Submeter remote sensing image recognition of trees based on Landsat 8 OLI support.
-
摘要: 为研究高空间分辨率遥感影像与多光谱遥感影像协同进行面向对象树种识别的有效性,本研究以QuickBird高空间分辨率(全色0.61 m)和Landsat 8 OLI(30 m)遥感影像为基础数据,在分类的过程中采用2种分割方案(有Landsat 8 OLI遥感影像辅助的QuickBird遥感影像分割和无Landsat 8 OLI遥感影像辅助的QuickBird遥感影像分割)进行多尺度分割,对2种分割方案进行比较。基于QuickBird遥感影像和Landsat 8 OLI遥感影像提取光谱、纹理、空间3方面68种分类特征,应用最邻近分类法和支持向量机分类方法进行面向对象树种分类,采用相同的分类系统、统一的分割尺度以及同一套验证样本,利用Kappa系数、总精度、生产者精度和用户精度4个评价指标进行精度评价。结果表明:单独使用QuickBird高空间分辨率遥感影像的分割结果优于QuickBird高空间分辨率遥感影像与Landsat 8 OLI遥感影像协同分割的结果,最优分割阈值与合并阈值分别为25和90。在最优分割结果的基础上,多光谱Landsat 8 OLI遥感影像与QuickBird高空间分辨率遥感影像协同进行面向对象分类,最邻近分类法和支持向量机分类方法的分类总精度分别为85.35%(Kappa=0.701 3)和88.12%(Kappa=0.853 6);单独使用QuickBird高空间分辨率遥感影像进行面向对象分类,2种方法的分类总精度分别为79.67%(Kappa=0.693 9)和83.33%(Kappa=0.792 5)。QuickBird遥感影像在Landsat 8 OLI遥感影像辅助下,分类结果的地物边界更加清晰,总体精度及主要树种识别精度均得到了提高。研究成果应用在实地森林调查与区划时可有效缩短调査时间、减少调查成本、降低劳动强度、提高成果质量。Abstract: In order to study the validity of the object-based identification of tree species with high spatial resolution remote sensing image (QuickBird) and multi spectral remote sensing image (Landsat 8 OLI) coordinated, based on QuickBird high spatial resolution (panchromatic 0.61 m) remote sensing image and Landsat 8 OLI(30 m) remote sensing image, we used 2 segmentation schemes (segmentation based on QuickBird remote sensing image with Landsat 8 OLI remote sensing image as an auxiliary or not) to do multi-scale segmentation, and compared the 2 segmentation schemes in the classification processing. This research applied nearest neighbor classification and support vector machine object-based classification methods, the same classification system, the unified segmentation scale and the same set of validation samples to classify tree species with 68 classification features in terms of spectral, texture and spatial extracted by QuickBird remote sensing image and Landsat 8 OLI remote sensing image, and then take use of Kappa coefficient, total accuracy, producer accuracy and user accuracy to evaluate the accuracy. The results showed that the segmentation result based on QuickBird high spatial resolution remote sensing image only was better than that based on QuickBird high spatial resolution remote sensing image and Landsat 8 OLI remote sensing image coordinated. The best segmentation threshold was 25 and the best merging threshold was 90. On the basis of the best segmentation threshold, applying Landsat 8 OLI multi spectral remote sensing image and QuickBird high spatial resolution remote sensing image together to take the object-based classification, the total accuracy of nearest neighbor classification method and support vector machine classification method was 85.35% (Kappa=0.701 3) and 88.12% (Kappa=0.853 6). And the total accuracy of the above two methods was 79.67% (Kappa=0.693 9) and 83.33% (Kappa=0.792 5) when using the QuickBird high spatial resolution remote sensing image only. Under the support of Landsat 8 OLI remote sensing image, object boundary of the classification result is clearer, the total accuracy and the accuracy of major tree species are significantly improved. The research results can effectively shorten the time and reduce the cost of investigation and survey, reduce labor intensity, improve the quality of products when it was applied in field forest survey and zoning.
-
Keywords:
- object-based method /
- QuickBird /
- forest classification /
- high spatial resolution
-
-
[1] HELLER R C,DOVERSPIKE G E,ALDRICH R C. Identification of tree species on large-scale panchromatic and color aerial photographs[M]. Washington D C: USDA Handbook,1964,261:1-17.
[1] [2] VIEIRA I C G,ALMEIDA A S D,DAVIDSON E A,et al. Classifying successional forests using Landsat spectral properties and ecological characteristics in eastern Amazonia[J]. Remote Sensing of Environment,2003,87(4):470-481.
[2] HAN N,ZHANG X Y,WANG X M,et al. Extraction of Torreya grandis Merrillii based on objeet-oriented method from IKONOS image[J]. Journal of Zhejiang University (Agriculture Life Siciences),2009,35(6):670-676.
