Please wait a minute...
 
国土资源遥感  2020, Vol. 32 Issue (2): 73-80    DOI: 10.6046/gtzyyg.2020.02.10
  技术方法 本期目录 | 过刊浏览 | 高级检索 |
基于分布函数的对象级森林变化快速检测
冯林艳1,2, 谭炳香1,2(), 王晓慧1,2, 陈新云3, 曾伟生3, 戚曌1,2
1.中国林业科学研究资源信息研究所,北京 100091
2.国家林业和草原局林业遥感与信息技术重点实验室,北京 100091
3.国家林业和草原局调查规划设计院,北京 100714
Object-oriented rapid forest change detection based on distribution function
Linyan FENG1,2, Bingxiang TAN1,2(), Xiaohui WANG1,2, Xinyun CHEN3, Weisheng ZENG3, Zhao QI1,2
1. Research Institute of Forest Resources Information Techniques, Chinese Academy of Forestry, Beijing 100091, China
2. Key Laboratory of Forestry Remote Sensing and Information System, NFGA, Beijing 100091, China
3. Academy of Forest and Grassland Inventory and Planning, Beijing 100714, China
全文: PDF(4518 KB)   HTML  
输出: BibTeX | EndNote (RIS)      
摘要 

南方人工林生长迅速,轮伐期短。为探讨一种有效更新森林资源数据库的森林变化检测方法,快速检测短时期内森林采伐与更新的动态变化。以变化频繁快速,变化图斑多且小的广西人工林作为研究区,以2个时相的高分二号(GF-2)影像为数据源,利用多尺度分割和光谱差异分割2种方法对2期影像进行分割,通过对象的归一化差值植被指数(normalized difference vegetation index,NDVI)差值并基于分布函数确定阈值来提取变化区域与变化类型,实现森林变化快速检测。基于像元采用同样的方法进行处理,与面向对象NDVI差值法进行比较。结果表明面向对象NDVI差值法的总体精度达89.76%,Kappa系数为0.81,精度和提取效果优于基于像元NDVI差值法,更能刻画变化图斑的形状和边界,也能较准确地检测出微小变化的面积。该方法能适应南方人工林的变化特点,在实现快速检测变化的目的下,可用于森林资源数据库的更新。

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
冯林艳
谭炳香
王晓慧
陈新云
曾伟生
戚曌
关键词 GF-2变化检测NDVI面向对象分布函数    
Abstract

Plantation in southern China is growing rapidly, and rotation cutting period is short. To explore the forest change detection method used to update the forest resource database effectively and to monitor the dynamic changes in forest harvesting and renewal in a short period, the authors chose the plantation area of Shangsi County in Guangxi as the study area, where the plantation area changes frequently and rapidly and the change patterns are numerous and small. The GF-2 remote sensing images of two phases were used as data sources. Multi-scale segmentation and spectral difference segmentation were used to segment the two-phase images. The change areas and change types were extracted from the NDVI difference of the objects and the threshold value was determined based on the distribution function, so as to realize the rapid detection of forest change. In addition, the same method was adopted for pixel-based processing in comparison with object-oriented NDVI difference method. The results show that the overall accuracy of the object-oriented NDVI difference method is 87.12%, and the Kappa coefficient is 0.81. The accuracy and extraction effect are better than those of the pixel-based NDVI difference method, indicating that the object-oriented NDVI difference method can better depict the shape and boundary of the change spots and can also more accurately detect the small change area. This method can be adapted to detect the changing characteristics of plantation in south China and can also be used to update the forest resource database for the purpose of rapid change detection.

Key wordsGF-2    change detection    NDVI    object-oriented    distribution function
收稿日期: 2019-06-06      出版日期: 2020-06-18
:  TP79  
基金资助:中央级公益性科研院所基本科研业务费专项资金项目“高分辨率影像对象级的森林资源变化检测”(CAFYBB2017MB012);高分辨率对地观测系统重大专项(民用部分)子课题“面向林地类型精细识别的GF-6卫星最优数据选择研究”(21-Y20A06-9001-17/18-1)
通讯作者: 谭炳香
作者简介: 冯林艳(1995-),女,硕士研究生,主要研究方向为森林资源遥感监测。Email: 1040857742@qq.com。
引用本文:   
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.
Linyan FENG, Bingxiang TAN, Xiaohui WANG, Xinyun CHEN, Weisheng ZENG, Zhao QI. Object-oriented rapid forest change detection based on distribution function. Remote Sensing for Land & Resources, 2020, 32(2): 73-80.
