TY - GEN
T1 - Spotlight SAR image recognition based on dual-channel feature map convolutional neural network
AU - Liu, Junjie
AU - Fu, Xiongjun
AU - Liu, Kaiqiang
AU - Wang, Miao
AU - Zhang, Chengyan
AU - Su, Qinning
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/7
Y1 - 2019/7
N2 - Synthetic Aperture Radar (SAR) is widely used in agriculture, remote sensing and many other fields due to its allweather working mode and its excellent penetration. However, the decipherment of synthetic aperture radar imaging is very difficult compared to optical images. This problem is even worse in the SAR target recognition. Although the traditional feature engineering method is helpful for SAR image information content extraction, the effect is not satisfied with the requirements in practice. Convolutional neural network is an effective method to extract synthetic aperture radar imaging features and recognize targets. In this paper, a dualchannel feature map convolutional neural network (DCFM-CNN) is proposed, using two different down sampling methods, - pooling and convolution, to extract features for SAR image automatic target recognition (SAR-ATR). An average recognition accuracy of 99.45% was achieved on MSTAR public data set. Preprocessing of synthetic aperture radar imaging is not needed here, and the target recognition is completed by the CNN model. The proposed object recognition approach is effective with low overhead.
AB - Synthetic Aperture Radar (SAR) is widely used in agriculture, remote sensing and many other fields due to its allweather working mode and its excellent penetration. However, the decipherment of synthetic aperture radar imaging is very difficult compared to optical images. This problem is even worse in the SAR target recognition. Although the traditional feature engineering method is helpful for SAR image information content extraction, the effect is not satisfied with the requirements in practice. Convolutional neural network is an effective method to extract synthetic aperture radar imaging features and recognize targets. In this paper, a dualchannel feature map convolutional neural network (DCFM-CNN) is proposed, using two different down sampling methods, - pooling and convolution, to extract features for SAR image automatic target recognition (SAR-ATR). An average recognition accuracy of 99.45% was achieved on MSTAR public data set. Preprocessing of synthetic aperture radar imaging is not needed here, and the target recognition is completed by the CNN model. The proposed object recognition approach is effective with low overhead.
KW - Convolutional neural network
KW - Deep learning
KW - Dual-channel feature map
KW - Object recognition
KW - Synthetic aperture radar imaging
UR - http://www.scopus.com/inward/record.url?scp=85074393648&partnerID=8YFLogxK
U2 - 10.1109/SIPROCESS.2019.8868672
DO - 10.1109/SIPROCESS.2019.8868672
M3 - Conference contribution
AN - SCOPUS:85074393648
T3 - 2019 IEEE 4th International Conference on Signal and Image Processing, ICSIP 2019
SP - 65
EP - 69
BT - 2019 IEEE 4th International Conference on Signal and Image Processing, ICSIP 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 4th IEEE International Conference on Signal and Image Processing, ICSIP 2019
Y2 - 19 July 2019 through 21 July 2019
ER -