基于超像素分割与CRF的高分辨率遥感影像变化检测

doi:10.13474/j.cnki.11-2246.2022.0038

测绘通报 ›› 2022, Vol. 0 ›› Issue (2): 25-30,49.doi: 10.13474/j.cnki.11-2246.2022.0038

基于超像素分割与CRF的高分辨率遥感影像变化检测

杨景玉^1,2, 贾多科¹, 王阳萍^1,2

1. 兰州交通大学电子与信息工程学院, 甘肃兰州 730070;
2. 甘肃省人工智能与图形图像处理工程研究中心, 甘肃兰州 730070

收稿日期:2021-03-04 修回日期:2021-12-28 发布日期:2022-03-11
作者简介:杨景玉(1979-),男,博士,副教授,主要从事遥感图像处理的研究工作。E-mail:yangjy@mail.lzjtu.cn
基金资助:
国家自然科学基金（62067006）；甘肃省教育科技创新项目（2021jyjbgs-05）；甘肃省高等学校创新基金（2021B-098）；甘肃省重点研发计划（21YF5GA158）

detection based on superpixel segmentation and CRF for high-resolution remote sensing images

YANG Jingyu^1,2, JIA Duoke¹, WANG Yangping^1,2

1. School of Electronics and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China;
2. Gansu Provincial Engineering Research Center for Artificial Intelligence and Graphics & Image Processing, Lanzhou 730070, China

Received:2021-03-04 Revised:2021-12-28 Published:2022-03-11

摘要/Abstract

摘要： 针对目前高分辨率遥感影像变化检测算法对于光谱变化过敏感问题，本文提出了一种基于超像素分割与条件随机场（CRF）的遥感影像变化检测算法。首先采用空间约束的t混合模型驱动的分割模型，获得同质性超像素块，实现良好的边界附着性和亮度均匀性。然后计算分割得到的双时相影像块之间的特征差异性，获取变化幅度图像。最后利用模糊聚类算法（FCM）对变化幅度图像进行聚类，得到隶属度图像作为CRF一阶势，并利用光谱-空间相似度约束的函数构建CRF二阶势。试验结果表明，与现有方法相比，该方法检测精度可提高5%，错检率和漏检率可降低3%，能较好地应对输入图像的光谱变化，并保持变化检测结果的边缘细节。

关键词: 变化检测, 超像素分割, 条件随机场, 光谱-空间约束, 边缘保持

Abstract: High-resolution remote sensing image change detection algorithms are too sensitive to spectral changes, a new algorithm based on super-pixel segmentation and improved conditional random field (CRF) is proposed in this paper to detect changes in remote sensing images. Firstly, the student's-t mixture model (SMM) with spatial constraints super-pixel segmentation model is used to generate homogeneous patches,which has characteristic of boundary adhesion and brightness uniformity. Then the algorithm obtains change amplitude image by calculating the feature difference between the segmented dual phase image patches. Finally, the change amplitude image is clustered by FCM, and clustering result is used as the first-order potential of CRF, and the spectral spatial similarity constrained function is used as the second-order potential of CRF. Experiments results show that the detection accuracy of the method proposed in this paper is improved by 5%, and the false detection rate and missed detection rate are reduced by 3%, this method can better handle the spectral changes of the input image and keep the edge details of the change detection results.

Key words: change detection, super-pixel segmentation, conditional random field, spectral-spatial constraints, edge keeping

中图分类号:

P237

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.

YANG Jingyu, JIA Duoke, WANG Yangping. detection based on superpixel segmentation and CRF for high-resolution remote sensing images[J]. Bulletin of Surveying and Mapping, 2022, 0(2): 25-30,49.

