Locating individual tree from high resolution satellite images based on CV model

doi:10.12302/j.issn.1000-2006.202102020

JOURNAL OF NANJING FORESTRY UNIVERSITY ›› 2022, Vol. 46 ›› Issue (5): 143-151.doi: 10.12302/j.issn.1000-2006.202102020

Previous Articles Next Articles

Locating individual tree from high resolution satellite images based on CV model

CHENG Xiaofei(), WU Gang()

School of Information Science & Technology,Beijing Forestry University, Beijing 100089, China

Received:2021-02-26 Revised:2022-04-12 Online:2022-09-30 Published:2022-10-19
Contact: WU Gang E-mail:1010067465@qq.com;wugang@bjfu.edu.cn

Abstract

Abstract:

【Objective】Traditional forest resources surveys take sub-compartments as a unit, and use sampling or a census to obtain tree information. High resolution remote sensing images can be used to improve forest resource surveys from stand accuracy to the individual tree level, as well as extracting individual tree information such as the individual tree position, structural parameters and tree species. An individual tree database can then be established to implement intensive management for individual trees. This is of considerable importance in achieving precision forestry, and especially the sustainable management of urban trees. In recent years, research on individual tree locations based on remote sensing images has increased. However, the use of traditional methods can lead to missing and misjudging individual crown and the overlapping crown area.【Method】This paper attempts to apply a method based on a Chan-Vase (CV) model for individual tree localization. The forest area is first extracted based on the greenness segmentation, so that the individual tree localization algorithm only works on the tree area. The Gaussian filtering method is then used to reduce the noise generated during the process of image formation and to enhance the difference between the canopy and non-canopy. The local maximum region is extracted by combining the morphological features of the tree crown and its image spectral features, and the connected region is searched and marked. The CV model is then used to construct the level set function, and the initial contour line is iterated to obtain the individual tree crown contour. Finally, the individual tree location information is calculated. Seven high-resolution satellite images of different forest types including coniferous forest, broad-leaved forest, economic forest, and non-forest stands were selected successively for this paper. This was based on visual interpretation data as a reference, and compared with the traditional individual tree positioning method for experimental analysis.【Result】Compared with traditional methods such as the gradient watershed method, the marker watershed method, and the local maximum method, the individual tree location method based on the CV model has a higher matching rate with an average improvement of nearly 23%.【Conclusion】By automatically setting the initial contour, this research method solves the problem that CV model often use interactive or manual settings for the initial contour position. This is inefficient and leads to considerable differences in the results. It can also better deal with the joint and overlap conditions of the tree crowns and has a better positioning effect with strong application potential.

Key words: Chan-Vase (CV) model, individual tree location, high resolution satellite image, individual tree crown extraction

CLC Number:

TP751
S758

CHENG Xiaofei, WU Gang. Locating individual tree from high resolution satellite images based on CV model[J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2022, 46(5): 143-151.

