Developing a Spectral-Based Strategy for Urban Object Detection From Airborne Hyperspectral TIR and Visible Data

摘要: Classification and detection of urban objects have been big challenges for years. High spatial resolution hyperspectral thermal infrared (HSR-HTIR) is a novel source data that became available in recent years object detection. In this research, method proposed integration HTIR very high (VHSR) visible image to classify objects. First, atmospheric corrections were enforced the HSR-HTIR. Second, first time, projection pursuit (PP) band reduction was applied data, results achieved are better than those obtained by applying principal component analysis (PCA) as well-known approach. Then, various features derived from HSR-HTIR VHSR images fed pixel-based support vector machine (SVM) classification algorithm, seven classes detected. Afterward, an innovative strategy, using object-rule-based postprocessing approach, introduced postclassification raw results. Finally, decision-based overlaying process carried out produce final map. The indicate potential only spectral features. Consequently, its implementation becomes more feasible accuracies competitive comparison announced previously IEEE Geoscience Remote Sensing Society (GRSS) Data Fusion contest 2014.