无人机航高对落叶松毛虫虫害遥感监测精度的影响

doi:10.12302/j.issn.1000-2006.202204047

国家林草科技领军期刊
中国精品科技期刊
中国高校百佳科技期刊
江苏省新闻出版政府奖期刊奖
RCCSE林学权威期刊（A+）
CSCD核心期刊
Scopus数据库收录期刊
中文核心期刊
SCD核心期刊

作者加群：102861116

微信公众号：南京林业大学学报

高级检索

南京林业大学学报（自然科学版） ›› 2023, Vol. 47 ›› Issue (4): 13-22.doi: 10.12302/j.issn.1000-2006.202204047

所属专题：第三届中国林草计算机应用大会论文精选（Ⅱ）

• 专题报道：第三届中国林草计算机应用大会论文精选（Ⅱ）（执行主编李凤日） • 上一篇下一篇

无人机航高对落叶松毛虫虫害遥感监测精度的影响

杨乐¹(), 黄晓君¹^,^*(), 包玉海¹, 包刚¹, 佟斯琴¹, 苏都毕力格²

1.内蒙古师范大学地理科学学院,内蒙古自治区遥感与地理信息系统重点实验室,内蒙古自治区蒙古高原灾害与生态安全重点实验室,内蒙古呼和浩特 010022
2.东北师范大学环境学院,吉林长春 130024

收稿日期:2022-04-25 修回日期:2023-04-16 出版日期:2023-07-30 发布日期:2023-07-20
通讯作者: * 黄晓君(hxj3s@qq.com),副教授。
作者简介:杨乐(1433713407@qq.com)。
基金资助:
国家自然科学基金项目(41861056);内蒙古自然科学基金项目(2022MS04005);内蒙古自治区科技计划(2021GG0183);内蒙古高校青年科技英才支持计划(NJYT22030);内蒙古师范大学引进高层次人才科研启动经费项目(2020YJRC051)

Effects of UAV flight altitude on the accuracy of monitoring Dendrolimus superans pests by remote sensing

YANG Le¹(), HUANG Xiaojun¹^,^*(), BAO Yuhai¹, BAO Gang¹, TONG Siqin¹, Sudubilig ²

1. Inner Mongolia Key Laboratory of Remote Sensing & Geography Information System, Inner Mongolia Key Laboratory of Disaster and Ecological Security on the Mongolia Plateau, College of Geographical Science, Inner Mongolia Normal University, Hohhot 010022, China
2. College of Environment, Northeast Normal University, Changchun 130024, China

Received:2022-04-25 Revised:2023-04-16 Online:2023-07-30 Published:2023-07-20

摘要/Abstract

摘要：

【目的】探究无人机航高对落叶松毛虫(Dendrolimus superans)虫害监测精度的影响机制,以期构建先进的森林虫害监测技术框架,为无人机近地面森林虫害遥感监测提供重要参考。【方法】以大兴安岭落叶松毛虫虫害频发区为试验区,以无人机不同航高下采集的多光谱遥感影像为基础数据,获得健康、轻度和重度虫害的386株落叶松树冠层光谱指数和纹理特征,通过方差分析法(ANOVA)及连续投影算法(SPA)提取对虫害严重程度敏感的光谱特征,结合随机森林(RF)和支持向量机(SVM)算法构建虫害严重程度监测模型,揭示航高对监测精度的影响。【结果】①光谱指数和纹理特征的总体(轻度+重度)监测精度均随航高上升呈下降趋势,而轻度和重度虫害的监测精度却有不同变化态势。②光谱指数(修正型三角植被指数2、绿光归一化差值植被指数2、绿光归一化差值植被指数、差值植被指数、简单比值指数1)+纹理特征(MEA 3)组合的虫害监测精度达到最优(总体精度和Kappa值分别为92.3%和0.891),但其总体和轻度的监测精度随航高上升呈下降趋势(下降速率分别为0.04%/m和0.03%/m),重度的监测精度有上升趋势(上升速率为0.03%/m)。【结论】航高对无人机近地虫害监测精度具有明显影响,并且轻度和重度监测精度随航高的变化速率和趋势有差异。与重度虫害相比,轻度的监测精度随航高的变化速率较快。无人机对虫害早期高精度遥感识别宜选择低航高,而适当提升航高亦能获得对虫害严重度评估监测的预期效果。

