结合Gabor小波和形态学的高分辨率图像树冠提取方法

doi:10.12082/dqxxkx.2019.180280

地球信息科学学报 ›› 2019, Vol. 21 ›› Issue (2): 249-258.doi: 10.12082/dqxxkx.2019.180280

结合Gabor小波和形态学的高分辨率图像树冠提取方法

施慧慧¹(), 王妮^1,^2,^*(), 滕文秀³, 刘玉婵^1,²

1. 滁州学院地理信息与旅游学院,滁州 239000
2. 安徽省地理信息智能感知与服务工程实验室,滁州 239000
3. 南京林业大学林学院,南京 210037

收稿日期:2018-06-11 修回日期:2018-11-29 出版日期:2019-02-20 发布日期:2019-01-30
作者简介:
作者简介：施慧慧（1996-）,女,安徽亳州人,硕士生,研究方向为地理信息科学。E-mail: shihuihui899@163.com
基金资助:
国家自然科学基金项目（41601455）;安徽高校省级自然科学研究重点项目（KJ2016A531）;滁州学院大学生创新创业训练计划项目资助（201810377040、2018CXXL041）

Tree Canopy Extraction Method of High Resolution Image based on Gabor Filter and Morphology

Huihui SHI¹(), Ni WANG^1,^2,^*(), Wenxiu TENG³, Yuchan LIU^1,²

1. School of Geographic Information and Tourism, Chuzhou University, Chuzhou 239000, China
2. Anhui Engineering Laboratory of Geographical Information Intelligent Sensor and Service, Chuzhou 239000, China
3. College of Forest, Nanjing Forestry University, Nanjing 210037, China

Received:2018-06-11 Revised:2018-11-29 Online:2019-02-20 Published:2019-01-30
Contact: Ni WANG
Supported by:
National Natural Science Foundation of China, No.41601455;College Natural Science Research Key Program of An Hui Province, No.KJ2016A531;College Students Innovation and Entrepreneurship Training Program Project Subsidy of Chuzhou University, No.201810377040, 2018CXXL041

摘要/Abstract

摘要：

树冠信息的遥感提取能有效辅助森林参数反演、林分长势监测、树种识别等森林调查活动。随着遥感信息自动化提取的需求不断加强,本文基于高空间分辨率遥感数据,以滁州市皇甫山林场为研究区域,设计了一种结合Gabor小波和形态学的树冠提取方法。该方法首先采用Gabor小波提取出纹理特征,其次结合K-means聚类分析方法,对PCA降维后的纹理特征向量提取出阔叶林区,最后基于形态学理论降低影像噪声,并利用前景后景标记的分水岭方法进行单木树冠提取。经过与人工解译的树冠信息结果对比发现,在郁闭度较高的阔叶林区,该自动化方法提取树冠精度较高,分割准确率A_d为79.59%,F测度达到了79.00%能有效提供精确的单木树冠信息,为林业经济调查技术的发展具有一定的实践意义。

关键词: 单木树冠提取, Gabor小波, PCA, K-means聚类, 标记分水岭

Abstract:

As an important part of forestry economy and an important physiological structure of photosynthesis, tree canopy is also an important forest parameter and stand factor in the process of forest inventory such as growth monitoring and tree species identification. Accurate extraction of tree crown information can effectively provide support for forest inventory. With the development of remote sensing technology, the disadvantages of traditional forest survey methods are obvious, and they are gradually developing towards the direction of combining remote sensing information extraction with traditional forest inventory. In order to improve the accuracy of remote sensing information extraction, people began to use high spatial resolution remote sensing images, combined with computer automation technology, to develop remote sensing information automatic extraction methods. As the demand of the automatic extraction of remote sensing information continuously strengthen, based on high spatial resolution remote sensing data in Chuzhou HuangFu Mountain tree farm field as the study area, we proposed a method that combination of Gabor wavelet and morphology of canopy extraction. First we extracted texture features by Gabor filter, K-means clustering analysis was used to extract dense forest area from the texture feature by PCA (Principal Component Analysis) extracted broadleaf forest region, based on the morphological theory to reduce image noise, and used the prospect foreground markers of the watershed method extract individual tree crown. After comparing with the artificial interpretation canopy information found that the canopy precision automation method extracted in the dense forest area, segmentation accuracy is 79.59%, F measure reached 79.00%, and can accurately provide individual tree crown information, it has a certain practical significance of the development of forestry economic survey technology.