[3] WOLTER P T,HOST G E,MLADENOFF D J,et al. Improved forest classification in the northern Lake States using multi-temporal Landsat imagery[J]. Photogrammetric Engineering and Remote Sensing,1995,61(9):1129-1143.
[3] SUN X Y,DU H Q,HAN N,et al.Multi-scale segmentation, object-based extraction of moso bamboo forest from SPOT5 imagery[J]. Scientia Silvae Sinicae,2013,49(10):80-87.
[4] LI C G, SHAO G F. Using Landsat 7 ETM+ images as ancillary data for forest cover classification of SPOT 5 images[J]. Journal of Beijing Forestry University,2010,32(4):1-5.
[4] COLSTOUN E C B D,STORY M H,THOMPSON C,et al. National Park vegetation mapping using multi-temporal Landsat 7 data and a decision tree classifier[J]. Remote Sensing of Environment,2003,85(3):316-327.
[5] DENG S B, CHEN Q J,DU H J, et al. Remote sensing image processing method of ENVI[M]. 2nd ed.Beijing: Higher Education Press,2014:204-217.
[5] CLARK M L,ROBERTS D A,CLARK D B. Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales[J]. Remote Sensing of Environment,2005,96(3):375-398.
[6] WANG T T,LI S S,LI A, et al. Land cover classification in Beijing using Landsat 8 image[J]. Journal of Image and Graphics,2015,20(9):1275-1284.
[6] GOODENOUGH D G,NIEMANNK O,PEARLMAN J S,et al. Processing Hyperion and ALI for forest classification[J]. IEEE Transactions on GeoScience and Remote Sensing,2003,41(6):1321-1331.
[7] LAWRENCE R L,WOOD S D,SHELEY R L. Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (randomForest)[J]. Remote Sensing of Environment,2006,100(3):356-362.
[7] XU H Q, TANG F. Analysis of new characteristics of the first Landsat 8 image and their eco-environmental significance[J]. Acta Ecologica Sinica,2013,33(11):3249-3257.
[8] MARTIN M E,NEWMAN S D,ABER J D,et al. Determining forest species composition using high spectral resolution remote sensing data[J]. Remote Sensing of Environment,1998,65(3):249-254.
[9] GOODENOUGH D G,CHEN H, DYK A,et al. Multisensor data fusion for aboveground carbon estimation[C/OL]∥Proceedings of XXVIIIth General Assembly of the International Union of Radio Science (URSI). [2015-12-01]. http:∥paperuri:(79e7798 b3e791ff0d9f6c93b22d267b6).
[10] WULDER M A,HALL R J,COOPS N C,et al. High spatial resolution remotely sensed data for ecosystem characterization[J]. BioScience,2009,54:511-521.
[11] FRANKLIN S E. Using spatial co-occurrence texture to increase forest structure and species classification accuracy[J]. Photogrammetric Engineering and Remote Sensing,2001,67(7):849-855.
[12] TREITZ P,HOWARTH P. Integrating spectral,spatial,and terrain variables for forest ecosystem classification[J]. Photogrammetric Engineering and Remote Sensing,2000,66(3):305-318.
[13] ZHANG C. Geostatistical and texture analysis of airborne-acquired images used in forest classification[J]. International Journal of Remote Sensing,2004,25(25):859-865.
[14] FLANDERS D,HALLBEYER M,PEREVERZOFF J. Preliminary evaluation of eCognition object-based software for cut block delineation and feature extraction[J]. Canada Journal of Remote Sensing,2003,29(4):441-452.
[15] KOSAKA N, AKIYAMA T,TSAI B,et al. Forest classification using data fusion of multispectral and panchromatic high-resolution satellite imageries[J]. IEEE International Geoscience and Remote Sensing Symposium,2005,4:2980-2983.
[16] 韩凝,张秀英,王小明,等.基于面向对象的IKONOS影像香榧树分布信息提取研究[J].浙江大学学报(农业与生命科学版),2009,35(6):670-676. [17] BRENNER J C,CHRISTMAN Z,ROGAN J. Segmentation of Landsat thematic mapper imagery improves buffelgrass (Pennisetum ciliare) pasture mapping in the Sonoran Desert of Mexico[J]. Applied Geography,2012,34:569-575.
[18] 孙晓艳,杜华强,韩凝,等.面向对象多尺度分割的SPOT 5影像毛竹林专题信息提取[J].林业科学,2013,49(10):80-87. [19] CHUBEY M S. Object-based analysis of IKONOS-2 imagery for extraction of forest inventory parameters[J]. Photogrammetric Engineering and Remote Sensing,2006,72(4):383-394.
