顾及单木三维形态的无人机立体影像单木识别算法

doi:10.12082/dqxxkx.2021.210117

地球信息科学学报 ›› 2021, Vol. 23 ›› Issue (10): 1861-1872.doi: 10.12082/dqxxkx.2021.210117

顾及单木三维形态的无人机立体影像单木识别算法

刘见礼¹^,²^,³(), 廖小罕¹^,²^,^*(), 倪文俭²^,³, 王勇¹^,², 叶虎平¹^,², 岳焕印¹^,²

1.中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室,北京 100101
2.中国科学院大学,北京 100049
3.中国科学院空天信息创新研究院遥感科学国家重点实验室, 北京 100101

收稿日期:2021-03-09 修回日期:2021-04-15 出版日期:2021-10-25 发布日期:2021-12-25
通讯作者: * 廖小罕（1963— ）,男,贵州贵阳人,博士,研究员,主要从事无人机组网遥感研究以及无人机低空公共航路规划研究。E-mail: liaoxh@igsnrr.ac.cn
作者简介:刘见礼（1990— ）,男,山东济宁人,博士生,主要从事无人机组网遥感研究。E-mail: liujl.18b@igsnrr.ac.cn
基金资助:
中国科学院战略性先导科技专项(XDA19050501);国家重点研发计划项目(2017YFB0503005);国家自然科学基金项目(41971359);国家自然科学基金项目(41771388)

Individual Tree Recognition Algorithm of UAV Stereo Imagery Considering Three-dimensional Morphology of Tree

LIU Jianli¹^,²^,³(), LIAO Xiaohan¹^,²^,^*(), NI Wenjian²^,³, WANG Yong¹^,², YE Huping¹^,², YUE Huanyin¹^,²

1. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
2. University of Chinese Academy of Sciences, Beijing 100049, China
3. State Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, China

Received:2021-03-09 Revised:2021-04-15 Online:2021-10-25 Published:2021-12-25
Contact: LIAO Xiaohan
Supported by:
Strategic Priority Research Program of Chinese Academy of Sciences(XDA19050501);National Key Research and Development Program of China(2017YFB0503005);National Natural Science Foundation of China(41971359);National Natural Science Foundation of China(41771388)

摘要/Abstract

摘要：

单木参数对当前的森林资源管理、生态研究以及生物多样性保护等具有重要意义。无人机立体影像数据与单木识别算法为单木参数的低成本、自动化获取提供了基础。现有研究表明,常用的基于局部最大值搜索的单木识别算法面对密集林分时存在严重的漏识别问题,影响了参数提取的精度,因此本文提出了顾及单木三维形态的无人机立体影像单木识别新算法。算法首先综合利用无人机立体影像的高程与RGB光谱信息,通过随机森林分类进行林冠区的提取;然后利用形态学的多层腐蚀、膨胀与连通区标记进行树冠相连单木的分离与树冠中心点的提取,从而实现单木自动化识别。本文选取内蒙古大兴安岭林区和四川王朗林区的4块样地进行验证,以目视解译数据为参考,分别与基于高程值的局部最大值搜索算法（算法A）、基于RGB光谱亮度值的局部最大值搜索算法（算法B）进行比较。结果显示：本文提出的算法在4个样地的平均F1-score为94.17%,与算法A和算法B相比分别提高了15.85%和9.37%;而对于密集样地,本文提出的算法在查全率上相比算法A和算法B分别提高51.79%和35.64%。结果表明本文提出的算法在不同林区均能够实现较好的单木识别效果,特别是能够有效避免密集林分下的漏识别问题,为基于无人机立体影像的单木识别研究提供了一种新的思路。

关键词: 无人机, 遥感, 立体影像, 单木识别, 形态学, 局部最大值搜索, 大兴安岭, 王朗

Abstract:

