我们的网站为什么显示成这样?

可能因为您的浏览器不支持样式,您可以更新您的浏览器到最新版本,以获取对此功能的支持,访问下面的网站,获取关于浏览器的信息:

|Table of Contents|

基于HSV阈值法的无人机影像变色松树识别(PDF)

《南京林业大学学报(自然科学版)》[ISSN:1000-2006/CN:32-1161/S]

Issue:
2019年03期
Page:
99-106
Column:
研究论文
publishdate:
2019-05-15

Article Info:/Info

Title:
Recognition of red-attack pine trees from UAV imagery based on the HSV threshold method
Article ID:
1000-2006(2019)03-0099-08
Author(s):
TAO Huan1 LI Cunjun1* XIE Chunchun2 ZHOU Jingping1 HUAI Heju1 JIANG Liya3 LI Fengtao2
1. Beijing Research Center for Information Technology in Agriculture, Beijing 100097, China; 2. Shandong Ruida Harmful Organism Control and Prevention Co., Ltd., Ji’nan 250101, China; 3. Bureau of Anhui Province for Forest Pests Control and Quarantine, Hefei 230031, China
Keywords:
pine wilt disease red attack pine trees unmanned aerial vehicle(UAV)imagery hue-saturation-value(HSV)model red-green-blue(RGB)model
Classification number :
S771. 8
DOI:
10.3969/j.issn.1000-2006.201711035
Document Code:
A
Abstract:
【Objective】A hue-saturation-value(HSV)threshold method was used for the recognition of red attack pine trees from unmanned aerial vehicle(UAV)imagery. To improve the investigation efficiency of red-attack damage and provide basic data for sanitation logging. 【Method】The extraction rules of the HSV threshold method were built according to the difference between red attack pine trees and other elements in the “H-V space”. The recognition results of red attack pine trees between the RGB threshold method and HSV threshold method were compared under different scenarios. Next, the evaluation accuracy of both methods was calculated. 【Result】① Samples of red attack pine trees plotted in the “H-V space” point cloud showed significant clustering and a banding distribution in the “G-R space” point cloud. ② A strong correlation among the components in the RGB color space was a main factor for the large omission errors of red attack pine tree extraction using the RGB threshold method. The overall accuracy of the HSV threshold method, based on decoupling of the hue and value from the HSV color space and its convenient threshold segmentation, outperformed that of the RGB threshold method for red attack pine tree recognition based on UAV imagery. ③ The HSV threshold method performed well for monitoring pines affected by pine wilt disease in a late stage, which achieved 60%-65% overall accuracy when the distribution of pine trees before infection from high-resolution imagery was used as a mask. 【Conclusion】 The HSV threshold method shows some advantages for monitoring red attack pine trees based on UAV imagery compared to manual interpretation. This method provides theoretical and methodological support for the recognition of red attack pine trees from UAV imagery.