关键词: 落叶松毛虫, 虫害, 无人机, 航高, 多光谱遥感监测

Abstract:

【Objective】This study aims to explore the influence of unmanned aerial vehicles(UAV) flight altitude mechanism on the accuracy of monitoring larch caterpillar (Dendrolimus superans) insect pests, and provide an important reference for ground UAV remote sensing monitoring of forest pests.【Method】 The areas known for frequent occurrences of D. superans in Da Hinggan Mountains were selected and multispectral remote sensing images collected by UAV at different flight altitudes were used as the basic data. This study obtained the canopy spectral indexes and texture features of 386 healthy, mild, and severely damaged trees by D. superans. Analysis of variances and continuous projection algorithms were used to extract the spectral features sensitive to pest severity. The pest severity monitoring model was constructed using random forest and support vector machine algorithms, and expounded the influence of flight altitude on monitoring accuracy.【Result】(1) The accuracy of overall (mild + severe) monitoring of the spectral indexes and texture features decreased with an increase in flight altitudes. However, the accuracy of mild and severe monitoring of trees damaged by D. superans exhibited different trends. (2) The pest monitoring accuracy of the combination of spectral indices (MTVI 2, GNDVI 2, DVI, GMI 1 and GNDVI) + texture feature (MEA 3) was the best, and the overall accuracy and Kappa coefficient were 92.3% and 0.891, respectively. However, the overall and accuracy of mild monitoring decreased with an increase in flight altitudes, where the decline rate was 0.04%/m and 0.03%/m, respectively, and the accuracy of severe monitoring increased (the rise rate was 0.03%/m). 【Conclusion】 The flight altitudes significantly impacted the accuracy of UAV ground pest monitoring. There was a difference in the rate and trend between the accuracies of mild and severe monitoring. The rate of change in the accuracy of mild monitoring with flight altitude was faster than that of the accuracy of the severe monitoring. Thus, an early identification of pests using a high-precision UAV remote sensing, adaptable to various flight altitudes, is needed to monitor pest severity and improve the expected effects.

Key words: Dendrolimus superans, insect pest, unmanned aerial vehicles(UAV), flight altitude, multi-spectral remote sensing monitoring

中图分类号:

S763.305

杨乐,黄晓君,包玉海,等. 无人机航高对落叶松毛虫虫害遥感监测精度的影响[J]. 南京林业大学学报（自然科学版）, 2023, 47(4): 13-22.

YANG Le, HUANG Xiaojun, BAO Yuhai, BAO Gang, TONG Siqin, Sudubilig . Effects of UAV flight altitude on the accuracy of monitoring Dendrolimus superans pests by remote sensing[J].Journal of Nanjing Forestry University (Natural Science Edition), 2023, 47(4): 13-22.DOI: 10.12302/j.issn.1000-2006.202204047.

图/表 6

表1

光谱指数及其计算公式依据"

光谱指数 spectral index	公式 formula	参考文献 reference
花青素反射指数1 ARI 1	(1/B₂)-(1/B₄)	Gitelson等^[18]
类胡萝卜素反射指数1 CRI 1	(1/B₂)-(1/B₃)	Gitelson等^[19]
差值植被指数DVI	B₅-B₃	Jordan^[20]
增强植被指数EVI	B₅/B₃	Pearson等^[21]
简单比值指数GMI 1	B₁/B₄	Lichtenthaler^[22]
绿光归一化差值植被指数GNDVI	B₄/B₂	Gitelson等^[23]
绿光归一化差值植被指数2 GNDVI 2	(B₅-B₃)/(B₅+B₃)	Rouse等^[24]
利希滕塔莱指数LIC 3	(B₅-B₂)/(B₅+B₂)	Gitelson等^[25]
修正型三角植被指数MTVI 2	(B₄-B₂)/(B₄+B₂)	Gitelson等^[25]
归一化植被指数NDVI	2.5(B₅-B₃)/[1+B₅+6B₃-7.5B₁]	Huete等^[26]
比值植被指数RVI	1.5[1.2(B₅-B₂)-2.5(B₃-B₂)]/ $[(2 B 5 + 1) 2$ - (6B₅- $B 3$ -0.5)	Haboudane等^[27]
三角形植被指数TVI	0.5[120(B₄-B₂)-200(B₃-B₂)]	Broge等^[28]

