Acta Geodaetica et Cartographica Sinica ›› 2015, Vol. 44 ›› Issue (9): 1003-1013.doi: 10.11947/j.AGCS.2015.20140388

Previous Articles     Next Articles

Incremental Classification Algorithm of Hyperspectral Remote Sensing Images Based on Spectral-spatial Information

WANG Junshu1,2, JIANG Nan1,2, ZHANG Guoming3, LI Yang1,2, LV Heng1,2   

  1. 1. Key Laboratory for Virtual Geographic Environment, Ministry of Education, Nanjing Normal University, Nanjing 210023, China;
    2. Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application, Nanjing 210023, China;
    3. Center of Health Statistics and Information of Jiangsu Province, Nanjing 210008, China
  • Received:2014-07-21 Revised:2015-06-08 Online:2015-09-24 Published:2015-09-24
  • Contact: 江南,njiang@njnu.edu.cn E-mail:njiang@njnu.edu.cn
  • Supported by:
    The National Natural Science Foundation of China (No.41171269) The National Environmental Protection Public Welfare Science and Technology Research Program of China (No.201309037) A Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions (No.164320H101) Data-sharing Network of Earth System Science (No.2005DKA32300) Program of Natural Science Research of Jiangsu Higher Education Institutions of China (No.14KJB170010) Colleges and Universities in Jiangsu Province Plans to Graduate Research and Innovation (No.1812000002A403)

Abstract: An incremental classification algorithm INC_SPEC_MPext was proposed for hyperspectral remote sensing images based on spectral and spatial information. The spatial information was extracted by building morphological profiles based on several principle components of hyperspectral image. The morphological profiles were combined together in extended morphological profiles (MPext). Combine spectral and MPext to enrich knowledge and utilize the useful information of unlabeled data at the most extent to optimize the classifier. Pick out high confidence data and add to training set, then retrain the classifier with augmented training set to predict the rest samples. The process was performed iteratively. The proposed algorithm was tested on AVIRIS Indian Pines and Hyperion EO-1 Botswana data, which take on different covers, and experimental results show low classification cost and significant improvements in terms of accuracies and Kappa coefficient under limited training samples compared with the classification results based on spectral, MPext and the combination of sepctral and MPext.

Key words: hyperspectral remote sensing image, morphology, spatial information, spectral information, incremental classification

CLC Number: