Please wait a minute...
 
国土资源遥感  2020, Vol. 32 Issue (2): 19-25    DOI: 10.6046/gtzyyg.2020.02.03
  技术方法 本期目录 | 过刊浏览 | 高级检索 |
面向对象的高空间分辨率遥感影像箱线图变化检测方法
张春森1, 吴蓉蓉1, 李国君1, 崔卫红2, 冯晨轶1
1.西安科技大学测绘科学与技术学院,西安 710054
2.武汉大学遥感信息工程学院,武汉 430079
High resolution remote sensing image object change detection based on box-plot method
Chunsen ZHANG1, Rongrong WU1, Guojun LI1, Weihong CUI2, Chenyi FENG1
1. College of Geomatics, Xi’an University of Science and Technology, Xi’an 710054, China
2. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
全文: PDF(4391 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

传统基于统计的高空间分辨率遥感影像变化检测需假设数据服从正态分布,如基于卡方检验的变化检测,但受困于样本数据不严格服从正态分布,检测效果并不理想。针对此问题提出一种基于箱线图的变化检测方法,不需任何假设,根据数据结构本身固有模型进行变化检测。首先,经由矢量引导的增长式分割获得对象; 然后,结合纹理与光谱特征计算其余弦值; 最后,采用箱线图算法获得变化对象。以高分一号融合影像为实验数据进行验证,结果表明,结合矢量夹角余弦与箱线图进行变化检测的总体精度可达88.21%,相比马氏距离与卡方检测的方法和结合马氏距离与箱线图的方法具有更好的准确性与稳定性。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
张春森
吴蓉蓉
李国君
崔卫红
冯晨轶
关键词 变化检测高空间分辨率遥感影像增长式分割箱线图    
Abstract

The traditional statistics-based change detection method requires the prerequisite that the dataset should obey the Gaussian distribution, such as the iterative chi-square test based change detection method. However, the dataset does not strictly obey the Gaussian distribution, and hence the result is not ideal. A novel change detection method is proposed in this paper, which does not need any assumptions and can take change detection by its own structure. First, an incremental segmentation method is adapted to get objects. After that, spectral and contextual features are combined to calculate its cosine value. Finally, changed objects are found by the box-plot. High-resolution remote sensing images of GF-1 are used as the experimental data. The results are much better than the results of the traditional statistical object-based change detection.

Key wordschange detection    high resolution remote sensing image    incremental segmentation    box-plot
收稿日期: 2019-06-06      出版日期: 2020-06-18
ZTFLH:  TP753  
基金资助:国家自然科学基金项目“反射率与叶绿素荧光协同的小麦白粉病早期探测机理与方法研究”(41601467);陕西省自然基金项目“矿井巷道围岩变形监测摄影测量计算机视觉方法关键技术研究”(2018JM5103)
作者简介: 张春森(1963-),男,博士,教授,主要从事摄影测量与遥感应用的研究。Email: zhchunsen@aliyun.com。
引用本文:   
张春森, 吴蓉蓉, 李国君, 崔卫红, 冯晨轶. 面向对象的高空间分辨率遥感影像箱线图变化检测方法[J]. 国土资源遥感, 2020, 32(2): 19-25.
Chunsen ZHANG, Rongrong WU, Guojun LI, Weihong CUI, Chenyi FENG. High resolution remote sensing image object change detection based on box-plot method. Remote Sensing for Land & Resources, 2020, 32(2): 19-25.
链接本文:  
http://www.gtzyyg.com/CN/10.6046/gtzyyg.2020.02.03      或      http://www.gtzyyg.com/CN/Y2020/V32/I2/19
Fig.1  本文方法流程
Fig.2  增长式分割流程
序号 特征组合 OIF
1 MEAR+G+B+NIR+MEDR+G+B+NIR+STANR+G+B+NIR 0.073 6
2 MEAR+G+B+MEDR+G+B+STANR+G+B 0.120 1
3 MEAR+G+B+NIR+MEDR+G+B+NIR+STANR+G+B+NIR+NDVI+角二阶矩 0.808 8
4 MEAR+G+B+NIR+MEDR+G+B+NIR+STANR+G+B+NIR+NDWI+NDVI+熵+角二阶矩 1.031 5
5 MEAR+G+B+NIR+MEDR+G+B+NIR+STANR+G+B+NIR+NDWI+NDVI+熵 1.628 1
6 PCA前3个主成分分量 3.827 5
Tab.1  不同特征组合的OIF
Fig.3  箱线图结构
Fig.4  变化检测影像与结果
Fig.5  研究区采用不同方法变化检测结果(局部)
评价指标 0.90 0.95 0.97 0.99
正确率 50.37 70.67 73.67 79.43
遗漏率 6.58 10.30 15.21 19.67
总体精度 58.37 77.10 80.21 85.35
Tab.2  不同置信水平下的精度评定
评价指标 马氏距离与
卡方检测
马氏距离与
箱线图
矢量夹角余弦
与箱线图
正确率 79.43 80.25 83.14
遗漏率 19.67 16.82 17.37
总体精度 85.35 86.34 88.21
Tab.3  不同方法的变化检测精度评定
Fig.6  马氏距离数据拟合图
Fig.7  基于不同相似度量方法的箱线图及变化指数曲线
[1] Lu D, Mausel P, Brondizio E, et al. Change detection techniques[J]. International Journal of Remote Sensing, 2004,25(12):2365-2401.