链接本文:  
https://www.gtzyyg.com/CN/10.6046/gtzyyg.2020.02.10      或      https://www.gtzyyg.com/CN/Y2020/V32/I2/73
Fig.1  研究区影像及地理位置示意图
(GF-2 B4(R),B3(G),B2(B)假彩色合成)
Fig.2  技术路线
空间分辨率/m 最小可检测面积/hm2
250~1 000 6~100
10~30 0.05~0.30
0.5~5 0.01
Tab.1  传感器空间分辨率与最小可检测面积的关系
图层 分割方法 分割对象 分割尺度 形状参数 紧致度参数 对象数量/个
1 多尺度分割 全部像元 70 0.1 0.5 73 328
2 光谱差异分割 图层1 50 69 134
Tab.2  图像分割参数
Fig.3  影像局部地区分割结果
Fig.4  2种方法的NDVI差值影像统计
变化类型 面向对象判定条件 基于像元判定条件
植被变裸地 Mi≤-0.085 Mi≤-0.098
裸地变植被 Mi≥0.18 Mi≥0.148
未变化 -0.085<△Mi<0.18 -0.098<△Mi<0.148
Tab.3  各变化类型的判定条件
Fig.5  2种方法的变化检测结果
检测
方法
检测变化
类型
实际变化类型 合计 漏分
误差/%
错分
误差/%
总体
精度/%
Kappa系数
植被变裸地 裸地变植被 未变化
面向对象NDVI差值法 植被变裸地 19 121 755 1 465 21 341 9.80 10.40
裸地变植被 0 12 589 5 082 17 671 10.91 28.76 89.76 0.81
未变化 2 078 787 57 314 60 179 10.25 4.76
基于像元NDVI差值法 植被变裸地 17 590 596 1 363 19 549 17.02 10.02
裸地变植被 0 12 813 6 484 19 297 9.33 33.60 87.12 0.76
未变化 3 609 722 56 014 60 345 12.29 7.18
合计 21 199 14 131 63 861 99 191
Tab.4  变化检测结果混淆矩阵
Fig.6  局部变化检测结果
[1] 赵宪文, 李崇贵, 斯林, 等. 基于信息技术的森林资源调查新体系[J]. 北京林业大学学报, 2002,24(5/6):147-155.
Zhao X W, Li C G, Si L, et al. Building a new system of forest resources inventory by information technology[J]. Journal of Beijing University, 2002,24(5/6):147-155.
[2] Ban Y, Yousif O. Change techniques:A review[M]. Multitemporal Remote Sensing.Stockholm:Springer, 2016.
[3] 陈雅如, 肖文发, 冯源, 等. 三峡库区1992—2012年森林景观格局演变研究[J]. 林业科学研究, 2017,30(4):542-550.
Chen Y R, Xiao W F, Feng Y, et al. Evolution of forest landscape pattern in the There Gorges reservoir area during 1992—2012[J]. Forest Research, 2017,30(4):542-550.
[4] 沈文娟, 李明诗, 黄成全. 长时间序列多源遥感数据的森林干扰监测算法研究进展[J]. 遥感学报, 2018,22(6):1005-1022.
Shen W J, Li M S, Huang C Q. Review of remote sensing algorithms for monitoring forest disturbance from time series and multi-source data fusion[J]. Journal of Remote Sensing, 2018,22(6):1005-1022.
[5] Ian H, Robert C, Mark F. An evaluation of forest health insect and disease survey data and satellite-based remote sensing forest change detection methods:Case studies in the United States[J]. Remote Sensing, 2018,10(8):1184-1192.
[6] Kim D H, Sexton J O, Noojipady P, et al. Global, Landsat-based forest-cover change from 1990 to 2000[J]. Remote Sensing of Environment, 2014,155:178-193.
doi: 10.1016/j.rse.2014.08.017
[7] 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.doi: 10.6046/gtzyyg.2018.01.22.
Diao J J, Gong X Y, Li M S. A comprehensive change detection method for updating land cover data base[J]. Remote Sensing for Land and Resources, 2018,30(1):157-165.doi: 10.6046/gtzyyg.2018.01.22.
[8] 陈幸良, 巨茜, 林昆仑. 中国人工林发展现状、问题与对策[J]. 世界林业研究, 2014,27(6):54-59.
Chen X L, Ju Q, Lin K L. Development status, issues and countermeasures of China’s plantation[J]. World Forestry Research, 2014,27(6):54-59.
[9] 史文中, 张鹏林. 光学遥感影像变化检测研究的回顾与展望[J]. 武汉大学学报(信息科学版), 2018,43(12):1832-1837.
Shi W Z, Zhang P L. State-of-the-art remotely sensed images-based change detection methods[J]. Geomatics and Information Science of Wuhan University, 2018,43(12):1832-1837.