表1

图1

表2

表3

基于纹理特征的虫害严重程度监测模型参数"

模型 model	航高/m flight- altitude	窗口大小 window size	均值 mean		方差 variance		协同性 homogeneity		对比度 contrast		相异性 dissimilarity		信息熵 entropy		二阶矩 second moment		相关性 correlation
模型 model	航高/m flight- altitude	窗口大小 window size	OA/%	Kappa	OA/%	Kappa	OA/%	Kappa	OA/%	Kappa	OA/%	Kappa	OA/%	Kappa	OA/%	Kappa	OA/%	Kappa
支持向量机 SVM	100	3×3	85.9	0.806	56.4	0.468	65.4	0.555	55.1	0.459	64.1	0.543	62.8	0.530	64.1	0.543	51.3	0.426
		5×5	83.3	0.776	60.3	0.505	66.7	0.568	56.4	0.470	64.1	0.543	65.4	0.554	64.1	0.543	43.6	0.333
		7×7	84.6	0.791	60.3	0.505	60.3	0.505	61.5	0.518	64.1	0.543	65.4	0.554	65.4	0.555	43.6	0.333
		9×9	84.6	0.791	60.3	0.505	66.7	0.568	57.7	0.477	64.1	0.543	65.4	0.554	65.4	0.555	44.9	0.353
	150	3×3	67.9	0.594	48.7	0.402	52.6	0.437	48.7	0.396	50.0	0.407	57.7	0.482	57.7	0.480	48.7	0.395
		5×5	69.2	0.610	53.8	0.442	50.0	0.414	50.0	0.404	51.3	0.420	56.4	0.469	59.0	0.494	50.0	0.402
		7×7	66.7	0.577	57.7	0.481	52.6	0.440	55.1	0.468	52.6	0.437	55.1	0.457	57.7	0.481	52.6	0.436
		9×9	62.8	0.536	57.7	0.491	55.1	0.466	55.1	0.455	52.6	0.438	53.8	0.444	57.7	0.481	51.3	0.414
	200	3×3	74.4	0.675	56.4	0.481	53.8	0.441	51.3	0.415	51.3	0.415	53.8	0.452	57.7	0.490	43.6	0.334
		5×5	73.1	0.662	57.7	0.492	56.4	0.475	53.8	0.449	55.1	0.462	55.1	0.462	59.0	0.504	43.6	0.337
		7×7	76.9	0.702	59.0	0.504	53.8	0.450	57.7	0.490	53.8	0.456	57.7	0.483	56.4	0.476	46.2	0.365
		9×9	75.6	0.687	60.3	0.519	57.7	0.490	56.4	0.466	59.0	0.504	55.1	0.453	59.0	0.504	44.9	0.353
随机森林 RF	100	3×3	73.1	0.651	51.3	0.443	48.7	0.399	55.1	0.478	57.7	0.501	46.2	0.384	51.3	0.438	35.9	0.280
		5×5	74.4	0.669	43.6	0.355	46.2	0.370	47.4	0.389	51.3	0.434	51.3	0.424	47.4	0.388	41.0	0.328
		7×7	75.6	0.685	46.2	0.384	46.2	0.384	47.4	0.388	57.7	0.503	52.6	0.450	53.8	0.460	34.6	0.263
		9×9	73.1	0.661	46.2	0.387	52.6	0.445	51.3	0.443	51.3	0.436	47.4	0.403	53.8	0.462	39.7	0.318
	150	3×3	56.4	0.473	43.6	0.360	44.9	0.367	44.9	0.370	42.3	0.351	51.3	0.444	35.9	0.281	37.2	0.291
		5×5	61.5	0.533	42.3	0.334	47.4	0.402	53.8	0.461	39.7	0.317	44.9	0.369	44.9	0.372	47.4	0.400
		7×7	60.3	0.520	48.7	0.410	41.0	0.329	39.7	0.319	39.7	0.319	47.4	0.396	48.7	0.410	39.7	0.324
		9×9	56.4	0.488	48.7	0.406	46.2	0.385	39.7	0.331	42.3	0.330	47.4	0.393	42.3	0.342	42.3	0.345
	200	3×3	69.2	0.623	51.3	0.434	38.5	0.298	39.7	0.311	44.9	0.376	46.2	0.385	37.2	0.282	41.0	0.335
		5×5	59.0	0.516	47.4	0.404	37.2	0.277	44.9	0.370	50.0	0.429	41.0	0.331	42.3	0.337	33.3	0.248
		7×7	66.7	0.602	43.6	0.356	48.7	0.414	56.4	0.493	53.8	0.464	47.4	0.400	48.7	0.415	44.9	0.377
		9×9	72.6	0.653	38.5	0.298	56.4	0.494	47.4	0.397	55.1	0.480	50.0	0.425	60.3	0.529	38.5	0.304