[20] YU Q,GONG P,CLINTON N,et al. Object-based detailed vegetation classification with airborne high spatial resolution remote sensing imagery[J]. Photogrammetric Engineering and Remote Sensing,2006,72(7):799-811.
[21] SUN X Y,DU H Q,HAN N,et al. Synergistic use of Landsat TM and SPOT5 imagery for object-based forest classification[J]. Journal of Applied Remote Sensing,2014,8(9):1-15.
[22] 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 Sensing of Environment,2009,113(3):518-531.
[23] CLARK M L,ROBERTS D A,EWEL J J,et al. Estimation of tropical rain forest aboveground biomass with small-footprint lidar and hyperspectral sensors[J]. Remote Sensing of Environment,2011,115(11):2931-2942.
[24] 李春干,邵国凡. Landsat 7 ETM+ 图像用作SPOT 5图像森林分类的辅助数据研究[J].北京林业大学学报,2010,32(4):1-5. [25] KE Y,QUACKENBUSH L J,IM J. Synergistic use of QuickBird multispectral imagery and LIDAR data for object-based forest species classification[J]. Remote Sensing of Environment,2010,114(6):1141-1154.
[26] HAN N,WANG K,YU L,et al. Integration of texture and landscape features into object-based classification for delineating Torreya using IKONOS imagery[J]. International Journal of Remote Sensing,2012,33(7):2003-2033.
[27] 邓书斌,陈秋锦,杜会建,等. ENVI遥感影像处理方法[M].2版.北京:高等教育出版社,2014: 204-217. [28] CORTES C,VAPNIK V. Support vector networks [J]. Machine Learning,1995,20(3):273-297.
[29] JANSSEN L L F,FRANS J M,WEL V D. Accuracy assessment of satellite derived land cover data:a review[J]. Potogammetric Engineering and Remote Sensing,1994,60(4):419-426.
[30] 王婷婷,李山山,李安,等.基于Landsat 8卫星影像的北京地区土地覆盖分类[J].中国图像图形学报,2015,20(9):1275-1284. [31] 徐涵秋,唐菲.新一代Landsat 8系列卫星:Landsat 8遥感影像新增特征及其生态环境意义[J].生态学报,2013,33(11):3249-3257. [32] CHEN J M, BLACK T A, PRICE D T,et al. Model for calculating photosynthetic photon flux densities in forest openings on slope[J]. Journal of Applied Meteorology,2010,32(10):1656-1665.
-
期刊类型引用(11)
1. 陈晓林，陈亚鹏，李卫红，王玉阳. 干旱区不同地下水埋深下胡杨细根空间分布特征. 植物科学学报. 2018(01): 45-53 . 
百度学术
2. 王琪，容丽. 环境影响下植物根系的生长分布特征研究进展. 贵阳学院学报(自然科学版). 2015(04): 61-66 . 百度学术
3. 杨婵婵，李宏，郭光华. 红枣中龄期吸收根和输导根空间分布特征. 北京农业. 2013(09): 30-32 . 百度学术
4. 王磊，马英杰，赵经华，洪明，游磊. 干旱区滴灌核桃树有效吸水根系的分布与模拟研究. 节水灌溉. 2013(10): 17-20 . 百度学术
5. 荐圣淇，赵传燕，方书敏，余凯，彭守璋，柳逸月，李彦甫. 基于地理信息技术油松(Pinus tabuliformis)根长密度估算及空间分布特征分析. 干旱区地理. 2012(04): 599-606 . 百度学术
6. 田盼盼，董新光，姚鹏亮，谢美玲. 干旱区不同灌溉方式下枣树根系分布特性研究. 水资源与水工程学报. 2012(01): 102-105 . 百度学术
7. 叶茂，徐海量，王晓峰，申瑞新. 塔里木河下游阿拉干断面胡杨根系空间分布规律研究. 西北植物学报. 2011(04): 801-807 . 百度学术
8. 李建林，冯起，司建华，常宗强，巨登三. 极端干旱区胡杨根系分布对土壤水分的响应. 干旱区资源与环境. 2009(11): 186-190 . 百度学术
9. 杨胜利，刘洪禄，郝仲勇，吴文勇. 畦灌条件下樱桃树根系的空间分布特征. 农业工程学报. 2009(S1): 34-38 . 百度学术
10. 李建林，冯起，司建华，常宗强，巨登三，郭巧玲. 极端干旱区胡杨根系吸水的二维数学模型. 生态学杂志. 2009(06): 1188-1193 . 百度学术
11. 冯起，司建华，李建林，席海洋. 胡杨根系分布特征与根系吸水模型建立. 地球科学进展. 2008(07): 765-772 . 百度学术
其他类型引用(10)
计量
- 文章访问数: 2156
- HTML全文浏览量: 322
- PDF下载量: 64
- 被引次数: 21
下载:
