收稿：2015-12-24，
纸质出版：2017-01
移动端阅览
传统的多时相遥感图像分类大多拘泥于单一特征，本文基于多时相的Landsat 8遥感数据，开展了综合多特征的特征提取与特征选择方法研究。综合了NDVI时间序列、最佳时相反射率光谱特征以及纹理特征作为初始分类特征，并采用基于属性重要度的粗糙集特征选择算法对其进行特征约简。分类结果表明：(1)利用初始分类特征，分类的总体精度达到92.81%，棉花提取精度达87.4%，与仅利用NDVI时间序列相比，精度分别提高5.53%和5.05%；(2)利用粗糙集选择后的特征分类，分类总体精度可达93.66%，棉花分类精度达92.73%，与初始分类特征提取结果相比，棉花分类精度提高5.33%。基于属性重要度的粗糙集特征选择不仅提高了分类精度，同时有效降低了分类器的计算复杂度。
Cotton is a significant economic crop
and cotton extraction plays an important role in effective and controllable agricultural management. Multi-temporal remote sensing images have been widely used in cotton extraction
but these studies mainly focused on sole features
such as the Normalized Difference Vegetation Index (NDVI). An effective method of integrated multi-features based on multi-temporal Landsat 8 images was proposed to extract cotton information.In this study
we chose north-central Shawan County in Xinjiang Uygur Autonomous Region as the study area. Nine images taken by Landsat 8 in 2013 were collected for cotton extraction. NDVI time series were generated to characterize the phenological pattern of each land cover type. The optimal temporal reflectance image was selectedby analyzing the difference in NDVI profile between cotton and other crop types. Texture features were calculated by the gray-level co-occurrence matrix method. NDVI time series
optimal temporal reflectance image
and texture features were combined as the original classification features. When the training samples were sufficient
butthe featureswereexcessive
the classification accuracy may decrease because of redundant information. We completed feature selection by using the rough set method and then obtained the selective features of the original features. The NDVI time series
original features
and selective features were used for classification by the support vector machine. The cotton distribution map was generated based on the classification result of the highest accuracy. Finally
we evaluated the accuracy of classification results by confusion matrix.①The selection of the optimal temporal reflectance image for cotton identification is important
and the optimum phase of this studyis on September 4. In this period
wheat was harvested; corn and sunflower were in the mature period; andcotton was in the blossom period. Significant differences were observed among these crops in the optimum phase. ②The original features achieved accuracies of 87.4% and 87.93% for cotton producers and users
respectively
and the overall accuracy was 92.81%. Compared with the classification results of the NDVI time series
the overall accuracy increased by 5.53% and the accuracy of cotton producers increased by 5.05%.Moreover
the classification accuracies of other land cover types increased to varying extents. ③The selective features achieved accuracies of 92.73% and 90.36% for cotton producers and users
respectively
and the overall accuracy was 93.66%. Compared with the classification results of the original features
the overall accuracy increased by 0.85% and the accuracy of cotton producers increased by 5.33%.Experiments showed that feature selection by the rough set method not only improved the classification accuracy but also effectively reduced the classification complexity. The proposed method achieved an accuracy of 92.73% for cotton extraction. The method of integrated multi-features based on multi-temporal Landsat 8 images is promising for crop extraction
even for land cover classification.
