Enhancement of Ship Type Classification from a Combination of CNN and KNN

Abstract

Ship type classification of synthetic aperture radar imagery with convolution neural network (CNN) has been faced with insufficient labeled datasets, unoptimized and noised polarization images that can deteriorate a classification performance. Meanwhile, numerous labeled text information for ships, such as length and breadth, can be easily obtained from various sources and can be utilized in a classification with k-nearest neighbor (KNN). This study proposes a method to improve the efficiency of ship type classification from Sentinel-1 dual-polarization data with 10 m pixel spacing using both CNN and KNN models. In the first stage, Sentinel-1 intensity images centered on ship positions were used in a rectangular shape to apply an image processing procedure such as head-up, padding and image augmentation. The process increased the accuracy by 33.0% and 31.7% for VH (vertical transmit and horizontal receive) and VV (vertical transmit and vertical receive) polarization compared to the CNN-based classification with original ship images, respectively. In the second step, a combined method of CNN and KNN was compared with a CNN-alone case. The f1-score of CNN alone was up to 85.0%, whereas the combination method showed up to 94.3%, which was a 9.3% increase. In the future, more details on an optimization method will be investigated through field experiments of ship classification.