基于线性谱聚类的林地图像中枯死树监测
|
摘要
【目的】将基于线性谱聚类超像素的方法应用在森林病虫害防治领域,可智能监测无人机森林虫害图像中的枯死树,为森林有害生物的监测工作提供技术支撑。【方法】分别以湖北省受松材线虫与辽宁省受红脂大小蠹侵害的松林无人机图像为试验数据,首先使用线性谱聚类超像素分割算法将图像划分为多个超像素;然后基于枯死树木的颜色特征,初步提取可能为枯死树的超像素区域;最后基于枯死树木与其他干扰地物具有不同的纹理特征,计算超像素的区域密度和缝隙量,利用支持向量机对初步提取的超像素进行分类,从而检测出图像中的枯死树。【结果】基于线性谱聚类超像素和支持向量机的枯死树监测方法可有效排除与枯死树木颜色相近的其他干扰地物,较准确地提取出枯死树木。使用该方法与基于植被颜色指数的阈值分割方法、基于简单线性迭代聚类超像素和随机森林的方法,对35幅受灾松林无人机图像进行试验,并选用交并比、虚警率和漏检率3个评价指标对3种方法进行定量对比分析。结果表明,基于线性谱聚类超像素的方法监测出的枯死树区域最精确,其监测结果与人工检测结果的交并比均值大于58%,且虚警率和漏检率均优于另外2种方法。【结论】基于线性谱聚类超像素的枯死树监测方法能实现松林中枯死树的快速、准确检测及定位。
【Objective】In this paper,the method based on linear spectral clustering(LSC) superpixel was applied in the field of forest pest control,which was able to intelligently monitor dead trees in forest pest images taken from the unmanned aerial vehicle(UAV),and provide technological support for intelligently monitoring of forest pests. 【Method】The UAV images of pine forests infected by Bursaphelenchus xylophilus and Dendroctonus valens respectively from Hubei and Liaoning provinces were chosen as the experiment data. Firstly,the linear spectral clustering superpixel algorithm was used to divide the image into many compact and uniform superpixels. Then,on a basis of the different color characteristics of dead trees and healthy trees,the superpixels which might be dead trees were initially extracted. Next,based on the different texture features of dead trees and other red disturbances,the area density and the lacunarity of the initially extracted superpixels were calculated. Finally,the support vector machine based on texture features was used to classify the initially extracted superpixels to detect dead trees in the image.【Result】The method based on LSC superpixel was able to exclude other interference objects that were similar in color to dead trees,and accurately extracted dead trees. The 35 UAV images of the pest-infected pine forest were used for comparing quantitatively this method with the other two methods. One is threshold segmentation method based on vegetation color index,and the other is simple linear iterative clustering(SLIC) superpixel and random forest method. Furthermore,the three evaluation indexes: intersection over union,the false alarm rate and the misdetection rate were used to quantitatively compare and analyze the three methods.The experimental results showed that the algorithm based on LSC superpixel and SVM was the most accurate to detect dead trees. The mean of intersection over union between this method's result and manual detection result was more than 58% and the false alarm rate and the misdetection rate were better than the other two algorithms. 【Conclusion】Our results showed that the dead tree monitoring method based on LSC superpixel was able to detect and locate dead trees quickly and precisely in the UAV pine forest images and effectively protect forest resources.
【Objective】In this paper,the method based on linear spectral clustering(LSC) superpixel was applied in the field of forest pest control,which was able to intelligently monitor dead trees in forest pest images taken from the unmanned aerial vehicle(UAV),and provide technological support for intelligently monitoring of forest pests. 【Method】The UAV images of pine forests infected by Bursaphelenchus xylophilus and Dendroctonus valens respectively from Hubei and Liaoning provinces were chosen as the experiment data. Firstly,the linear spectral clustering superpixel algorithm was used to divide the image into many compact and uniform superpixels. Then,on a basis of the different color characteristics of dead trees and healthy trees,the superpixels which might be dead trees were initially extracted. Next,based on the different texture features of dead trees and other red disturbances,the area density and the lacunarity of the initially extracted superpixels were calculated. Finally,the support vector machine based on texture features was used to classify the initially extracted superpixels to detect dead trees in the image.【Result】The method based on LSC superpixel was able to exclude other interference objects that were similar in color to dead trees,and accurately extracted dead trees. The 35 UAV images of the pest-infected pine forest were used for comparing quantitatively this method with the other two methods. One is threshold segmentation method based on vegetation color index,and the other is simple linear iterative clustering(SLIC) superpixel and random forest method. Furthermore,the three evaluation indexes: intersection over union,the false alarm rate and the misdetection rate were used to quantitatively compare and analyze the three methods.The experimental results showed that the algorithm based on LSC superpixel and SVM was the most accurate to detect dead trees. The mean of intersection over union between this method's result and manual detection result was more than 58% and the false alarm rate and the misdetection rate were better than the other two algorithms. 【Conclusion】Our results showed that the dead tree monitoring method based on LSC superpixel was able to detect and locate dead trees quickly and precisely in the UAV pine forest images and effectively protect forest resources.
引文
丁雷龙,李强子,杜鑫,等.2016.基于无人机图像颜色指数的植被识别.国土资源遥感,28(1):78-86.(Ding L L,Li Q Z,Du X,et al.2016.Vegetation extraction method based on color indices from UAV images.Remote Sensing for Land and Resources,28(1):78-86.[in Chinese])
费运巧,刘文萍,陆鹏飞,等.2017.基于无人机图像分形特征的油松受灾级别判定.计算机应用研究,34(4):1253-1256.(Fei Y Q,Liu W P,Lu P F,et al.2017.Judgment on disaster classification of Chinese pine based on fractal features in UAVimage.Application Research of Computers,34(4):1253-1256.[in Chinese])
韩阳阳,王焱,项杨,等.2015.基于Maxent生态位模型的松材线虫在中国的适生区预测分析.南京林业大学学报:自然科学版,39(1):6-10.(Han Y Y,Wang Y,Xiang Y,et al.2015.Prediction of potential distribution of Bursaphelenchus xylophilus in China based on Maxent ecological niche model.Journal of Nanjing Forestry University:Natural Sciences Edition,39(1):6-10.[in Chinese])
胡根生,张学敏,梁栋,等.2013.基于加权支持向量数据描述的遥感图像病害松树识别.农业机械学报,44(5):258-263.(Hu G S,Zhang X M,Liang D,et al.2013.Infected pine recognition in remote sensing images based on weighted support vector data description.Transactions of the Chinese Society for Agricultural Machinery,44(5):258-263.[in Chinese])
李卫正,申世广,何鹏,等.2014.低成本小型无人机遥感定位病死木方法.林业科技开发,28(6):102-106.(Li W Z,Shen S G,He P,et al.2014.A precisely positioning technique by remote sensing the dead trees in stands with inexpensive small UAV.China Forestry Science&Technology,28(6):102-106.[in Chinese])
刘丽,匡纲要.2009.图像纹理特征提取方法综述.中国图象图形学报,14(4):622-635.(Liu L,Kuang G Y.2009.Overview of image textural feature extraction methods.Journal of Image and Graphics,14(4):622-635.[in Chinese])
吕晓君,王君,喻卫国,等.2016.无人机监测林业有害生物初探.湖北林业科技,45(4):30-33.(LüX J,Wang J,Yu W G,et al.2016.Study on monitoring forest pests and diseases by Unmanned Aerial Vehicle.Hubei Forestry Science&Technology,45(4):30-33.[in Chinese])
宋熙煜,周利莉,李中国,等.2015.图像分割中的超像素方法研究综述.中国图象图形学报,20(5):599-608.(Song X Y,Zhou L L,Li Z G,et al.2015.Review on superpixel methods in image segmentation.Journal of Image and Graphics,20(5):599-608.[in Chinese])
王成波.2015.变色松树的图像识别与地面调查综合技术研究.北京:中国科学院大学博士学位论文.(Wang C B.2015.Study on integrated technology of image recognition and field investigation of infested pine trees.Beijing:PhD thesis of University of Chinese Academy of Sciences.[in Chinese])
徐洪儒,李颖超,李镇宇.2006.红脂大小蠹在中国成灾原因及扩散趋势分析.植物检疫,20(5):278-280.(Xu H R,Li Y C,Li Z Y.2006.The analysis of outbreak reason and spread directions of dendroctonus valens.Plant Quarantine,20(5):278-280.[in Chinese])
赵建兴.2006.红脂大小蠹生物防治研究.北京:中国林业科学研究院博士学位论文.(Zhao J X.2006.Study on biological control of red turpentine beetle dendroctonus valens(Coleoptera::Scolytidae)in China.Beijing:PhD thesis of Chinese Academy of Forestry.[in Chinese])
Achanta R,Shaji A,Smith K,et al.2012.SLIC superpixels compared to state-of-the-art superpixel methods.IEEE Transactions on Pattern Analysis&Machine Intelligence,34(11):2274-2282.
Chen J S,Li Z Q,Huang B.2017.Linear spectral clustering superpixel.IEEE Transactions on Image Processing A Publication of the IEEESignal Processing Society,26(7):3317-3330.
Dhillon I S,Guan Y Q,Kulis B.2004.Kernel K-means:spectral clustering and normalized cuts.proceedings of the Tenth ACMSIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,551-556.