Forest is not only the main body of terrestrial ecosystem, but also one of the most important natural resources for human being. Individual tree parameters are of great significance to current forest resource management, ecological research, and biodiversity protection. However, the traditional forest surveys are realized through manual measurement of each tree, which is labor intensive and low efficient. UAV stereo imagery and individual tree recognition algorithms provide the foundations for low-cost and automatic acquisition of individual tree parameters. In recent years, there are a lot of research on individual tree recognition based on UAV stereo imagery. The existing studies show that the commonly used individual tree recognition algorithm based on local maximum search has a serious problem of missing recognition in dense stands, which affects the accuracy of tree parameters. Therefore, it is necessary to develop a robust individual tree recognition algorithm to overcome the problem of missing recognition for UAV stereo imagery. In this paper, a new algorithm of individual tree recognition in UAV stereo imagery was proposed, which takes into account the three-dimensional morphology of tree crown. Firstly, the height and RGB spectral information of UAV stereo imagery were used synthetically to extract the canopy area based on Random Forest (RF) classifier. Secondly, the multi-layers morphological corrosion, expansion, and connected area labeling were used to separate the connected trees and extract the center coordinates of the tree crown, so as to realize the individual tree recognition. Thirdly, in order to verify the recognition effect of the algorithm on different forest types, four sample plots in Daxing'anling forest region and Wanglang forest region were selected for verification. The visual interpretation data was used as reference and compared with local maximum search algorithm based on elevation value (algorithm A) and local maximum search algorithm based on RGB spectral brightness values (algorithm B). Results show that combination of DOM and DSM can improve the extraction accuracy of the forest canopy area to a certain extent. Meanwhile, the average F1 score of the proposed algorithm in four plots is 94.17%, which is 15.85% and 9.37% higher than those of algorithm A and B. For dense sample plots, the recall of this algorithm is 51.79% and 35.64% higher than those of algorithm A and algorithm B. The proposed algorithm can achieve good recognition effect in different forest areas. Moreover, it can effectively avoid the problem of missing recognition on dense forest stands. This paper provides a new idea for individual tree recognition based on UAV stereo imagery.

Key words: UAV, remote sensing, stereo imagery, individual tree recognition, morphology, local maximum search, Daxing'anling, Wanglang

刘见礼, 廖小罕, 倪文俭, 王勇, 叶虎平, 岳焕印. 顾及单木三维形态的无人机立体影像单木识别算法[J]. 地球信息科学学报, 2021, 23(10): 1861-1872.DOI:10.12082/dqxxkx.2021.210117

LIU Jianli, LIAO Xiaohan, NI Wenjian, WANG Yong, YE Huping, YUE Huanyin. Individual Tree Recognition Algorithm of UAV Stereo Imagery Considering Three-dimensional Morphology of Tree[J]. Journal of Geo-information Science, 2021, 23(10): 1861-1872.DOI:10.12082/dqxxkx.2021.210117

