Urban landscape classification using Chinese advanced high-resolution satellite imagery and an object-oriented multi-variable model

详细信息    查看全文

• 作者：Li-gang Ma (1)
  Jin-song Deng (1) (2)
  Huai Yang (1)
  Yang Hong (2) (3)
  Ke Wang (1)
  
  1. Institute of Applied Remote Sensing & Information Technology ; Zhejiang University ; Hangzhou ; 310058 ; China
  2. School of Civil Engineering and Environmental Sciences and School of Meteorology ; University of Oklahoma ; Norman ; OK ; 73019 ; USA
  3. State Key Laboratory of Hydroscience and Engineering ; Department of Hydraulic Engineering ; Tsinghua University ; Beijing ; 100084 ; China
  
• 关键词：ZY ; 1 02C satellite ; Classification ; Urban ; Multi ; variable model ; TP751.1
• 刊名：Journal of Zhejiang University - Science C
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：16
• 期：3
• 页码：238-248
• 全文大小：1,114 KB
• 参考文献：1. Adams, JB, Sabol, DE, Kapos, V (1995) Classification of multispectral images based on fractions of endmembers: application to land-cover change in the Brazilian Amazon. Remote Sens. Environ. 52: pp. 137-154 CrossRef
  2. Aguilar, MA, Salda帽a, MM, Aguilar, FJ (2013) GeoEye-1 and WorldView-2 pan-sharpened imagery for object-based classification in urban environments. Int. J. Remote Sens. 34: pp. 2583-2606 CrossRef
  3. Carlson, TN, Ripley, DA (1997) On the relation between NDVI, fractional vegetation cover, and leaf area index. Remote Sens. Environ. 62: pp. 241-252 CrossRef
  4. Chen, Y, Shi, P, Fung, T (2007) Object-oriented classification for urban land cover mapping with ASTER imagery. Int. J. Remote Sens. 28: pp. 4645-4651 CrossRef
  5. Deng, JS, Wang, K, Deng, YH (2008) PCA-based land-use change detection and analysis using multitemporal and multisensor satellite data. Int. J. Remote Sens. 29: pp. 4823-4838 CrossRef
  6. Durieux, L, Lagabrielle, E, Nelson, A (2008) A method for monitoring building construction in urban sprawl areas using object-based analysis of Spot 5 images and existing GIS data. ISPRS J. Photogr. Remote Sens. 63: pp. 399-408 CrossRef
  7. Han, N, Wang, K, Yu, L (2012) Integration of texture and landscape features into object-based classification for delineating Torreya using IKONOS imagery. Int. J. Remote Sens. 33: pp. 2003-2033 CrossRef
  8. Hermosilla, T, Ruiz, LA, Recio, JA (2012) Assessing contextual descriptive features for plot-based classification of urban areas. Landscape Urban Plan. 106: pp. 124-137 andurbplan.2012.02.008" target="_blank" title="It opens in new window">CrossRef
  9. Hu, S, Wang, L (2013) Automated urban land-use classification with remote sensing. Int. J. Remote Sens. 34: pp. 790-803 CrossRef
  10. Jacquin, A, Misakova, L, Gay, M (2008) A hybrid object-based classification approach for mapping urban sprawl in periurban environment. Landscape Urban Plan. 84: pp. 152-165 andurbplan.2007.07.006" target="_blank" title="It opens in new window">CrossRef
  11. Li, G, Weng, Q (2005) Using Landsat ETM+ imagery to measure population density in Indianapolis, Indiana, USA. Photogr. Eng. Remote Sens. 71: pp. 947 CrossRef
  12. Livingston, F (2005) Implementation of Breiman鈥檚 random forest machine learning algorithm. ECE591Q Machine Learning Journal Paper.
  13. Lu, D, Weng, Q (2006) Use of impervious surface in urban land-use classification. Remote Sens. Environ. 102: pp. 146-160 CrossRef
  14. Lu, D, Weng, Q (2007) A survey of image classification methods and techniques for improving classification performance. Int. J. Remote Sens. 28: pp. 823-870 CrossRef
  15. Mathieu, R, Freeman, C, Aryal, J (2007) Mapping private gardens in urban areas using object-oriented techniques and very high-resolution satellite imagery. Landscape Urban Plan. 81: pp. 179-192 andurbplan.2006.11.009" target="_blank" title="It opens in new window">CrossRef
  16. Novack, T, Esch, T, Kux, H (2011) Machine learning comparison between WorldView-2 and QuickBird-2-simulated imagery regarding object-based urban land cover classification. Remote Sens. 3: pp. 2263-2282 CrossRef
  17. Pacifici, F, Chini, M, Emery, WJ (2009) A neural network approach using multi-scale textural metrics from very high-resolution panchromatic imagery for urban land-use classification. Remote Sens. Environ. 113: pp. 1276-1292 CrossRef
  18. Ridd, MK (1995) Exploring a V-I-S (vegetation-impervious surface-soil) model for urban ecosystem analysis through remote sensing: comparative anatomy for cities. Int. J. Remote Sens. 16: pp. 2165-2185 CrossRef
  19. Settle, JJ, Drake, NA (1993) Linear mixing and the estimation of ground cover proportions. Int. J. Remote Sens. 14: pp. 1159-1177 CrossRef
  20. Shaban, MA, Dikshit, O (2001) Improvement of classification in urban areas by the use of textural features: the case study of Lucknow City, Uttar Pradesh. Int. J. Remote Sens. 22: pp. 565-593 CrossRef
  21. Shahtahmassebi, A, Pan, Y, Lin, L (2014) Implications of land use policy on impervious surface cover change in Cixi County, Zhejiang Province, China. Cities 39: pp. 21-36 CrossRef
  22. Shanmugan, KS, Narayanan, V, Frost, VS (1981) Textural features for radar image analysis. IEEE Trans. Geosci. Remote Sens. GE-19: pp. 153-156 CrossRef
  23. Smith, MO, Ustin, SL, Adams, JB (1990) Vegetation in deserts: I. A regional measure of abundance from multispectral images. Remote Sens. Environ. 31: pp. 1-26 CrossRef
  eCognition Developer 8.7.1:Reference Book. T. Munich, Germany
  24. Wu, B, Wang, X, Shen, H (2012) Feature selection based on max-min-associated indices for classification of remotely sensed imagery. Int. J. Remote Sens. 33: pp. 5492-5512 CrossRef
  