Key words: the extraction of individual tree canopy, Gabor filter, PCA, K-means clustering, marker-controlled watershed

施慧慧, 王妮, 滕文秀, 刘玉婵. 结合Gabor小波和形态学的高分辨率图像树冠提取方法[J]. 地球信息科学学报, 2019, 21(2): 249-258.DOI:10.12082/dqxxkx.2019.180280

Huihui SHI, Ni WANG, Wenxiu TENG, Yuchan LIU. Tree Canopy Extraction Method of High Resolution Image based on Gabor Filter and Morphology[J]. Journal of Geo-information Science, 2019, 21(2): 249-258.DOI:10.12082/dqxxkx.2019.180280

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表1

参考文献 22

[1]	王平,周忠发,殷超.基于全极化SAR与多光谱的喀斯特山区农村林地提取[J].中国农业资源与区划,2017,38(7):41-50. doi: 10.7621/cjarrp.1005-9121.20170707
	[ Wang P, Zhou Z F, Yin C.Rural woodland extraction based on full polarization SAR and multispectral in karst mountain areas[J]. Chinese Journal of Agricultural Resources and Regional Planning, 2017,38(7):41-50. ] doi: 10.7621/cjarrp.1005-9121.20170707
[2]	周艳飞,张绘芳,李霞,等.基于高分辨遥感数据的胡杨与柽柳树冠提取[J].遥感技术与应用,2015,30(3):510-517. doi: 10.11873/j.issn.1004-0323.2015.3.0510
	[ Zhou Y F, Zhang H F, Li X, et al.Extraction of tree-crown of populous Euphratica and Tamarix Ramosissima based on high resolution remote sensing data[J]. Remote Sensing Technology and Application, 2015,30(3):510-517. ] doi: 10.11873/j.issn.1004-0323.2015.3.0510
[3]	李丹,柯樱海,宫辉力,等.基于高分辨率遥感影像的城市典型乔木树种分类研究[J].地理与地理信息科学,2016,32(1):84-89,127. doi: 10.3969/j.issn.1672-0504.2016.01.016
	[ Li D, Ke Y H, Gong H L, et al.Urban tree species classification with machine learning classifier using WorldView-2 imagery[J]. Geography and Geo-information Science, 2016,32(1):84-89,127. ] doi: 10.3969/j.issn.1672-0504.2016.01.016
[4]	Colgeon F A.A crown-following approach to the automatic delineation of individual tree crowns in high spatial resolution aerial images[J]. Canadian Journal of Remote Sensing, 1995,21(3):274-284. doi: 10.1080/07038992.1995.10874622
[5]	Pollock R J.The automatic recognition of individual trees in aerial images of forests based on a synthetic tree crown image model[D]. Vancouver: The University of British Colombia, 1996.
[6]	冯静静,张晓丽,刘会玲.基于灰度梯度图像分割的单木树冠提取研究[J].北京林业大学学报,2017,39(3):16-23. doi: 10.13332/j.1000--1522.20160373
	[ Feng J J, Zhang X L, Liu H L.Single tree crown extraction based on gray gradient image segmentation[J]. Journal of Beijing Forestry University, 2017,39(3):16-23. ] doi: 10.13332/j.1000--1522.20160373
[7]	张凝,张晓丽,叶栗.基于改进爬峰法高分辨率遥感影像分割的树冠提取[J].农业机械学报,2014,45(12):294-300. doi: 10.6041/j.issn.1000-1298.2014.12.042
	[ Zhang N, Zhang X L, Ye S.Tree crown extraction based on segmentation of high-resolution remote sensing image improved Peak-climbing algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery, 2014,45(12):294-300. ] doi: 10.6041/j.issn.1000-1298.2014.12.042
[8]	刘晓双,黄建文,胡红波.高空间分辨率遥感的单木树冠自动提取方法与应用[J].浙江林学院学报,2010,27(1):126-133. doi: 10.3969/j.issn.2095-0756.2010.01.021
	[ Liu X S, Huang J W, Hu H B.Research progress in the methods and applications of individual tree crown's automatic extraction by high spatial resolution remote sensing[J]. Journal of Zhejiang Forestry College, 2010,27(1):126-133. ] doi: 10.3969/j.issn.2095-0756.2010.01.021
[9]	崔少伟. 基于高分辨率遥感数据单木树冠提取研究[D].哈尔滨:东北林业大学,2011.
	[ Cui S W.Extraction research single tree crown based on high resolution remote sensing data[D]. Harbin: Northeast Forestry University, 2011. ]
[10]	郭昱杉,刘庆生,刘高焕,等.基于标记控制分水岭分割方法的高分辨率遥感影像单木树冠提取[J].地球信息科学学报,2016,18(9):1259-1266. doi: 10.3724/SP.J.1047.2016.01259
	[ Guo Y S, Liu Q S, Liu G H, et al.Individual tree crown extraction of high resolution image based on marker-controlled watershed segmentation method[J]. Journal of Geo-information Science, 2016,18(9):1259-1266. ] doi: 10.3724/SP.J.1047.2016.01259