References

[1] VOLLENWEIDER P, GüNTHARDT-GOERG M S. Diagnosis of abiotic and biotic stress factors using the visible symptoms in foliage[J]. Environmental Pollution, 2005, 137(3): 455-465. DOI:10.1016/j.envpol.2005.01.032.
[2] 陈元生, 黄燕洪, 周满生. 松材线虫病疫木伐桩除害处理技术概述[J]. 林业科技开发, 2014, 28(1): 12-14. DOI:10.13360/j.issn.1000-8101.2014.01.003.
CHEN Y S, HUANG Y H, ZHOU M S. A review on techniques of extinction treatment in diseased wood stumps caused by Bursaphelenchus xylophilus[J]. Journal of Forestry Engineering, 2014, 28(1): 12-14.
[3] 蒋丽雅, 盛常顺, 马圣安, 等. 松材线虫病疫木的微波除害处理技术[J]. 南京林业大学学报(自然科学版), 2006, 30(6): 87-90. DOI:10.3969/j.issn.1000-2006.2006.06.020.
JIANG L Y, SHENG C S, MA S A, et al. Study on processing timber infected with pine wood nematode using microwave[J]. Journal of Nanjing Forestry University(Natural Sciences Edition), 2006, 30(6): 87-90.
[4] WULDER M A, DYMOND C C, WHITE J C, et al. Surveying mountain pine beetle damage of forests:a review of remote sensing opportunities[J]. Forest Ecology and Management, 2006, 221(1/3): 27-41. DOI:10.1016/j.foreco.2005.09.021.
[5] WULDERM A, WHITE J C, BENTZ B J, et al. Augmenting the existing survey hierarchy for mountain pine beetle red-attack damage with satellite remotely sensed data[J]. Forestry Chronicle, 2006, 82(2): 187-202. DOI:10.5558/tfc82187-2.
[6] 国家林业局. 松材线虫普查监测技术规程:GB / T 23478 — 2009[S]. 北京:中国标准出版社, 2009.
[7] 张衡, 潘洁, 巨云为, 等. 基于高光谱数据的马尾松松萎蔫病早期监测[J]. 东北林业大学学报, 2014, 42(11): 115-119. DOI:10.3969/j.issn.1000-5382.2014.11.026.
ZHANG H, PAN J, JU Y W, et al. Early detection of pine wilt disease in Pinus massoniana with hyperspectral data[J]. Journal of Northeast Forestry University, 2014, 42(11): 115-119.
[8] 黄明祥, 龚建华, 李顺, 等. 松材线虫病害高光谱时序与敏感特征研究[J]. 遥感技术与应用, 2012, 27(6): 954-960.
HUANG M X, GONG J H, LI S, et al. Study onpine wilt disease hyper-spectral time series and sensitive features[J]. Remote Sensing Technology and Application, 2012, 27(6): 954-960.
[9] 王震, 张晓丽, 安树杰. 松材线虫病危害的马尾松林木光谱特征分析[J]. 遥感技术与应用, 2007, 22(3): 367-370. DOI:10.3969/j.issn.1004-0323.2007.03.012.
WANG Z, ZHANG X L, AN S J. Spectral characteristics analysis of Pinus massoniana suffered by Bursaphelenchus xylophilus[J]. Remote Sensing Technology and Application, 2007, 22(3): 367-370.
[10] 张红梅, 陆亚刚. 无人机遥感技术国内松材线虫病监测研究综述[J]. 华东森林经理, 2017, 31(3): 29-32.
[11] FASSNACHT F E, LATIFI H, GHOSH A, et al. Assessing the potential of hyperspectral imagery to map bark beetle-induced tree mortality[J]. Remote Sensing of Environment, 2014, 140(1): 533-548. DOI:10.1016/j.rse.2013.09.014.
[12] 武红敢, 常原飞. 高新技术在林业有害生物普查中的应用前景分析[J]. 中国森林病虫, 2014, 33(5): 30-34. DOI:10.3969/j.issn.1671-0886.2014.05.009.
WU H G, CHANG Y F. Application prospects of high-tech in survey of forest pests[J]. Forest Pest and Disease, 2014, 33(5): 30-34.
[13] 乔睿, 唐娉, 石进, 等. WorldView-2影像的红叶松树识别研究[J]. 北京林业大学学报, 2015, 37(11): 33-40. DOI:10.13332/j.1000-1522.20150112.
QIAO R, TANG P, SHI J, et al. Recognition of red-attack pine trees using WorldView-2 imagery[J]. Journal of Beijing Forestry University, 2015, 37(11): 33-40.
[14] DENNISON P E, BRUNELLE A R, CARTER V A. Assessing canopy mortality during a mountain pine beetle outbreak using GeoEye-1 high spatial resolution satellite data[J]. Remote Sensing of Environment, 2010, 114(11): 2431-2435. DOI:10.1016/j.rse.2010.05.018.
[15] HICKE J A, LOGAN J. Mapping whitebark pine mortality caused by a mountain pine beetle outbreak with high spatial resolution satellite imagery[J]. International Journal of Remote Sensing, 2009, 30(17): 4427-4441. DOI:10.1080/01431160802566439.