表3

表4

图2

参考文献 36

[1]	陈科屹, 王建军, 何友均, 等. 黑龙江大兴安岭重点国有林区森林碳储量及固碳潜力评估[J]. 生态环境学报, 2022, 31(9):1725-1734.
	CHEN K Y, WANG J J, HE Y J, et al. Assessment of forest carbon storage and carbon sequestration potential in key state-owned forest areas of the Great Khingan Mountains, Heilongjiang Province[J]. Journal of Ecological Environment, 2022, 31(9):1725-1734.DOI:10.16258/j.cnki.1674-5906.2022.09.002.
[2]	潘忠, 张立杰, 孙景波, 等. 大兴安岭林区调研后的思考[J]. 东北林业大学学报, 2004, 32(6):101-102.
	PAN Z, ZHANG L J, SUN J B, et al. Thinking after the survey of Greater Khingan Mountains Forest Area[J]. Journal of Northeast Forestry University, 2004, 32(6):101-102. DOI:10.3969/j.issn.1000-5382.2004.06.033.
[3]	黄晓君. 落叶松针叶虫害地面高光谱识别及遥感监测方法研究[D]. 兰州: 兰州大学, 2019.
	HUANG X J. Remote sensing identification and monitoring of larch needle pests based on ground hyperspectral data[D]. Lanzhou: Lanzhou University, 2019.
[4]	郝玉山, 周本志. 内蒙古大兴安岭林区主要森林害虫危害的分析[J]. 中国森林病虫, 2003, 22(2):40-41.
	HAO Y S, ZHOU B Z. Damage analysis of main forest pests in Daxing 'anling forest region of Inner Mongolia[J]. Forest Pests in China, 2003, 22(2):40-41. DOI:10.3969/j.issn.1671-0886.2003.02.017.
[5]	FRAMPTON W J, DASH J, WATMOUGH G, et al. Evaluating the capabilities of Sentinel-2 for quantitative estimation of biophysical variables in vegetation[J]. ISPRS J Photogramm Remote Sens, 2013, 82:83-92. DOI:10.1016/j.isprsjprs.2013.04.007.
[6]	HARATI S, PEREZ L, MOLOWNY-HORAS R. Integrating neighborhood effect and supervised machine learning techniques to model and simulate forest insect outbreaks in British Columbia, Canada[J]. Forests, 2020, 11(11):1215. DOI:10.3390/f11111215.
[7]	BÁRTA V, LUKEŠ P, HOMOLOVÁ L. Early detection of bark beetle infestation in Norway spruce forests of Central Europe using Sentinel-2[J]. Int J Appl Earth Obs Geoinformation, 2021, 100:102335. DOI:10.1016/j.jag.2021.102335.
[8]	HU G S, YIN C J, WAN M Z, et al. Recognition of diseased Pinus trees in UAV images using deep learning and AdaBoost classifier[J]. Biosyst Eng, 2020, 194:138-151. DOI:10.1016/j.biosystemseng.2020.03.021.
[9]	白力嘎, 黄晓君, DASHZEBEGD G, 等. 基于高光谱特征的雅氏落叶松尺蠖虫口密度估算[J]. 昆虫学报, 2021, 64(6):711-721.
	BAI L G, HUANG X J, DASHZEBEGD G, et al. Estimation of the population density of Erannis jacobsoni (Lepidoptera:Geometridae) based on hyperspectral features[J]. Acta Entomol Sin, 2021, 64(6):711-721. DOI:10.16380/j.kcxb.2021.06.007.
[10]	西桂林, 黄晓君, 包玉海, 等. 雅氏落叶松尺蠖不同危害程度下林木冠层颜色高光谱判别[J]. 光谱学与光谱分析, 2020, 40(9):2925-2931.
	XI G L, HUANG X J, BAO Y H, et al. Hyperspectral discrimination of different canopy colors in Erannis jacobsoni Djak-infested larch[J]. Spectrosc Spectr Anal, 2020, 40(9):2925-2931.
[11]	薛大暄, 张瑞瑞, 陈立平, 等. 基于Faster R-CNN的美国白蛾图像识别模型研究[J]. 环境昆虫学报, 2020, 42(6):1502-1509.
	XUE D X, ZHANG R R, CHEN L P, et al. Faster R-CNN based image recognition research of Hyphantria cunea[J]. J Environ Entomol, 2020, 42(6):1502-1509.
