基于无人机高分辨率影像的油松新造林健康树冠提取

doi:10.11707/j.1001-7488.20221011

摘要/Abstract

摘要：

目的: 基于新造林健康树冠的光谱特征和空间交错情况, 探讨复杂地面植被条件下健康树冠的光谱增强方式和多尺度分割阈值, 为造林核查的日常监测工作提供技术支撑。方法: 以冬奥核心区新造林地无人机航拍影像为试验数据, 首先, 基于健康树冠与其他干扰地物的不同颜色特征, 采用同态滤波增强影像并使用ExG光谱指数进行变换; 然后, 采用最大类间方差方法得到二值图像, 并使用多尺度形态学滤波方法进行分割并融合分割结果, 以分割交错的树冠区域对应提取原始图像中可能的健康树冠区域; 最后, 基于颜色向量、灰度共生矩阵和局部二值模式共同构建的特征向量, 采用随机森林识别提取区域, 从而检测图像中的健康树冠。结果: 基于光谱指数变换、多尺度形态学滤波方法能够有效分割交错连续的树冠区域, 排除与健康树冠颜色相近的地物干扰, 较为准确提取出可能为树冠的区域。采用该方法对不同造林密度、光照条件下的17幅无人机正射图像进行试验, 使用目视解译方式标记出树冠中心, 运用精确度、召回率和F1分数3个评价指标对随机森林和支持向量机的识别效果进行定量对比分析, 结果表明, 多尺度形态学滤波方法可提取96.78%的树冠, 随机森林的F1分数高于97%, 而支持向量机的召回率显著低于随机森林。结论: 基于光谱指数变换和多尺度形态学滤波的树冠提取方法能够对健康树冠进行快速、准确提取, 有效完成造林核查。

关键词: 无人机影像, 同态滤波, 光谱指数, 形态学滤波, 随机森林

Abstract:

Objective: Based on the spectral characteristics and spacial interlacing of healthy tree crowns in new afforestation, the spectral enhancement method and multi-scale segmentation thresholds of healthy tree crowns under complex ground vegetation conditions were discussed to provide technical support for the daily monitoring of afforestation verification. Method: The UAV images of newly planted trees in the core area of the Winter Olympics were chosen as experimental data. Firstly, based on the different color characteristics of healthy tree crowns and other disturbances, the images were enhanced by homomorphic filtering and transformed by ExG spectral index. Then, the Otsu method was used to obtain the binary image, and the multi-scale morphological filtering method was used for segmentation and fusion to segment the interlaced crown areas, correspondingly extract the possible healthy crown areas in the original image. Finally, based on the feature vector constructed by the color vector, the GLCM and the LBP, the random forest was used to classify the extracted area to detect the healthy tree crowns in the image. Result: The method based on spectral index transformation and multi-scale morphological filtering was able to effectively segment the interlaced and continuous crown areas, exclude other interference objects those were similar in color to healthy trees and accurately extract the areas those might be crowns. The 17 UAV orthophoto images with varying stand densities and lighting conditions were tested, and the crown centers were marked by visual interpretation. Furthermore, the three evaluation indexes: precision, recall and F1 score were used to quantitatively compare and analyze the recognition effects of random forest and SVM. The experimental result showed that 96.78% of the crowns were extracted using the multi-scale morphological filtering method, and the F1 score of random forest was higher than 97%, while the recall of support vector machine was significantly lower than that of random forest. Conclusion: Our result showed that the crown extraction method based on spectral index transformation and multi-scale morphological filtering could be able to extract the healthy crown quickly and accurately in the UAV images and effectively complete the afforestation verification.

Key words: UAV image, homomorphic filtering, spectral index, morphological filtering, random forest

中图分类号:

S758

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[J]. 林业科学, 2022, 58(10): 111-120.

Xuzhan Guo,Qiao Chen,Xiaofang Zhang,Liang Hong,Yuanyuan You,Shouzheng Tang,Liyong Fu. Extraction of Healthy Canopy of New Afforestation for Pinus tabulaeformis Based on UAV High-Resolution Image[J]. Scientia Silvae Sinicae, 2022, 58(10): 111-120.

