Feature concatenation for scene classification of VHR images based on canonical correlation analysis.

Abstract The recent advancements of technology in remote sensing enable us to get very high-resolution images (VHR). To do scene classification in these images turned significant and become a challenging problem due to the lack of availability of adequate labelled data. We get over fitting problems by training a limited amount of labelled data. Considering the features obtained by deep learning convolutional nets as inputs we address this issue. Here we utilize the existing VGG16, Alex Net frameworks as a feature extractor to extricate informative features from the authentic VHR Images. Succeeding, discuss feature concatenation and classification framework based on Canonical Correlation Analysis (CCA). This strategy uses the correspondence of two feature vectors of discriminant information and eradicates redundant information within the features. This permits a more effective approach than conventional extraction techniques exclusively. The experimental results demonstrate that the feature concatenation strategy based on the CCA technique produces good informative features and accomplishes a higher accuracy with much dimension reduction than exclusively using the raw deep features. We use a 0.3 sub-meter resolution UC MERCED data set to explore our approach.