CCNet: A high-speed cascaded convolutional neural network for ship detection with multispectral images
Received:October 31, 2018  Revised:November 27, 2018  download
Citation:
Hits: 112
Download times: 128
Author NameAffiliationE-mail
ZHANG Zhong-Xing Institute of Semiconductors, Chinese Academy of Sciences University of Chinese Academy of Sciences zhangzhongxing@semi.ac.cn 
LI Hong-Long Institute of Semiconductors, Chinese Academy of Sciences University of Chinese Academy of Sciences  
ZHANG Guang-Qian Institute of Semiconductors, Chinese Academy of Sciences University of Chinese Academy of Sciences  
ZHU Wen-Ping Institute of Semiconductors, Chinese Academy of Sciences University of Chinese Academy of Sciences  
LIU Li-Yuan Institute of Semiconductors, Chinese Academy of Sciences University of Chinese Academy of Sciences  
LIU Jian Institute of Semiconductors, Chinese Academy of Sciences University of Chinese Academy of Sciences  
WU Nan-Jian Institute of Semiconductors, Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences nanjian@red.semi.ac.cn 
Abstract:A novel ship detection method using cascaded convolutional neural network (CCNet) with multispectral image is proposed to achieve high-speed detection. The CCNet employs two cascaded convolutional neural networks (CNN) for extracting regions of interest (ROIs), locating and segmenting ship objects sequentially. Benefit from the abundant details of the multispectral image, CCNet can extract more robust feature for achieving more accurate detection. The efficiency of CCNet has been validated by the experiments on SPOT 6 satellite multispectral images. In comparison with the state-of-the-art deep learning based ship detection algorithms, the experimental results indicate that the proposed ship detection algorithm accelerates the processing by more than 5 times with a high accurate detection performance.
keywords:Ship detection, convolutional neural network, multispectral image, infrared image
View Full Text  View/Add Comment  Download reader

Copyright:《Journal of Infrared And Millimeter Waves》