Airport Detection on Remote Sensing Images Using Fater Region-based Convolutional Neural Network

Abstract

Abstract. An airport detection method on remote sensing images based on transfer learning and hard example mining is proposed. We use Faster region-based convolutional neural network framework with end-to-end advantage instead of the sliding windows and artificial features in the existing traditional methods. Transfer learning is used to solve this problem that the number of airport remote sensing data itself is limited. Hard example mining is used to make full use of hard examples. As a result, it can improve the ability to discriminate objects and make training more efficient. The experimental results show that the proposed method can detect different types of airports accurately under complex backgrounds. Compared with other airport detection methods, the proposed method has higher detection rate 92.6%, lower falsealarm rate 15% and shorter average processing time 0.2s.

A Feature Fusion Airport Detection Method Based on the Whole Scene Multispectral Remote Sensing Images

“…The second group of airport detection methods (post-2016) mainly uses deep-learning methods [e.g., ResNet [29], convolutional neural networks [30], and fast region-based convolutional neural networks [16]] that integrate computer-vision methods and biological-vision mechanisms based on the rapid development of image-processing techniques. Deep learning is an automated feature-learning and representation framework that can learn deep features in RSIs [31].…”