Figures/Tables 7

Table 1

Fig.1

Fig.2

Fig.3

Table 2

Table 3

Fig.4

References 44

[1]	周杨杨, 冯仲科, 陈世林. 我国面向森林资源管理的监测体系创新研究[J]. 世界林业研究, 2020, 33(2):83-89.
	ZHOU Y Y, FENG Z K, CHEN S L. Innovative research on forest resource management monitoring system of in China[J]. World For Res, 2020, 33(2):83-89.DOI:10.13348/j.cnki.sjlyyj.2019.0123.y.
[2]	LIEW S C, HUANG X, LIN E S, et al. Integration of tree database derived from satellite imagery and lidar point cloud data[J]. Int Arch Photogramm Remote Sens Spatial Inf Sci, 2018, XLII-4/W10:105-111.DOI:10.5194/isprs-archives-xlii-4-w10-105-2018.
[3]	GOMES M F, MAILLARD P, DENG H W. Individual tree crown detection in sub-meter satellite imagery using marked point processes and a geometrical-optical model[J]. Remote Sens Environ, 2018, 211:184-195.DOI:10.1016/j.rse.2018.04.002.
[4]	NEVALAINEN O, HONKAVAARA E, TUOMINEN S, et al. Individual tree detection and classification with UAV-based photogrammetric point clouds and hyperspectral imaging[J]. Remote Sens, 2017, 9(3):185.DOI:10.3390/rs9030185.
[5]	戴晓军. 广东省古树名木信息管理系统正式启用[J]. 国土绿化, 2017(6):55.
	DAI X J. Guangdong ancient and famous trees information management system was officially launched[J]. Land Green, 2017(6):55.
[6]	丁天茼, 何建勇. 北京编制首张“雌株密度图” 精准施策治理杨柳飞絮[J]. 绿化与生活, 2019(5):21-22.
	DING T T, HE J Y. Compile the first “Female Plant Density Map” in Beijing,and apply precise measures to control willow catkins[J]. Green Life, 2019(5):21-22.
[7]	TOTH C, JÓZKÓW G. Remote sensing platforms and sensors:a survey[J]. ISPRS J Photogramm Remote Sens, 2016, 115:22-36.DOI:10.1016/j.isprsjprs.2015.10.004.
[8]	BOUVIER M, DURRIEU S, FOURNIER R A, et al. Generalizing predictive models of forest inventory attributes using an area-based approach with airborne LiDAR data[J]. Remote Sens Environ, 2015, 156:322-334.DOI:10.1016/j.rse.2014.10.004.
[9]	WULDER M, NIEMANN K O, GOODENOUGH D G. Local maximum filtering for the extraction of tree locations and basal area from high spatial resolution imagery[J]. Remote Sens Environ, 2000, 73(1):103-114.DOI:10.1016/S0034-4257(00)00101-2.
[10]	PICOS J, BASTOS G, MÍGUEZ D, et al. Individual tree detection in a Eucalyptus plantation using unmanned aerial vehicle (UAV)-LiDAR[J]. Remote Sens, 2020, 12(5):885.DOI:10.3390/rs12050885.
[11]	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[J]. 北京林业大学学报, 2019, 41(11):66-75.
	SUN Z F, ZHANG X L, LI N W. Comparison of individual tree crown extraction method and suitability of airborne and spaceborne high-resolution remote sensing images[J]. J Beijing For Univ, 2019, 41(11):66-75.DOI:10.13332/j.1000-1522.20180446.
[12]	刘会玲, 张晓丽, 张莹, 等. 机载激光雷达单木识别研究进展[J]. 激光与光电子学进展, 2018, 55(8):40-48.
	LIU H L, ZHANG X L, ZHANG Y, et al. Review on individual tree detection based on airborne LiDAR[J]. Laser Optoelectron Prog, 2018, 55(8):40-48.DOI:10.3788/LOP55.082805.
[13]	LARSEN M, ERIKSSON M, DESCOMBES X, et al. Comparison of six individual tree crown detection algorithms evaluated under varying forest conditions[J]. Int J Remote Sens, 2011, 32(20):5827-5852.DOI:10.1080/01431161.2010.507790.
[14]	柯樱海, 李小娟, 宫辉力. 遥感技术在自动化森林资源清查中的应用研究[M]. 北京: 中国环境出版社, 2015:1-17
	KE Y H, LI X J, GONG H L. Research on the application of remote sensing technology in automated inventory of forest resources[M]. Beijing: China Environmental Science Press, 2015:1-17.
[15]	甄贞, 赵颖慧. 单木树冠遥感法提取原理与技术[M]. 北京: 科学出版社, 2017:2-65.
	ZHEN Z, ZHAO Y H. Principle and technology of remote sensing extraction of single tree crown[M]. Beijing: Science Press, 2017:2-65.
[16]	WANG L, GONG P, BIGING G S. Individual tree-crown delineation and treetop detection in high-spatial-resolution aerial imagery[J]. Photogramm Eng Remote Sensing, 2004, 70(3):351-357.DOI:10.14358/pers.70.3.351.
[17]	郑鑫, 王瑞瑞, 靳茗茗. 基于形态学阈值标记分水岭算法的高分辨率影像单木树冠提取[J]. 中南林业调查规划, 2017, 36(4):30-35,57.
	ZHENG X, WANG R R, JIN M M. Extraction of high-resolution images of single tree crown based on watershed algorithm with morphological threshold mark[J]. Central South For Invent Plan, 2017, 36(4):30-35,57.DOI:10.16166/j.cnki.cn43-1095.2017.04.008.
[18]	GOUGEON F. A crown-following approach to the automatic delineation of individual tree crowns in high spatial resolution aerial images[J]. Can J Remote Sens, 1995, 21(3):274-284.DOI:10.1080/07038992.1995.10874622.
[19]	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.
	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]. Trans Chin Soc Agric Mach, 2016, 47(9):17-22.DOI:10.6041/j.issn.1000-1298.2016.09.003.
[20]	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.
	ZHANG N, ZHANG X L, YE L. Tree crown extraction based on segmentation of high-resolution remote sensing image improved peak-climbing algorithm[J]. Trans Chin Soc Agric Mach, 2014, 45(12):294-300.DOI:10.6041/j.issn.1000-1298.2014.12.042.
[21]	董天阳, 周棋正. 基于形态Snake模型的遥感影像的单木树冠检测算法[J]. 计算机科学, 2018, 45(S2):269-273,291.
	DONG T Y, ZHOU Q Z. Single tree detection in remote sensing images based on morphological snake model[J]. Comput Sci, 2018, 45(S2):269-273,291.
[22]	刘玉锋, 潘英, 李虎. 基于高空间分辨率遥感数据的天山云杉树冠信息提取研究[J]. 国土资源遥感, 2019, 31(4):112-119.
	LIU Y F, PAN Y, LI H. Study of crown information extraction of Picea schrenkiana var.tianschanica based on high-resolution satellite remote sensing data[J]. Remote Sens Land Resour, 2019, 31(4):112-119.DOI:10.6046/gtzyyg.2019.04.15.
[23]	DONG T Y, SHEN Y Q, ZHANG J, et al. Progressive cascaded convolutional neural networks for single tree detection with google earth imagery[J]. Remote Sens, 2019, 11(15):1786.DOI:10.3390/rs11151786.
[24]	邓广. 高空间分辨率遥感影像单株立木识别与树冠分割算法研究[D]. 北京: 中国林业科学研究院, 2009.
	DENG G. Research on individual tree identification and crown segmentation algorithm in high spatial resolution remote sensing imagery[D]. Beijing: Chinese Academy of Forestry, 2009.
[25]	李明华, 陈雨竹, 周淑芳, 等. 运用分水岭算法对航片数据的单木信息提取与识别[J]. 东北林业大学学报, 2019, 47(9):58-62,70.
	LI M H, CHEN Y Z, ZHOU S F, et al. Extraction and recognition of individual tree information on aerial image data used watershed algorithm[J]. J Northeast For Univ, 2019, 47(9):58-62,70.DOI:10.13759/j.cnki.dlxb.2019.09.011.
[26]	滕文秀, 温小荣, 王妮, 等. 基于迭代H-minima改进分水岭算法的高分辨率遥感影像单木树冠提取[J]. 激光与光电子学进展, 2018, 55(12):499-507.
	TENG W X, WEN X R, WANG N, et al. Individual tree crown extraction in high resolution remote sensing image based on iterative H-minima improved watershed algorithm[J]. Laser Optoelectron Prog, 2018, 55(12):499-507.DOI:10.3788/LOP55.122802.
[27]	YANG J, HE Y H, 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 J Sel Top Appl Earth Obs Remote Sens, 2017, 10(4):1390-1401.DOI:10.1109/JSTARS.2016.2638822.
[28]	CHAN T F, VESE L A. Active contours without edges[J]. IEEE Trans Image Process, 2001, 10(2):266-277.DOI:10.1109/83.902291.
[29]	张开华. 主动轮廓模型在图像分割中的应用研究[D]. 合肥: 中国科学技术大学, 2009.
	ZHANG K H. Research on application of active contour model in image segmentation[D]. Hefei: University of Science and Technology of China, 2009.
[30]	王芳梅, 范虹, WANG Y. 利用改进CV模型连续水平集算法的核磁共振乳腺图像分割[J]. 西安交通大学学报, 2014, 48(2):38-43.
	WANG F M, FAN H, WANG Y. Continuous level set algorithm based on improved CV model for magnetic resonance breast image segmentation[J]. J Xi’an Jiaotong Univ, 2014, 48(2):38-43.DOI:10.7652/xjtuxb201402007.
[31]	耿楠, 于伟, 宁纪锋. 基于水平集和先验信息的农业图像分割方法[J]. 农业机械学报, 2011, 42(9):167-172.
	GENG N, YU W, NING J F. Segmentation of agricultural images using level set and prior information[J]. Trans Chin Soc Agric Mach, 2011, 42(9):167-172.DOI:10.3969/j.issn.1000-1298.
[32]	白明月, 薛河儒, 姜新华, 等. 改进C-V模型在YCbCr空间下的羊体图像分割[J]. 中国农业大学学报, 2018, 23(10):137-143.
	BAI M Y, XUE H R, JIANG X H, et al. Sheep image segmentation by an improved Chan-Vese model in YCbCr space[J]. J China Agric Univ, 2018, 23(10):137-143.DOI:10.11841/j.issn.1007-4333.2018.10.17.
[33]	胡秋霞, 田杰, 何东健, 等. 基于改进型C-V模型的植物病斑图像分割[J]. 农业机械学报, 2012, 43(5):157-161.
	HU Q X, TIAN J, HE D J, et al. Segmentation of plant lesion image using improved C-V model[J]. Trans Chin Soc Agric Mach, 2012, 43(5):157-161.DOI:10.6041/j.issn.1000-1298.2012.05.027.
[34]	冯冬竹, 范琳琳, 余航, 等. 自适应轮廓的变分水平集复杂背景多目标检测[J]. 软件学报, 2017, 28(10):2797-2810.
	FENG D Z, FAN L L, YU H, et al. Adaptive contour based variational level set model for multiple target detection in complex background[J]. J Softw, 2017, 28(10):2797-2810.DOI:10.13328/j.cnki.jos.005172.
[35]	白雪飞, 王文剑. 自适应初始轮廓的Chan-Vese模型图像分割方法[J]. 计算机科学与探索, 2013, 7(12):1115-1124.
	BAI X F, WANG W J. Chan-vese model with adaptive initial contour for image segmentation[J]. J Front Comput Sci Technol, 2013, 7(12):1115-1124.DOI:10.3778/j.issn.1673-9418.1306007.
[36]	刘文国, 刘玲, 袁玉欣. 不同黑杨无性系叶片及单木水平蒸腾特性研究[J]. 林业建设, 2012(4):7-16.
	LIU W G, LIU L, YUAN Y X. Study on consumption properties for leaf and individual level of different Populus deltoides clones[J]. For Constr, 2012(4):7-16.
[37]	刘江俊. 基于无人机影像的单木识别与单木结构参数提取研究[D]. 杭州: 浙江农林大学, 2020.
	LIU J J. Individual tree recognition and individual tree structure parameters extraction based on UAV imagery[D]. Hangzhou: Zhejiang A & F University, 2020.
[38]	徐永胜, 杨玉泽, 林文树. 基于不同拼接算法的无人机林区影像拼接效果研究[J]. 森林工程, 2020, 36(1): 50-59.
	XU Y S, YANG Y Z, LIN W S. Research on image stitching effect of UAV forest region based on different stitching algorithms[J]. Forest Engineering, 2020, 36(1): 50-59.
[39]	陈日强, 李长春, 杨贵军, 等. 无人机机载激光雷达提取果树单木树冠信息[J]. 农业工程学报, 2020, 36(22):50-59.
	CHEN R Q, LI C C, YANG G J, et al. Extraction of crown information from individual fruit tree by UAV LiDAR[J]. Trans Chin Soc Agric Eng, 2020, 36(22):50-59.DOI:10.11975/j.issn.1002-6819.2020.22.006.
[40]	李丹, 张俊杰, 赵梦溪. 基于FCM和分水岭算法的无人机影像中林分因子提取[J]. 林业科学, 2019, 55(5):180-187.
	LI D, ZHANG J J, ZHAO M X. Extraction of stand factors in UAV image based on FCM and watershed algorithm[J]. Sci Silvae Sin, 2019, 55(5):180-187.DOI:10.11707/j.1001-7488.20190520.
[41]	GUIJARRO M, RIOMOROS I, PAJARES G, et al. Discrete wavelets transform for improving greenness image segmentation in agricultural images[J]. Comput Electron Agric, 2015, 118:396-407.DOI:10.1016/j.compag.2015.09.011.
[42]	LIN Y, JIANG M, YAO Y J, et al. Use of UAV oblique imaging for the detection of individual trees in residential environments[J]. Urban For Urban Green, 2015, 14(2):404-412.DOI:10.1016/j.ufug.2015.03.003.
[43]	马益杭, 占利军, 谢传节, 等. 连通域标记算法的并行化研究[J]. 地理与地理信息科学, 2013, 29(4):67-71,2.
	MA Y H, ZHAN L J, XIE C J, et al. Parallelization of connected component labeling algorithm[J]. Geogr Geo Inf Sci, 2013, 29(4):67-71,2.DOI:10.7702/dlydlxxkx20130415.
[44]	董新宇, 李家国, 陈瀚阅, 等. 无人机遥感影像林地单株立木信息提取[J]. 遥感学报, 2019, 23(6):1269-1280.
	DONG X Y, LI J G, CHEN H Y, et al. Extraction of individual tree information based on remote sensing images from an unmanned aerial vehicle[J]. J Remote Sens, 2019, 23(6):1269-1280.

