aggregate the matching cost. Finally, to overcome the problems of disparity selection ambiguity of WTA (winner-take-all) strategy and the horizontal fringe introduced by left-right consistency (LRC) detection, the weighted median filter based on guided filter weight was used to carry out disparity refinement. According to the experiments, the method got more high matching accuracy, and the average error on the Middlebury test platform reached 5.25%.

show abstract

Ensemble Learning for Confidence Measures in Stereo Vision

Cited by 101 publications

References 18 publications

Ensemble Classifier for Combining Stereo Matching Algorithms

Ensemble Classifier for Combining Stereo Matching Algorithms

Learning to Detect Ground Control Points for Improving the Accuracy of Stereo Matching

Stereo Matching with Multi‐scale Based on Anisotropic Match Cost

Contact Info

Product

Resources

About