图/表 15

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

图10

图11

图12

图13

表2

参考文献 27

[1]	Crowther T W, Glick H B, Covey K R, et al. Mapping tree density at a global scale[J]. Nature, 2015, 525(7568):201-205. doi: 10.1038/nature14967
[2]	Hao Z Q, Zhang J A, Song B, et al. Vertical structure and spatial associations of dominant tree species in an old-growth temperate forest[J]. Forest Ecology and Management, 2007, 252(1/2/3):1-11. doi: 10.1016/j.foreco.2007.06.026
[3]	刘见礼, 张志玉, 倪文俭, 等. 无人机影像匹配点云单木识别算法[J]. 遥感信息, 2019, 34(1):93-101.
	[ Liu J L, Zhang Z Y, Ni W J, et al. Individual tree recognition algorithm based on unmanned aerial vehicle image matching point cloud[J]. Remote Sensing Information, 2019, 34(1):93-101. ]
[4]	刘清旺, 李增元, 陈尔学, 等. 利用机载激光雷达数据提取单株木树高和树冠[J]. 北京林业大学学报, 2008, 30(6):83-89.
	[ Liu Q W, Li Z Y, Chen E X, et al. Extracting height and crown of individual tree using airborne LIDAR data[J]. Journal of Beijing Forestry University, 2008, 30(6):83-89. ]
[5]	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(2):64-73. doi: 10.1007/s001380050091
[6]	Wang H, Zhao Y, Pu R, et al. Mapping robinia pseudoacacia forest health conditions by using combined spectral, spatial, and textural information extracted from Ikonos imagery and random forest classifier[J]. Remote Sensing, 2015, 7(7):9020-9044. doi: 10.3390/rs70709020
[7]	Coops N C, Johnson M, Wulder M A, et al. Assessment of Quickbird high spatial resolution imagery to detect red attack damage due to mountain pine beetle infestation[J]. Remote Sensing of Environment, 2006, 103(1):67-80. doi: 10.1016/j.rse.2006.03.012
[8]	Harri k, Juha h, Yu x w, et al. An international comparison of individual tree detection and extraction using airborne laser scanning[J]. Remote Sensing, 2012, 4(4):950. doi: 10.3390/rs4040950
[9]	Vauhkonen J, Ene L, Gupta S, et al. Comparative testing of single-tree detection algorithms under different types of forest[J]. Forestry: An International Journal of Forest Research, 2011, 85(1):27-40. doi: 10.1093/forestry/cpr051
[10]	Liao X H, Zhang Y, Su F Z, et al. UAVs surpassing satellites and aircraft in remote sensing over China[J]. International Journal of Remote Sensing, 2018, 39(21):7138-7153. doi: 10.1080/01431161.2018.1515511
[11]	Liao X H, Yue H Y, Liu R G, et al. Launching an unmanned aerial vehicle remote sensing data carrier: Concept, key components and prospects[J]. International Journal of Digital Earth, 2020, 13(10):1172-1185. doi: 10.1080/17538947.2019.1698664
[12]	Wang L, Gong P, Biging G S. Individual tree-crown delineation and treetop detection in high-spatial-resolution aerial imagery[J]. Photogrammetric Engineering & Remote Sensing, 2004, 70(3):351-357.
[13]	Popescu S C, Wynne R H, Nelson R F. Estimating plot-level tree heights with lidar: local filtering with a canopy-height based variable window size[J]. Computers and Electronics in Agriculture, 2002, 37(1):71-95. doi: 10.1016/S0168-1699(02)00121-7
[14]	Reitberger J, Schnörr C, Krzystek P, et al. 3D segmentation of single trees exploiting full waveform LIDAR data[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2009, 64(6):561-574. doi: 10.1016/j.isprsjprs.2009.04.002
[15]	Pollock R. The automatic recognition of individual trees in aerial images of forests based on a synthetic tree crown image model[D]. Canada:University of British Columbia, 1996.
[16]	Gougeon 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
[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 and Remote Sensing, 2012, 70:88-98. doi: 10.1016/j.isprsjprs.2012.04.003
[18]	Ayrey E, Fraver S, Kershaw J A, et al. Layer stacking: A novel algorithm for individual forest tree segmentation from LiDAR point clouds[J]. Canadian Journal of Remote Sensing, 2017, 43(1):16-27. doi: 10.1080/07038992.2017.1252907
[19]	Culman M, Delalieux S, Tricht K V. Individual palm tree detection using deep learning on rgb imagery to support tree inventory[J]. Remote Sensing, 2020, 12(21):3476. doi: 10.3390/rs12213476
[20]	Brandt M, Tucker C J, Kariryaa A, et al. An unexpectedly large count of trees in the West African Sahara and Sahel[J]. Nature, 2020, 587(7832):78-82. doi: 10.1038/s41586-020-2824-5
[21]	Hirschmugl M, Ofner M, Raggam J, et al. Single tree detection in very high resolution remote sensing data[J]. Remote Sensing of Environment, 2007, 110(4):533-544. doi: 10.1016/j.rse.2007.02.029
[22]	Monnet J, Mermin E, Chanussot J, et al. Tree top detection using local maxima filtering: a parameter sensitivity analysis[C]. The 10^th International Conference on LiDAR Applications for Assessing Forest Ecosystems. Freiburg, Germany, 2010.
[23]	李旺, 牛铮, 王成, 等. 机载LiDAR数据估算样地和单木尺度森林地上生物量[J]. 遥感学报, 2015, 19(4):669-679.
	[ Li W, Niu Z, Wang C, et al. Forest above-ground biomass estimation at plot and tree levels using airborne LiDAR data[J]. Journal of Remote Sensing, 2015, 19(4):669-679. ]
[24]	Tiede D, Hochleitner G, Blaschke T. A full GIS-based workflow for tree identification and tree crown delineation using laser scanning[C]// ISPRS Workshop CMRT. 2005.
[25]	Wulder M, Niemann KO, Goodenough DG. Local maximum filtering for the extraction of tree locations and basal area from high spatial resolution imagery[J]. Remote Sensing of Environment, 2000, 73(1):103-114. doi: 10.1016/S0034-4257(00)00101-2
[26]	Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32. doi: 10.1023/A:1010933404324
[27]	Solberg S, Naesset E, Bollandsas OM. Single tree segmentation using airborne laser scanner data in a structurally heterogeneous spruce forest[J]. Photogrammetric Engineering & Remote Sensing, 2006, 72(12):1369-1378.

