Dissertation > Excellent graduate degree dissertation topics show

Merging Terrasar-X and CBERS Images for Automatic Extraction of Water Body Information

Author: LiXiaoLing
Tutor: LiuGuoXiang；LiAiNong
School: Southwest Jiaotong University
Course: Photogrammetry and Remote Sensing
Keywords: image fusion wavelet transform edge enhancement quality evaluation water extraction
CLC: TP391.41
Type: Master's thesis
Year: 2010
Downloads: 178
Quote: 0
Read: Download Dissertation

Abstract


With the development of remote sensing technology, more and more different types of sensors are used for earth observation. Spectral information of data obtained from optical sensor is abundant, but it’s vulnerable to interference from atmospheric conditions. SAR is a coherent active microwave remote sensing system that can work whatever weather and time and penetrate some surface features. The texture information of SAR image is abundant, but there are a lot of speckle noise in the image. So it is necessary to integrate information of the two types of images, to achieve the purpose of strengths complemented and improving the spatial resolution and spectral information of the image. In this paper, CBERS multi-spectral image and TerraSAR-X image are data sources for fusion research, and extract water body information using classified method. The main works done including,(1) By the analysis of the pretreatment key technology of the image fusion, for the data sources of this paper we take different radiation enhancement method based on their respective features.(2) The algorithms of based on pixel-level fusion of multi-source images in remote sensing are summarized and analyzed. Focuses on the wavelet transform and wavelet packet transform, including the determination of the decomposition level, wavelet basis and fusion rules. Qualitative evaluation and quantitative evaluation of the performance of the algorithms are done. The results show that the wavelet transform method is able to maintain the spectral information and texture details of the original images.(3) Combining the edge detection and fusion algorithm based on the wavelet transform, the image fusion methods of edge characteristics enhanced are also discussed. Integrating edge enhancement operator and the algorithms of based on pixel-level fusion, the improved scheme of intensifying the edge feature are studied. The results show that the edge enhancement algorithms can highlight the edge features of the surface features and also lost some of the details.(4) By quantitative evaluation of different fusion algorithms, it indicates that the details and spectral information of the images are two factors whose relation is wane and wax. The merits and demerits of fusion images can not be determined based on some one indicator, more important is the application purpose.Therefore, this paper uses the results of water extraction to evaluate what kind of integration algorithm is more efficient.(5) The original CBERS multi-spectral image and fusion images are classified using the maximum likelihood method and support vector machine method. And extraction of water information is done, the results and the qualitative and quantitative evaluations are not consistent. By using the wavelet transform which have good capability of retaining spectral and details, there is higher miscarriage of justice rate of water with the fusion image. On the contrary for the fusion images used Brovey transformation, HIS transformation and weighted method, although the spectral distortion is greater, but the precision of extracting water body information is higher.

Related Dissertations

  1. Research of Image Mosaic Technology,TP391.41
  2. Research on Joint Target Detection for Dual-Sensor Image and System Implementation,TP391.41
  3. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  4. Multi-currency Notes Technology Research and Implementation,TP391.41
  5. Research on Identification System of Cashmere and Wool Fiber,TS101.921
  6. Comprehensive Evaluation of Flue-cured Tobacco Quality in Pingdingshan and Comparative Analysis with American Tobacco,S572
  7. Study on Teaching Quality Evaluating Index System of Academic Course,G642.4
  8. Image Fusion Algorithms Based on Multi-scale Analysis,TP391.41
  9. Feature Extraction Technologies Research and Implementation of 3D Models Based on Wavelet Transform,TP391.41
  10. The Research of Application of Ridgelet Transform in the Fusion of Multispectral and Panchromatic Images,TP391.41
  11. An Algorithm on Clustering and Anomaly Detection for Multiple Data Streams,TP311.13
  12. Research on Information Hiding Based on Images,TP309.7
  13. Design and Implication of Image Compression System Based on Wavelet and DM6446,TP391.41
  14. Research on Three-dimensional Surface Splicing Method Based on Genetic Algorithm and the Wavelet Transformation,TP391.41
  15. Study on Medical Image Segmentation Method Based on Parametric Active Contour Models,TP391.41
  16. SOPC Design of Transient Power Quality Disturbances Detecting Based on Nios Ⅱ,TN47
  17. The Research on Recycling Arsenic from Arsenic Waste Water Using Wet Method,X703
  18. Application Research of Genetic Neural Network in Surface Water Evaluation,X824
  19. Design and Research of the Agrogeology Investigation Database Management System Based on GIS,TP311.52
  20. Research on Design and Data Processing for Wireless Electrocardiogram Monitoring Systems,TP274
  21. The Study of Vibration Signal Analysis System Based on Wavelet Fractal Theory,TN911.6

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile