Dissertation > Excellent graduate degree dissertation topics show

Research on Change Detection for Remote Sensing Images Based on Discriminant Analysis

Author: ChenKe
Tutor: ZhangBaoMing
School: PLA Information Engineering University
Course: Photogrammetry and Remote Sensing
Keywords: Change detection Discriminant analysis Similarity Variation threshold Fisher criterion Boundary Tracing
CLC: TP751
Type: Master's thesis
Year: 2009
Downloads: 142
Quote: 4
Read: Download Dissertation

Abstract


A change detection based on remote sensing images of remote sensing images acquired from different time, quantitative analysis and to determine the characteristics of surface changes and process technology, it is established by the characteristics of remote sensing image data analysis methods can identify an object or phenomenon status change. Change change detection information, resources and the environment can be used to update and applications, disaster monitoring, assessment and prediction of the battlefield situation and battle damage assessment. Change detection theory, change detection technology can not only play a better role in the actual production, but also to promote the development of the theory. This article focused on how never phase of remote sensing images quickly and efficiently automatic extraction of change information to study in-depth discussion of the theories and methods of remote sensing image change detection. Work and innovation of the main points are as follows: 1. Based similarity discriminant analysis of remote sensing image change detection method, in which the similarity including collection and image similarity. Difference image optimal change the threshold value selected difficult problem, this paper sum up the previous change threshold select the method of basis, presented the first collection of similar nature, the different images are divided into the change area and did not change regional and avoid the optimal change the threshold value is difficult to select the problem; according to the change pixel image similarity \The classical Fisher criterion function is introduced into the remote sensing image change detection extended to the two-dimensional space, the original one-dimensional gray-scale value space, remote sensing image change detection 2D-Fisher criterion function method, an effective solution to the existing detection The sensitive issue of image noise. 2D-Fisher criterion function method is slow, can not meet the needs of the practical application of good, in order to improve the detection speed, two-dimensional threshold method for solving 2D-Fisher criterion function method to improve, its transformation solving two one-dimensional threshold, greatly improving the speed of detection. Improved 2D-Fisher criterion function method is applicable not only to the change detection, and is also applicable for other processing. Expression of remote sensing image change detection results. Using mathematical morphology method of binary image processing, and removal of isolated points and isolated areas; binary image is generated on the change detection boundary tracking, raster into vector data, to facilitate the subsequent use of the change information . Various algorithms proposed in the paper the use of simulation and real multitemporal remote sensing image experiment, and achieved satisfactory results, the reliability and validity of several classical methods are superior.

Related Dissertations

  1. Syntactic Features Based Pronoun Resolution,TP391.1
  2. Research of Multiple Emails Automatic Summarization,TP391.1
  3. Research of IRC Botnet Detection Based on Behavior,TP393.08
  4. Research on Auto-Evaluation Method of Programming Based on Similarity,TP312.1
  5. Analysis on Characteristics and Discriminant of Aroma Types of Flue-Cured Tobacco,S572
  6. Comprehensive Evaluation of Flue-cured Tobacco Quality in Pingdingshan and Comparative Analysis with American Tobacco,S572
  7. The Impact of Tourism on Typical Vegetation in Luya Mountain Nature Reserve, Shanxi Province,S759.9
  8. Ontology -based Semantic Web service matching and composition method,TP393.09
  9. WordNet and the \,G254
  10. Research of Text Clustering on Food Complaint Documents Based on Ontology,TP391.1
  11. Yuan Zhen and Bai Juyi’s Similar Research,I207.22
  12. Research on Relationship Extraction Based on Semantic Pattern Matching in Web Environment,TP391.1
  13. 16th Men of the World Basketball Championships China Basketball Man’s Team Point Guard Attack or Defense Ability to Analyze,G841
  14. Sentence Similarity Computing Research and Application of Intelligent Question Answering System,TP391.1
  15. Design and Implementation of the Character Classification System Used in Search Engine,TP391.3
  16. Research on Image Super-resolution Reconstruction Based on Non-local Similarity,TP391.41
  17. Research on Streaming Media Detection Methods Against DoS\DDoS Attack Based on Analysis of Self-similarity,TP393.08
  18. Study on Data Mining in Water Dispatching Decision Support System,TV697.11
  19. Synthesis and Design of Microwave Filters,TN713
  20. Finding Web Services Based on Clustering Probabilistic Semantic Approach,TP393.09
  21. The Research of Image Spam Detecting Based on Similarity Assessment,TP393.098

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