Single tree crown extraction based on gray gradient image segmentation

FENG Jing-jing; ZHANG Xiao-li; LIU Hui-ling.

doi:10.13332/j.1000-1522.20160373

Journal of Beijing Forestry University > 2017 > 39(3): 16-23. > DOI: 10.13332/j.1000-1522.20160373

FENG Jing-jing, ZHANG Xiao-li, LIU Hui-ling.. 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

Citation:

PDF (1335 KB)

Single tree crown extraction based on gray gradient image segmentation

College of Forestry, Key Laboratory of Precision Forestry, Provincial Key Laboratory of Forest Cultivation and Conservation, Beijing Forestry University, Beijing, 100083, P. R. China.

More Information

Received Date: November 15, 2016
Published Date: March 30, 2017

Graphical Abstract

Abstract

Abstract

Tree crown is an important part of trees. It is of significance to extract tree crown information based on remotely sensed images for forest resource inventory and monitoring. However, it’s difficult to extract the individual tree crown shape accurately. High spatial resolution image has an abundance of texture and spectral information, which provides a potentially efficient approach to delineate individual tree crown for forest resource inventory. However, with its abundance of information, the object-oriented image segmentation based on the original high resolution image has lower efficiency because of the large calculation and poor robustness since it needs setting spectrum or texture threshold manually. The method of image enhancement highlights or suppresses certain image features selectively by changing the image structure, so effective image enhancement can improve the accuracy and efficiency of the individual tree crown segmentation. In this article, a new gray-gradient image segmentation method was proposed to realize rapid and high accurate extraction of the individual tree crown. For the comparative analyses, we selected conventional Roberts and Laplacian operator, along with the proposed modified mathematical morphology operator as alternatives, subsequently, it was confirmed that the optimal operator was the modified mathematical morphology operator by combining visual interpretation and gradation histogram analysis. Furthermore, the modified mathematical morphology operator combined with object-oriented multiscale segmentation classification method was used for simplifying background information of raw image and extracting large-scaled single-tree crown information rapidly. To validate the efficiency of the method, CCD image of airborne laser radar in Dayekou forest region in Zhangye, Gansu Province of northwestern China was used to extract individual tree crown. The results showed that by using high spatial resolution gray gradient images, the location accuracy of tree crown was 83.19%, and the shape accuracy of crown was 88.62%, both of which were superior to the individual tree crown segmentation based on the original high spatial resolution image. The crown edges are drawn fast, efficiently and relatively accurate.
- crown width,
- mathematical morphology,
- object-oriented,
- multi-resolution segmentation

FullText(HTML)

References (32)