[12]	ZHANG N, ZHANG X L, YANG G J, et al. Assessment of defoliation during the Dendrolimus tabulaeformis Tsai et Liu disaster outbreak using UAV-based hyperspectral images[J]. Remote Sens Environ, 2018, 217:323-339. DOI:10.1016/j.rse.2018.08.024.
[13]	NÄSI R, HONKAVAARA E, LYYTIKÄINEN-SAARENMAA P, et al. Using UAV-based photogrammetry and hyperspectral imaging for mapping bark beetle damage at tree-level[J]. Remote Sens, 2015, 7(11):15467-15493. DOI:10.3390/rs71115467.
[14]	ZHANG N, WANG Y T, ZHANG X L. Extraction of tree crowns damaged by Dendrolimus tabulaeformis Tsai et Liu via spectral-spatial classification using UAV-based hyperspectral images[J]. Plant Methods, 2020, 16(1):1-19. DOI:10.1186/s13007-020-00678-2.
[15]	YU R, LUO Y Q, LI H N, et al. Three-dimensional convolutional neural network model for early detection of pine wilt disease using UAV-based hyperspectral images[J]. Remote Sens, 2021, 13(20):4065. DOI:10.3390/rs13204065.
[16]	黄晓君, 颉耀文, 包玉海, 等. 微分光谱连续小波系数估测雅氏落叶松尺蠖危害下的落叶松失叶率[J]. 光谱学与光谱分析, 2019, 39(9):2732-2738.
	HUANG X J, XIE Y W, BAO Y H, et al. Estimation of leaf loss rate in larch infested with Erannis jacobsoni Djak based on differential spectral continuous wavelet coefficient[J]. Spectrosc Spectr Anal, 2019, 39(9):2732-2738.
[17]	YU R, LUO Y Q, ZHOU Q, et al, A machine learning algorithm to detect pine wilt disease using UAV-based hyperspectral imagery and LiDAR data at the tree level[J]. Int J Appl Earth Obs Geoinformation, 2021, 101:102363. DOI:10.1016/j.jag.2021.102363.
[18]	GITELSON A A, MERZLYAK M N, CHIVKUNOVA O B. Optical properties and nondestructive estimation of anthocyanin content in plant leaves[J]. Photochem Photobiol, 2007, 74(1):38-45. DOI:10.1562/0031-8655(2001)0740038opaneo2.0.co2.
[19]	GITELSON A A, KAUFMAN Y J, STARK R, et al. Novel algorithms for remote estimation of vegetation fraction[J]. Remote Sens Environ, 2002, 80(1):76-87. DOI:10.1016/S0034-4257(01)00289-9.
[20]	JORDAN C F. Derivation of leaf-area index from quality of light on the forest floor[J]. Ecology, 1969, 50(4):663-666. DOI:10.2307/1936256.
[21]	PEARSON R L, MILLER L D. Remote mapping of standing crop biomass for estimation of productivity of the shortgrass prairie[J]. Remote Sensing of Environment, 1972,VIII:7-12. DOI:10.1177/002076409904500102.
[22]	LICHTENTHALER H K, LANG M, SOWINSKA M, et al. Detection of vegetation stress via a new high resolution fluorescence imaging system[J]. J Plant Physiol, 1996, 148(5):599-612. DOI:10.1016/S0176-1617(96)80081-2.
[23]	GITELSON A A, MERZLYAK M N. Signature analysis of leaf reflectance spectra: algorithm development for remote sensing of chlorophyll[J]. J Plant Physiol, 1996, 148(3/4):494-500. DOI:10.1016/S0176-1617(96)80284-7.
[24]	ROUSE J W, HAAS R H, SCHELL J A, et al. Monitoring vegetation system in the Great Plains with ERTS[C]// NASA Technical Reports Server, 1974, 309-317.
[25]	GITELSON A A, KAUFMAN Y J, MERZLYAK M N. Use of a green channel in remote sensing of global vegetation from EOS-MODIS[J]. Remote Sens Environ, 1996, 58(3):289-298. DOI:10.1016/S0034-4257(96)00072-7.
