Dissertation > Excellent graduate degree dissertation topics show

Multi-Class Object Recognition in High Resolution Remote Sensing Images

Author: YaoZuo
Tutor: WangYueHuan
School: Huazhong University of Science and Technology
Course: Pattern Recognition and Intelligent Systems
Keywords: Remote Sensing Image Multi Class Objects Detection and Recognition Geometrical Feature Region of Interest
CLC: TP751
Type: Master's thesis
Year: 2011
Downloads: 118
Quote: 2
Read: Download Dissertation

Abstract


Regarding the multi-class detection and recognition task in high-resolution remote sensing images, the method used in this dissertation is different from the traditional methods that build specific model for each class. The objectives of the dissertation lie in two folds: to detect and recognize multi-class objects in large scale images by extracting Regions of Interest (ROIs), and to obtain high recognition rate as well as reduced recognition time.Aiming to detect and recognize five classes of man-made construction: airport, harbor, bridge, highway and railway, geometrical features were used to extract ROIs and feature vectors, texture classification results were referred to judge context information, tree recognition structure was adopted in multi-resolution. The key points are: to generate validate feature vectors to depict each class, to extract ROIs to eliminate the background interferences, and to design effective classifiers to recognize potential objects.The main contributions given in this dissertation are as follows:Firstly, as the man-made constructions show lots of line segments, line segments were extracted as the basic features. The gradient direction group line segment extraction algorithm was improved by referring to the edge information obtained by Canny operator. Proved by the experiment results, this improved algorithm is with high efficiency, robust to noise, and able to extract the key line segments.Meanwhile, the structural matching and Bag of Features ideas were integrated to generate feature vectors. Based on the basic line segments’shape, geometrical and spatial relationships, the shape primitives and their attributes were calculated and the feature vectors were constructed.Secondly, as the man-made constructions represent dense line segments, a novel ROIs extraction method was proposed for man-made constructions in remote sensing images, the ROIs were obtained by calculating line density distribution surf. This method is proved to be able to extract the man-made regions excellently.Finally, the parameter optimization in designing SVM classifiers was discussed, and a method of multi-class objects detection and recognition in high resolution remote sensing images was proposed. The experiment results showed that a relatively high recognition rate and efficiency was obtained.

Related Dissertations

  1. High-performance Remote-Sensing Image Fusion Algorithm Research and It’s Implementation,TP751
  2. Research on SAR and Panchromatic Remote Sensing Image Fusion in Wavelet Domain,TP751
  3. Research of Real-time Object Tracking Based on Computer Vision,TP391.41
  4. Research on Cloud Detection and Removal of Remote Sensing Image,TP751
  5. Denoising and Cloud Shadow Removing of Remote Sensing Image Based on Contourlet Transform,TP751
  6. Remote-sensing Image Segmentation Based on Fuzzy C-means Algorithms Theory,TP751
  7. Road Enhancement and Extraction in Remote Sensing Images Based on Nonsubsampled Contourlet Transform,TP751
  8. Side-scan sonar image ROI extraction algorithm,TP391.41
  9. The Landscape Dynamic Analyzing of the Area along the Yangtze River in Jiangsu Based on RS and GIS,S771.8
  10. Classification of Hyperspectral Remote Sensing Image Based on the Cloud Model Theory,TP751
  11. Forest Edge Detection Based on High Spatial Resolution Remote Sensing Imagery and Wavelet Analysis,TP751
  12. Application of Non-negative Matrix Factorization Metho in Remote Sensing Image Recognition,TP751
  13. Research on Space-Borne Multi-Sensor Image Fusion Based on Non-Negative Matrix Factorization,TP751
  14. Research of Remote Sensing Image Fusion Based on Multi-Wavelet Transform,TP751
  15. Data Mining for Forest Space Information Features from Remote Sensing Images,TP751
  16. Study on the Spatial-temporal Change of Vegetation in Zhejiang Province and the Landscape Regeneration Design of Forest,Q948
  17. Applicability Analysis of Region Multi-center Method for Rs Imagery Classification,P237
  18. Ensemble of Multiple Descriptors for Automatic Image Annotation,TP391.41
  19. Research on Heigh-Level Semantic-Based Image Retrieval,TP391.41
  20. Region of interest image watermarking algorithm,TP309.7
  21. The Technology Research of Urban Road Extraction from High-resolution Remote Sensing Images,TP751

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