Dissertation > Excellent graduate degree dissertation topics show

Research on Techniches for Mixel Classification of Multispectral Imagery

Author: QiJianCheng
Tutor: ZhuShuLong
School: PLA Information Engineering University
Course: Photogrammetry and Remote Sensing
Keywords: Mixed pixel Classification Endmember Endmember extraction Abundance estimates Confusion matrix Convex monomer Monomer boundary Endmember independence Decision-making binary tree
CLC: TP751
Type: Master's thesis
Year: 2009
Downloads: 130
Quote: 1
Read: Download Dissertation

Abstract


In this paper, the multi-spectral image mix like a number of key issues in the meta-classification, focus on the end element automatically determines the number of initial endmembers automatically get endmember rapid extraction and high-precision mixed pixel classification theory and methods. Papers: 1. Summarized multispectral images mixed as the two key aspects of the meta-classification (ie endmember extraction and abundance estimates) Research on the deficiencies of the existing theories and methods, and pointed out the need for solve the main problem. Depth study endmember extraction and abundance estimation theory and methods, and discuss the generation mechanism of linear and nonlinear mixed spectra as well as linear and nonlinear mixed pixel classification model applicable to explore the mixed pixel yuan The classification accuracy of the evaluation criteria, on the convex surface of a monomer of the image is formed in its feature space and the end element, experimental quantitative comparison of four endmember extraction method in the accuracy, efficiency, noise immunity, sensitive to outliers and other performance indicators, analyze the impact of factors such as element classification accuracy, the hybrid reached a number of important conclusions. The number of endmember automatic extraction method, discusses the the endmember spectrum between the independence, the automatic extraction methods based on the endmember independence endmember number. The experiments show that: This method is not only able to determine a reasonable number of endmembers directly from the original image data, and much higher efficiency than the existing method. Initial endmembers and endmember search strategy for endmember extraction algorithm stability of the main solution algorithm instability problems, and proposed a new initial endmembers automatic acquisition strategy to simplify the The complexity of the algorithm, improved endmember extraction accuracy. 5. Convex surface the monomer boundary of the characteristics in the high-dimensional image feature space, the idea of ??a two-dimensional scatter plot boundaries and set approximation instead of high-dimensional convex monomer border, to solve the high-dimensional convex monomer boundary extraction problems. Discusses convex monomer border and end the relationship, proposed the fast algorithm for extracting a endmembers - monomer border algorithm. Endmember extraction experiments show that the algorithm is not only able to obtain the desired results, and can greatly reduce endmembers search range, greatly improved endmember extraction speed. Decision binary tree in remote sensing image classification, the decision-making binary tree the introduction of mixed-pixel classification, set reasonable decision making conditions proposed decision binary tree-based mixed pixel classification algorithm. The experimental results show that: the algorithm can reduce the endmember classification results, to improve the classification accuracy.

Related Dissertations

  1. K Company’s Improving Planning and Forecasting for the Reasonable Allocation of Inventory,F224
  2. The Simulation and Analysis of Spectrum Sensing Based on Higher Order Cumulants,TN911.23
  3. Research on the Classification Based on the Reconstruction of Solder Joint,TP391.41
  4. The Research and Implementation of Protein Classification Algorithm on the Basic of String Kernel,TP301.6
  5. Context-Dependent Lexical Paraphrasing,TP391.1
  6. Research on Text Classification Based on Biomimetic Pattern Recongnition,TP391.1
  7. Tourism Comments on the Internet’s Semantic Analysis and Usefulness Research,TP391.1
  8. Research on Classification Method of Tongue Substance Color and Tongue Coating Color Based on SVM,TP391.41
  9. Research and Application of Diverse Density Learning Algorithm,TP181
  10. Research on Target Tracking and System in Wireless Sensor Networks Based on Character of Movement and Terrain Restriction,TP212.9
  11. Study on the Preparation of the Low Molecular Weight Fuciodan from Sargassum Henslowianum (C.Agardh) and Anti-tumor Activity,TS254.9
  12. Uptake and Accumulation of Heavy Metals of Pistia Stratiotes and Eicharnia Crassipes under Combinated Pollution Condition,X173
  13. Application of Numerical Designing Cigarette Blending Formula on Computational Intelligence,TS44
  14. Establishment of the Molecular Identifying System of Curvualria and Application in Difficult Species,Q949.32
  15. Research on Nondestructive Detection Technology for External Qualities of Papayas Based-on Vision,S667.9
  16. Research on Design and Practice of Educational Video Co-Construction and Sharing Platform for the Public,G434
  17. Studies on Effects of Soybean Species on North Tofu Quality and Methods of Evaluation in North Tofu,TS214.2
  18. Comparison of Gene Expression Data Cluster Methods and Gene Network Construction for Phytophthora Sojae Genes,S435.651
  19. Study on Growth Monitoring Technique Based on Pixel Un-Mixing Method and HJ Remote Sensing Images in Paddy Rice,S511
  20. Methodology for Linkage-map-based Quantitative Trait Loci Synthesis Analysis,S562
  21. Shanghai Public Security Authorities of the Police Job Classification,D631.1

CLC: > Industrial Technology > Automation technology,computer technology > Remote sensing technology > Interpretation, identification and processing of remote sensing images > Image processing methods
© 2012 www.DissertationTopic.Net  Mobile