Brown J C, Kastens J H, Coutinho A C, de Castro Victoria D and Bishop C R. 2013. Classifying multiyear agricultural land use data from Mato Grosso using time-series MODIS vegetation index data. Remote Sensing of Environment, 130: 39–50
曹卫彬, 杨邦杰, 宋金鹏. 2004. TM影像中基于光谱特征的棉花识别模型. 农业工程学报, 20(4): 112–116
Cao W B, Yang B J and Song J P. 2004. Spectral information based model for cotton identification on Landsat TM image. Transactions of the CSAE, 20(4): 112–116
Conese C and Maselli F. 1991. Use of multitemporal information to improve classification performance of TM scenes in complex terrain. ISPRS Journal of Photogrammetry and Remote Sensing, 46(4): 187–197
谷延锋, 张晔. 2003. 基于自动子空间划分的高光谱数据特征提取. 遥感技术与应用, 18(6): 384–387
Gu Y F and Zhang Y. 2003. Feature extraction based on automatic subspace partition for hyperspectral images. Remote Sensing Technology and Application, 18(6): 384–387
Haralick R M, Shanmugam K and Dinstein I H. 1973. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 3(6): 610–621
Hlavka C A, Haralick R M, Carlyle S M and Yokoyama R. 1980. The discrimination of winter wheat using a growth-state signature. Remote Sensing of Environment, 9(4): 277–294
刘吉凯, 钟仕全, 梁文海. 2015. 基于多时相landsat8 OLI影像的作物种植结构提取. 遥感技术与应用, 30(4): 775–783
Liu J K, Zhong S Q and Liang W H. 2015. Extraction on crops planting structure based on multi-temporal Landsat 8 OLI images. Remote Sensing Technology and Application, 30(4): 775–783
刘玫岑, 李霞, 蒋平安, 盛建东. 2005. ASTER数据在棉花信息提取中的应用——以兵团农一师十六团为例. 遥感技术与应用, 20(6): 591–595
Liu M C, Li X, Jiang P A and Sheng J D. 2005. The application of ASTER data in cotton information classification-taking 16 farm of Nongyishi of production and construction group as an example. Remote Sensing Technology and Application, 20(6): 591–595
Oguro Y, Suga Y, Takeuchi S, Ogawal H and Tsuchiya K. 2003. Monitoring of a rice field using Landsat-5 TM and Landsat-7 ETM+ data. Advances in Space Research, 32(11): 2223–2228
潘远, 杨景辉, 武文波. 2012. 粗糙集约简的神经网络遥感分类应用. 遥感信息, 27(4): 86–90
Pan Y, Yang J H and Wu W B. 2012. Neural network based on rough sets reduction and its application to remote sensing image classification. Remote Sensing Information, 27(4): 86–90
Thangavel K and Pethalakshmi A. 2009. Dimensionality reduction based on rough set theory: a review. Applied Soft Computing, 9(1): 1–12
Vintrou E, Desbrosse A, Bégué A, Traoré S, Baron C and Lo Seen D. 2012. Crop area mapping in West Africa using landscape stratification of MODIS time series and comparison with existing global land products. International Journal of Applied Earth Observation and Geoinformation, 14(1): 83–93
王国胤, 姚一豫, 于洪. 2009. 粗糙集理论与应用研究综述. 计算机学报, 32(7): 1229–1246
Wang G Y, Yao Y Y and Yu H. 2009. A survey on rough set theory and applications. Chinese Journal of Computers, 32(7): 1229–1246
吴昊, 李士进, 林林, 万定生. 2010. 多策略结合的高光谱图像波段选择新方法. 计算机科学与探索, 4(5): 464–472
Wu H, Li S J, Lin L and Wan D S. 2010. Multiple-strategy combination based approach to band selection for hyper-spectral image classification. Journal of Frontiers of Computer Science and Technology, 4(5): 464–472
许新征. 2012. 基于粗糙集的粒度神经网络研究. 北京: 中国矿业大学 Xu X Z. 2012. Study on Granular Neural Networks based on Rough Sets. Beijing: China University of Mining and Technology
尹继豪, 王义松. 2010. 高光谱遥感影像中最佳谱段的快速选择方法. 遥感信息, 25(3): 3–6, 12
Yin J H and Wang Y S. 2010. An algorithm of rapid optimum band selection from hyperspectral remote sensing image. Remote Sensing Information, 25(3): 3–6, 12
赵春晖, 陈万海, 杨雷. 2007. 高光谱遥感图像最优波段选择方法的研究进展与分析. 黑龙江大学自然科学学报, 24(5): 592–602
Zhao C H, Chen W H and Yang L. 2007. Research advances and analysis of hyperspectral remote sensing image band selection. Journal of Natural Science of Heilongjiang University, 24(5): 592–602
郑长春. 2008. 水稻种植面积遥感信息提取研究. 乌鲁木齐: 新疆农业大学[DOI: 10.7666/d.y1256827] Zheng C C. 2008. Study on Remote Sensing Information Extraction of Paddy Rice Planting Area. Urumqi: Xinjiang Agriculture University
朱良, 平博, 苏奋振, 杜云艳, 苏伟光. 2013. 多时相TM影像决策树模型的水稻识别提取. 地球信息科学学报, 15(3): 446–451
Zhu L, Ping B, Su F Z, Du Y Y and Su W G. 2013. Using decision tree model to extract paddy rice information from multi-temporal TM images. Journal of Geo-information Science, 15(3): 446–451
相关作者
相关机构
京公网安备11010802024621