References

[1]	曹林,佘光辉.激光雷达技术估测森林生物量的研究现状及展望[J]. 南京林业大学学报(自然科学版),2013,41(3):163-169.
[1]	CAO L,SHE G H. Optimized extraction of forest parameters in subtropical forests based on airborne LiDAR technology [J].Journal of Nanjing Forestry University (Natural Sciences), 2013,41(3):163-169.
[2]	ZHANG H,WANG X R. Three-dimensional ecological characters of urban green space and its ecological function [J]. China Environmental Science,2001,21(2):101-104.
[2]	张浩,王祥荣.城市绿地的三维生态特征及其生态功能[J].中国环境科学,2001,21(2):101-104.
[3]	TIAN F,LI M Y,GE S, et al. GIS-based analysis of soundscape spatical pattern in Zijin Mountain National Forest Park[J]. Journal of Nanjing Forestry University (Natural Sciences), 2014,42(6):87-92.
[3]	田方,李明阳,葛飒,等. 基于GIS的紫金山国家森林公园声景观空间格局研究[J]. 南京林业大学学报(自然科学版),2014,42(6):87-92.
[4]	ZHANG H, WANG H Q, SUN X. Tree crown extraction combining color and texture feature [J]. Optical Technique, 2008,34(4):613-616.
[4]	张慧,王宏琦,孙显. 结合颜色和纹理特这的树冠提取方法 [J].光学技术,2008,34(4):613-616.
[5]	付尧,王新杰,孙玉军,等. 树冠提取技术研究进展[J]. 世界林业研究,2013(4):38-42.
[5]	FU Y,WANG X J, SUN Y J,et al. A study of tree crown information extraction method[J]. World Forestry Research,2013(4):38-42.
[6]	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,1996:172.
[6]	LIU X S,HUANG J W,JU 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.
[7]	HUANG J W, JU H B, ZHAO F, et al .Research on monitoring survival rate and growth condition of farmland returned to forests using remote sensing data[J].Journal of Remote Sensing,2007,11(6):899-905.
[7]	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):274-282.
[8]	BRANDTBERG T,WALTER F.Automated delineation of individual tree crowns in high spatial resolution aerial images by multiple-scale analysis[J].Machine Vision and Applications,1998,11(1):64-73.
[8]	WAN L,CHEN P C. Algorithm of image contrast enhancement based on mathematical norphology[J]. Modern Electronic Technology,2009(13):131-133.
[9]	CHEN S H, FU L X. Practical digital image processing[M]. Beijing: Science Press, 2005.
[9]	刘晓双,黄建文,鞠洪波.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.
[10]	LI B C, PENG T Q, PENG B,et al. Intelligent image processing technology[M]. Beijing:Electronics Industry Publishing House,2004.
[10]	黄建文,鞠洪波,赵峰,等. 利用遥感进行退耕还林成活率及长势监测方法的研究[J]. 遥感学报,2007,11(6):899-905.
[11]	CUI Y. Image processing and analysis method of mathematical morphology and application [M]. Beijing: Science Press, 2001.
[11]	万丽,陈普春. 一种基于数学形态学的图像对比度增强算法[J].现代电子技术,2009(13):131-133.
[12]	HE H Y. Multi-scale segmentation of object oriented high resolution image[D]. Wuhan:Huazhong University of Science and Technology,2013.
[12]	陈书海,傅录祥.实用数字图像处理[M].北京:科学出版社,2005.
[13]	李弼程,彭天强,彭波,等.智能图像处理技术[M]. 北京:电子工业出版社,2004.
[13]	SUN Y X.Object-oriented high image optimal cut and application scale method[J]. Heilongjiang Science and Technology Information,2003(24):93-94.
[14]	ZHANG N,FENG Y W, ZHANG X L,et al. Extracting individual tree crown by combining spectral and texture features from aerial images[J].Journal of Beijing Forestry University,2015,37(3):13-19.
[14]	GONZALES R C, WOODS R E.Digital image processing[M]. Beijing :Publishing House of Electronics Industry,2003.
[15]	崔屹.图像处理及分析-数学形态学方法及应用 [M].北京:科学出版, 2001.
[16]	贺洪元. 面向对象高分辨率影像多尺度分割[D].武汉:华中科技大学,2013.
[17]	孙燕霞. 面向对象的高分影像最优分割尺度方法的研究与应用[J]. 黑龙江科技信息,2013(24):93-94.
[18]	张凝,冯跃文,张晓丽,等.结合航空影像纹理和光谱特征的单木冠幅提取[J].北京林业大学学报,2015,37(3):13-19.

