基于动态极坐标参数化的遥感影像匹配方法

doi:10.12082/dqxxkx.2019.190081

地球信息科学学报 ›› 2019, Vol. 21 ›› Issue (10): 1586-1593.doi: 10.12082/dqxxkx.2019.190081

基于动态极坐标参数化的遥感影像匹配方法

孙嘉玉¹,左正康¹,孙逸渊¹,SanaUllah¹,张瑞华¹,赵海盟^1,^2,^*()

^1. 空间信息集成与3S工程应用北京市重点实验室(北京大学),北京 100871
^2. 桂林航天工业学院广西高校无人机遥测重点实验室,桂林 541004;

收稿日期:2019-02-27 修回日期:2019-05-23 出版日期:2019-10-25 发布日期:2019-10-29
作者简介:孙嘉玉（1993-）,男,吉林白山人,硕士生,主要从事遥感数字图像处理、三维重建等研究。E-mail: sunjiayu@pku.edu.cn
基金资助:
国家重点研发计划项目(2017YFB0503000);国家自然科学基金项目(61841101)

A Remote Sensing Image Matching Method based on Dynamic Polar Coordinate Parame-terization

SUN Jiayu¹,ZUO Zhengkang¹,SUN Yiyuan¹,ULLAH Sana¹,ZHANG Ruihua¹,ZHAO Haimeng^1,^2,^*()

^1. Space Information Integration and 3S Engineering Application Key Laboratory of Beijing, Peking University, Beijing 100871, China
^2. Guangxi Colleges and Universities Key Laboratory of Unmanned Aerial Vehicle (uav) Remote Sensing, Guilin University of Aerospace Technology, Guilin 541004, China

Received:2019-02-27 Revised:2019-05-23 Online:2019-10-25 Published:2019-10-29
Contact: ZHAO Haimeng
Supported by:
National Key Research and Development Program of China(2017YFB0503000);National Natural Science Foundation of China(61841101)

摘要/Abstract

摘要：

图像匹配作为三维重建至关重要的环节,其精度直接影响了平差优化、正射校正等模块的精度。对于城镇、农场等特征密集型区域,特征距离小,相似性强,易于匹配图像;而针对草地、沙漠等特征不明显区域,特征距离大,如果使用特征点匹配的方法,严格阈值下难以获得足够数量的匹配对,放宽阈值又将引入较多误匹配对,这也是导致稀疏点云不够均匀的原因之一。在此场景下,本文提出了基于动态极坐标参数化的无人机正视影像匹配算法,首先对图像做极坐标参数变化,采用动态策略解决极轴方向采样不均匀的问题,使用最小二乘法对得到的极坐标影像对做位移方向上的匹配,匹配后得到的旋转量和平移量,将该结果和SIFT算法的结果做比较。本文设计了2组实验,即参数已知的解算实验和参数未知的解算实验,且每组实验进行3次。在同等配置的计算机上,对两张7360像素×5400像素,32位的影像,本文方法的位姿解算时间相比SIFT的时间减少约57%,二者求得的位姿差通常小于1%。结论表明二者的结果在精度上表现相当,在时间上明显优于SIFT算法,具有实际的应用价值。

关键词: 无人机, 极坐标, 遥感影像匹配, 三维重建, 光束法平差, 参数化, 影像拼接

Abstract:

