Aircraft Detection in Remote Sensing Images Based On Deep Convolutional Neural Network

2018 4th International Conference on Environmental Science and Material Application

生态环境科学;材料科学

Li, Yibo^1 ; Zhang, Senyue^2 ; Zhao, Jingfei^1 ; Tan, Wenan^2

Shenyang Aerospace University, Shenyang, China^1

Nanjing University of Aeronautics, Nanjing, China^2

关键词: Automatic aircraft;    Complex background;    Convolutional neural network;    Detection models;    Google earths;    Learning abilities;    Remote sensing images;    State-of-the-art methods;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/252/5/052122/pdf
DOI  :  10.1088/1755-1315/252/5/052122

来源: IOP

【 摘 要 】

Aircraft detection in remote sensing images is always the research hotspot but a challenging task for the variations of aircraft type, pose, size and complex background. In the paper, we propose a region-based convolutional neural network to detect aircrafts. To enhance the learning ability of the network, a mult-resolution aircraft remote sensing dataset is collected from Google Earth. Then, the detection model is trained end to end by fine-tuning on the obtained dataset and realizes automatic aircraft recognition and positioning. Experiments show that the proposed method outperforms state-of-the-art method on the same dataset and the requirement for real-time can be satisfied simultaneously.