[26]	HUETE A R, LIU H Q, BATCHILY K, et al. A comparison of vegetation indices over a global set of TM images for EOS-MODIS[J]. Remote Sens Environ, 1997, 59(3):440-451. DOI:10.1016/S0034-4257(96)00112-5.
[27]	HABOUDANE D, MILLER J R, PATTEY E, et al. Hyperspectral vegetation indices and novel algorithms for predicting green LAI of crop canopies:modeling and validation in the context of precision agriculture[J]. Remote Sens Environ, 2004, 90(3):337-352. DOI:10.1016/j.rse.2003.12.013.
[28]	BROGE N H, LEBLANC E. Comparing prediction power and stability of broadband and hyperspectral vegetation indices for estimation of green leaf area index and canopy chlorophyll density[J]. Remote Sens Environ, 2001, 76(2):156-172. DOI:10.1016/S0034-4257(00)00197-8.
[29]	刘俊, 周靖靖, 菅永峰, 等. Worldview-2不同波段纹理特征对森林蓄积量估算精度影响[J]. 西北林学院学报, 2021, 36(3):175-181.
	LIU J, ZHOU J J, JIAN Y F, et al. Effects of texture parameters of different bands of worldview-2 images on the estimation of forest volume[J]. J Northwest For Univ, 2021, 36(3):175-181. DOI: 10.3969/j.issn.1001-7461.2021.03.26.
[30]	牛芳鹏, 李新国, 李新国, 麦麦提吐尔逊·艾则孜, 等. 基于光谱指数的博斯腾湖西岸湖滨绿洲土壤有机碳含量估算模型[J]. 江苏农业学报, 2022, 38(2):414-421.
	NIU F P, LI X G, Mamattursun·Eziz, et al. Estimation model of soil organic carbon content in lakeside oasis on the west coast of Bosten Lake based on spectral index[J]. Jiangsu J Agr Sci, 2022, 38(2):414-421.DOI:10.3969/j.issn.1000-4440.2022.02.015.
[31]	王蕾, 骆有庆, 张晓丽, 等. 遥感技术在森林病虫害监测中的应用研究进展[J]. 世界林业研究, 2008, 21(5):37-43.
	WANG L, LUO Y Q, ZHANG X L, et al. Application development of remote sensing technology in the assessment of forest pest disaster[J]. World For Res, 2008, 21(5):37-43. DOI:10.13348/j.cnki.sjlyyj.2008.05.002.
[32]	王正兴, 刘闯, ALFREDO H. 植被指数研究进展:从AVHRR-NDVI到MODIS-EVI[J]. 生态学报, 2003, 23(5):979-987.
	WANG Z X, LIU C, ALFREDO H. From AVHRR-NDVI to MODIS-EVI: advances in vegetation index research[J]. Acta Ecol Sin, 2003, 23(5):979-987. DOI: 10.3321/j.issn:1000-0933.2003.05.020.
[33]	关丽, 刘湘南. 两种用于作物冠层叶绿素含量提取的改进光谱指数[J]. 地球科学进展, 2009, 24(5):548-554.
	GUAN L, LIU X N. Two kinds of modified spectral indices for retrieval of crop canopy chlorophyll content[J]. Adv Earth Sci, 2009, 24(5):548-554. DOI: 10.3321/j.issn:1001-8166.2009.05.011.
[34]	陈玲, 郝文乾, 高德亮. 光学影像纹理信息在林业领域的最新应用进展[J]. 北京林业大学学报, 2015, 37(3):1-12.
	CHEN L, HAO W Q, GAO D L. The latest applications of optical image texture in forestry[J]. J Beijing For Univ, 2015, 37(3):1-12. DOI:10.13332/j.1000-1522.20140304.
[35]	FUCHS H, MAGDON P, KLEINN C, et al. Estimating aboveground carbon in a catchment of the Siberian forest tundra: combining satellite imagery and field inventory[J]. Remote Sens Environ, 2009, 113(3):518-531. DOI:10.1016/j.rse.2008.07.017.
[36]	ZHOU J J, ZHAO Z, ZHAO J, et al. A comparison of three methods for estimating the LAI of black locust (Robinia pseudoacacia L.) plantations on the Loess Plateau, China[J]. Int J Remote Sens, 2014, 35(1):171-188. DOI:10.1080/01431161.2013.866289.

