Dense Disparity Computing Method Based on Mesh Aggregation and Snake Optimization for Stereo Vision

2020 ◽  
Vol 13 (3) ◽  
pp. 95-112
Author(s):  
Liu Shuang ◽  
Yu Shuchun
Keyword(s):  
Stereo Vision ◽  
Stereo Matching ◽  
Cost Calculation ◽  
Segmentation Method ◽  
Suppression Effect ◽  
Cost Aggregation ◽  
Brightness Difference ◽  
Matching Cost ◽  
Computing Method ◽  
Snake Algorithm

In order to generate continuous and dense disparity images, a stereo matching method based on mesh aggregation and Snake optimization is proposed in this article. First, the reference pixels are obtained, so as to improve the suppression effect of the brightness difference in Census transform and improve the accuracy of initial matching cost calculation. Second, the image is divided by SLIC super pixel segmentation method, and the neighborhood pixels are searched according to the mesh search in the region, and the matching cost of these pixels are aggregated together according to the corresponding weight to complete cost aggregation of the pixels to be matched. Third, the Snake algorithm is used in optimizing the boundary of the disparity region. Eight classes of images on the Middlebury platform are selected as the test images, and the four algorithms on the Middlebury platform are selected as reference algorithms to carry out the experimental research. The experimental results show that proportion to bad pixels is low and disparity is continuous and dense on the disparity image calculated by the algorithm proposed in this article. Performance of the proposed method is close to LocalExp algorithm which is the best on the Middlebury platform, and the proposed method can be better applied in the stereo vision.

scholarly journals Review on Stereo Vision Based Depth Estimation

2020 ◽  
pp. 665-671
Author(s):  
Sheshang Degadwala ◽  
Dhairya Vyas ◽  
Arpana Mahajan
Keyword(s):  
Stereo Vision ◽  
Stereo Matching ◽  
Depth Estimation ◽  
Cost Calculation ◽  
Driver Assistance Systems ◽  
Sound System ◽  
Cost Aggregation ◽  
Exact Difference ◽  
Refinement Process ◽  
Cost Efficient

Stereo vision is a challenging problem and it is a wide research topic in computer vision. It has got a lot of attraction because it is a cost efficient way in place of using costly sensors. Stereo vision has found a great importance in many fields and applications in today’s world. Some of the applications include robotics, 3-D scanning, 3-D reconstruction, driver assistance systems, forensics, 3-D tracking etc. The fundamental test of sound system vision is to create exact difference map. Sound system vision calculations for the most part perform four stages: first, coordinating cost calculation; second, cost collection; third, dissimilarity calculation or enhancement; and fourth, divergence refinement. Sound system coordinating issues are likewise examined. An enormous number of calculations have been produced for sound system vision. But characterization of their performance has achieved less attraction. This paper gives a brief overview of the existing stereo vision algorithms. After evaluating the papers we can say that focus has been on cost aggregation and multi-step refinement process. Segment-based methods have also attracted attention due to their good performance. Also, using improved filter for cost aggregation in stereo matching achieves better results.

scholarly journals Effective Stereo Matching with Segment-based Cost Aggregation and Dual-path Refinement

2020 ◽  
Author(s):  
Chih-Shuan Huang ◽  
Ya-Han Huang ◽  
Din-Yuen Chan ◽  
Jar-Ferr Yang
Keyword(s):  
Stereo Matching ◽  
Texture Features ◽  
Spatial Proximity ◽  
Depth Maps ◽  
Cost Aggregation ◽  
Main Challenge ◽  
Color Similarity ◽  
Matching Cost ◽  
Iterative Procedures ◽  
Selection Of

Abstract Stereo matching is one of the most important topics in computer vision and aims at generating precise depth maps for various applications. The main challenge of stereo matching is to suppress inevitable errors occurring in smooth, occluded and discontinuous regions. To solve the aforementioned problems, in this paper, the proposed robust stereo matching system by using segment-based superpixels and magapixels to design adaptive stereo matching computation and dual-path refinement. After determination for 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 utilize 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 left-most and right most regions, the segment-based refinement can greatly improve the mismatched disparity holes. The experimental results demonstrate that the proposed system can obtain higher accurate depth maps compared with the conventional methods.

scholarly journals Local Stereo Matching Using Adaptive Cross-Region-Based Guided Image Filtering with Orthogonal Weights

2021 ◽  
Vol 2021 ◽  
pp. 1-20
Author(s):  
Lingyin Kong ◽  
Jiangping Zhu ◽  
Sancong Ying
Keyword(s):  
Stereo Matching ◽  
Computing Time ◽  
Image Filtering ◽  
Computation Method ◽  
Aggregation Method ◽  
Additional Time ◽  
Matching Algorithm ◽  
Cost Aggregation ◽  
Matching Cost ◽  
Guided Image Filtering

Adaptive cross-region-based guided image filtering (ACR-GIF) is a commonly used cost aggregation method. However, the weights of points in the adaptive cross-region (ACR) are generally not considered, which affects the accuracy of disparity results. In this study, we propose an improved cost aggregation method to address this issue. First, the orthogonal weight is proposed according to the structural feature of the ACR, and then the orthogonal weight of each point in the ACR is computed. Second, the matching cost volume is filtered using ACR-GIF with orthogonal weights (ACR-GIF-OW). In order to reduce the computing time of the proposed method, an efficient weighted aggregation computing method based on orthogonal weights is proposed. Additionally, by combining ACR-GIF-OW with our recently proposed matching cost computation method and disparity refinement method, a local stereo matching algorithm is proposed as well. The results of Middlebury evaluation platform show that, compared with ACR-GIF, the proposed cost aggregation method can significantly improve the disparity accuracy with less additional time overhead, and the performance of the proposed stereo matching algorithm outperforms other state-of-the-art local and nonlocal algorithms.

