Fast aircraft detection in satellite images based on convolutional neural networks
Hui Wu, Hui Zhang, Jinfang Zhang, Fanjiang Xu · 2015
Aircraft detection in satellite images is generally difficult due to the variations of aircraft type, pose, size and complex background. In this paper, we propose a new aircraft detection framework based on objectiveness detection techniques (e.g., BING) and Convolutional Neural Networks (CNN). The advantages are two folds. On one hand, we first introduce the CNN for aircraft detection, as CNN can learn rich features from the raw data automatically and has yielded a state-of-the-art performance in many object detection tasks. On the other hand, the use of candidate object regions proposed by BING achieves a high object detection rate and saves time simultaneously. Experimental results show that the proposed method is fast and effective to detect aircrafts in complex airport scenes. We also construct a dataset for aircraft detection obtained from Google Earth.