Dissertation > Excellent graduate degree dissertation topics show

Semi-supervised Band Selection for Hyperspectral Remote Sensing Data

Author: LvZhiQiang
Tutor: HuangZuo
School: Shanghai University
Course: Communication and Information System
Keywords: Hyperspectral data Classification Band selection Semi-supervisedlearning Graph Laplacian Sample selection
CLC: TP79
Type: Master's thesis
Year: 2013
Downloads: 1
Quote: 0
Read: Download Dissertation

Abstract


Hyperspectral remote sensing, which could acquire the continuous spectrum ofground objects from visible to near infrared bands, is an important measure ofobtaining remote sensing information. Since the hyperspectral data ishigh-dimensional and massive, it has brought us great challenges in the subsequentdata processing and analysis. Dimensionality reduction through band selection forhigh-dimensional data has become a significant pre-processing method inhyperspectral data processing. Currently, most of band selection methods are onlybased on the label information, and the information from the small size of labeledsamples usually misleads these supervised band selection. The semi-supervised bandselection, combining information in labeled and unlabeled samples, is an efficientmeasure of dimensionality reduction in case of limited labeled samples. Against thisbackground, this dissertation researches the semi-supervised band selection forhyperspectral remote sensing data and the main contents are as follows:(1) Systematically study on band selection theory and semi-supervised learning.Do a summary of several semi-supervised band selection methods with theiradvantages and disadvantages.(2) Propose GST_FS which is a semi-supervised band selection based on graphLaplacian and self-training idea. The method first puts forward the semi-supervisedcriterion for feature ranking to generate the initial band subset. Then, the supervisedclassification are carried out based on the band subset and some unlabeled sampleswith higher confidence values are added into the labeled sample set. Afterwards theband subset is updated according to the feature ranking based on the newly generatedlabeled and unlabeled data, and is used for classification. The process is repeated toobtain the final subset. The experiments on hyperspectral data sets are carried out tomake comparisons among GST_FS, several unsupervised, supervised andsemi-supervised band selection methods. The results show that GST_FS can produce the band subset with better performance.(3) Introduce sample reduction for graph-based method to cut down the databundle in constructing the graph. In the method, the principal component analysis isfirst used for the dimension reduction. Subsequently, the watershed algorithm isapplied for over-segmentation of the reduced images. Finally, some percent ofunlabeled samples are randomly selected from the clusters. These chosen samples arecombined with the labeled samples to construct the graph in GST_FS to complete thesemi-supervised band selection. The experiments on hyperspectral data sets show thatthe proposed has better performance than the simple sampling approach. The method,selecting the representative unlabeled samples for the graph-based algorithms, notonly reduces the computational burdens greatly, but also enhances the algorithmperformances.

Related Dissertations

  1. Study on Segmentation of X-ray Image Based on SVM,TP391.41
  2. CHRIS based on radiative transfer models and data inversion wheat LAI,S512.12
  3. Mixed voice signal frequency domain convolution Blind Separation,TN912.3
  4. The Research about the Acoustic Model,TN912.34
  5. Studies about Methods on Survey of Mining Area Vegetation Restoration Based on the RS,S771.8
  6. Research on Feature Selection and Pattern Classification Method Based on Radar Returns,TN957.51
  7. The Research on Fusion Methods of Landsat-7 Remote Sensing Images Based on 1:50000 Relief Map Updating,P283.8
  8. Laplace eigenvalue of a few class diagram,O157.5
  9. Based on data mining technology in power system short-term load forecasting,TM715
  10. New Method of Modeling and Optimal Control for the Boiler Combustion System in Large Power Plants,TM621.2
  11. Sample Selection Model and Its Application in Study of the Influence of Medical Expenses,R197.1
  12. Road Condition Mapping with Hyperspectral Remote Sensing,U418.6
  13. Research on Content-based Image Search Reranking,TP391.41
  14. Research on Multichannel Ground Moving Target Indicator Radar with Robust Array Processing,TN959.71
  15. The key land use remote sensing technology and its application - for example in Jiangxi Poyang Lake region,S127
  16. Research on Sample Selection and Its Applications in Pattern Recognition,TP18
  17. Some Novel Classifiers and Their Applications on Face Recognition,TP391.41
  18. Extracting Urban Land Use Information Based on Hvperspectral Remote Sensing Data,P237
  19. Estimation of Winter Wheat Residue Cover of Yucheng Area, Shandong,S127
  20. Research on speech emotion recognition based on semi supervised learning,TN912.34
  21. Mobile Busy Traffic Forecasting Based on Support Vector Regression Machine,TP181

CLC: > Industrial Technology > Automation technology,computer technology > Remote sensing technology > The application of remote sensing technology
© 2012 www.DissertationTopic.Net  Mobile