参考文献

[1] AI Bin, MA Chunlei, ZHAO Jun, et al. The impact of rapid urban expansion on coastal mangroves:a case study in Guangdong province, China[J]. Frontiers of Earth Science, 2020, 14(1):37-49.
[2] 赵展,夏旺,闫利.基于多源数据的土地利用变化检测[J].国土资源遥感, 2018, 30(4):148-155.
[3] 赵敏,赵银娣.面向对象的多特征分级CVA遥感影像变化检测[J].遥感学报, 2018, 22(1):119-131.
[4] 李成龙,张景发.基于主成分分析的遥感震害变化检测方法与应用[J].地震, 2013, 33(2):103-108.
[5] ZHAO Yan, REN Huazhong, CAO Desheng.The research of building earthquake damage object-oriented change detection based on ensemble classifier with remote sensing image[C]//Proceedings of 2018 IEEE International Geoscience and Remote Sensing Symposium. Valencia:IEEE, 2018:4950-4953.
[6] LI Ying, XU Longhao, LIU Tao. Unsupervised change detection for remote sensing images based on object-based MRF and stacked autoencoders[C]//Proceedings of 2016 International Conference on Orange Technologies (ICOT). Melbourne, VIC:IEEE, 2016:64-67.
[7] 王丽云,李艳,汪禹芹.基于对象变化矢量分析的土地利用变化检测方法研究[J].地球信息科学学报, 2014, 16(2):307-313.
[8] WIRATAMA W, SIM D. Fusion network for change detection of high-resolution panchromatic imagery[J]. Applied Sciences, 2019, 9(7):1441.
[9] ZHOU Licun, CAO Guo, LI Yupeng, et al. Change detection based on conditional random field with region connection constraints in high-resolution remote sensing images[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(8):3478-3488.
[10] 王超,张雪红,石爱业,等.结合阴影补偿的对象级高分辨率遥感影像多尺度变化检测[J].通信学报, 2018, 39(9):159-167.
[11] SHAO Pan, SHI Wenzhong, HE Pengfei, et al. Novel approach to unsupervised change detection based on a robust semi-supervised FCM clustering algorithm[J]. Remote Sensing, 2016, 8(3):264.
[12] WANG Pengyu, ZHU Hongqing, LING Xiaofeng. Content-based superpixel matching using spatially constrained student's-t mixture model and scale-invariant key-superpixels[J]. IEEE Access, 2020, 8:31198-31213.
[13] 崔宾阁,马秀丹,谢小云.小样本的高光谱图像降噪与分类[J].遥感学报, 2017, 21(5):728-738.
[14] NGUYEN T M, WU Q M J. Fast and robust spatially constrained Gaussian mixture model for image segmentation[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2013, 23(4):621-635.
[15] KUCZMA M. An Introduction to the Theory of Functional Equations and Inequalities[M]. Basel:Birkhäuser Basel, 2009.
[16] 张东波,易良玲,许海霞,等.多尺度局部结构主导二值模式学习图像表示[J].电子与信息学报, 2019, 41(4):896-903.
[17] ALY S, SAYED A. Human action recognition using bag of global and local Zernike moment features[J]. Multimedia Tools and Applications, 2019, 78(17):24923-24953.
[18] 巫兆聪,胡忠文,张谦,等.结合光谱、纹理与形状结构信息的遥感影像分割方法[J].测绘学报, 2013, 42(1):44-50.
[19] 屈亚.矢量数据辅助的高分辨率遥感影像高铁沿线变化检测方法研究[D].成都:西南交通大学, 2016.
[20] LEI Tao, XUE Dinghua, LÜ Zhiyong, et al. Unsupervised change detection using fast fuzzy clustering for landslide mapping from very high-resolution images[J]. Remote Sensing, 2018, 10(9):1381.
[21] LÜ Pengyuan, ZHONG Yanfei, ZHAO Ji, et al. Change detection based on structural conditional random field framework for high spatial resolution remote sensing imagery[C]//Proceedings of 2017 IEEE International Geoscience and Remote Sensing Symposium. Fort Worth, TX:IEEE, 2017:1059-1062.
[22] 魏立飞,牟紫微,王晓燕,等.基于CRF模型的高分辨率遥感影像变化检测[J].测绘通报, 2017(9):28-31.

基于超像素分割与CRF的高分辨率遥感影像变化检测

detection based on superpixel segmentation and CRF for high-resolution remote sensing images

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	郑艳, 何欢, 卜丽静, 金鑫. 自相似性和边缘保持分解的超分辨率重建算法[J]. 测绘通报, 2022, 0(7): 54-59.
[2]	阮明浩, 卢永华, 刘玉贤, 汤圣君, 王伟玺, 张宇琦, 李游. 激光与倾斜点云精确配准与无缝融合[J]. 测绘通报, 2022, 0(4): 6-10.
[3]	潘建平, 李鑫, 孙博文, 胡勇, 李明明. 基于注意力密集连接金字塔网络的新增建设用地变化检测[J]. 测绘通报, 2022, 0(3): 41-46,59.
[4]	郁汀, 王铎, 陈钦. 基于伪语义相似度模型的中文地址匹配方法[J]. 测绘通报, 2022, 0(3): 101-106.
[5]	乐颖, 夏元平. 基于比值法的多源多时相数据城区变化检测[J]. 测绘通报, 2022, 0(2): 56-61.
[6]	车子杰, 高飞, 吴兆福, 李振轩. 基于改进U-Net网络的多源遥感影像洪涝灾害信息提取与变化分析[J]. 测绘通报, 2022, 0(1): 26-32.
[7]	周秀华, 李乃强. 基于多种相似度特征的道路实体融合方法[J]. 测绘通报, 2021, 0(8): 102-105,157.
[8]	苏艺凡, 党建武, 王阳萍, 杨景玉. 改进的区间二型模糊聚类遥感影像变化检测[J]. 测绘通报, 2021, 0(7): 44-51,58.
[9]	刘海飞, 杨敏华, 王晶, 徐刚, 陈杰. 利用结构面对象的高分遥感影像建筑物变化检测[J]. 测绘通报, 2021, 0(6): 16-20.
[10]	张伟良, 刘琦, 吴长彬, 杨光迪. 基于孪生神经网络的土地利用现状年度变化检测[J]. 测绘通报, 2021, 0(3): 91-95,104.
[11]	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.
[12]	赖正文, 夏小云. 像素级和对象级高分辨率遥感图像变化检测分析[J]. 测绘通报, 2021, 0(2): 59-63.
[13]	刘广进, 王光辉, 毕卫华, 刘慧杰, 杨化超. 改进D-LinkNet模型在国产卫星影像云检测中的应用[J]. 测绘通报, 2021, 0(11): 54-58,64.
[14]	韩建平. 青海省地震灾后地物变化的快速识别[J]. 测绘通报, 2021, 0(11): 120-123.
[15]	韩建平. 基于遥感影像的青海省环境变化监测[J]. 测绘通报, 2021, 0(10): 123-126,145.