Improvement of stereo matching algorithm for 3D surface reconstruction

Hamzah, Rostam Affendi; Kadmin, A. F.; Hamid, M. S.; Ghani, Sulaiman Ab; Ibrahim, Haidi

doi:10.1016/j.image.2018.04.001

Cited by 62 publications

(44 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adaptive weighting method [4] is the so-called principle of weight distribution. The idea is to use weight and distance information to weight each pixel.…”

Section: A Adaptive Weight Methodsmentioning

confidence: 99%

Improvement of Several Classical Matching Algorithms for Underground Positioning

Huang¹,

Tong²,

Tang³

et al. 2018

Proceedings of the 2018 3rd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2018)

View full text Add to dashboard Cite

Abstract-It is an urgent task for the coal industry in China and even the world to realize the position of the injured and the excavation equipment under the mine. Due to its advantages of high efficiency, low cost, and suitable accuracy, binocular stereo vision measurement methods have become a popular trend in recent years to achieve dynamic target positioning. The stereo matching problem is a key problem in the binocular stereo vision system. This paper analyzes and improves several classical matching algorithms, and combines the improved algorithms together for positioning research. Finally through simulation experiments, an area adaptive matching algorithm with advantages is obtained.

show abstract

“…The adaptive weighting method [4] is the so-called principle of weight distribution. The idea is to use weight and distance information to weight each pixel.…”

Section: A Adaptive Weight Methodsmentioning

confidence: 99%

Improvement of Several Classical Matching Algorithms for Underground Positioning

Huang¹,

Tong²,

Tang³

et al. 2018

Proceedings of the 2018 3rd International Conference on Electrical, Automation and Mechanical Engineering (EAME 2018)

View full text Add to dashboard Cite

show abstract

“…16 It is difficult to automatically match because of image noise, textureless regions, and consistency that are inherent in the captured images or video frames. 17 In this paper, we proposed a new corresponding points matching algorithm suitable for VCSEL to generate encoding dot-pattern structured light. And the proposed miniaturized 3D measurement system is suitable for portable devices, such as mobile phones.…”

Section: Introductionmentioning

confidence: 99%

Time‐resolved coded structured light for 3D measurement

Zhou

2020

Micro & Optical Tech Letters

View full text Add to dashboard Cite

Corresponding points matching is the fundamental computational task underlying stereo vision, and the key issue in making stereo vision practical is to find the most suitable algorithm to quickly match corresponding points, which leads to 3D reconstruction. In this paper, we proposed a new encoding strategy of dot-pattern structured light based on temporal modulated vertical cavity surface emitting laser (VCSEL) array, which is especially suitable for the dot projector in miniaturized devices for stereo vision. Although VCSEL has been used in Apple's iPhone X for dot projector, the time dimension information is not used. VCSEL array has the capability of controlling each light source separately, so we can encode the information of time dimension into the structured light, which improves the stereo-matching accuracy and simplifies the algorithm. In addition, compared to the temporal random speckle structured light method, this time-resolved coded dot-pattern structured light method greatly reduces the number of frames of projecting images required, which has great significance for real-time 3D reconstruction in practical applications. Therefore, the method proposed here could be of high interest for its potentials in 3D measurement in mobile phones and other miniaturized devices. The proof-of-principle experiment results verify the computational efficiency and matching accuracy of the method.

show abstract

“…Moreover, in the realistic world, disparity maps bring on a significant function in three‐dimensional (3D) reconstruction from the input images. Disparity map shows crucial 3D information for assigning the image pixels to precisely produce the depth of the dissimilar detected objects when looking at the contrastive perspectives [1 ]. Yet, depth estimation for disparity map is one of the most challenging and delicate problems.…”

Section: Introductionmentioning

confidence: 99%

“…Hence, this noise will be filtered at second stage which is known as cost aggregation step. After that, optimisation and disparity selection take place which fundamentally consist of several methods as explained in [1 ]. At final stage, the disparity refinement process is required to improve the final results.…”

Section: Introductionmentioning

confidence: 99%

Improvement of disparity map refinement stage using adaptive least square plane fitting technique

Hamzah

Ibrahim

2020

Electronics Letters

View full text Add to dashboard Cite

This Letter presents an improvement of disparity map refinement stage using adaptive least square plane fitting technique. This technique is proposed to increase the accuracy on the final stage of stereo matching algorithm. Fundamentally, the accuracy of matching process depends on the robustness of an algorithm on the plain colour region, depth discontinuity and repetitive pattern area. These regions are difficult to be matched and very challenging. Thus, this Letter proposes multiple point selections of disparities on a plane to adaptively group similar disparity values. Then, the distance of each disparity is calculated to ensure the values are accurately grouped. The distance refers to an assigned reference radius disparity location. Based on the experimental results using the KITTI and Middlebury benchmark images, the proposed method is capable of increasing the accuracy on the challenging regions and the quantitative measurement.

show abstract

Improvement of stereo matching algorithm for 3D surface reconstruction

Cited by 62 publications

References 41 publications

Improvement of Several Classical Matching Algorithms for Underground Positioning

Improvement of Several Classical Matching Algorithms for Underground Positioning

Time‐resolved coded structured light for 3D measurement

Improvement of disparity map refinement stage using adaptive least square plane fitting technique

Contact Info

Product

Resources

About