模型 model	光谱指数 spectral index	不同航高OA/% overall accuracy for different flight altitude			不同航高Kappa值 Kappa for different flight altitude
模型 model	光谱指数 spectral index	100 m	150 m	200 m	100 m	150 m	200 m
支持向量机 SVM	ARI 1	50.0	56.4	51.3	0.424	0.472	0.426
	CRI 1	85.9	82.1	82.1	0.806	0.761	0.764
	DVI	88.5	75.6	85.9	0.838	0.689	0.806
	EVI	85.9	76.9	69.2	0.806	0.695	0.607
	GMI 1	89.7	84.6	84.6	0.856	0.791	0.792
	GNDVI	83.3	82.1	79.5	0.780	0.764	0.734
	GNDVI 2	91.0	84.6	80.8	0.874	0.793	0.751
	LIC 3	89.7	79.5	85.9	0.854	0.732	0.805
	MTVI 2	92.3	91.9	88.5	0.889	0.874	0.840
	NDVI	92.9	91.0	88.5	0.884	0.871	0.840
	RVI	92.3	89.7	85.9	0.890	0.855	0.808
	TVI	89.7	83.3	78.2	0.854	0.776	0.721
随机森林 RF	ARI1	47.4	35.9	39.7	0.403	0.287	0.318
	CRI 1	76.9	75.6	69.2	0.704	0.683	0.623
	DVI	84.6	73.1	76.9	0.792	0.657	0.703
	EVI	79.5	55.1	53.8	0.732	0.460	0.457
	GMI 1	84.6	78.2	73.1	0.792	0.716	0.662
	GNDVI	80.8	79.5	73.1	0.749	0.730	0.666
	GNDVI 2	88.5	79.5	76.9	0.841	0.725	0.706
	LIC 3	87.2	73.1	84.6	0.821	0.661	0.794
	MTVI 2	90.6	89.7	85.9	0.867	0.854	0.809
	NDVI	88.5	85.9	84.6	0.840	0.809	0.788
	RVI	80.8	78.2	76.1	0.744	0.720	0.708
	TVI	80.8	76.9	75.6	0.742	0.704	0.688