• 刊物类别：Computer Science
• 刊物主题：Computer Science, general
  
• 出版者：Zhejiang University Press, co-published with Springer
• ISSN：1869-196X

文摘

The Chinese ZY-1 02C satellite is one of the most advanced high-resolution earth observation systems designed for terrestrial resource monitoring. Its capability for comprehensive landscape classification, especially in urban areas, has been under constant study. In view of the limited spectral resolution of the ZY-1 02C satellite (three bands), and the complexity and heterogeneity across urban environments, we attempt to test its performance of urban landscape classification by combining a multi-variable model with an object-oriented approach. The multiple variables including spectral reflection, texture, spatial autocorrelation, impervious surface fraction, vegetation, and geometry indexes were first calculated and selected using forward stepwise linear discriminant analysis and applied in the following object-oriented classification process. Comprehensive accuracy assessment which adopts traditional error matrices with stratified random samples and polygon area consistency (PAC) indexes was then conducted to examine the real area agreement between a classified polygon and its references. Results indicated an overall classification accuracy of 92.63% and a kappa statistic of 0.9124. Furthermore, the proposed PAC index showed that more than 82% of all polygons were correctly classified. Misclassification occurred mostly between residential area and barren/farmland. The presented method and the Chinese ZY-1 02C satellite imagery are robust and effective for urban landscape classification.