[10] 李亮, 王蕾, 孙晓鹏, 等. 面向对象变化向量分析的遥感影像变化检测[J]. 遥感信息, 2017,32(6):71-77.
Li L, Wang L, Sun X P, et al. Remote sensing change detection method based on object-oriented change vector analysis[J]. Remote Sensing Information, 2017,32(6):71-77.
[11] Cai S, Liu D. A comparison of object-based and contextual pixel-based classifications using high and medium spatial resolution images[J]. Remote Sensing Letters, 2013,4(10):998-1007.
[12] Mahmoudi F T, Samadzadegan F, Reinartz P. Context aware modification on the object based image analysis[J]. Journal of the Indian Society of Remote Sensing, 2015,43(4):709-717.
[13] 冯文卿, 眭海刚, 涂继辉, 等. 高分辨率遥感影像的随机森林变化检测方法[J]. 测绘学报, 2017,46(11):1880-1890.
Feng W Q, Sui H G, Tu J H, et al. Change detection method for high resolution remote sensing images using random forest[J]. Acta Geodaetica et Cartographica sinica, 2017,46(11):1880-1890.
[14] 王光辉, 李建磊, 王华斌, 等. 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.doi: 10.6046/gtzyyg.2018.02.13.
Wang G H, Li J L, Wang H B, et al. Change detection based on adaptive fusion of multiple features[J]. Remote Sensing for Land and Resources, 2018,30(2):93-99.doi: 10.6046/gtzyyg.2018.02.13.
[15] 于洋洋, 程飞, 廖博一, 等. 林地清理方式对桉树人工林生长的影响[J]. 福建农林大学学报(自然科学版), 2019,48(1):41-47.
Yu Y Y, Cheng F, Liao B Y, et al. Effects of ground clearance on the growth of Eucalyptus plantation[J]. Journal of Fujian Agriculture and Forestry University(Natural Science Edition), 2019,48(1):41-47.
[16] 李德仁. 利用遥感影像进行变化检测[J]. 武汉大学学报(信息科学版), 2003,28(s1):7-12.
Li D R. Change detection from remote sensing images[J]. Geomatics and Information Science of Wuhan University, 2003,28(s1):7-12.
[17] 眭海刚, 冯文卿, 李文卓, 等. 多时相遥感影像变化检测方法综述[J]. 武汉大学学报(信息科学版), 2018,43(12):1885-1898.
Sui H G, Feng W Q, Li W Z, et al. Review of change detection methods for multi-temporal remote sensing imagery[J]. Geomatics and Information Science of Wuhan University, 2018,43(12):1885-1898.
[18] Song D X, Huang C, Sexton J O, et al. Use of landsat and corona data for mapping forest cover change from the mid-1960s to 2000s:Case studies from the eastern United States and central Brazil[J]. Isprs Journal of Photogrammetry & Remote Sensing, 2015,103:81-92.
[19] Wenqing F, Haigang S, Jihui T, et al. A novel change detection approach for multi-temporal high-resolution remote sensing images based on rotation forest and coarse-to-fineuncertainty analyses[J]. Remote Sensing, 2018,10(7):1015-1022.
[20] 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 B B. Statistical object-based method for forest change detection using high-resolution remote sensing images[J]. Scientia Silvae Sinicae, 2017,53(5):74-81.
[21] 尹凌宇, 覃先林, 孙桂芬, 等. 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.doi: 10.6046/gtzyyg.2018.01.01.
Yin L Y, Qin X L, Sun G F, et al. The method for detecting forest cover change in GF-1 images by using KPCA[J]. Remote Sensing for Land and Resources, 2018,30(1):95-101.doi: 10.6046/gtzyyg.2018.01.01.
[22] 郑志峰, 曹建农, 张雯佼. PLS与EM算法支持下的遥感影像变化检测[J]. 测绘通报, 2018,498(9):33-37.
Zheng Z F, Cao J N, Zhang W J. Remote sensing image change detection based on PLS and EM algorithm[J]. Bulletin of Surveying and Mapping, 2018,498(9):33-37.
[23] Paolini L, Grings F, Sobrino J A, et al. Radiometric correction effects in landsat multi-date/multi-sensor change detection studies[J]. International Journal of Remote Sensing, 2006,27(4):685-704.
[24] Sui H G, Zhou Q M, Gong J Y, et al. Processing of multi-temporal data and change detection[M] //Li Z L,Chen J,Baltsavias E.Advances in photogrammetry,remote sensing and spatial information sciences.London:Taylor and Francis Group, 2008: 227-247.
[25] Couturier S, Núňez J M, Kolb M. Measuring tropical deforestation with error margins:A method for REDD monitoring in south-eastern Mexico[M]// Sudarshana,Nageswara-Rao,Soneji.Tropical Forests.Intech Open Access Publishing, 2012.
