Accurate and fast segment-based cost aggregation algorithm for stereo matching

Chang, Da-Fang; Wu, Sih-Sian; Hou, Hsin-Yu; Chen, Liang-Gee

doi:10.1109/mmsp.2017.8122284

Cited by 2 publications

(7 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, unlike in other methods [32, 33], the matching costs C was formed by combining the two costs from pixel‐space and SLIC‐space,

C false(p, d false) = false(1 - α false) C_{p}^{*} false(p, d false) + α C_{p} false(p, d false)

…”

Section: Methodsmentioning

confidence: 99%

“…Bad 1.0 is set as the error threshold in non-occluded regions. SAS [32], SCA [33], and the proposed method are implemented with the SLIC algorithm. GF_EMA [39] employed the EWMA filter and guided filter for smoothing in the cost volume in pixel space.…”

Section: 21mentioning

confidence: 99%

“…But errors still existed in low-textured regions owing to few identifiable correlations. To improve this problem, Chang [33] employed the SLIC segmentation algorithm and blended the cost of multiple neighbourhood segments. However, these segment-based methods have a common shortage: the disparities between segments may be discontinuous.…”

Section: Cost Aggregation Based On Segmentation and Iterative Filteringmentioning

confidence: 99%

See 2 more Smart Citations

An efficient local stereo matching method based on an adaptive exponentially weighted moving average filter in SLIC space

Yang

Lei

Liu

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

Rapidly obtaining accurate dense disparity maps has been the focus of stereo matching research. At present, approaches that achieve superior disparity maps require a large amount of computation, which is not suitable for practical applications. To address this issue, this paper proposes an efficient local matching method based on an adaptive exponentially weighted moving average filter and simple linear iterative clustering segmentation algorithm. First, an effective matching cost is introduced to adaptively integrate absolute intensity difference with Census transform, which is robust against texture free and luminance variate. Following this, during the cost aggregation, the exponentially weighted moving average filter and the SLIC segmentation are combined to handle the problems of computing consumption and adaptive expansion of the cost aggregation window. Finally, the dense disparity map is obtained by a winner-takes-all approach and disparity refinement. To demonstrate its efficiency and validity, the method is quantitatively tested and compared to existing approaches on the Middlebury benchmark. The results show that it has a non-occlusion accuracy of 90.66% and an average runtime of 7.01 s on the 2014 Middlebury dataset. Compared with existing competitive methods, the proposed method achieves superior matching results with a lower time cost. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

“…Finally, unlike in other methods [32, 33], the matching costs C was formed by combining the two costs from pixel‐space and SLIC‐space,

C false(p, d false) = false(1 - α false) C_{p}^{*} false(p, d false) + α C_{p} false(p, d false)

…”

Section: Methodsmentioning

confidence: 99%

Section: 21mentioning

confidence: 99%

Section: Cost Aggregation Based On Segmentation and Iterative Filteringmentioning

confidence: 99%

See 1 more Smart Citation

An efficient local stereo matching method based on an adaptive exponentially weighted moving average filter in SLIC space

Yang

Lei

Liu

et al. 2021

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…Once the cost of the paired pixels in the stereo images is calculated, the cost aggregation is further applied to achieve more robust results by including more pixels, which have the same tendency. For local stereo matching, the window-based aggregation considers the similarities of the surrounding pixels in a designated window [19][20][21][22][23][24][25]. The ideal windows are designed to include the nearby pixels, which are in the same object as possible.…”

Section: Cost Aggregationmentioning

confidence: 99%

“…In (24), not only with disparity similarity, we further include the color tolerance to label the pixels. For L(x, y) = 0, the mismatched pixels are further categorized into two types: small holes or big holes.…”

Section: Iterative Dual-path Depth Refinementmentioning

confidence: 99%

Shape-reserved stereo matching with segment-based cost aggregation and dual-path refinement

Huang

Chan

et al. 2020

J Image Video Proc.

View full text Add to dashboard Cite

Stereo matching is one of the most important topics in computer vision and aims at generating precise depth maps for various applications. The major challenge of stereo matching is to suppress inevitable errors occurring in smooth, occluded, and discontinuous regions. In this paper, the proposed stereo matching system uses segment-based superpixels and matching cost. After determination of edge and smooth regions and selection of matching cost, we suggest the segment-based adaptive support weights in cost aggregation instead of color similarity and spatial proximity only. The proposed dual-path depth refinements use the cross-based support region by referring texture features to correct the inaccurate disparities with iterative procedures to improve the depth maps for shape reserving. Specially for leftmost and rightmost regions, the segment-based refinement can greatly improve the mismatched disparity holes. The experimental results show that the proposed system can achieve higher accurate depth maps than the conventional methods.

show abstract

Accurate and fast segment-based cost aggregation algorithm for stereo matching

Cited by 2 publications

References 20 publications

An efficient local stereo matching method based on an adaptive exponentially weighted moving average filter in SLIC space

An efficient local stereo matching method based on an adaptive exponentially weighted moving average filter in SLIC space

Shape-reserved stereo matching with segment-based cost aggregation and dual-path refinement

Contact Info

Product

Resources

About