طبقه بندي تصاوير ابرطيفي مبتني بر تلفيق ويژگي هاي مستخرج از روش هاي كدگذاري تنك، تبديلات خطي و غيرخطي

Hyperspectral Image Classification Based on the Fusion of the Features Generated by Sparse Representation Methods, Linear and Non-linear Transformations

طبقه­ بندي يكي از مهم­ترين روش ­هاي استخراج اطلاعات از تصاوير ابرطيفي است. در اين مقاله، راهكاري نوين با هدف توليد ويژگي بمنظور طبقه‌بندي اين تصاوير پيشنهاد شده است. اين راهكار تلفيقي از تبديلات خطي، غيرخطي و نمايش تنك بمنظور توليد ويژگي‌هاي موثر در فرايند طبقه‌بندي تصاوير ابرطيفي است. در روند پيشنهادي، ابتدا با رويكردي جديد و نظارت شده از تبديل غيرخطي تحليل مؤلفه‌‌هاي اصلي (NLPCA) بمنظور انتقال داده‌‌هاي طيفي به فضايي با ابعاد بيشتر استفاده شده است. در مرحله دوم، بكمك تبديل تحليل تفكيك‌پذيري خطي(LDA) فرامكعب حاصل از مرحله قبل به فضايي با بعد كمتر انتقال مي‌يابد. در ادامه با هدف هم مقياس‌ كردن ويژگي‌هاي توليدي و بهره‌گيري از پتانسيل تمامي داده‌هاي آموزشي، داده‌ها از طريق روش‌هاي تخمين تنك سيگنال به فضاي ويژگي جديدي با بعدي متناظر با تعداد كلاس‌هاي طبقه‌بندي منتقل مي‌شوند. در اين تحقيق از طبقه‌بندي كننده­ي k نزديكترين همسايه‌ي وزندار براي طبقه‌بندي فضاي ويژگي استفاده شده است. اين راهكار در دو داده‌ي ابرطيفي پياده‌سازي شده و به طور متوسط بهبود دقت 6 درصدي را نسبت به باندهاي طيفي و ساير زير‌ مجموعه‌هاي تلفيق ويژگي از روش پيشنهادي نشان داده است. كسب دقت كلي تا 99 درصد و همچنين تفكيك پذيري بيشتر كلاس‌هاي با داد‌‌‌ه‌هاي آموزشي اندك از ويژگي‌هاي اين روش محسوب مي‌شود.

The ability of recording the high resolution spectral signature of earth surface would be the most important feature of hyperspectral sensors. On the other hand, classification of hyperspectral imagery is known as one of the methods to extracting information from these remote sensing data sources. Despite the high potential of hyperspectral images in the information content point of view, there are a numerous challenges in reliable extraction of information from these images. The issues such as 1- spectral similarity of different phenomena, 2- sensor noises and atmospheric effects, 3- the effects of high dimensionality in the pattern recognition algorithms, 4- the necessity of large number of training data to perform a reliable classification, and 5- spectral variability of similar phenomena could be considered as some of the challenges in hyperspectral data processing. Decreasing of the high dimensionality effects via the dimension reduction algorithms (e.g. band selection and feature extraction algorithms), as well as increasing the separability of the overlapped classes through the linear/non-linear mappings into the feature spaces with the higher dimensional are two opposite and conventional approaches of hyperspectral data processing. These approaches would be used based on the factors such as 1- complexities of classes in the imaging area, 2- spectral range of imaging sensor, and 3- the restrictions of processing algorithms. In this paper the fusion of these two approaches is used to perform an accurate hyperspectral image classification. To do so, a novel feature extraction method is proposed to be used in the hyperspectral image classification. The core of this method is the fusion of the linear, non-linear and sparse representation based features which is used to produce the effective features in the weighted K-Nearest Neighbors (KNN) classification method. In this procedure, a set of supervised and nonlinear features are extracted as the first step through the Nonlinear Principal Component Analysis (NLPCA). The supervised usage of NLPCA in order to extract features is known as one of the novelties of this paper. In this step, the spectral bands are usually mapped to a high dimensional feature space through the self-estimator artificial neural networks (ANNs) which are trained separately by ground truth data. In the second step, the previously extracted features are linearly transformed by the Linear Discriminate Analysis (LDA) method in order to reduce the dimension of the hypercube generated via supervised NLPCA to a separable feature space. In the last step, a set of features which is proportional to the number of classes is generated based on the sparse representation theory. The sparse representation features were hired to handle the effects of the inter-class variability. The precisions of the classified features in the two different hyperspectral images were on average shown 6 percent improvements in comparison with the spectral bands and the other combinations of extracted features. Furthermore, reach to the approximately 99% overall accuracies in the classes with the few training data could be considered as other achievements of the proposed method.