ORB-SLAM3 and dense mapping algorithm based on improved feature matching

IF 3.4 3区工程技术 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

Signal Processing-Image Communication Pub Date : 2025-04-10 DOI:10.1016/j.image.2025.117322

Delin Zhang , Guangxiang Yang , Guangling Yu , Baofeng Yang , Xiaoheng Wang

{"title":"ORB-SLAM3 and dense mapping algorithm based on improved feature matching","authors":"Delin Zhang , Guangxiang Yang , Guangling Yu , Baofeng Yang , Xiaoheng Wang","doi":"10.1016/j.image.2025.117322","DOIUrl":null,"url":null,"abstract":"<div><div>ORB-SLAM3 is currently the mainstream visual SLAM system, which uses feature matching based on ORB keypoints. However, ORB-SLAM3 faces two main issues: Firstly, feature matching is time-consuming, and the insufficient number of feature point matches results in lower algorithmic localization accuracy. Secondly, it lacks the capability to construct dense point cloud maps, therefore limiting its applicability in high-demand scenarios such as path planning. To address these issues, this paper proposes an ORB-SLAM3 and dense mapping algorithm based on improved feature matching. In the feature matching process of ORB-SLAM3, motion smoothness constraints are introduced and the image is gridded. The feature points that are at the edge of the grid are divided into multiple adjacent grids to solve the problems, which are unable to correctly partition the feature points to the corresponding grid and algorithm time consumption. This reduces matched time and increases the number of matched pairs, improving the positioning accuracy of ORB-SLAM3. Moreover, a dense mapping construction thread has been added to construct dense point cloud maps in real-time using keyframes and corresponding poses filtered from the feature matching stage. Finally, simulation experiments were conducted using the TUM dataset for validation. The results demonstrate that the improved algorithm reduced feature matching time by 75.71 % compared to ORB-SLAM3, increased the number of feature point matches by 88.69 %, and improved localization accuracy by 9.44 %. Furthermore, the validation confirmed that the improved algorithm is capable of constructing dense maps in real-time. In conclusion, the improved algorithm demonstrates excellent performance in terms of localization accuracy and dense mapping.</div></div>","PeriodicalId":49521,"journal":{"name":"Signal Processing-Image Communication","volume":"137 ","pages":"Article 117322"},"PeriodicalIF":3.4000,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Signal Processing-Image Communication","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0923596525000694","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}

引用次数: 0

Abstract

ORB-SLAM3 is currently the mainstream visual SLAM system, which uses feature matching based on ORB keypoints. However, ORB-SLAM3 faces two main issues: Firstly, feature matching is time-consuming, and the insufficient number of feature point matches results in lower algorithmic localization accuracy. Secondly, it lacks the capability to construct dense point cloud maps, therefore limiting its applicability in high-demand scenarios such as path planning. To address these issues, this paper proposes an ORB-SLAM3 and dense mapping algorithm based on improved feature matching. In the feature matching process of ORB-SLAM3, motion smoothness constraints are introduced and the image is gridded. The feature points that are at the edge of the grid are divided into multiple adjacent grids to solve the problems, which are unable to correctly partition the feature points to the corresponding grid and algorithm time consumption. This reduces matched time and increases the number of matched pairs, improving the positioning accuracy of ORB-SLAM3. Moreover, a dense mapping construction thread has been added to construct dense point cloud maps in real-time using keyframes and corresponding poses filtered from the feature matching stage. Finally, simulation experiments were conducted using the TUM dataset for validation. The results demonstrate that the improved algorithm reduced feature matching time by 75.71 % compared to ORB-SLAM3, increased the number of feature point matches by 88.69 %, and improved localization accuracy by 9.44 %. Furthermore, the validation confirmed that the improved algorithm is capable of constructing dense maps in real-time. In conclusion, the improved algorithm demonstrates excellent performance in terms of localization accuracy and dense mapping.

查看原文本刊更多论文

基于改进特征匹配的ORB-SLAM3和密集映射算法

ORB- slam3是目前主流的视觉SLAM系统，它采用基于ORB关键点的特征匹配。然而，ORB-SLAM3面临两个主要问题：一是特征匹配耗时长，特征点匹配数量不足导致算法定位精度较低。其次，缺乏构建密集点云图的能力，限制了其在路径规划等高需求场景中的适用性。针对这些问题，本文提出了一种基于改进特征匹配的ORB-SLAM3和密集映射算法。在ORB-SLAM3的特征匹配过程中，引入了运动平滑性约束，并对图像进行了网格化处理。将位于网格边缘的特征点划分为多个相邻的网格，解决了无法将特征点正确划分到相应网格和算法耗时的问题。这减少了匹配时间，增加了匹配对的数量，提高了ORB-SLAM3的定位精度。此外，还增加了密集映射构建线程，利用特征匹配阶段过滤的关键帧和相应的姿态实时构建密集点云地图。最后，利用TUM数据集进行了仿真实验验证。结果表明，与ORB-SLAM3相比，改进后的算法特征匹配时间缩短了75.71%，特征点匹配数量增加了88.69%，定位精度提高了9.44%。进一步验证了改进算法能够实时构建密集地图。综上所述，改进算法在定位精度和密集映射方面表现出优异的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Signal Processing-Image Communication 工程技术-工程：电子与电气

CiteScore

8.40

自引率

2.90%

发文量

138

审稿时长

5.2 months

期刊介绍： Signal Processing: Image Communication is an international journal for the development of the theory and practice of image communication. Its primary objectives are the following: To present a forum for the advancement of theory and practice of image communication. To stimulate cross-fertilization between areas similar in nature which have traditionally been separated, for example, various aspects of visual communications and information systems. To contribute to a rapid information exchange between the industrial and academic environments. The editorial policy and the technical content of the journal are the responsibility of the Editor-in-Chief, the Area Editors and the Advisory Editors. The Journal is self-supporting from subscription income and contains a minimum amount of advertisements. Advertisements are subject to the prior approval of the Editor-in-Chief. The journal welcomes contributions from every country in the world. Signal Processing: Image Communication publishes articles relating to aspects of the design, implementation and use of image communication systems. The journal features original research work, tutorial and review articles, and accounts of practical developments. Subjects of interest include image/video coding, 3D video representations and compression, 3D graphics and animation compression, HDTV and 3DTV systems, video adaptation, video over IP, peer-to-peer video networking, interactive visual communication, multi-user video conferencing, wireless video broadcasting and communication, visual surveillance, 2D and 3D image/video quality measures, pre/post processing, video restoration and super-resolution, multi-camera video analysis, motion analysis, content-based image/video indexing and retrieval, face and gesture processing, video synthesis, 2D and 3D image/video acquisition and display technologies, architectures for image/video processing and communication.