图/表 8

图1

图2

图3

图4

图5

图6

图7

表1

参考文献 0

	卜帆, 石玉立. 机载LiDAR高差和高分影像的城市树冠提取比较. 遥感技术与应用, 2017, 32 (5): 875- 882.
	Bu F , Shi Y L . The comparison of urban tree crown extraction based on airborne LiDAR elevation difference and high resolution imagery. Remote Sensing Technology and Application, 2017, 32 (5): 875- 882.
	程浈浈, 祁力钧, 程一帆, 等. 基于M-LP特征加权聚类的果树冠层图像分割方法. 农业机械学报, 2020, 51 (4): 191- 198.191-198, 260
	Cheng Z Z , Qi L J , Cheng Y F , et al. Fruit tree canopy image segmentation method based on M-LP features weighted clustering. Transactions of the Chinese Society for Agricultural Machinery, 2020, 51 (4): 191- 198.191-198, 260
	董雪, 林明星. 基于变分结构引导滤波的低照度图像增强算法. 山东大学学报(理学版), 2020, 55 (9): 72- 80.
	Dong X , Lin M X . Low-light image enhancement algorithm based on variational structure guided filtering. Journal of Shandong University(Natural Science), 2020, 55 (9): 72- 80.
	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. 北京林业大学学报, 2017, 29 (3): 16- 23.
	Feng J J , Zhang X L , Liu H L . Single tree crown extraction based on gray gradient image segmentation. Journal of Beijing Forestry University, 2017, 29 (3): 16- 23.
	金忠明, 曹姗姗, 王蕾, 等. 天山云杉林无人机可见光影像树冠信息提取方法研究. 林业资源管理, 2020, (1): 125- 135.
	Jin Z M , Cao S S , Wang L , et al. Study on extraction of tree crown information from UAV visible light image of Picea schrenkiana var. tianschanica forest. Forest Resources Management, 2020, (1): 125- 135.
	刘清旺, 李世明, 李增元, 等. 无人机激光雷达与摄影测量林业应用研究进展. 林业科学, 2017, 53 (7): 134- 148.
	Liu Q W , Li S M , Li Z Y , et al. Review on the applications of UAV-based LiDAR and photogrammetry in forestry. Scientia Silvae Sinicae, 2017, 53 (7): 134- 148.
	宋以宁, 刘文萍, 骆有庆, 等. 基于线性谱聚类的林地图像中枯死树监测. 林业科学, 2019, 55 (4): 187- 195.
	Song Y N , Liu W P , Luo Y Q , et al. Monitoring of dead trees in forest images based on linear spectral clustering. Scientia Silvae Sinicae, 2019, 55 (4): 187- 195.
	Allison T D , Root T L , Frumhoff P C . Thinking globally and siting locally-renewable energy and biodiversity in a rapidly warming world. Climatic Change, 2014, 126 (1/2): 1- 6.
	Csillik O , Cherbini J , Johnson R , et al. Identification of citrus trees from unmanned aerial vehicle imagery using convolutional neural networks. Drones, 2018, 2 (4): 39.
	Eklundh L , Johansson T , Solberg S . Mapping insect defoliation in scots pine with MODIS time-series data. Remote Sensing of Environment, 2009, 113 (7): 1566- 1573.
	Garg M , Dhiman G . A novel content-based image retrieval approach for classification using GLCM features and texture fused LBP variants. Neural Computing and Applications, 2021, 33 (4): 1311- 1328.
	Guo X , Liu Q , Sharma R P , et al. Tree recognition on the plantation using UAV Images with ultrahigh spatial resolution in a complex environment. Remote Sensing, 2021, 13 (20): 4122.
	Hirschmugl H , Ofner M , Raggam J , et al. Single tree detection in very high resolution remote sensing data. Remote Sensing of Environment, 2007, 110 (4): 533- 544.
	Jing L , Hu B , Noland T , et al. An individual tree crown delineation method based on multi-scale segmentation of imagery. ISPRS Journal of Photogrammetry & Remote Sensing, 2012, 70, 88- 98.
	Kyere-Boateng R , Marek M V . Analysis of the social-ecological causes of deforestation and forest degradation in ghana: application of the DPSIR framework. Forests, 2021, 12 (4): 409.
	Malambo L , Popescu S C , Murray S C , et al. Multitemporal field-based plant height estimation using 3D point clouds generated from small unmanned aerial systems high-resolution imagery. International Journal of Applied Earth Observation and Geoinformation, 2018, 64, 31- 42.
	Midhun M S , Carlos K , Carine J , et al. Individual tree detection from unmanned aerial vehicle(UAV) derived canopy height model in an open canopy mixed conifer forest. Forests, 2017, 8 (9): 340.
	Ojala T , Pietikainen M , Maenpaa T . Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on pattern analysis, 2002, 24 (7): 971- 987.
	Pan Y D , Birdsey R A , Fang J Y , et al. A large and persistent carbon sink in the world's forests. Science, 2011, 333 (6045): 988- 993.
	Secord J , Zakhor A . Tree detection in urban regions using aerial LiDAR and image data. IEEE Geoscience Remote Sensing Letters, 2007, 4 (2): 196- 200.
	Selim S , Sonmez N K , Coslu M , et al. Semi-automatic tree detection from images of unmanned aerial vehicle using object-based image analysis method. Journal of the Indian Society of Remote Sensing, 2019, 47 (2): 193- 200.
	Seow M J, Asari V K. 2004. Homomorphic processing system and ratio rule for color image enhancement. IEEE International Conference on Neural Networks- Conference Proceedings, 4: 2507-2512.
	Song W , Mu X , Yan G , et al. Extracting the green fractional vegetation cover from digital images using a shadow-resistant algorithm(SHAR-LABFVC). Remote Sensing, 2015, 7 (8): 10425.
	Sunday J M . The pace of biodiversity change in a warming climate. Nature, 2020, 580 (7804): 460- 461.
	Tseng C C, Lee S L. 2017. A weak-illumation image enhancement method uisng homomorphic filter and image fusion. IEEE 6^th Global Conference on Consumer Electronics(GCCE), 1-2.
	Woebbecke D M , Meyer G E , Von Bargen K , et al. Color Indices for weed identification under various soil, residue, and lighting conditions. Transactions of the ASAE, 1995, 38 (1): 259- 269.
	Wulder M A , White J C , Coops N C , et al. Multi-temporal analysis of high spatial resolution imagery for disturbance monitoring. Remote Sensing of Environment, 2008, 112 (6): 2729- 2740.
	Xu W , Deng S , Liang D , et al. A crown morphology-based approach to individual tree detection in subtropical mixed broadleaf urban forests using UAV LiDAR data. Remote Sensing, 2021, 13 (7): 1278.
	Yuan Y , Hu X . Random forest and objected-based classification for forest pest extraction from UAV aerial imagery. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2016, 1093- 1098.
	Yun T , Jiang K , Li G , et al. Individual tree crown segmentation from airborne LiDAR data using a novel Gaussian filter and energy function minimization-based approach. Remote Sensing of Environment, 2021, 256, 112307.

