SAR Ship Classification Based on Multi-convolutional Neural Network Fusion

Abstract

Abstract: The accuracy of small ship classification in Syntactic Aperture Radar （SAR） images is low. To solve the problem， a classification approach based on the weighted fusion of different convolutional neural network results is proposed. Firstly， a high-resolution convolutional neural network is constructed to conduct multi-scale feature fusion， fine-tuning model and label smoothing are introduced to reduce the problem of training over-fitting. Then three single classification models are trained using the high-resolution network， MobileNetv2 network and SqueezeNet network. Finally， the results of three classification models are fused by weighted voting. The fusion method is used to carry out classification experiment on GF-3 ship dataset， the results obtained are: precision 94.83%， recall rate 95.43%， F1 score 0.9513. Experimental results show that the algorithm model proposed in this paper has better classification ability， which verifies its effectiveness in high-resolution SAR image ship classification.

Key words: SAR images； high-resolution convolutional neural networks； fine tuning model, label smooth； weighted voting； ship classification

ZHANG Xiao, LYU Ji-yu, ZHAO Shuang, WU Yu-lun, WANG Chun-le. SAR Ship Classification Based on Multi-convolutional Neural Network Fusion[J]. Computer and Modernization, 2023, 0(01): 37-42.

References

［1］邓云凯，禹卫东，张衡，等. 未来星载SAR技术发展趋势［J］. 雷达学报， 2020，9（1）:1-33.
［2］邹浩，林赟，洪文. 基于多角度合成SAR图像的目标识别性能分析［J］. 中国科学院大学学报， 2019，36（2）:226-234.
［3］ RAJ J A， IDICULA S M， PAUL B. A novel ship detection method from SAR image with reduced false alarm［J］. Journal of Physics Conference Series， 2021，1817（1）. DOI:10.
1088/1742-6596/1817/1/012010.
［4］ SHARIFZADEH F， AKBARIZADEH G， KAVIAN Y S. Ship classification in SAR images using a new hybrid CNN-MLP classifier［J］. Journal of the Indian Society of Remote Sensing， 2019，47（4）:551-562.
［5］孙忠镇，熊博莅，冷祥光，等. 基于精细分割的SAR图像舰船目标几何结构特征提取［J］. 电波科学学报， 2020，35（4）:585-593.
［6］ KNAPSKOG A O， BROVOLL S， TORVIK B. Characteristics of ships in harbour investigated in simultaneous images from TerraSAR-X and PicoSAR［C］// 2010 IEEE Radar Conference. 2010:422-427.
［7］ LENG X G， JI K F， ZHOU S L， et al. 2D comb feature for analysis of ship classification in high resolution SAR imagery［J］. Electronics Letters， 2017，53（7）:500-502.
［8］贾程澄，王军，邱峰. 多特征提取和多核SVM 的舰船目标识别方法［J］. 电光与控制， 2021，28 （11）:106-111．
［9］张晓，王莉莉. 基于多分类器融合的卫星图像舰船目标识别［J］. 通信技术， 2019，52（9）:2143-2148.
［10］ XUE R H， BAI X R， ZHOU F. Spatial-temporal ensemble convolution for sequence SAR target classification［J］. IEEE Transactions on Geoscience and Remote Sensing， 2021，59（2）:1250-1262.
［11］ WANG L， BAI X R， XUE R H， et al. Few-shot SAR automatic target recognition based on Conv-BiLSTM prototypical network［J］. Neurocomputing， 2021，443（1）: 235-246.
［12］ HUANG L Q， LIU B， LI B Y， et al. OpenSARShip: A dataset dedicated to Sentinel-1 ship interpretation［J］. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing， 2018，11（1）:195-208.
［13］ HOU X Y， AO W， XU F. End-to-end automatic ship detection and recognition in high-resolution Gaofen-3 spaceborne SAR images ［C］// IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. 2019:9486-9489.