A Parallel Stereo Matching Algorithm Core for FPGA Modeled by DSP Builder

2014 ◽  
Vol 536-537 ◽  
pp. 67-76
Author(s):  
Xiang Zhang ◽  
Zhang Wei Chen
Keyword(s):  
Stereo Matching ◽  
Cost Calculation ◽  
Stereo Pair ◽  
Disparity Map ◽  
High Definition ◽  
Matching Algorithm ◽  
Census Transform ◽  
Cost Aggregation ◽  
Dsp Builder ◽  
Fpga Chip

This paper proposes a FPGA implementation to apply a stereo matching algorithm based on a kind of sparse census transform in a FPGA chip which can provide a high-definition dense disparity map in real-time. The parallel stereo matching algorithm core involves census transform, cost calculation and cost aggregation modules. The circuits of the algorithm core are modeled by the Matlab/Simulink-based tool box: DSP Builder. The system can process many different sizes of stereo pair images through a configuration interface. The maximum horizon resolution of stereo images is 2048.

scholarly journals Local stereo matching algorithm using modified dynamic cost computation

2021 ◽  
Vol 22 (3) ◽  
pp. 1312
Author(s):  
A. F. Kadmin ◽  
R. A. Hamzah ◽  
M. N. Abd Manap ◽  
M. S. Hamid ◽  
T. F. Tg. Wook
Keyword(s):  
Stereo Matching ◽  
Depth Information ◽  
Computation Method ◽  
Local Method ◽  
Matching Algorithm ◽  
Depth Measurement ◽  
Cost Aggregation ◽  
Matching Cost ◽  
Winner Takes All ◽  
The Cost

Stereo matching is an essential subject in stereo vision architecture. Traditional framework composition consists of several constraints in stereo correspondences such as illumination variations in images and inadequate or non-uniform light due to uncontrollable environments. This work improves the local method stereo matching algorithm based on the dynamic cost computation method for depth measurement. This approach utilised modified dynamic cost computation in the matching cost. A modified census transform with dynamic histogram is used to provide the cost in the cost computation. The algorithm applied the fixed-window strategy with bilateral filtering to retain image depth information and edge in the cost aggregation stage. A winner takes all (WTA) optimisation and left-right check with adaptive bilateral median filtering are employed for disparity refinement. Based on the Middlebury benchmark dataset, the algorithm developed in this work has better accuracy and outperformed several other state-of-the-art algorithms.

scholarly journals A Nonlocal Method with Modified Initial Cost and Multiple Weight for Stereo Matching

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Shenyong Gao ◽  
Haohao Ge ◽  
Hua Zhang ◽  
Ying Zhang
Keyword(s):  
Weight Function ◽  
Stereo Matching ◽  
Minimum Spanning Tree ◽  
Color Difference ◽  
Tree Structure ◽  
Segmentation Method ◽  
Aggregation Method ◽  
Color Distribution ◽  
Cost Aggregation ◽  
Initial Cost

This paper presents a new nonlocal cost aggregation method for stereo matching. The minimum spanning tree (MST) employs color difference as the sole component to build the weight function, which often leads to failure in achieving satisfactory results in some boundary regions with similar color distributions. In this paper, a modified initial cost is used. The erroneous pixels are often caused by two pixels from object and background, which have similar color distribution. And then inner color correlation is employed as a new component of the weight function, which is determined to effectively eliminate them. Besides, the segmentation method of the tree structure is also improved. Thus, a more robust and reasonable tree structure is developed. The proposed method was tested on Middlebury datasets. As can be expected, experimental results show that the proposed method outperforms the classical nonlocal methods.

scholarly journals Improved Cost Computation and Adaptive Shape Guided Filter for Local Stereo Matching of Low Texture Stereo Images

2020 ◽  
Vol 10 (5) ◽  
pp. 1869
Author(s):  
Hua Liu ◽  
Rui Wang ◽  
Yuanping Xia ◽  
Xiaoming Zhang
Keyword(s):  
Cost Function ◽  
Stereo Matching ◽  
Guided Filter ◽  
Disparity Map ◽  
Cost Aggregation ◽  
Dense Stereo Matching ◽  
Gradient Based ◽  
Matching Cost ◽  
Cost Measurement ◽  
Image Pairs

Dense stereo matching has been widely used in photogrammetry and computer vision applications. Even though it has a long research history, dense stereo matching is still challenging for occluded, textureless and discontinuous regions. This paper proposed an efficient and effective matching cost measurement and an adaptive shape guided filter-based matching cost aggregation method to improve the stereo matching performance for large textureless regions. At first, an efficient matching cost function combining enhanced image gradient-based matching cost and improved census transform-based matching cost is introduced. This proposed matching cost function is robust against radiometric variations and textureless regions. Following this, an adaptive shape cross-based window is constructed for each pixel and a modified guided filter based on this adaptive shape window is implemented for cost aggregation. The final disparity map is obtained after disparity selection and multiple steps disparity refinement. Experiments were conducted on the Middlebury benchmark dataset to evaluate the effectiveness of the proposed cost measurement and cost aggregation strategy. The experimental results demonstrated that the average matching error rate on Middlebury standard image pairs is 9.40%. Compared with the traditional guided filter-based stereo matching method, the proposed method achieved a better matching result in textureless regions.

Sign in / Sign up

Export Citation Format

Share Document