[16] 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.
[17] QIN L, WANG X, JIANG J, et al. Use hyperspectral remote sensing technique to monitoring pine wood nomatode disease preliminary[C]//LIU W Q, WANG J N. Hyperspectral remote sensing applications and environmental monitoring and safety testing technology. Beijing: Society of Photo-Optical Instrumentation Engineers(SPIE), 2016.
[18] MEDDENS A J H, HICKE J A, VIERLING L A, et al. Evaluating methods to detect bark beetle-caused tree mortality using single-date and multi-date Landsat imagery[J]. Remote Sensing of Environment, 2013, 132(10): 49-58. DOI:10.1016/j.rse.2013.01.002.
[19] MEDDENS A J H, HICKE J A. Spatial and temporal patterns of Landsat-based detection of tree mortality caused by a mountain pine beetle outbreak in Colorado, USA[J]. Forest Ecologyand Management, 2014, 322(3):78-88. DOI:10.1016/j.foreco.2014.02.037.
[20]WULDER M A, WHITE J C, COOPS N C, et al. Multi-temporal analysis of high spatial resolution imagery for disturbance monitoring[J]. Remote Sensing of Environment, 2008, 112(6):2729-2740. DOI: 10.1016/j.rse.2008.01.010.
[21] MEIGS G W, KENNEDY R E, COHEN W B. A landsat time series approach to characterize bark beetle and defoliator impacts on tree mortality and surface fuels in conifer forests[J]. Remote Sensing of Environment, 2011, 115(12): 3707-3718. DOI:10.1016/j.rse.2011.09.009.
[22]WULDER M A, WHITE J C, BENTZ B, et al. Estimating the probability of mountain pine beetle red-attack damage[J]. Remote Sensing of Environment, 2006, 101(2):150-166. DOI: 10.1016/j.rse.2005.12.010.
[23]SKAKUN R S, WULDER M A, FRANKLIN S E. Sensitivity of the thematic mapper enhanced wetness difference index to detect mountain pine beetle red-attack damage[J]. Remote Sensing of Environment, 2003, 86(4):433-443. DOI: 10.1016/S0034-4257(03)00112-3.
[24]LEHMANN J R K, NIEBERDING F, PRINZ T, et al. Analysis of unmanned aerial system-based CIR images in forestry: a new perspective to monitor pest infestation levels[J]. Forests, 2015, 6(3):594-612. DOI: 10.3390/f6030594.
[25]PARK J K, KIM M G. Acquisition of geospatial information for forest management using unmanned aerial vehicle[J]. Advanced Science and Technology Letters, 2014, 62:78-82. DOI: 10.14257/astl.2014.62.20.
[26] 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 Sensing, 2015, 7(11): 15467-15493. DOI:10.3390/rs71115467.
[27] 吕晓君, 王君, 喻卫国, 等. 无人机监测林业有害生物初探[J]. 湖北林业科技, 2016, 45(4):30-33. DOI:10.3969/j.issn.1004-3020.2016.04.008.
Lü X J, WANG J, YU W G, et al. Study on monitoring forests pests and diseases by unmanned aerialvehicle[J]. Hubei Forestry Science and Technology, 2016, 45(4):30-33.
[28] 李卫正, 申世广, 何鹏, 等. 低成本小型无人机遥感定位病死木方法[J]. 林业科技开发, 2014, 28(6): 102-106.DOI:10.13360/j.issn.1000-8101.2014.06.025.
LI W Z, SHEN S G, HE P, et al. A precisely positioning technique by remote sensing the dead trees in stands with inexpensive small UAV[J]. Journal of Forestry Engineering, 2014, 28(6): 102-106.
[29] 胡根生, 张学敏, 梁栋,等. 基于加权支持向量数据描述的遥感图像病害松树识别[J]. 农业机械学报, 2013, 44(5):258-263. DOI:10.6041/j.issn.1000-1298.2013.05.045.
HU G S, ZHANG X M, LIANG D, et al. Infected pine recognition in remote sensing images based on weighted support vector data description[J]. Transactions of the Chinese Society for Agricultural Machinery, 2013,44(5):258-263.
[30] 胡根生, 张学敏, 梁栋. 基于WWSVDD多分类的遥感图像病害松树识别[J]. 北京邮电大学学报, 2014, 37(2):23-27.DOI: 10.13190/j.jbupt.2014.02.006.
HU G S, ZHANG X M, LIANG D. Infected pine recognition in remote sensing images using WWSVDD multi-classification[J]. Journal of Beijing University of Posts and Telecommunications, 2014, 37(2):23-27.