[11]	Yang J, He Y, Caspersen J P, et al.Delineating individual tree crowns in an uneven-aged, mixed broadleaf forest using multispectral watershed segmentation and multiscale fitting[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2016,10(4):1390-1401. doi: 10.1109/JSTARS.2016.2638822
[12]	滕文秀,温小荣,王妮,等.迭代H-Minima改进分水岭的高分影像单木树冠提取[J].激光与光电子学进展,2018,55(12):122802.
	[ Teng W X, Wen X R, W N, et al. Iterative H-Minima improved watershed method for individual tree crown delineation in high spatial-resolution remote sensing image[J]. Laser & Optoelectronics Progress, 2018,55(12):122802. ]
[13]	Huang H, Li X, Chen C.Individual tree crown detection and delineation from very-high-resolution UAV images based on bias field and marker-controlled watershed segmentation algorithms[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2018,11(7):2253-2262. doi: 10.1109/JSTARS.2018.2830410
[14]	甄贞,李响,修思玉,等.基于标记控制区域生长法的单木树冠提取[J].东北林业大学学报,2016,44(10):22-29.
	[ Zhen Z, Li X, Xiu S Y, et al.Individual tree crown delineation using maker-controlled region growing method[J].Journal of Beijing Forestry University, 2016,44(10):22-29. ]
[15]	吴见,王帅帅,谭靖.基于改进分割算法的退耕地树冠信息提取[J].南京林业大学学报(自然科学版),2016,40(2):167-172. doi: 10.3969/j.issn.1000-2006.2016.02.028
	[ Wu J, Wang S S, Tan J.Tree-crown information extraction in returning farmland to forest land based on improved segmentation algorithm[J]. Journal of Nanjing Forestry University (Natural Sciences Edition), 2016,40(2):167-172. ] doi: 10.3969/j.issn.1000-2006.2016.02.028
[16]	姜仁荣,汪春燕,沈利强,等.基于高分辨率遥感图像的荔枝林树冠信息提取方法研究[J].农业机械学报,2016,47(9):17-22. doi: 10.6041/j.issn.1000-1298.2016.09.003
	[ Jiang R R, Wang C Y, Shen L Q, et al.A method for lichee's tree-crown information extraction based on high spatial resolution image[J]. Transactions of the Chinese Society for Agricultural Machinery, 2016,47(9):17-22. ] doi: 10.6041/j.issn.1000-1298.2016.09.003
[17]	Jing L, Hu B, Noland T, et al.An individual tree crown delineation method based on multi-scale segmentation of imagery[J]. Isprs Journal of Photogrammetry & Remote Sensing, 2012,70(3):88-98. doi: 10.1016/j.isprsjprs.2012.04.003
[18]
[19]	赵洪伟,谢永芳,曹斌芳,等.基于Gabor小波和LPP的浮选过程泡沫纹理特征提取及应用[J].上海交通大学学报,2014,48(7):942-947.
	[ Zhao H W, Xie Y F, Cao B F, et al.Extraction and application of forth texture feature based on Gabor wavelets and LPP in flotation process[J]. Journal of Shanghai Jiaotong University, 2014,48(7):942-947. ]
[20]	杨信廷,孙文娟,李明,等.基于K均值聚类和开闭交替滤波的黄瓜叶片水滴荧光图像分割[J].农业工程学报,2016(17):136-143. doi: 10.11975/j.issn.1002-6819.2016.17.019
	[ Yang X T, Sun W J, Li M, et al.Water droplets fluorescence image segmentation of cucumber leaves based on K-means clustering with opening and closing alternately filtering[J]. Transactions of the Chinese Society of Agricultural Engineering,2016(17):136-143. ] doi: 10.11975/j.issn.1002-6819.2016.17.019
[21]	赵红丹,田喜平.基于K-means算法分割遥感图像的阈值确定方法研究[J].科学技术与工程,2017,17(9):250-254.
	[ Zhao H D, Tian X P.Based on K-means algorithm of remote sensing image threshold segmentation method for determining the research[J]. Science Technology and Engineering, 2017,17(9):250-254. ]
[22]	卜帆,石玉立.机载LiDAR高差和高分影像的城市树冠提取比较[J].遥感技术与应用,2017,32(5):875-882. doi: 10.11873/j.issn.1004-0323.2017.5.0875
	[ Bu F, Shi Y L.The comparison of urban tree crown extraction based on airborne LiDAR elevation difference and high resolution imagery[J]. Remote Sensing Technology and Application, 2017,32(5):875-882. ] doi: 10.11873/j.issn.1004-0323.2017.5.0875