[1]	Fan Yinglong, Tang Sainan, Tan Bingxiang. Forest cover change detection based on multi-scale segmentation and tasseled cap transformation over plateau area[J]. Journal of Beijing Forestry University, 2023, 45(4): 60-69. DOI: 10.12171/j.1000-1522.20220375
[2]	Liu Xiaoshuang, Li Caiwen, Zhao Yibing. Rapid detection of object-level invaded forest map patch based on high spatial resolution time series image[J]. Journal of Beijing Forestry University, 2022, 44(11): 60-69. DOI: 10.12171/j.1000-1522.20210261
[3]	Wu Yanshuang, Zhang Xiaoli. Object-oriented tree species classification with multi-scale texture features based on airborne hyperspectral images[J]. Journal of Beijing Forestry University, 2020, 42(6): 91-101. DOI: 10.12171/j.1000-1522.20190155
[4]	Zhu Fangyan, Shen Wenjuan, Li Mingshi. Object-oriented multi-index integrated vegetation change analysis based on WorldView2 and GF-2[J]. Journal of Beijing Forestry University, 2019, 41(11): 54-65. DOI: 10.13332/j.1000-1522.20180435
[5]	Wang Xiaosong, Yang Gang. A multi-objective optimization segmentation method for tree image based on fusion clustering and classification algorithm[J]. Journal of Beijing Forestry University, 2018, 40(12): 124-131. DOI: 10.13332/j.1000-1522.20180160
[6]	Chen Jidai, Niu Shukui. Classification and change analysis of forest fuels by multi-temporal high resolution remote sensing images[J]. Journal of Beijing Forestry University, 2018, 40(12): 38-48. DOI: 10.13332/j.1000-1522.20180269
[7]	Zhu Jiyou, Xu Chengyang, Wu Ju. Fast estimation of stomatal density and stomatal area of plant leaves based on eCognition[J]. Journal of Beijing Forestry University, 2018, 40(5): 37-45. DOI: 10.13332/j.1000-1522.20170412
[8]	FENG Jing-jing, ZHANG Xiao-li, LIU Hui-ling. 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
[9]	ZHANG Juan, HAN Dian-yuan, HUANG Xin-yuan. Image segmentation of Prunus mume flower under natural background.[J]. Journal of Beijing Forestry University, 2012, 34(3): 64-70.
[10]	QI Heng-nian, CHEN Feng-nong, FANG Lu-ming, MA Ling-fei. A method for wood pore image segmentation based on mathematical morphology.[J]. Journal of Beijing Forestry University, 2008, 30(4): 12-16.

Cited By

Cited by

Periodical cited type(29)