[31]PASHER J, KING D J. Mapping dead wood distribution in a temperate hardwood forest using high resolution airborne imagery[J]. Forest Ecology and Management, 2009, 258(7):1536-1548. DOI: 10.1016/j.foreco.2009.07.009.
[32] 吴琼. 基于遥感图像的松材线虫病区域检测算法研究[D]. 合肥:安徽大学, 2013.
WU Q. Research on Bursaphelenchus xylophilus area detection based on remote sensing image[D]. Hefei: Anhui University, 2013.
[33] 刘焕秀, 武海卫, 杨晓霞, 等. 黄岛区林业病虫害发生的现状、原因及防治措施探究[J]. 青海农林科技, 2017(2): 88-92. DOI:10.3969/j.issn.1004-9967.2017.02.024.
LIU H X, WU H W, YANG X X, et al. Current situation, causes and control measures of forest pests and diseases in Huangdao District[J]. Science and Technology of Qinghai Agriculture and Forestry, 2017(2): 88-92.
[34] CHENG H D, JIANG X H, SUN Y, et al. Color image segmentation: advances and prospects[J]. Pattern Recognition, 2001, 34(12): 2259-2281. DOI:10.1016/s0031-3203(00)00149-7.
[35] DONY R D, WESOLKOWSKI S. Edge detection on color images using RGB vector angles[C]//MENG M. Engineering solutions for the next millennium. 1999 IEEE Canadian Conference on Electrical and Computer Engineering, Edmonton, 1999: 687-692.
[36] PEKEL J F, VANCUTSEM C, BASTIN L, et al. A near real-time water surface detection method based on HSV transformation of MODIS multi-spectral time series data[J]. Remote Sensing of Environment, 2014, 140: 704-716. DOI:10.1016/j.rse.2013.10.008.
[37] JAIN A K. Fundamentals of digital image processing[M]. New Jersey: Prentice Hall, 1989.
[38]葛宏立, 王鑫, 杜华强, 等. 无人机航片松材线虫病病死木的膨胀:剔除信息提取法: CN 101770577[P]. 2010-07-07.
[39] 黄昌狄, 徐芳. 基于真彩色高分辨遥感影像稀疏植被覆盖检测[J]. 测绘地理信息, 2016, 41(5):42-46. DOI:10.14188/j.2095-6045.2016.05.010.
HUANG C D, XU F. Extraction of sparse vegetation based on true color high resolution remote sensing image[J]. Journal of Geomatics, 2016, 41(5):42-46.
[40] PEKEL J F, CECCATO P, VANCUTSEM C, et al. Development and application of multi-temporal colorimetric transformation to monitor vegetation in the desert locust habitat[J]. IEEE Journal of Selected Topics in Applied Earth Observationsand Remote Sensing, 2011, 4(2): 318-326. DOI:10.1109/jstars.2010.2052591.
[41] 王成波. 面向松材线虫病监测的无人机影像变色松树提取与地面调查综合技术研究[D]. 北京: 中国科学院大学, 2015.
WANG C B. Study on automatic recognition of pinewood nematode infested pine trees on UVA images and services-oriented informationized field investigations[D].Beijing: University of Chinese Academy of Sciences, 2015.
[42] ORTIZ S M, BREIDENBACH J, KÄNDLER G. Early detection of bark beetle green attack using TerraSAR-X and RapidEye data[J]. Remote Sensing, 2013, 5(4):1912-1931.DOI:10.3390/rs5041912.
[43] EITEL J U H, VIERLING L A, LITVAK M E, et al. Broadband, red-edge information from satellites improves early stress detection in a New Mexico conifer woodland[J]. Remote Sensing of Environment, 2011, 115(12):3640-3646.DOI: 10.1016/j.rse.2011.09.002.
[44] 马菁, 刘维, 张晓丽. 遥感在松材线虫病早期监测预测上的研究进展[J]. 林业调查规划, 2011, 36(5): 75-80. DOI:10.3969/j.issn.1671-3168.2011.05.018.
MA J, LIU W, ZHANG X L. Remote sensing research on early monitoring and prediction of pine wilt disease[J]. Forest Inventory and Planning, 2011, 36(5): 75-80.
[45] SAFRANYIK L, CARROLL A L. The biology and epidemiology of the mountain pine beetle in lodgepole pine forests[C]// SAFRANYIK L, WILSON B. The mountain pine beetle: a synthesis of biology, management, and impacts on lodgepole pine. Victoria B C: Natural Resources Canada, Canadian Forest Service, 2006:123-154.

Last Update: 2019-05-15