吉林大学学报(工学版) ›› 2024, Vol. 54 ›› Issue (7): 2080-2085.doi: 10.13229/j.cnki.jdxbgxb.20230039

• 计算机科学与技术 • 上一篇    

基于仿射不变算子的无人机多光谱影像匹配算法

唐毅1,2(),潘杨1,2(),郜明3,易虹辰1,韦安琦1   

  1. 1.苏州科技大学 环境科学与工程学院,江苏 苏州 215009
    2.苏州科技大学 城市生活污水资源化利用技术国家地方联合工程实验室,江苏 苏州 215009
    3.四川大学 机械工程学院,成都 610065
  • 收稿日期:2023-01-26 出版日期:2024-07-01 发布日期:2024-08-05
  • 通讯作者: 潘杨 E-mail:zzz200399@yeah.net;panyang@mail.usts.edu.cn
  • 作者简介:唐毅(1978-),男,高级实验师.研究方向:摄影测量,数字图像处理.E-mail: zzz200399@yeah.net
  • 基金资助:
    国家自然科学基金项目(41801148)

Multi spectral image matching algorithm of unmanned aerial vehicle based on affine invariant operator

Yi TANG1,2(),Yang PAN1,2(),Ming GAO3,Hong-chen YI1,An-qi WEI1   

  1. 1.School of Environmental Science and Engineering,Suzhou University of Science and Technology,Suzhou 215009,China
    2.National and Local Joint Engineering Laboratory of Urban Domestic Sewage Recycling Technology,Suzhou University of Science and Technology,Suzhou 215009,China
    3.School of Mechanical Engineering,Sichuan University,Chengdu 610065,China
  • Received:2023-01-26 Online:2024-07-01 Published:2024-08-05
  • Contact: Yang PAN E-mail:zzz200399@yeah.net;panyang@mail.usts.edu.cn

摘要:

针对传统的无人机多光谱影像匹配算法存在匹配精度不高、匹配准确度不高、整体效果不佳等问题,提出了一种基于仿射不变算子的无人机多光谱影像匹配算法。首先,通过直方图均衡方法对无人机多光谱影像进行增强处理并通过仿射不变算子提取无人机多光谱影像的仿射不变区域;其次,通过多尺度乘积LoG方法完成无人机多光谱影像角点检测及特征点提取;最后,使用形状描述算子描述影像特征点,并利用高斯加权距离算法完成最终的影像匹配。实验结果表明,本文方法的无人机多光谱影像匹配精确度更高、误差更小、整体效果更佳。

关键词: 仿射不变算子, 无人机, 多光谱影像, 图像匹配, 特征点提取

Abstract:

The traditional unmanned aerial vehicle (UAV) multispectral image matching algorithm has some problems, such as low matching accuracy, low matching accuracy, and poor overall effect. In order to solve the problems in traditional methods, a UAV multispectral image matching algorithm based on affine invariant operator is proposed. Firstly, the UAV multispectral image is enhanced by histogram equalization method, and the affine invariant region of the UAV multispectral image is extracted by affine invariant operator; Secondly, corner detection and feature point extraction of UAV multispectral image are completed by multi-scale product LoG method; Finally, the shape description operator is used to describe the image feature points, and the Gaussian weighted distance algorithm is used to complete the final image matching. The experimental results show that the proposed method has higher accuracy, smaller error and better overall effect for UAV multispectral image matching.

Key words: affine invariant operator, unmanned aerial vehicle, multi spectral image, image matching, feature point extraction

中图分类号: 

  • TP391.41

图1

实验对象"

图2

3种算法的正确匹配点结果"

表1

3种算法的匹配数据统计"