1.	胥东海，杨旸谷. 基于无人机遥感影像的单木冠幅提取研究. 中南林业调查规划. 2024(02): 36-40 .
2.	赵各进，孙梦莲，宋贤芬，郝振帮，李明慧，武红梅，刘健，余坤勇. 无人机可见光遥感木麻黄人工林株数提取方法比较研究. 西南林业大学学报(自然科学). 2023(03): 127-135 .
3.	周小成，王佩，谭芳林，陈崇成，黄洪宇，林宇. 基于多时相无人机影像的高郁闭度森林采伐生物量估算. 农业机械学报. 2023(06): 168-177 .
4.	曹明兰，李亚昆，张力小，武俊喜，李亚东. 深度学习在无人机遥感城市行道树提取中的应用. 中南林业科技大学学报. 2023(06): 79-84+115 .
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. 地球信息科学学报. 2023(12): 2387-2401 .
6.	周辰琴，余拥军，方陆明，刘雨真，胡建锦. 飞行高度与郁闭度对水杉冠幅提取影响的研究. 林业资源管理. 2022(01): 150-156 .
7.	奚祥书，夏凯，杨垠晖，杜晓晨，冯海林 . 结合多光谱影像降维与深度学习的城市单木树冠检测. 遥感学报. 2022(04): 711-721 .
8.	张玉薇，陈棋，田湘云，史小蓉，张超. 基于UAV可见光遥感的单木冠幅提取研究. 西部林业科学. 2022(03): 49-59 .
9.	谢运鸿，荆雪慧，孙钊，丁志丹，李睿，李豪伟，孙玉军. 基于实例分割的高郁闭度林分单木树冠无人机遥感提取. 林业科学研究. 2022(05): 14-21 .
10.	邱琳，刘敏，王磊. 基于多尺度光谱角制图的遥感影像单木树冠提取方法. 安徽农业科学. 2022(21): 119-125 .
11.	郭旭展，陈巧，张晓芳，洪亮，尤媛媛，唐守正，符利勇. 基于无人机高分辨率影像的油松新造林健康树冠提取. 林业科学. 2022(10): 111-120 .
12.	仝真，徐爱俊. 基于改进ResNet-UNet的立木图像分割方法. 中南林业科技大学学报. 2021(01): 132-139 .
13.	杨雪峰，昝梅，木尼热·买买提. 基于无人机的胡杨（Populus euphratica）结构参数获取技术研究. 干旱区地理. 2021(02): 441-449 .
14.	张玉薇，张超，王娟，李华玉，白明雄，杨安蓉. 基于UAV遥感的单木冠幅提取及胸径估算模型研究. 林业资源管理. 2021(03): 67-75 .
15.	杨全月，董泽宇，马振宇，吴悠，崔琪，卢昊. 基于SfM的针叶林无人机影像树冠分割算法. 农业机械学报. 2020(06): 181-190 .
16.	曾霞辉，王颖，曾掌权，周璀. 无人机影像树冠信息提取研究. 中南林业科技大学学报. 2020(08): 75-82 .
17.	李文静，王瑞瑞，石伟，苏婷婷. 基于无人机多光谱影像的单木树冠提取方法. 福建农林大学学报(自然科学版). 2020(05): 639-645 .
18.	李波，弋玮玮. 三维运动图像多参考帧边缘差异动态分割仿真. 计算机仿真. 2020(06): 365-368+373 .
19.	孙钊，潘磊，孙玉军. 基于无人机影像的高郁闭度杉木纯林树冠参数提取. 北京林业大学学报. 2020(10): 20-26 . 本站查看
20.	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. 地球信息科学学报. 2019(02): 249-258 .
21.	张怡卓，梁玉亮，王小虎，于慧伶. 一种基于K-means与Close-Form融合的树木图像提取方法. 西北林学院学报. 2019(02): 240-245 .
22.	曾健，张晓丽，周雪梅，尹田. 倾斜摄影测量技术提取落叶松人工林地形信息. 北京林业大学学报. 2019(08): 1-12 . 本站查看
23.	李明华，陈雨竹，周淑芳，肖舜祯. 运用分水岭算法对航片数据的单木信息提取与识别. 东北林业大学学报. 2019(09): 58-62+70 .
24.	孙振峰，张晓丽，李霓雯. 机载与星载高分遥感影像单木树冠分割方法和适宜性对比. 北京林业大学学报. 2019(11): 66-75 . 本站查看
25.	李越帅，郑宏伟，罗格平，杨辽，王伟胜，桂东伟. 集成U-Net方法的无人机影像胡杨树冠提取和计数. 遥感技术与应用. 2019(05): 939-949 .
26.	陈宗铸，杨琦，雷金睿，陈小花，李苑菱. 基于激光雷达数据的森林数据分析与处理系统的设计与实现. 热带林业. 2018(01): 61-66 .
27.	陈宗铸，杨琦，雷金睿，陈小花，李苑菱. 基于激光雷达数据的热带森林冠高模型生成及平均树高估计. 中南林业科技大学学报. 2018(07): 1-7 .
28.	杨婷婷，管昉立，徐爱俊. 基于Graph Cut算法的多株立木轮廓提取方法. 南京林业大学学报(自然科学版). 2018(06): 91-98 .
29.	王上上，王军，孙思. 无人机遥感技术对园林树木的计数统计. 仲恺农业工程学院学报. 2017(03): 37-42 .

Other cited types(25)

Get Citation

PDF

XML

Article views (1753) PDF downloads (45) Cited by(54)

Turn off MathJax

Article Contents

Abstract

References

Single tree crown extraction based on gray gradient image segmentation

Abstract

References

Related Articles

Cited by

Periodical cited type(29)

Other cited types(25)

Catalog

Single tree crown extraction based on gray gradient image segmentation

Abstract

References

Related Articles

Cited by

Periodical cited type(29)

Other cited types(25)

Catalog

Export File

Citation

Format

Content