[2] 赵忠明, 孟瑜, 岳安志, 等, 遥感时间序列影像变化检测研究进展[J]. 遥感学报, 2016,20(5):1110-1125.
Zhao Z M, Meng Y, Yue A Z, et al. Review of remotely sensed time series data for change detection[J]. Journal of Remote Sensing, 2016,20(5):1110-1125.
[3] Coppin P, Jonckheere I, Nackaerts K, et al. Digital change detection methods in ecosystem monitoring:A view[J]. International Journal of Remote Sensing, 2004,25(9):1565-1596.
[4] Falowski M J, Wulder M A, White J C, et al. Supporting large-area, sample-based forest inventories with very high spatial resolution satellite imagery[J]. Progress in Physical Geography, 2009,33(3):403-423.
[5] Hay G J, Hemchandran B, Kyle C D. HEAT (home energy assessment technologies):Residential waste heat monitoring,google maps and airborne thermal imagery [C]//Proceedings of the ISPRS Conference GEOBIA.ISPRS, 2010.
[6] Fisher P F, Comber A J, Wadsworth R. Land use and land cover:Contradiction or complement[G].Fisher P F,Re-Presenting GIS.Hoboken:John Wiley and Sons Ltd., 2005: 85-98.
[7] Hussain M, Chen D, Cheng A, et al. Change detection from remotely sensed images:From pixel-based to object-based approaches[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013,80(2):91-106.
[8] 赵敏. 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.
Zhao M. Object-oriented and multi-feature hierarchical change detection based on CVA for high-resolution remote sensing imagery[J]. Journal of Remote Sensing, 2018,22(1):119-131.
[9] Chen G, Hay G J, Carvalho L M T,et al.Object-based change detection[J]. International Journal of Remote Sensing, 2012,33(14):4434-4457.
[10] Janalipour M, Taleai M. Building Change detection after earthquake using multi-criteria decision analysis based on extracted information from high spatial resolution satellite images[J]. International Journal of Remote Sensing, 2017,38(1):82-99.
doi: 10.1080/01431161.2016.1259673
[11] Yang X T, Liu H P, Gao X F. Land cover changed object detection in remote sensing data with medium spatial resolution[J]. International Journal of Applied Earth Observations and Geoinformation, 2015,38:129-137.
[12] Liang L, Ying G, Wen X, et al. Object-oriented change detection based on spatiotemporal relationship in multitemporal remote-sensing images [C]//36th International Symposium on Remote Sensing of Environment.IAPRS, 2015: 1241-1248.
[13] Moghadam N K, Delavar M R, Forati A. Vegetation monitoring of mashhad using an object-oriented POST classification comparison method[J]. 2017 Tehran’s Joint ISPRS Conferences of GI Research,SMPR and EOEC,IAPRS, 2017: 123-131.
[14] An K, Zhang J S, Xiao Y. Object-oriented urban dynamic monitoring:A case study of Haidian Distirict of Beijing[J]. Chinese Geographical Science, 2007,17(3):236-242.
[15] Peng D F, Zhang Y J. Object-based change detection from satellite imagery by segmentation optimization and multi-features fusion[J]. International Journal of Remote Sensing, 2017,38(13):3886-3905.
doi: 10.1080/01431161.2017.1308033
[16] Desclée B, Bogaert P, Defourny P. Forest change detection by statistical object-based method[J]. Remote Sensing of Environment, 2006,102(1):1-11.
[17] Bontemps S, Bogaert P, Titeux N, et al. An object-based change detection method accounting for temporal dependences in time series with medium to coarse spatial resolution[J]. Remote Sensing of Environment, 2008,112(6):3181-3191.
doi: 10.1016/j.rse.2008.03.013
[18] 李春干, 代华兵. 基于统计检验的面向对象高分辨率遥感图像森林变化检测[J]. 林业科学, 2017,53(5):74-81.
Li C G, Dai H B. Statistical object-based method for forest change detection using high-resolution remote sensing image[J]. Scientia Silvae Sinicae, 2017,53(5):74-81.