样地名	DOM林冠区提取精度/%	DSM林冠区提取精度/%	综合DOM和DSM的林冠区提取精度/%
样地1	92.56	78.46	98.84
样地2	98.71	78.85	98.85
样地3	90.40	76.76	91.50
样地4	83.37	71.21	86.40

样地名	参考单木株数	算法	识别株数/株	过、错识别/株		正确识别/株	查准率/%	查全率/%	F1-score/%
样地1	172	本文算法	173	8	7	165	95.38	95.93	95.65
		算法A	178	13	7	165	92.70	95.93	94.29
		算法B	154	13	31	141	91.56	81.98	86.50
样地2	390	本文算法	393	12	9	381	96.95	97.69	97.32
		算法A	195	16	211	179	91.79	45.90	61.20
		算法B	247	5	148	242	97.98	62.05	75.98
样地3	89	本文算法	103	14	0	89	86.41	100.00	92.71
		算法A	61	3	31	58	95.08	65.17	77.33
		算法B	68	0	21	68	100.00	76.40	86.62
样地4	104	本文算法	118	17	3	101	85.59	97.12	90.99
		算法A	75	3	32	72	96.00	69.23	80.45
		算法B	98	7	13	91	92.86	87.50	90.10

顾及单木三维形态的无人机立体影像单木识别算法

Individual Tree Recognition Algorithm of UAV Stereo Imagery Considering Three-dimensional Morphology of Tree

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 15

参考文献 27

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	杨颖频, 吴志峰, 黄启厅, 骆剑承, 吴田军, 董文, 胡晓东, 肖文菊. 协同遥感与统计数据的粤西甘蔗种植分布提取及时空分析[J]. 地球信息科学学报, 2023, 25(5): 1012-1026.
[2]	刘潇, 刘智, 林雨准, 王淑香, 左溪冰. 面向遥感影像场景分类的类中心知识蒸馏方法[J]. 地球信息科学学报, 2023, 25(5): 1050-1063.
[3]	侯慧太, 蓝朝桢, 徐青. 基于卫星影像全局和局部深度学习特征检索的无人机绝对定位方法[J]. 地球信息科学学报, 2023, 25(5): 1064-1074.
[4]	衡雪彪, 许捍卫, 唐璐, 汤恒, 许怡蕾. 基于改进全卷积神经网络模型的土地覆盖分类方法研究[J]. 地球信息科学学报, 2023, 25(3): 495-509.
[5]	高鹏飞, 曹雪峰, 李科, 游雄. 融合多元稀疏特征与阶层深度特征的遥感影像目标检测[J]. 地球信息科学学报, 2023, 25(3): 638-653.
[6]	秦肖伟, 程博, 杨志平, 李林, 董文, 张新, 杨树文, 靳宗义, 薛庆. 基于时序遥感影像的西南山区地块尺度作物类型识别[J]. 地球信息科学学报, 2023, 25(3): 654-668.
[7]	陈凯, 雷少华, 代文, 王春, 刘爱利, 李敏. 基于开源数据和条件生成对抗网络的地形重建方法[J]. 地球信息科学学报, 2023, 25(2): 252-264.
[8]	饶子昱, 卢俊, 郭海涛, 余东行, 侯青峰. 利用视角转换的跨视角影像匹配方法[J]. 地球信息科学学报, 2023, 25(2): 368-379.
[9]	王龙号, 蓝朝桢, 姚富山, 侯慧太, 武蓓蓓. 多源遥感影像深度特征融合匹配算法[J]. 地球信息科学学报, 2023, 25(2): 380-395.
[10]	甘聪聪, 邱炳文, 张建阳, 姚铖鑫, 叶智燕, 黄姮, 黄莹泽, 彭玉凤, 林艺真, 林多多, 苏中豪. 基于Sentinel-1/2动态耦合移栽期特征的水稻种植模式识别[J]. 地球信息科学学报, 2023, 25(1): 153-162.
[11]	于明洋, 陈肖娴, 张文焯, 刘耀辉. 融合网格注意力阀门和特征金字塔结构的高分辨率遥感影像建筑物提取[J]. 地球信息科学学报, 2022, 24(9): 1785-1802.
[12]	吴亚楠, 郭长恩, 于东平, 段爱民, 刘玉, 董士伟, 单东方, 吴耐明, 李西灿. 基于不确定性分析的遥感分类空间分层及评估方法[J]. 地球信息科学学报, 2022, 24(9): 1803-1816.
[13]	吕爱锋, 亓珊珊. 遥感及再分析降水产品在缺资料干旱内陆盆地的适用性评估[J]. 地球信息科学学报, 2022, 24(9): 1817-1834.
[14]	廖周伟, 关燕宁, 郭杉, 蔡丹路, 于敏, 姚武韬, 张春燕, 邓锐. 基于网格的街区尺度城市绿度度量方法[J]. 地球信息科学学报, 2022, 24(8): 1475-1487.
[15]	闵杰, 张永生, 于英, 吕可枫, 王自全, 张磊. 增强型遥感影像SRGAN算法及其在三维重建精度提升中的应用[J]. 地球信息科学学报, 2022, 24(8): 1631-1644.