结合Gabor小波和形态学的高分辨率图像树冠提取方法

Tree Canopy Extraction Method of High Resolution Image based on Gabor Filter and Morphology

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 12

参考文献 22

相关文章 8

Metrics

本文评价

推荐阅读 0

[1]	李雨欣, 王瑛, 马庆媛, 刘天雪, 司丽丽, 俞海洋. 基于DTW与K-means算法的河北场雨及雨型分区特征研究[J]. 地球信息科学学报, 2021, 23(5): 860-868.
[2]	罗耀文, 任周鹏, 葛咏, 韩李涛, 刘梦晓, 何亚文. 基于PCA-GWR方法的村级贫困时空格局及致贫因素分析[J]. 地球信息科学学报, 2020, 22(2): 231-245.
[3]	何惠馨, 范俊甫, 陈文贺, 周玉科, 张鹏, 俞宵. 基于亮度补偿的遥感影像阴影遮挡道路提取方法[J]. 地球信息科学学报, 2020, 22(2): 258-267.
[4]	王法溧,何晓宇,方泽兴,魏显虎,叶虎平,施令飞. 基于长时间序列遥感数据的阿伯德尔国家公园生态环境质量评价[J]. 地球信息科学学报, 2019, 21(9): 1479-1479.
[5]	林金煌, 张岸, 邓超, 陈文惠, 梁春阳. 闽三角城市群地质灾害敏感性评价[J]. 地球信息科学学报, 2018, 20(9): 1286-1297.
[6]	李沛婷, 赵庆展, 陈洪. 回波强度约束下的无人机LiDAR点云K-means聚类滤波[J]. 地球信息科学学报, 2018, 20(4): 471-479.
[7]	王飞, 丁建丽, 魏阳. “一带一路”国家和地区百年尺度干旱化特征分析[J]. 地球信息科学学报, 2017, 19(11): 1442-1455.
[8]	冯美臣, 牛波, 杨武德, 肖璐洁. 晋中地区荞麦品质气候区划的GIS多元分析[J]. 地球信息科学学报, 2012, 14(6): 807-813.

算法	匹配	接近匹配	漏分	合并	错分	目视解译
标记控制分水岭	66	12	5	57	5	199
本文算法	137	19	11	36	4	199