[19] 吴森, 韦灼彬, 王绍忠, 等. 基于AR模型和主成分分析的损伤识别方法[J]. 振动、测试与诊断, 2012,32(5):841-845.
Wu S, Wei Z B, Wang S Z, et al. The damage identification method based on AR model and principal component analysis[J]. Journal of Vibration,Measurement and Diagnosis, 2012,32(5):841-845.
[20] Li X, Yeh A G O, Qian J, et al.A matching algorithm for detecting land use changes using case-based reasoning[J]. Photogrammetric Engineering and Remote Sensing, 2009,75(11):1319-1332
doi: 10.14358/PERS.75.11.1319
[21] Im J, Jensen J R, Tullis J A. Object-based change detection using correlation image analysis and image segmentation[J]. International Journal of Remote Sensing, 2008,29(2):399-423.
[22] Ouma Y O, Tetuko J, Tatteishi R. Analysis of co-occurrence and discrete wavelet transform textures for differentiation of forest and non-forest vegetation in very-high-resolution optical-sensor imagery[J]. International Journal of Remote Sensing, 2008,29(12):3417-3456.
[23] Tukey J W. Exploratory data analysis[J]. Journal of the American Statistical Association, 1977,26(2):163-182.
[24] 龚晶晶, 李方林, 杨刚刚, 等. 基于Excel VBA实现箱图剔除法确定化探异常下限[J]. 物探与化探, 2013,37(5):926-933.
Gong J J, Li F L, Yang G G, et.al.The application of box-plot method to determining geochemical anomaly thresholds based on VBA procedure in Excel[J]. Geophysical and Geochemical Exploration, 2013,37(5):926-933.
[1] 冯林艳,谭炳香,王晓慧,陈新云,曾伟生,戚曌. 基于分布函数的对象级森林变化快速检测[J]. 国土资源遥感, 2020, 32(2): 73-80.
[2] 姚丙秀,黄亮,许艳松. 一种结合超像素和图论的高空间分辨率遥感影像分割方法[J]. 国土资源遥感, 2019, 31(3): 72-79.
[3] 周阳,张云生,陈斯飏,邹峥嵘,朱耀晨,赵芮雪. 基于DCNN特征的建筑物震害损毁区域检测[J]. 国土资源遥感, 2019, 31(2): 44-50.
[4] 刘义志,赖华荣,张丁旺,刘飞鹏,蒋小蕾,曹庆安. 多特征混合核SVM模型的遥感影像变化检测[J]. 国土资源遥感, 2019, 31(1): 16-21.
[5] 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.
[6] 王立娟,靳晓,贾虎军,唐尧,马国超. 基于国产高分卫星数据的矿山环境变化检测[J]. 国土资源遥感, 2018, 30(3): 151-158.
[7] 朱欣然,吴波,张强. 一种改进CVAPS的LUCC分类自动更新方法[J]. 国土资源遥感, 2018, 30(2): 29-37.
[8] 王光辉,李建磊,王华斌,杨化超. 基于多特征融合的遥感影像变化检测算法[J]. 国土资源遥感, 2018, 30(2): 93-99.
[9] 尹凌宇, 覃先林, 孙桂芬, 刘树超, 祖笑锋, 陈小中. 利用KPCA法检测高分一号影像中的森林覆盖变化[J]. 国土资源遥感, 2018, 30(1): 95-101.
[10] 刁娇娇, 龚鑫烨, 李明诗. 利用综合变化检测方法进行土地覆盖变化制图[J]. 国土资源遥感, 2018, 30(1): 157-165.
[11] 何超. 地质灾害体遥感变化信息检测及趋势分析[J]. 国土资源遥感, 2017, 29(s1): 27-33.
[12] 李春干, 梁文海. 基于面向对象变化向量分析法的遥感影像森林变化检测[J]. 国土资源遥感, 2017, 29(3): 77-84.
[13] 朱红春, 黄伟, 刘海英, 张忠芳, 王彬. 基于KL散度的面向对象遥感变化检测[J]. 国土资源遥感, 2017, 29(2): 46-52.
[14] 项盛文, 文贡坚, 高峰. 知识驱动下的飞机目标变化检测方法[J]. 国土资源遥感, 2016, 28(4): 77-82.
[15] 唐菲菲, 阮志敏, 张亚利, 彭丽. 基于机载LiDAR和GIS数据的建筑物变化信息自动检测方法[J]. 国土资源遥感, 2016, 28(1): 57-62.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
京ICP备05055290号-2
版权所有 © 2015 《自然资源遥感》编辑部
地址:北京学院路31号中国国土资源航空物探遥感中心 邮编:100083
电话:010-62060291/62060292 E-mail:zrzyyg@163.com
本系统由北京玛格泰克科技发展有限公司设计开发