基于球面全等映射的全景图像匹配

doi:10.13474/j.cnki.11-2246.2025.1010

测绘通报 ›› 2025, Vol. 0 ›› Issue (10): 57-62.doi: 10.13474/j.cnki.11-2246.2025.1010

基于球面全等映射的全景图像匹配

肖尧^1,2, 杨雨生^1,2, 史航¹, 解杨敏^1,2

1. 上海大学机电工程与自动化学院, 上海 200444;
2. 上海大学上海市智能制造及机器人重点实验室, 上海 200444

收稿日期:2025-02-24 发布日期:2025-10-31
通讯作者: 解杨敏。E-mail:xieym@shu.edu.cn
作者简介:肖尧(1999-),男,硕士,主要研究方向为图像特征匹配、SLAM等。E-mail:xiaoyao_dean@shu.edu.cn
基金资助:
国家自然科学基金青年基金(62303294)

Panoramic image matching based on spherical congruence projection

XIAO Yao^1,2, YANG Yusheng^1,2, SHI Hang¹, XIE Yangmin^1,2

1. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 200444, China;
2. Shanghai Key Laboratory of Intelligent Manufacturing and Robotics, Shanghai University, Shanghai 200444, China

Received:2025-02-24 Published:2025-10-31

摘要/Abstract

摘要： 随着广角视觉传感器在多个领域的广泛应用,传统的平面透视相机已逐渐显现出其局限性,特别是在复杂的视觉感知任务中。广角镜头虽能够提供更广阔的视野,但其引入的图像畸变严重影响了图像特征匹配的准确性和可靠性。为解决这一问题,本文提出一种创新的基于球面全等映射的全景图像匹配技术。该技术首先将全景图像基于Scaramuzza相机模型投影成球面全等映射图像,消除原始全景图像在平面结构中不一致畸变的特性;在此基础上,构建相应的球面数据结构,并采用FAST角点提取方案,进一步提出一种适用于球面像素结构的改进rBRIEF算法,并构建相应的特征描述子,实现高精度、高稳健性的全景图像匹配。

关键词: 全景图像, 球面结构, 改进ORB, 像素分割, 球面描述子

Abstract: With the widespread application of wide-angle vision sensors in various fields, traditional perspective cameras have gradually revealed their limitations, especially in complex visual perception tasks.Although wide-angle lenses provide a broader field of view, the introduced image distortion severely affects the accuracy and reliability of feature matching.To address this issue, this study proposes an innovative panoramic image matching technique based on spherical isometric mapping.The technique firstly projects the panoramic image into a spherical isometric mapping image using the scaramuzza camera model, eliminating the inconsistency distortion inherent in panoramic images in a planar structure.On this basis, a corresponding spherical data structure is constructed, and the FAST corner detection method is adopted.Furthermore, an improved rBRIEF algorithm tailored for spherical pixel structures is proposed, along with the construction of corresponding feature descriptors, to achieve high-precision and highly robust panoramic image matching.

Key words: panoramic image, spherical structure, improved ORB, pixel segmentation, spherical descriptor

中图分类号:

P237

肖尧, 杨雨生, 史航, 解杨敏. 基于球面全等映射的全景图像匹配[J]. 测绘通报, 2025, 0(10): 57-62.

XIAO Yao, YANG Yusheng, SHI Hang, XIE Yangmin. Panoramic image matching based on spherical congruence projection[J]. Bulletin of Surveying and Mapping, 2025, 0(10): 57-62.

参考文献

[1] 陈坚炜,何元烈,何铭臻,等. 多目鱼眼视觉SLAM特征点误匹配的剔除优化[J]. 大连工业大学学报,2024,43(1):61-72. [2] 张煌,何佳洲,王景石,等. 基于全景图像的无人艇激光雷达杂波滤除方法[J]. 光学学报,2022,42(18):74-84. [3] 杨娜,张翀,李天昊. 基于无人机与计算机视觉的中国古建筑木结构裂缝监测系统设计[J]. 工程力学,2021,38(3): 27-39. [4] 丁颖,刘延伟,刘金霞,等. 虚拟现实全景图像显著性检测研究进展综述[J]. 电子学报,2019,47(7): 1575-1583. [5] 陈令羽,贾奋励,宋国民. 基于全景图的地理现实增强技术研究[J]. 测绘通报,2015(4): 14-17. [6] 王步云,李宏伟,赵姗. 融合点云与全景影像的路侧多目标识别[J]. 测绘通报,2023(10): 40-46. [7] JI Shunping,QIN Zijie,SHAN Jie,et al. Panoramic SLAM from a multiple fisheye camera rig[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2020,159: 169-183. [8] RUBLEE E,RABAUD V,KONOLIGE K,et al. ORB: an efficient alternative to SIFT or SURF[C]//Proceedings of 2011 International Conference on Computer Vision. Barcelona: IEEE,2011: 2564-2571. [9] LEUTENEGGER S,CHLI M,SIEGWART R Y. BRISK: Binary Robust invariant scalable keypoints[C]//Proceedings of 2011 International Conference on Computer Vision. Barcelona: IEEE,2011: 2548-2555. [10] SEOK H,LIM J. ROVO: robust omnidirectional visual odometry for wide-baseline wide-FOV camera systems[C]//Proceedings of 2019 International Conference on Robotics and Automation (ICRA). Montreal:IEEE,019: 6344-6350. [11] LIU Shuai,ZHAO Lingli,LI Junsheng,et al. Th SIFT features matching for spherical panoramic images[C]//Proceedings of the 11th IEEE International Conference on Control ＆ Automation (ICCA). Taichung:IEEE,2014: 914-917. [12] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision,2004,60(2): 91-110. [13] 王奕丹,闫利. POS辅助车载组合全景影像路面角点特征匹配算法[J]. 测绘通报,2016(4): 24-27. [14] YANG Yusheng,GAO Zhiyuan,ZHANG Jinghan,et al. UVS-CNNs: Constructing general convolutional neural networks on quasi-uniform spherical images[J]. Computers ＆ Graphics,2024,122: 103973. [15] SCARAMUZZA D,MARTINELLI A,SIEGWART R. A toolbox for easily calibrating omnidirectional cameras[C]//Proceedings of 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems. Beijing: IEEE,2006: 5695-5701.

基于球面全等映射的全景图像匹配

Panoramic image matching based on spherical congruence projection

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	杨景玉, 贾多科, 王阳萍. 基于超像素分割与CRF的高分辨率遥感影像变化检测[J]. 测绘通报, 2022, 0(2): 25-30,49.
[2]	陈利燕, 林鸿, 吴健华. 融合随机森林和超像素分割的建筑物自动提取[J]. 测绘通报, 2021, 0(2): 49-53.
[3]	徐启恒, 黄滢冰, 陈洋. 结合超像素和卷积神经网络的国产高分辨率遥感影像云检测方法[J]. 测绘通报, 2019, 0(1): 50-55.
[4]	肖明虹, 冯文卿, 眭海刚. 超像素分割和多方法融合的遥感影像变化检测方法[J]. 测绘通报, 2018, 0(10): 93-97,121.
[5]	吕楠, 苟永刚, 龙川, 张婕. 多相机图像拼接匀色算法[J]. 测绘通报, 2016, 0(7): 44-47.