首页--天文学、地球科学论文--测绘学论文--摄影测量学与测绘遥感论文--测绘遥感技术论文

Advanced Techniques for Object-Based Classification of Hyperspectral Remote Sensing

ABSTRACT第3-4页
Chapter:1 Introduction第8-21页
    1.1 Overview on Remote Sensing第8-9页
    1.2 Overview on the last generation of hyperspectral remote sensing第9-12页
    1.3 Challenge 1: Accuracy第12-17页
        1.3.1 Object-based Classification第14页
        1.3.2 Scale Selection Problems第14-15页
        1.3.3 SVM第15-16页
        1.3.4 KNN第16页
        1.3.5 Multi-resolution Segmentation第16页
        1.3.6 Rotation-based object-oriented (RoBOO)第16-17页
    1.4 Challenge 2: Efficiency第17-19页
        1.4.1 Increased volume of data第17页
        1.4.2 Scale and Diversity第17-19页
    1.5 Thesis Overview第19-21页
Chapter:2 Multi-resolution Segmentation for Object-based hyperspectral remote sensing data第21-35页
    2.1 Introduction第21-25页
    2.2 Motivation第25-26页
        2.2.1 Complexity第26页
        2.2.2 Scale第26页
    2.3 A short Review on image segmentation第26-27页
    2.4 Design Goal第27-28页
        2.4.1 High Quality Image Object Primitives:第28页
        2.4.2 Multi-resolution第28页
        2.4.3 Similar Resolution第28页
        2.4.4 Reproducibility第28页
        2.4.5 Universality第28页
        2.4.6 Speed第28页
    2.5 Criteria for the evaluation of segmentation results第28-29页
        2.5.1 Quantitative Criteria Given第28-29页
        2.5.2 Qualitative Criteria第29页
    2.6 Proposed Framework第29-30页
    2.7 Decision Heuristics第30-32页
    2.8 Criteria for the evaluation of segmentation results第32-33页
        2.8.1 Difference between adjacent objects第32页
        2.8.2 Change of heterogeneity in a virtual merge第32-33页
    2.9 Results第33-35页
Chapter:3 Support vector machines for Object-based Hyperspectral classification of remote sensing data第35-57页
    3.1 Introduction第35-39页
    3.2 Support vector machine classifiers第39-44页
        3.2.1 Training of linear SVM-maximal margin algorithm第39-41页
        3.2.2 Training of linear SVM-soft margin algorithm第41-43页
        3.2.3 Training of nonlinear SVM-kernel trick第43-44页
    3.3 Classification of University of Pavia Image第44-45页
    3.4 SVM for the classification of RS data第45-55页
    3.5 Summary of object-basedSVM classification第55-57页
Chapter:4 Rotation-matrix object-oriented classification of Hyperspectral Remote Sensing第57-67页
    4.1 Overview of hyperspectral classification第57-59页
    4.2 Rotation-Based Object-Oriented (RoBOO)第59-61页
    4.3 Experimental Setup and Data第61-62页
    4.4 Results and Discussion第62-65页
    4.5 Accuracy Assessment第65-66页
    4.6 Summary of outcomes第66-67页
Chapter:5 Conclusions and Future Works第67-71页
    5.1 Conclusions第67页
    5.2 Summary and Discussion第67-69页
    5.3 Future Developments第69-71页
Acknowledgements第71-72页
REFERENCES第72-84页

论文共84页,点击 下载论文
上一篇:基于机器视觉的文档与印鉴缺陷检测的方法与实现
下一篇:基于无人机航拍图像的道路检测