模型 model	组合光谱指数 combine spectral signatures	不同航高OA/% overall accuracy for different flight altitude			不同航高Kappa值 Kappa for different flight altitude
模型 model	组合光谱指数 combine spectral signatures	100 m	150 m	200 m	100 m	150 m	200 m
SVM 支持向量机	SI1+TF(3)	92.3	89.7	88.5	0.891	0.857	0.842
	SI2+TF(5)	92.3	88.5	85.9	0.891	0.841	0.810
	SI3+TF(7)	92.3	89.7	87.2	0.891	0.857	0.825
	SI4+TF(9)	92.3	89.7	87.2	0.891	0.857	0.825
RF 随机森林	SI1+TF(3)	93.6	91.0	84.6	0.908	0.874	0.794
	SI2+TF(5)	93.5	92.3	83.3	0.907	0.890	0.778
	SI3+TF(7)	91.0	91.0	87.2	0.874	0.874	0.825
	SI4+TF(9)	92.3	91.0	87.2	0.890	0.874	0.825

无人机航高对落叶松毛虫虫害遥感监测精度的影响

Effects of UAV flight altitude on the accuracy of monitoring Dendrolimus superans pests by remote sensing

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 36

相关文章 15

编辑推荐

Metrics

本文评价

作者

读者

审稿

[1]	牛弘健, 刘文萍, 陈日强, 宗世祥, 骆有庆. 基于Resnet的林地无人机图像去雾改进算法[J]. 南京林业大学学报（自然科学版）, 2024, 48(2): 175-18.
[2]	张华聪, 谭新建, 喻龙华, 厉月桥, 陈永富, 刘仁, 张怀清. 基于增强Frost局部滤波及单木距离图重构标记的CHM树冠分割[J]. 南京林业大学学报（自然科学版）, 2023, 47(5): 9-18.
[3]	高家军, 张旭, 郭颖, 刘昱坤, 郭安琪, 石蒙蒙, 王鹏, 袁莹. 融合Swin Transformer的虫害图像实例分割优化方法研究[J]. 南京林业大学学报（自然科学版）, 2023, 47(3): 1-10.
[4]	杨堃, 范习健, 薄维昊, 刘婕, 王俊玲. 基于视觉加强注意力模型的植物病虫害检测[J]. 南京林业大学学报（自然科学版）, 2023, 47(3): 11-18.
[5]	吴炅, 蒋馥根, 彭邵锋, 马开森, 陈松, 孙华. 结合树冠体积的油茶树高与产量估测研究[J]. 南京林业大学学报（自然科学版）, 2022, 46(2): 53-62.
[6]	赵颖慧, 杨海城, 甄贞. 基于ULS、TLS和超声测高仪的天然次生林中不同林冠层树高估测[J]. 南京林业大学学报（自然科学版）, 2021, 45(4): 23-32.
[7]	程建斌,汪继斌,王年金,姚小华. 无人机辅助授薄壳山核桃花粉对山核桃的结实效应[J]. 南京林业大学学报（自然科学版）, 2019, 43(04): 199-202.
[8]	陶欢,李存军,谢春春,周静平,淮贺举,蒋丽雅,李凤涛. 基于HSV阈值法的无人机影像变色松树识别[J]. 南京林业大学学报（自然科学版）, 2019, 43(03): 99-106.
[9]	薛羿,孟昭军,董效文,牛豪杰,严善春. 5种林分中性信息素对亚洲型舞毒蛾的诱捕作用[J]. 南京林业大学学报（自然科学版）, 2018, 42(05): 71-76.
[10]	代婷婷,马骏,徐雁南. 基于Agisoft PhotoScan 的无人机影像自动拼接在风景园林规划中的应用[J]. 南京林业大学学报（自然科学版）, 2018, 42(04): 165-170.
[11]	王玮,王浩,李卫正,乌日汗,田晓冬,郭苏明,陈周翔,张浩峰. 基于小型无人机摄影测量的江南景观水资源综合利用分析[J]. 南京林业大学学报（自然科学版）, 2018, 42(01): 7-14.
[12]	张青萍,梁慧琳,李卫正,杨梦珂,朱灵茜,黄安. 数字化测绘技术在私家园林中的应用研究[J]. 南京林业大学学报（自然科学版）, 2018, 42(01): 1-6.
[13]	金兰,茹煜,孙曼利,贾志成,王秉玺. 圆锥管状电极式航空静电喷头的性能试验[J]. 南京林业大学学报（自然科学版）, 2015, 39(05): 155-160.
[14]	张慧春，郑加强，周宏平. 基于决策树技术的智能植保机械决策支持系统[J]. 南京林业大学学报（自然科学版）, 2011, 35(01): 95-98.
[15]	茹煜，周宏平，贾志成，吴小伟，范庆妮. 航空静电喷雾系统的设计及应用[J]. 南京林业大学学报（自然科学版）, 2011, 35(01): 91-94.