With the promotion of 3D reconstruction technology in various scenarios, especially in 3D reconstruction from remote sensing images, the demand for accurate 3D point clouds are becoming more and more intense. Image matching is an important procedure in 3D reconstruction, and its result directly affects the accuracy of subsequent procedures such as bundle adjustment and orthore.pngication. In feature-intensive areas such as towns and farms, the feature distance is small enough to match well. Based on high confidence, the precision of image matching is high. However, in featureless areas such as grassland and desert, the large feature distance may cause mismatch between images. If the feature point matching method is used, it is difficult to obtain correct pose under high thresholds. If a sufficient number of matching pairs is promoted, the matching pairs will contain many mismatching ones, which will cause failure to image matching, and the sparse point cloud will not be evenly distributed. In this scenario, a forward-looking image matching algorithm based on dynamic polar coordinate parameterization was presented. First, a polar transform was designed to a pair of normal images, a dynamic strategy was designed to solve the problem of uneven sampling in the polar axis direction. The obtained polar coordinate image pair was matched with the least squares method in the rotation and translation directions. After the rotation and translation parameters were calculated, we used the result to compared with the result of the SIFT algorithm. In this paper, two sets of experiments were designed to obtain poses between images: one is to use simulation datasets with known rotation and translation parameters; the other is to use true scene datasets with unknown rotation and translation parameters. In each set of the experiments, we used 3 different pair of images, and 3 different known rotation and translation parameters in the first set. With the same computer hardware, and with two images with a resolution of 7360 pixels * 5400 pixels and depth of 32 bit, the proposed method took about 57% less than the time took by the SIFT algorithm, and the rotation and translation error in the two methods was usually less than 1%. Our findings suggest that the proposed algorithm gets image poses with an accuracy similar to that of the SIFT algorithm, but its time consumption is significantly less. Our algorithm shows good practical application value.

Key words: Unmanned Aerial Vehicle （UAV）, polar coordinate, image matching, 3D reconstruction, bundle adjustment, parameterizations, imge stitching

孙嘉玉,左正康,孙逸渊,SanaUllah,张瑞华,赵海盟. 基于动态极坐标参数化的遥感影像匹配方法[J]. 地球信息科学学报, 2019, 21(10): 1586-1593.DOI:10.12082/dqxxkx.2019.190081

SUN Jiayu,ZUO Zhengkang,SUN Yiyuan,ULLAH Sana,ZHANG Ruihua,ZHAO Haimeng. A Remote Sensing Image Matching Method based on Dynamic Polar Coordinate Parame-terization[J]. Journal of Geo-information Science, 2019, 21(10): 1586-1593.DOI:10.12082/dqxxkx.2019.190081

