Stereo matching with space-constrained cost aggregation and segmentation-based disparity refinement

Peng, Yi; Li, Ge; Wang, Ronggang; Wang, Wenmin

doi:10.1117/12.2083741

Cited by 6 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…− Disparity refinement: in the last stage of the framework, standard approaches for post-processing and disparity refinement were implemented. Peng et al [35] integrated the mean shift and super-pixel with segmentation (SEG) approach which clusters the disparity map according to colour.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Refining disparity maps using deep learning and edge-aware smoothing filter

Abd Gani,

Miskon,

Hamzah

et al. 2024

Bulletin EEI

View full text Add to dashboard Cite

Stereo matching algorithm is crucial for applications that rely on three-dimensional (3D) surface reconstruction, producing a disparity map that contains depth information by computing the disparity values between corresponding points from a stereo image pair. In order to yield desirable results, the proposed stereo matching algorithm must possess a high degree of resilience against radiometric variation and edge inconsistencies. In this article convolutional neural network (CNN) is employed in the first stage to generate the raw matching cost, which is subsequently filtered with a bilateral filter (BF) and applied with cross-based cost aggregation (CBCA) during the cost aggregation stage to enhance precision. Winner-take-all (WTA) strategy is implemented to normalise the disparity map values. Finally, the resulting output is subjected to an edge-aware smoothing filter (EASF) to reduce the noise. Due to its resistance to high contrast and brightness, the filter is found to be effective in refining and eliminating noise from the output image. Despite discontinuities like adiron's lost cup handle or artl's shattered rods, this approach, based on experimental research utilizing a Middlebury standard validation benchmark, yields a high level of accuracy, with an average non-occluded error of 6.79%, comparable to other published methods.

show abstract

Section: Methodsmentioning

confidence: 99%

“…− Weighted median filter (WMF) is implemented where it essentially combines box aggregation with a weighted median, effectively eliminates noise from outliers while conserving the edges [36]. Median filter (MF) was utilised in [35]. MF is accurate at the edges but inaccurate in low-textured regions.…”

Section: Methodsmentioning

confidence: 99%

Refining disparity maps using deep learning and edge-aware smoothing filter

Abd Gani,

Miskon,

Hamzah

et al. 2024

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…In the last stage, postprocessing and disparity refinement standard techniques were executed. Peng et al [39] implemented the integration of mean shift and superpixel with segmentation method (SEG). This approach clusters the disparity map based on colour.…”

Section: Disparity Refinementmentioning

confidence: 99%

Stereo matching algorithm using deep learning and edge-preserving filter for machine vision

Abd Gani,

Miskon,

Hamzah

et al. 2024

Bulletin EEI

View full text Add to dashboard Cite

Machine vision research began with a single-camera system, but these systems had various limitations from having just one point-of-view of the environment and no depth information, therefore stereo cameras were invented. This paper proposes a hybrid method of a stereo matching algorithm with the goal of generating an accurate disparity map critical for applications such as 3D surface reconstruction and robot navigation to name a few. Convolutional neural network (CNN) is utilised to generate the matching cost, which is then input into cost aggregation to increase accuracy with the help of a bilateral filter (BF). Winner-take-all (WTA) is used to generate the preliminary disparity map. An edge-preserving filter (EPF) is applied to that output based on a transform that defines an isometry between curves on the 2D image manifold in 5D and the real line to eliminate these artefacts. The transform warps the input signal adaptively to allow linear 1D filtering. Due to the filter's resistance to high contrast and brightness, it is effective in refining and removing noise from the output image. Based on experimental research employing a Middlebury standard validation benchmark, this approach gives high accuracy with an average non-occluded error of 6.71% comparable to other published methods.

show abstract

“…This fact is evident in Table I that shows the computational times of the proposed method and the approaches in TSGO, JSOSP+GCP and KADI (the respective computational times were obtained from [45], [46] and [47]). Table V shows that the proposed approach has better ranking SSCBP [51]. The computational complexity of SSCBP [51] is not available to compare it against our approach.…”

Section: B Middlebury Online Stereo Evaluation Benchmarkmentioning

confidence: 99%

“…Table V shows that the proposed approach has better ranking SSCBP [51]. The computational complexity of SSCBP [51] is not available to compare it against our approach. Table I also includes the CPU computation time of the ADCensus [13] approach that is listed in Table V.The proposed method has Fig.…”

Section: B Middlebury Online Stereo Evaluation Benchmarkmentioning

confidence: 99%

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

Stereo matching with space-constrained cost aggregation and segmentation-based disparity refinement

Cited by 6 publications

References 7 publications

Refining disparity maps using deep learning and edge-aware smoothing filter

Refining disparity maps using deep learning and edge-aware smoothing filter

Stereo matching algorithm using deep learning and edge-preserving filter for machine vision

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

Contact Info

Product

Resources

About