Dhillon I S,Guan Y Q,Kulis B.2007.Weighted graph cuts without eigenvectors a multilevel approach.IEEE Transactions on Pattern Analysis and Machine Intelligence,29(11):1944-1957.
Hall R J,Castilla G,White J C,et al.2016.Remote sensing of forest pest damage:A review and lessons learned from a Canadian perspective.The Canadian Entomologist,148(S1):S296-S356.
Kim H,Lee S,Lee D,et al.2015.Real-time human pose estimation and gesture recognition from depth images using superpixels and svm classifier.Sensors,15(6):12410-12427.
Kohavi R.1995.A study of cross-validation and bootstrap for accuracy estimation and model selection.International Joint Conference on Artificial Intelligence,14(2):1137-1145.
Laliberte A S,Rango A.2009.Texture and scale in object-based analysis of subdecimeter resolution unmanned aerial vehicle(UAV)imagery.IEEETransactions on Geoscience&Remote Sensing,47(3):761-770.
Liu W P,Wu L,Hung C.2013.Texture segmentation based on Ada Boost classifier using fractal feature-lacunarity.Journal of Information&Computational Science,10(4):997-1006.
Meyer G E,Neto J C.2008.Verification of color vegetation indices for automated crop imaging applications.Computers&Electronics in Agriculture,63(2):282-293.
Rahman M A,Wang Y.2016.Optimizing intersection-over-union in deep neural networks for image segmentation.International Symposium on Visual Computing,Springer,234-244.
Rodriguez G R,Thomas S,Cerro J,et al.2012.A real-time method to detect and track moving objects(datmo)from unmanned aerial vehicles(uavs)using a single camera.Remote Sensing,4(4):1090-1111.
Shi J,Malik J.2000.Normalized cuts and image segmentation.IEEETransactions on Pattern Analysis and Machine Intelligence,22(8):888-905.
Suykens J A K,Vandewalle J.1999.Least squares support vector machine classifiers.Neural Processing Letters,9(3):293-300.
Torresan C,Berton A,Carotenuto F,et al.2017.Forestry applications of UAVS in Europe:a review.International Journal of Remote Sensing,38(8-10):2427-2447.
Von Luxburg U.2007.A tutorial on spectral clustering.Statistics and Computing,17(4):395-416.
Woebbecke D M,Meyer G E,von Bargen K,et al.1995.Color indices for weed identification under various soil,residue,and lighting conditions.Transactions of the ASAE,38(1):259-269.
Yan Z L,Sun J,Don O,et al.2005.The red turpentine beetle,Dendroctonus valens Leconte(Scolytidae):an exotic invasive pest of pine in china.Biodiversity and Conservation,14(7):1735-1760.
Yuan Y,Hu X Y.2016.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,41(B1):1093-1098.
费运巧,刘文萍,陆鹏飞,等.2017.基于无人机图像分形特征的油松受灾级别判定.计算机应用研究,34(4):1253-1256.(Fei Y Q,Liu W P,Lu P F,et al.2017.Judgment on disaster classification of Chinese pine based on fractal features in UAVimage.Application Research of Computers,34(4):1253-1256.[in Chinese])
韩阳阳,王焱,项杨,等.2015.基于Maxent生态位模型的松材线虫在中国的适生区预测分析.南京林业大学学报:自然科学版,39(1):6-10.(Han Y Y,Wang Y,Xiang Y,et al.2015.Prediction of potential distribution of Bursaphelenchus xylophilus in China based on Maxent ecological niche model.Journal of Nanjing Forestry University:Natural Sciences Edition,39(1):6-10.[in Chinese])
胡根生,张学敏,梁栋,等.2013.基于加权支持向量数据描述的遥感图像病害松树识别.农业机械学报,44(5):258-263.(Hu G S,Zhang X M,Liang D,et al.2013.Infected pine recognition in remote sensing images based on weighted support vector data description.Transactions of the Chinese Society for Agricultural Machinery,44(5):258-263.[in Chinese])
李卫正,申世广,何鹏,等.2014.低成本小型无人机遥感定位病死木方法.林业科技开发,28(6):102-106.(Li W Z,Shen S G,He P,et al.2014.A precisely positioning technique by remote sensing the dead trees in stands with inexpensive small UAV.China Forestry Science&Technology,28(6):102-106.[in Chinese])
刘丽,匡纲要.2009.图像纹理特征提取方法综述.中国图象图形学报,14(4):622-635.(Liu L,Kuang G Y.2009.Overview of image textural feature extraction methods.Journal of Image and Graphics,14(4):622-635.[in Chinese])
吕晓君,王君,喻卫国,等.2016.无人机监测林业有害生物初探.湖北林业科技,45(4):30-33.(LüX J,Wang J,Yu W G,et al.2016.Study on monitoring forest pests and diseases by Unmanned Aerial Vehicle.Hubei Forestry Science&Technology,45(4):30-33.[in Chinese])