图/表 10

图1

图2

图3

表1

表2

图4

表3

表4

表5

图5

参考文献 20

[1]	廖小罕, 周成虎, 苏奋振 , 等. 无人机遥感众创时代[J]. 地球信息科学学报, 2016,18(11):1439-1447.
	[ Liao X H, Zhou C H, Su F Z , et al. The mass innovation era of UAV remote sensing[J]. Journal of Geo-information Science, 2019,18(11):1439-1447. ]
[2]	郭倩茜 . 图像匹配的主要方法分析[J]. 科技创新与应用, 2016(20):81-81.
	[ Guo Q Q . Analysis of main methods of image matching[J]. Technological innovation and application, 2016(20):81-81. ]
[3]	Yitzhaki, Shlomo. "Gini's mean difference: A superior measure of variability for non-normal distributions"[J]. Metron International Journal of Statistics. Springer Verlag, 2003,61(2):285-316.
[4]	Barnea D I, Silverman H F . A class of algorithms for fast digital image registration[J]. IEEE transactions on Computers, 1972,100(2):179-186.
[5]	陈宁江, 李介谷 . 用归一化灰度组合法进行图像匹配[J]. 红外与激光工程, 2000(5):1-1.
	[ Chen N J, Li J G . Image matching using normalized intensity combination 2000(5):1-1. ]
[6]	山海涛, 郭建星, 耿则勋 . 影像匹配中几种相似性测度的分析[J]. 测绘信息与工程, 2003,28(4):11-13.
	[ Shan H T, Guo J X, Geng Z X , et al. Analysis of several similarity measures in image matching[J]. Journal of Surveying and Mapping Information and Engineering, 2003,28(4):11-13. ]
[7]	Smith S M, Brady J M . SUSAN: A new approach to low level image processing[J]. International Journal of computer vision, 1997,23(1):45-78.
[8]	Harris, Christopher G, Stephens M. "A combined corner and edge detector."[C]. Alvey vision conference, 1988.
[9]	Lowe D G. Object recognition from local scale-invariant features[C]. ICCV. 1999,99(2):1150-1157.
[10]	Lowe D G . Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004,60(2):91-110.
[11]	Bosch A, Zisserman A, Muñoz X. Scene classification via pLSA[C]. European conference on computer vision. Springer, Berlin, Heidelberg, 2006: 517-530.
[12]	Bosch A, Zisserman A, Muñoz X . Scene classification using a hybrid generative/discriminative approach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008,30(4):712-727.
[13]	Yan K, Sukthankar R . PCA-SIFT: A more distinctive repre- sentation for local image descriptors[J]. IEEE Conference on Computer Vision and Pattern Recognition(2), 2004,4:506-513.
[14]	Morel, Jean-Michel, and Guoshen Yu. ASIFT: A new framework for fully affine invariant image comparison[J]. SIAM journal on imaging sciences 2. 2(2009):438-469.
[15]	Wang J G, Li J, Yau W Y, et al. Boosting dense SIFT descriptors and shape contexts of face images for gender recognition[C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition-Workshops.IEEE, 2010: 96-102.
[16]	杨佳宾, 姜永涛, 杨幸彬 , 等. 基于Dense SIFT特征的无人机影像快速拼接方法[J]. 地球信息科学学报, 2019,21(4):588-599.
	[ Yang J B, Jiang Y T, Yang X B , et al. UAV image fast matching method based on Dense SIFT feature[J]. Journal of Geo-information Science, 2019,21(4):588-599. ]
[17]	宫阿都, 何孝莹, 雷添杰 , 等. 无控制点数据的无人机影像快速处理[J]. 地球信息科学学报, 2011,12(2):254-260.
	[ Gong A D, He X Y, Lei T J , et al. Rapid processing of UAV images without control point data[J]. Journal of Geo-information Science, 2011,12(2):254-260. ]
[18]	Rublee E, Rabaud V, Konolige K, et al. ORB: An efficient alternative to SIFT or SURF[C]. IEEE International Conference on Computer Vision, 2011,11(1):2.
[19]	Rosten E, Drummond T. Machine learning for high-speed corner detection[C]. European conference on computer vision. Springer, Berlin, Heidelberg, 2006: 430-443.
[20]	Wolberg G, Zokai S. Robust image registration using log-polar transform[C]. Proceedings 2000 International Conference on Image Processing. IEEE, 2000,1:493-496.

操作	旋转角度/°			差异度
操作	实际变换值	本文实验结果	SIFT实验结果	差异度
1	40	41.25	41.05	0.20
2	60	59.50	58.00	1.50
3	120	121.12	120.45	0.67

操作	放缩因子/倍			差异度
操作	实际变换值	本文实验结果	SIFT实验结果	差异度
1	1.1	1.082	1.079	<0.01
2	1.2	1.124	1.163	0.04
3	0.9	0.937	0.945	<0.01

项目	值
宽度	7364像元
高度	5400像元
水平分辨率/dpi	3734
垂直分辨率/dpi	3734
位深度	24

实验记录	本文实验结果		SIFT实验结果		差异度
实验记录	放缩因子/倍	旋转角度/°	放缩因子/倍	旋转角度/°	放缩因子	旋转角度
1	1.026	5.44	1.002	4.38	0.024	0.242
2	0.958	8.02	0.978	9.15	0.020	0.123
3	1.034	4.69	1.056	4.92	0.021	0.146

实验记录	本文实验耗时/s	SIFT耗时/s	节约率/%
1	0.832	2.235	62.8
2	0.904	2.127	57.5
3	0.866	2.165	60.3

基于动态极坐标参数化的遥感影像匹配方法

A Remote Sensing Image Matching Method based on Dynamic Polar Coordinate Parame-terization

