Region Based CNN for Foreign Object Debris Detection on Airfield Pavement

Xiaoguang Cao; Peng Wang; Cai Meng; Xiangzhi Bai; Guoping Gong; Miaoming Liu; Jun Qi

doi:10.3390/s18030737

Region Based CNN for Foreign Object Debris Detection on Airfield Pavement

Sensors (Basel). 2018 Mar 1;18(3):737. doi: 10.3390/s18030737.

Authors

Xiaoguang Cao¹, Peng Wang², Cai Meng³, Xiangzhi Bai^{4

5}, Guoping Gong⁶, Miaoming Liu⁷, Jun Qi⁸

Affiliations

¹ Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. xgcao@buaa.edu.cn.
² Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. paulwp@buaa.edu.cn.
³ Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. tsai@buaa.edu.cn.
⁴ Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. jackybxz@buaa.edu.cn.
⁵ State Key Laboratory of Virtual Reality Technology and Systems, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. jackybxz@buaa.edu.cn.
⁶ Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. gonggp@buaa.edu.cn.
⁷ Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. liumiaoming@ime.ac.cn.
⁸ Image Processing Center, Beijing University of Aeronautics and Astronautics, Beijing 100191, China. qijun1994@126.com.

Abstract

In this paper, a novel algorithm based on convolutional neural network (CNN) is proposed to detect foreign object debris (FOD) based on optical imaging sensors. It contains two modules, the improved region proposal network (RPN) and spatial transformer network (STN) based CNN classifier. In the improved RPN, some extra select rules are designed and deployed to generate high quality candidates with fewer numbers. Moreover, the efficiency of CNN detector is significantly improved by introducing STN layer. Compared to faster R-CNN and single shot multiBox detector (SSD), the proposed algorithm achieves better result for FOD detection on airfield pavement in the experiment.

Keywords: convolutional neural network; foreign object debris; object detection; vehicular imaging sensors.