识别方法Method	标定树冠Marked crowns	提取树冠Extracted crowns	精确率Precision(%)	召回率Recall(%)	F1分数F1 core(%)
随机森林Random forest	1 804	1 746	94.77	99.58	97.32
支持向量机SVM	1 804	1 746	93.41	74.56	82.93

[1]	田惠玲,朱建华,何潇,陈新云,简尊吉,李宸宇,郭学媛,黄国胜,肖文发. 基于随机森林模型的东北三省乔木林生物质碳储量预测[J]. 林业科学, 2022, 58(4): 40-50.
[2]	刘鑫源,杨光,宁吉彬,耿道通,于宏洲,邸雪颖. 红松人工林地表可燃物燃烧释放颗粒物质量及影响因素[J]. 林业科学, 2022, 58(3): 97-106.
[3]	石永磊,王志慧,李世明,李春意,肖培青,张攀,常晓格. 基于光学遥感的稀疏乔灌木地上部分生物量反演方法[J]. 林业科学, 2022, 58(2): 13-22.
[4]	孙忠秋,高金萍,吴发云,高显连,胡杨,高剑新. 基于机载激光雷达点云和随机森林算法的森林蓄积量估测[J]. 林业科学, 2021, 57(8): 68-81.
[5]	由珈齐,李明泽,范文义,全迎,王斌,莫祝坤,祝子枭. 基于高光谱和激光雷达数据的林分类型识别[J]. 林业科学, 2021, 57(5): 119-129.
[6]	潘颖,丁鸣鸣,林杰,代侨,郭赓,崔琳琳. 基于PROSAIL模型和多角度遥感数据的森林叶面积指数反演[J]. 林业科学, 2021, 57(4): 90-106.
[7]	李文博,吕振刚,黄选瑞,张志东. 河北省北部华北落叶松人工林立地指数空间分布预测[J]. 林业科学, 2021, 57(3): 79-89.
[8]	丁家祺,黄文丽,刘迎春,胡杨. 基于机器学习和多源数据的湘西北森林地上生物量估测[J]. 林业科学, 2021, 57(10): 36-48.
[9]	张雷, 孙鹏森, 刘世荣. 川西亚高山森林不同恢复阶段生长季蒸腾特征[J]. 林业科学, 2020, 56(1): 1-9.
[10]	侯晓静, 明金科, 秦荣水, 朱霁平. 基于随机森林模型的交界域火灾风险分析[J]. 林业科学, 2019, 55(8): 194-200.
[11]	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.
[12]	兰洁,雷相东,张毓涛. 天山中部雪岭云杉林多功能权衡与协同关系[J]. 林业科学, 2019, 55(11): 9-18.
[13]	张英凯,刘鹏举,刘长春,任怡. 基于空间聚类的杉木生长预测方法[J]. 林业科学, 2019, 55(11): 137-144.
[14]	陈亮, 周国模, 杜华强, 刘玉莉, 毛方杰, 徐小军, 李雪建, 崔璐, 李阳光, 朱迪恩. 基于随机森林模型的毛竹林CO₂通量模拟及其影响因子[J]. 林业科学, 2018, 54(8): 1-12.
[15]	李晓红, 陈尔学, 李增元, 李世明. 综合应用多源遥感数据的面向对象土地覆盖分类方法[J]. 林业科学, 2018, 54(2): 68-80.