[26] 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.doi: 10.6046/gtzyyg.2017.03.11.
Li C G, Liang W H. Forest change detection using remote sensing image based on object-oriented change vector analysis[J]. Remote Sensing for Land and Resources, 2017,29(3):77-84.doi: 10.6046/gtzyyg.2017.03.11.
[27] Tab F A, Naghdy G, Mertins A. Scalable multiresolution color image segmentation[J]. Signal Processing, 2006,86(7):1670-1687.
[28] 陈春雷, 武刚. 面向对象的遥感影像最优分割尺度评价[J]. 遥感技术与应用, 2011,26(1):96-102.
Chen C L, Wu G. Evaluation of optimal segmentation scale with object-oriented method in remote sensing[J]. Remote Sensing Technology and Application, 2011,26(1):96-102.
[29] 陈韬亦, 陈金勇, 赵和鹏, 等. 基于Ecognition的光学遥感图像舰船目标检测[J]. 无线电工程, 2013,43(11):11-13.
Chen T Y, Chen J Y, Zhao H P, et al. Ecognition-based ship detection on optical remote sensing images[J]. Radio Engineering of China, 2013,43(11):11-13.
[1] 史飞飞, 高小红, 肖建设, 李宏达, 李润祥, 张昊. 基于集成学习和多时相遥感影像的枸杞种植区分类[J]. 自然资源遥感, 2022, 34(1): 115-126.
[2] 胡盈盈, 戴声佩, 罗红霞, 李海亮, 李茂芬, 郑倩, 禹萱, 李宁. 2001—2015年海南岛橡胶林物候时空变化特征分析[J]. 自然资源遥感, 2022, 34(1): 210-217.
[3] 柳明星, 刘建红, 马敏飞, 蒋娅, 曾靖超. 基于GF-2 PMS影像和随机森林的甘肃临夏花椒树种植监测[J]. 自然资源遥感, 2022, 34(1): 218-229.
[4] 薛白, 王懿哲, 刘书含, 岳明宇, 王艺颖, 赵世湖. 基于孪生注意力网络的高分辨率遥感影像变化检测[J]. 自然资源遥感, 2022, 34(1): 61-66.
[5] 潘建平, 徐永杰, 李明明, 胡勇, 王春晓. 结合相关系数和特征分析的植被区域自动变化检测研发[J]. 自然资源遥感, 2022, 34(1): 67-75.
[6] 范莹琳, 娄德波, 张长青, 魏英娟, 贾福东. 基于面向对象的铁尾矿信息提取技术研究——以迁西地区北京二号遥感影像为例[J]. 自然资源遥感, 2021, 33(4): 153-161.
[7] 李轶鲲, 杨洋, 杨树文, 王子浩. 耦合模糊C均值聚类和贝叶斯网络的遥感影像后验概率空间变化向量分析[J]. 自然资源遥感, 2021, 33(4): 82-88.
[8] 王译著, 黄亮, 陈朋弟, 李文国, 余晓娜. 联合显著性和多方法差异影像融合的遥感影像变化检测[J]. 自然资源遥感, 2021, 33(3): 89-96.
[9] 刘咏梅, 范鸿建, 盖星华, 刘建红, 王雷. 基于无人机高光谱影像的NDVI估算植被盖度精度分析[J]. 自然资源遥感, 2021, 33(3): 11-17.
[10] 蔡祥, 李琦, 罗言, 齐建东. 面向对象结合深度学习方法的矿区地物提取[J]. 国土资源遥感, 2021, 33(1): 63-71.
[11] 苏龙飞, 李振轩, 高飞, 余敏. 遥感影像水体提取研究综述[J]. 国土资源遥感, 2021, 33(1): 9-11.
[12] 杜方洲, 石玉立, 盛夏. 基于深度学习的TRMM降水产品降尺度研究——以中国东北地区为例[J]. 国土资源遥感, 2020, 32(4): 145-153.
[13] 徐锐, 余小于, 张驰, 杨瑨, 黄宇, 潘俊. 融合Unet网络和IR-MAD的建筑物变化检测方法[J]. 国土资源遥感, 2020, 32(4): 90-96.
[14] 刁明光, 刘文静, 李静, 刘芳, 王彦佐. 矿山遥感监测矢量成果数据动态变化检测方法[J]. 国土资源遥感, 2020, 32(3): 240-246.
[15] 张鹏, 林聪, 杜培军, 王欣, 唐鹏飞. 南京市生态红线区高分辨率遥感精准监测方法与应用[J]. 国土资源遥感, 2020, 32(3): 157-164.
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