Metrics

Comments

www.nldxb.njfu.edu.cn

Edited ＆ Published by Editorial Department of Nanjing Forestry University(Natural Sciences Edition)
Address： No.159 Longpan Road,Nanjing 210037 Jiangsu,P.R.China
E-mail ：xuebao@njfu.edu.cn , xuebao@njfu.com.cn
Telephone +86-25-85428247,85427076
Distributed by China International Book Trading Corporation P.O. Box 399, Beijing ,P.R. China

影像编号 image No.	影像位置 image location	地理坐标 coordinate	树种 tree species	林分类型 stand type	影像来源 image source	获取时间 acquisition time	目视解译数量 number of visual interpretation
1	北京市海淀区东升八家郊野公园	116°19'24.25″E, 40°0'46.68″N	圆柏 Sabina chinensis	针叶林	Google影像	2019年5月	397
2	河北省文安县界围农场	116°30'00.00″E, 38°57'37.08″N	杨树Populus spp.	阔叶树	Google影像	2020年10月	77
3	浙江省临安市青山湖绿道	119°44'57.14″E, 30°14'32.67″N	水杉Metasequoia glyptostroboides	针叶林	Google影像	2017年11月	75
4	深圳市宝安区荔枝园	113°53'26.34″E, 22°38'41.22″N	荔枝 Litchi chinensis	经济林	Google影像	2017年12月	111
5	山东省栖霞市苹果园	120°42'13.54″E, 37°10'25.55″N	苹果 Malus pumila	经济林	Google影像	2015年7月	71
6	北京林业大学篮球场	116°20'8.76″E, 40°0'6.52″N	国槐 Sophora japonica 馒头柳 Salix matsudana var. matsudana f. umbraculifera	四旁树	Google影像	2019年6月	24
7	北京林业大学篮球场	116°20'8.76″E, 40°0'6.52″N	国槐 Sophora japonica 馒头柳Salix matsudana var. matsudana f. umbraculifera	四旁树	“北京二号” 卫星	2018年第2季度	24

