Automatic Classification of Winter Wheat: Based on Geometry Semantic Knowledge

doi:10.11924/j.issn.1000-6850.casb19010038

Abstract

Abstract: [Objective]The purpose of the study is to realize crop automatic classification based on remote sensing images, and to explore the roles of spatial information in crop classification, [Method]The paper proposes a crop classification method with the combination of spectral and spatial information. Firstly, the spectral information is utilized to realize the initial division of ground objects; secondly, by taking the historical spatial distribution of target crops as semantic constraints, the target crops are extracted based on degree of membership; Finally, under the condition of multi temporal remote sensing images, the method is verified by taking winter wheat as target crop. [Result]The result shows that, the method proposed in this paper can realize winter wheat automatic extraction and identification, with the overall accuracy of 95.33%，and Kappa coefficient of 0.90. The can meet the practical demand of agricultural condition monitoring. In addition, under the condition of mono temporal remote sensing image, the crop classification accuracy of the proposed method with the combination of geometric semantic knowledge also has reached a high level. [Conclusion]Compared with the remote sensing image classification method with single spectral information, the method proposed in this paper makes use of crop spatial information, and it not only meet requirement of accuracy, but also realizes automatic classification. It has certain reference value for engineering application.

CLC Number:

S252

References

[1] Branca G, McCarthy N, Lipper L, Jolejole M C. Climate-smart agriculture: a synthesis of empirical evidence of food security and mitigation benefits from improved cropland management[J]. Mitigation of Climate Change in Agriculture Series no. 3, 2011, Food and Agriculture Organization of the United Nations (FAO), Rome, Italy.
[2] L?w F, Michel U. Impact of feature selection on the accuracy and spatial uncertainty of per-field crop classification using Support Vector Machines[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 85(6): 102－119.
[3] Dong Q H, Eerens Herman, Chen Z X. Crop area assessment using remote sensing on the north China plain[J]. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Science, 2008, Vol, XXXVII. Part B8, pp. 957－962.
[4] Ustuner M, Sanli F B, Abdikan S, et al. Crop type classification using vegetation indices of rapideye imagery[J]. ISPRS-International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2014, XL-7(7): 195-198.
[5] Perumal K, Bhaskaran R. Supervised classification performance of multispectral images[J]. Computer Science, 2010, 2(2): 124－129.
[6] Dhumal R K, Rajendra Y D, Kale K V, et al. Classification of crops from remotely sensed images: AnOverview[J]. International Journal of Engineering Research and Application, 2013, 3(3): 758－761.
[7] Lunetta R S, Johnson D M, Lyon J D, et al. Impacts of imagery temporal frequency on land-cover change detection monitoring[J]. Remote Sensing of Environment, 2004, 89(4): 444－454.
[8] Jia K, Li Q Z, Tian Y C, et al. A review of classification methods of remote sensing imagery[J]. Spectroscopy and Spectral Analysis, 2011, 31(10): 2618－2623.
[9] Foody G M. Fuzzy modelling of vegetation from remotely sensed imagery[J]. Ecological Modelling, 1996, 85(1): 3－12.
[10] Tso B, Mather P M. Classification methods for remotely sensed data[M]. New York: Taylor and Francis Inc, 2001.
[11] Pal M, Mather P M. An assessment of effectiveness of decision tree methods for land cover classification[J]. Remote Sensing of Environment, 2003, 86(4): 554－565.
[12] Gallego F J. Remote sensing and land cover area estimation[J]. International Journal of Remote Sensing, 2004, 25(15): 3019－3047.