参数文献[3]算法文献[4]算法本文算法
描述时间/ms159522081109
匹配时间/ms194519541177
平均匹配误差0.99560.99980.8810
1 眭海刚,刘畅,干哲,等.多模态遥感图像匹配方法综述[J].测绘学报,2022,519:1848-1861.
Sui Hai-gang, Liu Chang, Gan Zhe, et al. Overview of multi-modal remote sensing image matching methods[J]. Acta Geodaetica et Cartographica Sinica, 2022,51(9): 1848-1861.
2 郝帅,吴瑛琦,马旭,等.基于CycleGAN-SIFT的可见光和红外图像匹配[J].光学精密工程,2022,30(5):602-614.
Hao Shuai, Wu Ying-qi, Ma Xu, et al. Visible and infrared image matching based on CycleGAN-SIFT[J]. Optics and Precision Engineering, 2022,30(5): 602-614.
3 王昱皓,唐泽恬,钟岷哲,等.基于掩模搜索的快速尺度不变特征变换图像匹配算法[J].激光与光电子学进展,2021,58(4):175-181.
Wang Yu-hao, Tang Ze-tian, Zhong Min-zhe, et al. Image matching algorithm for fast scale-invariant feature transformation based on mask search[J].Laser & Optoelectronics Progress, 2021,58(4): 175-181.
4 高莎,袁希平,甘淑,等.集成SIFT算法与检测模型优化的UAV影像匹配方法[J].光谱学与光谱分析,2022,42(5):1497-1503.
Gao Sha, Yuan Xi-ping, Gan Shu, et al. UAV image matching method integrating SIFT algorithm and detection model optimization[J]. Spectroscopy and Spectral Analysis, 2022,42(5): 1497-1503.
5 岳振宇,范大昭,董杨,等.一种星载平台轻量化快速影像匹配方法[J].地球信息科学学报,2022,24(5):925-939.
Yue Zhen-yu, Fan Da-zhao, Dong Yang, et al.A generation method of spaceborne lightweight and fast matching[J]. Journal of Geo-information Science, 2022, 24(5): 925-939.
6 黄淑英,胡威,杨勇,等.基于渐进式双网络模型的低曝光图像增强方法[J].计算机学报,2021,44(2):384-394.
Huang Shu-ying, Hu Wei, Yang Yong, et al.A low-exposure image enhancement based on progressive dual network model[J]. Chinese Journal of Computers, 2021, 44(2): 384-394.
7 路皓翔,刘振丙,张静,等.结合多尺度循环卷积和多聚类空间的红外图像增强[J].电子学报,2022,50(2):415-425.
Lu Hao-xiang, Liu Zhen-bing, Zhang Jing, et al. Infrared image enhancement based on multi-scale cyclic convolution and multi-clustering space[J]. Acta Electronica Sinica, 2022, 50(2): 415-425.
8 张传辉,姚国标,张力,等.多分支网络联合的倾斜影像仿射不变特征匹配[J].测绘学报, 2021, 50(5):641-651.
Zhang Chuan-hui, Yao Guo-biao, Zhang Li, et al. Affine invariant feature matching of oblique images based on multi-branch network[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(5): 641-651.
9 陈玲玲,周旭东,谢傢成,等.快速仿射非局部均值图像去噪[J].图学学报, 2021, 42(5):762-766.
Chen Ling-ling, Zhou Xu-dong, Xie Jia-cheng, et al. Fast affine non-local means image denosing[J]. Journal of Graphics, 2021, 42(5): 762-766.
10 朱代先,吴栋,刘树林,等.AKAZE结合自适应局部仿射匹配的视差图像特征匹配算法[J].应用光学,2021, 42(6):1048-1055.
Zhu Dai-xian, Wu Dong, Liu Shu-lin, et al. Disparity image feature matching algorithm based on AKAZE and adaptive local affine matching[J]. Journal of Applied Optics, 2021,42(6): 1048-1055.