影像编号 image No.	林分类型 stand type	方法 method	N_r	N_a	N_match	N_error	N_leave	M	R_mat	R_com	R_om
1	针叶林 coniferous forest	CV模型	397	390	366	24	31	0.87	0.92	0.06	0.08
		梯度分水岭	397	145	145	0	252	0.37	0.37	0.00	0.64
		标记分水岭	397	198	195	3	203	0.49	0.49	0.02	0.51
		局部最大值	397	431	348	92	49	0.71	0.88	0.19	0.12
2	阔叶林 broad-leaved forest	CV模型	77	78	63	14	15	0.68	0.82	0.19	0.18
		梯度分水岭	77	119	61	58	16	0.45	0.79	0.49	0.21
		标记分水岭	77	94	67	27	10	0.64	0.87	0.29	0.13
		局部最大值	77	84	57	27	20	0.55	0.74	0.32	0.26
3	针叶林 coniferous forest	CV模型	75	80	60	20	15	0.63	0.80	0.25	0.20
		梯度分水岭	75	78	55	23	20	0.56	0.73	0.29	0.27
		标记分水岭	75	112	70	42	5	0.60	0.93	0.38	0.07
		局部最大值	75	83	49	36	14	0.49	0.65	0.41	0.35
4	经济林 economic forest	CV模型	111	127	91	20	36	0.62	0.82	0.28	0.18
		梯度分水岭	111	149	90	59	21	0.53	0.81	0.40	0.19
		标记分水岭	111	371	111	260	0	0.30	1.00	0.70	0.00
		局部最大值	111	204	76	128	35	0.32	0.68	0.63	0.32
5	经济林 economic forest	CV模型	71	79	52	3	19	0.70	0.73	0.34	0.27
		梯度分水岭	71	110	57	53	14	0.46	0.80	0.48	0.20
		标记分水岭	71	125	58	67	13	0.42	0.82	0.53	0.18
		局部最大值	71	88	63	25	8	0.66	0.89	0.28	0.11
6	四旁树 trees of the “Four Sides”	CV模型	24	21	17	4	7	0.61	0.71	0.19	0.29
		梯度分水岭	24	73	24	49	0	0.33	1.00	0.67	0.00
		标记分水岭	24	50	24	26	0	0.48	1.00	0.52	0.00
		局部最大值	24	71	24	47	0	0.34	1.00	0.66	0.00
7	四旁树 trees of the “Four Sides”	CV模型	24	20	19	1	4	0.79	0.79	0.05	0.21
		梯度分水岭	24	103	24	79	0	0.23	1.00	0.77	0.00
		标记分水岭	24	61	23	39	1	0.37	0.96	0.62	0.44
		局部最大值	24	46	21	25	3	0.43	0.88	0.54	0.13

方法 method	M	R_mat	R_com	R_om
CV模型 CV model	0.701	0.799	0.196	0.201
梯度分水岭 gradient watershed	0.443	0.724	0.438	0.205
标记分水岭 marked watershed	0.470	0.867	0.437	0.133
局部最大值 local maximum	0.499	0.817	0.434	0.183

Locating individual tree from high resolution satellite images based on CV model

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 44

Related Articles 7

Recommended Articles

Metrics

Comments

Author

Reader

Reviewer

[1]	ZHAO Yinghui, ZHANG Dali, ZHEN Zhen. Individual tree species classification based on nonparametric classification algorithms and multi-source remote sensing data [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2019, 43(5): 103-112.
[2]	ZHANG Jianchen, CUI Jie, CHENG Yi, HUANG Jian, DU Jingyuan, GE Hongli. Supervised visualization of multispectral remotely sensed data based on principal component transformation [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2018, 42(05): 121-128.
[3]	ZHOU Yu, ZHANG Li-ning, WU Li-mei. Design and Implementation of Multi-source Remote Sensing Image Fusion Platform [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2006, 30(04): 85-88.
[4]	ZHANG Lianhua, LI Chungan. Automatic extraction of forest training sample and their application in change detection using high resolution remote sensing image [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2015, 39(03): 13-17.
[5]	SHI Yunsong, SHI Yufeng. Classification of remote sensing image based on kernel fuzzy Cmeans [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2010, 34(06): 164-168.
[6]	ZHANG Li ning, ZHOU Yu. Research on Fusion Approaches of SPOT5 and Multi-spectral Images [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2007, 31(04): 89-92.
[7]	GE Yu-feng,ZHOU Hong-ping~*,ZHENG Jia-qiang,ZHANG Hui-chun. A Tree Image Segmentation Algorithm Based On Relative Color Indices [J]. JOURNAL OF NANJING FORESTRY UNIVERSITY, 2004, 28(04): 19-22.