[13] Dixon B, Candade N. Multispectral landuse classification using neural networks and support vector machines: one or the other, or both?[J] International Journal of Remote Sensing, 2008, 29(4): 1185－1206.
[14] Rogan J, Franklin J, Stow D, et al. Mapping land-cover modifications over large areas: a comparison of machine learning algorithms[J]. Remote Sensing of Environment, 2008, 112(5): 2272－2283.
[15] Murthy C S, Raju P V, Badrinath K V S. Classification of wheat crop with multi-temporal images: performance of maximum likelihood and artificial neural networks[J]. International Journal of Remote Sensing, 2003, 24(23): 4871－4890.
[16] Carrizosa E, Morales D R. Supervised classification and mathematical optimization[J]. Computers Operations Research, 2013, 40(1): 150－165.
[17] Ince T. Unsupervised classification of polarimetric SAR image with dynamic clustering: An image processing approach[J]. Advances in Engineering Software, 2010, 41(4): 636－646.
[18] Song H, Yang W, Bai Y, Xu X L. Unsupervised classification of polarimetric SAR imagery using large-scale spectral clustering with spatial constraints[J]. International Journal of Remote Sensing, 2015, 36(11): 2816－2830.
[19] Wardlow B D, Egbert S L, Kastens J H. Analysis of time-series MODIS 250m vegetation index data for crop classification in the U.S. Central Great Plains[J]. Remote Sensing of Environment, 2007, 108(3): 290-310.
[20] Arvor D, Jonathan M, Dubreuil V, et al. Classification of MODIS EVI time series for crop mapping in the state of Mato Grosso, Brazil[J]. International Journal of Remote Sensing, 2011, 32(22): 7847－7871.
[21] Wardlow B D, Egbert S L. Large-area crop mapping using time-series MODIS 250m NDVI data: an assessment for the U.S. Central Great Plains[J]. Remote Sensing of Environment, 2008, 112(3): 1096-1116.
[22] 刘佳,王利民,杨福刚,等．基于HJ时间序列数据的农作物种植面积估算[J]．农业工程学报,2015,31(3)：199－206．
[23] 王利民,刘佳,杨玲波,等．基于 NDVI 加权指数的冬小麦种植面积遥感监测[J]．农业工程学报,2016,32(17)：127－135．
[24] Conese C, Maselli F. Use of multi temporal information to improve classification performance of TM scenes in complex terrain[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1991, 46(4): 187－197.
[25] 刘佳,王利民,杨玲波,等．基于6S模型的GF-1卫星影像大气校正及效果[J]．农业工程学报,2015,31(19)：159－168．
[26] 刘佳,王利民,杨玲波,等．基于有理多项式模型区域网平差的GF-1影像几何校正[J]．农业工程学报,2015,31(22)：146－154．
[27] Santos L M R, Munari P, Costa A M, et al. A branch-price-and-cut method for the vegetable crop rotation scheduling problem with minimal plot sizes[J]. European Journal of Operational Research, 2015, 245(2): 581－590.
[28] Memarsadeghi N, Mount D M, Netanyahu N S, et al. A fast implementation of the ISODATA clustering algorithm[J]. International Journal of Computational Geometry and Applications, 2007, 17(1): 71－103.
[29] Thompson-Schill S L, Desposito M, Aguirre G K, et al. Role of left inferior prefrontal cortex in retrieval of semantic knowledge: a reevaluation[J]. Proceedings of the National Academy of Sciences of the United States of America, 1997, 94(26): 14792－14797.
[30] Garciamolina H. Using semantic knowledge for transaction processing in a distributed database[J]. ACM Transactions on Database Systems, 1983, 8(2): 186－213.
[31] 袁烨城,刘海江,裴韬,等．基于语义知识的空间关系识别研究[J]．地球信息科学,2014,16(5)：681-689.
[32] Nguyen T M, Wu Q M J. A fuzzy c-means based spatial pixel and membership relationships for image segmentation[C]// Computer Robot Vision, Canadian, 2011: 278－284.
[33] Salakhutdinov R, Tenenbaum J B, Torralba A. Learning with hierarchical-deep models[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1958－1971.
[34] Barron A R. Universal approximation bounds for superpositions of a sigmoidal function[J]. IEEE Transactions on Information Theory, 1993, 39(3): 930－945.
[35] Gan Z, Henao R, Carlson D, et al. Learning deep sigmoid belief networks with data augmentation[C]// Artificial Intelligence and Statistics, 2015.