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 20

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	张文元, 陈江媛, 谈国新. 基于3D基元拟合的复杂屋顶点云三维重建[J]. 地球信息科学学报, 2023, 25(8): 1531-1545.
[2]	张寒博, 李彤, 李晓芳, 邓滢, 邓应彬, 荆文龙, 胡义强, 李勇, 杨骥. 无人机遥感和GWR结合的水华短时预测方法[J]. 地球信息科学学报, 2023, 25(8): 1682-1698.
[3]	令振飞, 刘涛, 杜萍, 赵丹, 陈朴一, 马天恩. 一种支持建筑群组相似模式检索的变分图卷积自编码模型[J]. 地球信息科学学报, 2023, 25(7): 1405-1417.
[4]	侯慧太, 蓝朝桢, 徐青. 基于卫星影像全局和局部深度学习特征检索的无人机绝对定位方法[J]. 地球信息科学学报, 2023, 25(5): 1064-1074.
[5]	何海清, 周福阳, 陈敏, 陈婷, 官云兰, 曾怀恩, 魏燕. 耦合卷积神经网络与注意力机制的无人机摄影测量果树树冠分割方法[J]. 地球信息科学学报, 2023, 25(12): 2387-2401.
[6]	吉蒙, 徐永明, 莫亚萍, 张杨, 周睿禹, 祝善友. 基于无人机热红外遥感和大气同步廓线的地表温度反演方法[J]. 地球信息科学学报, 2023, 25(12): 2456-2467.
[7]	闵杰, 张永生, 于英, 吕可枫, 王自全, 张磊. 增强型遥感影像SRGAN算法及其在三维重建精度提升中的应用[J]. 地球信息科学学报, 2022, 24(8): 1631-1644.
[8]	蒯宇, 王彪, 吴艳兰, 陈搏涛, 陈兴迪, 薛维宝. 基于多尺度特征感知网络的城市植被无人机遥感分类[J]. 地球信息科学学报, 2022, 24(5): 962-980.
[9]	郝明, 林惠晶, 高彦彦. 基于改进主动轮廓模型的无人机影像矿区地裂缝提取[J]. 地球信息科学学报, 2022, 24(12): 2448-2457.
[10]	刘树超, 邵全琴, 杨帆, 郭兴健, 王东亮, 黄海波, 汪阳春, 刘纪远, 樊江文, 李愈哲. 黄河源区放牧家畜数量及空间分布无人机遥感调查[J]. 地球信息科学学报, 2021, 23(7): 1286-1295.
[11]	李芹, 刘旭林, 李荣昊, 冯朝晖, 李子锦, 赵红颖. 基于野外台站无人机组网遥感仿真航迹规划[J]. 地球信息科学学报, 2021, 23(5): 948-957.
[12]	朱婉雪, 孙志刚, 李彬彬, 杨婷, 刘振, 彭金榜, 朱康莹, 李仕冀, 娄金勇, 侯瑞星, 李静, 于武江, 王永利, 张峰, 刘向冶, 胡华浪, 欧阳竹. 基于无人机遥感的滨海盐碱地土壤空间异质性分析与作物光谱指数响应胁迫诊断[J]. 地球信息科学学报, 2021, 23(3): 536-549.
[13]	刘见礼, 廖小罕, 倪文俭, 王勇, 叶虎平, 岳焕印. 顾及单木三维形态的无人机立体影像单木识别算法[J]. 地球信息科学学报, 2021, 23(10): 1861-1872.
[14]	陈昂, 杨秀春, 徐斌, 金云翔, 张文博, 郭剑, 邢晓语, 杨东. 基于面向对象与深度学习的榆树疏林识别方法研究[J]. 地球信息科学学报, 2020, 22(9): 1897-1909.
[15]	王学文, 赵庆展, 韩峰, 马永建, 龙翔, 江萍. 机载多光谱影像语义分割模型在农田防护林提取中的应用[J]. 地球信息科学学报, 2020, 22(8): 1702-1713.