Dissertation > Excellent graduate degree dissertation topics show

Study of Remote Sensing Image Classification Methods Based on Minimum Noise Fraction and Support Vector Machine

Author: JiNa
Tutor: LiRui
School: Northwest University of Science and Technology
Course: Land resources and space IT
Keywords: Remote Sensing image classification Feature selection and extraction Minimum Noise Fraction Support Vector Machine Maximum Likihood Classifier Classification precision
CLC: P237
Type: Master's thesis
Year: 2009
Downloads: 110
Quote: 0
Read: Download Dissertation

Abstract


Using computer classification technique to abstract land use information from remote sensing image is one of the most important applications of remote sensing technique. The precision of remote sensing image classification is a key issue in remote sensing image research. Improvement of classification precision is of great importance for remote sensing image application.In this study, original remote sensing image were pre-processed firstly, and combined with selected auxiliary data, new band combination were established to provide the basis for image classification. A support vector machine (SVM) method was employed during the process of classification, and it shows a good classification precision. The main results are as follows:(1) Firstly, original remote sensing images were processed by minimum noise fraction, and the first 4 bands which contain most of land use information were selected. Secondly, NDVI index which contain large amount of canopy coverage and greenness information were abstracted from the remote sensing image. Meanwhile, DEM was applied as a single band during the classification, due to the complicated topography of the research area.(2)Based on the new bands combination, the image classification process was designed particularly. Samples were selected from the original image, and support vector machine method was employed to classify the original image and get the classified image. Compared to the support vector machine method, a traditional maximum likelihood method was applied to get the classification image as well.(3) The classification results of support vector machine method and traditional classification method were analyzed respectively. Compared with maximum likelihood methods, support vector machine method showed a higher classification precision and Kappa coefficient. The classification precision and Kappa coefficient of support vector machine method is 88.33% and 0.8605, compared with 36.66% and 0.4061 of maximum likelihood method. The result showed that, SVM method can be better used in hilly and gully region of loess plateau.(4) As to SMV classification based on multi-source data, the classification precision can be improved comparatively when auxiliary information was added during the classification. SVM classification based on multi-source information shows a better result, compared with SVM classification based on pure spectrum information, and the classification precision and Kappa coefficient can be increased by 23.2099% and 0.1513 respectively.

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. Research on Autamatic Music Structrue Analysis,TN912.3
  3. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  4. Fault Diagnosis Method Based on Support Vector Machine,TP18
  5. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  6. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  7. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  8. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  9. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  10. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  11. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  12. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  13. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52
  14. Research of Facial Expression Recognition Algorithm,TP391.41
  15. Fundus Image Segmentation Based on SVM and Template Matching,TP391.41
  16. Research and Realization of License Plate Character Recognition Algorithm Based on SVM,TP391.41
  17. Cloud Classification Based on Geostationary Meteorological Satellite Imagery,TP391.41
  18. The Studies on Some Improvements of the GA and Their Applications in SVM,TP18
  19. The Research and Implementation of the Fault Management System for Triple Play,TP315
  20. Modulation Classification Algorithms of Digital Communication Signals,TN914.3
  21. Computer virus detection method,TP309.5

CLC: > Astronomy,Earth Sciences > Surveying and Mapping > Photogrammetry and Surveying, Mapping and Remote Sensing > Surveying, Mapping and Remote Sensing technology
© 2012 www.DissertationTopic.Net  Mobile