Binocular stereo matching algorithm based on MST cost aggregation

被引：12

作者：

Zhang, Jian ^{[1
]}

Zhang, Yan ^{[2
]}

Wang, Cong ^{[1
]}

Yu, Huilong ^{[1
]}

Qin, Cui ^{[1
]}

机构：

[1] Nanjing Inst Technol, Sch Informat & Commun Engn, Nanjing 211167, Peoples R China

[2] Swissgrid Ltd, Short Term Network Modelling, Bleichemattstr 31, CH-5001 Aarau, Switzerland

来源：

MATHEMATICAL BIOSCIENCES AND ENGINEERING | 2021年 / 18卷 / 04期

关键词：

binocular vision; stereo matching; cost aggregation; minimum spanning tree;

D O I：

10.3934/mbe.2021160

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

For common binocular stereo matching algorithms in computer vision, it is not easy to obtain high precision and high matching speed at the same time. In this paper, an improved binocular stereo matching algorithm based on Minimum Spanning Tree (MST) cost aggregation is proposed. Firstly, the performance of the parallel algorithm can be improved by reducing the height of the tree. Then, an improved Root to Leaf (L2R) cost aggregation algorithm is proposed. By combining stereo matching technology with parallel computing technology, the above method can realize synchronous parallel computing at the algorithm level. Experimental results show that the improved algorithm has high accuracy and high matching speed for binocular stereo vision.

引用

页码：3215 / 3226

页数：12

共 10 条

[1] Measuring the Wave Height Based on Binocular Cameras [J].

Cang, Yan ;

He, Hengxiang ;

Qiao, Yulong .

SENSORS, 2019, 19 (06)

[2] Curb Detection for Road and Sidewalk Detection [J].

Cheng, Mingmei ;

Zhang, Yigong ;

Su, Yingna ;

Alvarez, Jose M. ;

Kong, Hui .

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2018, 67 (11) :10330-10342

[3] DEVELOPMENT OF GIS TOOL FOR THE SOLUTION OF MINIMUM SPANNING TREE PROBLEM USING PRIM'S ALGORITHM [J].

Dutta, Suvajit ;

Patra, Debasish ;

Shankar, Hari ;

Verma, Prabhakar Alok .

ISPRS TECHNICAL COMMISSION VIII SYMPOSIUM, 2014, 40-8 :1105-1114

[4] Autonomous 3D Exploration of Large Structures Using an UAV Equipped with a 2D LIDAR [J].

Faria, Margarida ;

Ferreira, Antonio Sergio ;

Perez-Leon, Hector ;

Maza, Ivan ;

Viguria, Antidio .

SENSORS, 2019, 19 (22)

[5] Accelerating BFS via Data Structure-Aware Prefetching on GPU [J].

Guo, Hui ;

Huang, Libo ;

Lu, Yashuai ;

Ma, Jianqiao ;

Qian, Cheng ;

Ma, Sheng ;

Wang, Zhiying .

IEEE ACCESS, 2018, 6 :60234-60248

[6]

Mozerov M. G., 2019, IEEE T IMAGE PROCESS, V6, P1

[7]

Umamaheswaran S., 2019, 2019 International Conference on Information Technology (ICIT), P201, DOI 10.1109/ICIT48102.2019.00042

[8]

Wang R., 2020, WORLD J CLIN CASES, V8, P69

[9] DrivingStereo: A Large-Scale Dataset for Stereo Matching in Autonomous Driving Scenarios [J].

Yang, Guorun ;

Song, Xiao ;

Huang, Chaoqin ;

Deng, Zhidong ;

Shi, Jianping ;

Zhou, Bolei .

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :899-908

[10] Edge-Preserving Stereo Matching Using Minimum Spanning Tree [J].

Zhang, Congxuan ;

He, Chao ;

Chen, Zhen ;

Liu, Wen ;

Li, Ming ;

Wu, Junjie .

IEEE ACCESS, 2019, 7 :177909-177921

← 1 →