［14］ HOU X Y， AO W， SONG Q， et al. FUSAR-Ship: Building a high-resolution SAR-AIS matchup dataset of Gaofen-3 for ship detection and recognition ［J］. Science China Information Sciences volume， 2020，63（4）:36-54.
［15］ BENTES C， VELOTTO D， TINGS B. Ship classification in TerraSAR-X images with convolutional neural networks［J］. IEEE Journal of Oceanic Engineering， 2018，43（1）:258-266.
［16］ WU Y X， YUAN Y， GUAN J， et al. Joint convolutional neural network for small-scale ship classification in SAR images［C］// IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. 2019:2619-2622.
［17］ HE J L， WANG Y H， LIU H W. Ship classification in medium-resolution SAR Images via densely connected triplet CNNs integrating fisher discrimination regularized metric learning［J］. IEEE Transactions on Geoscience and Remote Sensing， 2021，59（4）:3022-3039.
［18］ ZHANG T W， ZHANG X L， KE X， et al. HOG-ShipCLSNet: A novel deep learning network with hog feature fusion for SAR ship classification［J］. IEEE Transactions on Geoscience and Remote Sensing， 2021，60（1）:1-22.
［19］ XU Y J， LANG H T. Ship classification in SAR images with geometric transfer metric learning［J］. IEEE Transactions on Geoscience and Remote Sensing， 2020，59 （8）:6799-6813.
［20］ LU C C， LI W H. Ship classification in high-resolution SAR images via transfer learning with small training dataset［J］. Sensors， 2018，19（1）:63.
［21］ WANG Y Y， WANG C， ZHANG H. Ship classification in high-resolution SAR images using deep learning of small datasets［J］. Sensors， 2018，18（9）:2929.
［22］ ZHANG D， LIU J， HENG W， et al. Transfer learning with convolutional neural networks for SAR ship recognition［J］. IOP Conference， 2018，322（7）:248-260.
［23］张梦雨. 基于ResNet和注意力机制的花卉识别［J］. 计算机与现代化， 2021 （4）:61-67.
［24］ DONG Y B， ZHANG H， WANG C， et al. Fine-grained ship classification based on deep residual learning for high-resolution SAR images［J］. Remote Sensing Letters， 2019，10 （11）: 1095-1104.
［25］ SANDLER M， HOWARD A， ZHU M L， et al. Mobilenetv2: Inverted residuals and linear bottlenecks［C］// Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition. 2018:4510-4520.
［26］ IANDOLA F N， HAN S， MOSKEWICZ M W， et al. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5 MB model size［J］. arXiv preprint arXiv:1602.07360， 2016.
［27］ ZHANG C B， JIANG P T， HOU Q B， et al. Delving deep into label smoothing［J］. IEEE Transactions on Image Processing， 2021，30:5984-5996.
［28］ WEI Y X， LIU Q X， ZHANG G X， et al. Label smoothing technique for ordinal classification in cloud assessment［C］// IGARSS 2020-2020 IEEE International Geoscience and Remote Sensing Symposium. 2020: 2264-2267.
［29］冯泽安，王鹏. 基于多分类模型加权投票法的人脸微笑检测［J］. 计算机技术与发展， 2019，29（2）:81-86.
［30］李佳，郭剑毅，刘艳超，等. 基于多分类器加权投票法的越南语组合歧义消歧［J］. 计算机科学， 2018，45（1）:167-172.
［31］ CUI Y， ZHOU G Y， YANG J Y， et al. On the iterative censoring for target detection in SAR images［J］. IEEE Geoscience and Remote Sensing Letters， 2011，8（4）:641-645.
［32］ MA N N， ZHANG X Y， ZHENG H T， et al. Shufflenet v2: Practical guidelines for efficient cnn architecture design［C］// Proceedings of the European Conference on Computer Vision （ECCV）. 2018:122-138.
［33］ HUANG G， LIU Z， VAN DER MAATEN L， et al. Densely connected convolutional networks ［C］// Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. 2017: 2261-2269.