宋熙煜,周利莉,李中国,等.2015.图像分割中的超像素方法研究综述.中国图象图形学报,20(5):599-608.(Song X Y,Zhou L L,Li Z G,et al.2015.Review on superpixel methods in image segmentation.Journal of Image and Graphics,20(5):599-608.[in Chinese])
王成波.2015.变色松树的图像识别与地面调查综合技术研究.北京:中国科学院大学博士学位论文.(Wang C B.2015.Study on integrated technology of image recognition and field investigation of infested pine trees.Beijing:PhD thesis of University of Chinese Academy of Sciences.[in Chinese])
徐洪儒,李颖超,李镇宇.2006.红脂大小蠹在中国成灾原因及扩散趋势分析.植物检疫,20(5):278-280.(Xu H R,Li Y C,Li Z Y.2006.The analysis of outbreak reason and spread directions of dendroctonus valens.Plant Quarantine,20(5):278-280.[in Chinese])
赵建兴.2006.红脂大小蠹生物防治研究.北京:中国林业科学研究院博士学位论文.(Zhao J X.2006.Study on biological control of red turpentine beetle dendroctonus valens(Coleoptera::Scolytidae)in China.Beijing:PhD thesis of Chinese Academy of Forestry.[in Chinese])
Achanta R,Shaji A,Smith K,et al.2012.SLIC superpixels compared to state-of-the-art superpixel methods.IEEE Transactions on Pattern Analysis&Machine Intelligence,34(11):2274-2282.
Chen J S,Li Z Q,Huang B.2017.Linear spectral clustering superpixel.IEEE Transactions on Image Processing A Publication of the IEEESignal Processing Society,26(7):3317-3330.
Dhillon I S,Guan Y Q,Kulis B.2004.Kernel K-means:spectral clustering and normalized cuts.proceedings of the Tenth ACMSIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,551-556.
Dhillon I S,Guan Y Q,Kulis B.2007.Weighted graph cuts without eigenvectors a multilevel approach.IEEE Transactions on Pattern Analysis and Machine Intelligence,29(11):1944-1957.
Hall R J,Castilla G,White J C,et al.2016.Remote sensing of forest pest damage:A review and lessons learned from a Canadian perspective.The Canadian Entomologist,148(S1):S296-S356.
Kim H,Lee S,Lee D,et al.2015.Real-time human pose estimation and gesture recognition from depth images using superpixels and svm classifier.Sensors,15(6):12410-12427.
Kohavi R.1995.A study of cross-validation and bootstrap for accuracy estimation and model selection.International Joint Conference on Artificial Intelligence,14(2):1137-1145.
Laliberte A S,Rango A.2009.Texture and scale in object-based analysis of subdecimeter resolution unmanned aerial vehicle(UAV)imagery.IEEETransactions on Geoscience&Remote Sensing,47(3):761-770.
Liu W P,Wu L,Hung C.2013.Texture segmentation based on Ada Boost classifier using fractal feature-lacunarity.Journal of Information&Computational Science,10(4):997-1006.
Meyer G E,Neto J C.2008.Verification of color vegetation indices for automated crop imaging applications.Computers&Electronics in Agriculture,63(2):282-293.
Rahman M A,Wang Y.2016.Optimizing intersection-over-union in deep neural networks for image segmentation.International Symposium on Visual Computing,Springer,234-244.
Rodriguez G R,Thomas S,Cerro J,et al.2012.A real-time method to detect and track moving objects(datmo)from unmanned aerial vehicles(uavs)using a single camera.Remote Sensing,4(4):1090-1111.
Shi J,Malik J.2000.Normalized cuts and image segmentation.IEEETransactions on Pattern Analysis and Machine Intelligence,22(8):888-905.
Suykens J A K,Vandewalle J.1999.Least squares support vector machine classifiers.Neural Processing Letters,9(3):293-300.
Torresan C,Berton A,Carotenuto F,et al.2017.Forestry applications of UAVS in Europe:a review.International Journal of Remote Sensing,38(8-10):2427-2447.
Von Luxburg U.2007.A tutorial on spectral clustering.Statistics and Computing,17(4):395-416.
Woebbecke D M,Meyer G E,von Bargen K,et al.1995.Color indices for weed identification under various soil,residue,and lighting conditions.Transactions of the ASAE,38(1):259-269.
Yan Z L,Sun J,Don O,et al.2005.The red turpentine beetle,Dendroctonus valens Leconte(Scolytidae):an exotic invasive pest of pine in china.Biodiversity and Conservation,14(7):1735-1760.
Yuan Y,Hu X Y.2016.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,41(B1):1093-1098.