11 王丁丁,王万银,朱莹洁,等.位场边缘识别特征点提取方法及应用[J].地球物理学报,2021,64(4):1401-1411.
Wang Ding-ding, Wang Wan-yin, Zhu Ying-jie, et al. Extraction methods and application of feature points of edge recognition for potential field[J]. Chinese Journal of Geophysics, 2021,64(4): 1401-1411.
12 王辉,袁杰.改进的均匀化AGAST特征提取算法[J].电光与控制,2022,29(5):33-38.
Wang Hui, Yuan Jie. An improved homogenized AGAST feature extraction algorithm[J]. Electronics Optics & Control, 2022,29(5): 33-38.
13 刘磊,邹媛媛,陈泊璇.二维形状特征描述及分类识别研究进展综述[J].计算机工程与应用,2021,57(14):39-47.
Liu Lei, Zou Yuan-yuan, Chen Bo-xuan. Review on research progress of 2D shape description and classification[J]. Computer Engineering and Applications, 2021, 57(14): 39-47.
14 曹明兰,李亚东,李长青,等.VDVI与AKAZE结合的无人机森林影像匹配方法[J].中南林业科技大学学报, 2021, 41(8):1-8.
Cao Ming-lan, Li Ya-dong, Li Chang-qing,et al. Forest image matching method of unmanned aerial vehicle based on the combination of VDVI and AKAZE[J]. Journal of Central South University of Forestry & Technology, 2021, 41(8): 1-8.
15 陆可,郑伯桢,卢春盛,等.基于数学形态学改进的无人机影像配准算法[J].合肥工业大学学报:自然科学版,2021, 44(10):1406-1412, 1419.
Lu Ke, Zheng Bo-zhen, Lu Chun-sheng,et al. Improved UAV image registration algorithm based on mathematical morphology[J]. Journal of Hefei University of Technology (Natural Science), 2021,44(10): 1406-1412, 1419.
[1] 鲜斌,王光怡,蔡佳明. 多无人机吊挂负载运输系统的非线性鲁棒控制设计[J]. 吉林大学学报(工学版), 2024, 54(6): 1788-1795.
[2] 王殿伟,张池,房杰,许志杰. 基于高分辨率孪生网络的无人机目标跟踪算法[J]. 吉林大学学报(工学版), 2024, 54(5): 1426-1434.
[3] 申富媛,李炜,蒋栋年. 四旋翼无人机寿命预测和自主维护方法[J]. 吉林大学学报(工学版), 2023, 53(3): 841-852.
[4] 胡江平,周子粲,陈波. 基于方位测量的固定时间多目标定位和环航控制[J]. 吉林大学学报(工学版), 2023, 53(3): 923-932.
[5] 徐卓君,王耀祥,黄兴,彭程. 多无人机地面移动目标搜寻和定位[J]. 吉林大学学报(工学版), 2023, 53(3): 832-840.
[6] 于雅静,郭健,王荣浩,秦伟,宋明武,向峥嵘. 基于状态观测器的多四旋翼无人机时变编队控制[J]. 吉林大学学报(工学版), 2023, 53(3): 871-882.
[7] 薛珊,张亚亮,吕琼莹,曹国华. 复杂背景下的反无人机系统目标检测算法[J]. 吉林大学学报(工学版), 2023, 53(3): 891-901.
[8] 何颖,樊俊松,王巍,孙庚,刘衍珩. 无人机空地安全通信与航迹规划的多目标联合优化方法[J]. 吉林大学学报(工学版), 2023, 53(3): 913-922.
[9] 王小艺,刘迪一,于家斌,何卓昀,赵峙尧. 复杂风场环境下的多旋翼无人机编队故障检测方法[J]. 吉林大学学报(工学版), 2023, 53(3): 823-831.
[10] 潘弘洋,刘昭,杨波,孙庚,刘衍珩. 基于新一代通信技术的无人机系统群体智能方法综述[J]. 吉林大学学报(工学版), 2023, 53(3): 629-642.
[11] 陈珑茏,冯天宇,吕宗阳,吴玉虎. 共轴倾转旋翼无人机有限时间滑模姿态控制[J]. 吉林大学学报(工学版), 2023, 53(3): 883-890.
[12] 鲜斌,李杰奇,古训. 基于非线性扰动观测器的无人机地面效应补偿[J]. 吉林大学学报(工学版), 2022, 52(8): 1926-1933.
[13] 朱航,于瀚博,梁佳辉,李宏泽. 基于电场模型的无人机搜寻改进算法及仿真分析[J]. 吉林大学学报(工学版), 2022, 52(12): 3029-3038.
[14] 曲优,李文辉. 基于锚框变换的单阶段旋转目标检测方法[J]. 吉林大学学报(工学版), 2022, 52(1): 162-173.
[15] 鲜斌,张诗婧,韩晓薇,蔡佳明,王岭. 基于强化学习的无人机吊挂负载系统轨迹规划[J]. 吉林大学学报(工学版), 2021, 51(6): 2259-2267.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!