Abstract
Automatic ship detection from synthetic aperture radar (SAR) imagery plays a significant role in many urban applications. Recently, owing to the impressive performance of deep learning, various SAR ship detection methods based on the convolution neural network (CNN) have been proposed for optical SAR images. However, existing CNN-based methods and spatial-domain-based methods exhibit certain limitations. Some algorithms do not consider the detection speed and model scale when improving the detection accuracy, which limits the real-time application and deployment of SAR. To solve this problem, a lightweight, high-speed and high-accurate SAR ship detection method based on yolov3 has been proposed. First, the backbone part of the model is improved, the pure integer quantization network is applied as the core to reduce a small amount of accuracy while reducing the model scale by more than half; Second, modify the feature pyramid network to improve the detection performance of small-scale ships by enhancing feature receptive fields; third, introduce the IoU loss branch to further improve the detection and positioning accuracy; finally, the feature distillation is applied to handle the problem of accuracy decrease caused by model integer quantization. The experimental results on the two public SAR ship datasets show that this algorithm has certain practical significance in the real-time SAR application, and its lightweight parameters are helpful for future FPGA or DSP hardware transplantation.
Bing Chen and Yuting Zhu contributed to the work equally and should be regarded as co-first authors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Hui, M., Xiaoqing, W., Jinsong, C., Xiangfei, W., Weiya, K.: Doppler spectrum-based NRCS estimation method for low-scattering areas in ocean SAR images. Remote Sensing (2017)
Chen, G., Li, G., Liu, Y., Zhang, X.P., Zhang, L.: Sar image despeckling based on combination of fractional-order total variation and nonlocal low rank regularization. IEEE Trans. Geosci. Remote Sens. 58(3), 2056–2070 (2021)
Gui, G.: A parzen-window-kernel-based CFAR algorithm for ship detection in SAR images. 8(3), 557–561 (2011)
Jiang, S., Chao, W., Bo, Z., Hong, Z.: Ship detection based on feature confidence for high resolution SAR images. In: Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International (2012)
Wang, C., Bi, F., Liang, C., Jing, C.: A novel threshold template algorithm for ship detection in high-resolution SAR images. In: IGARSS 2016 - 2016 IEEE International Geoscience and Remote Sensing Symposium (2016)
Li, J., Qu, C., Shao, J.: Ship detection in SAR images based on an improved faster R-CNN. In: Sar in Big Data Era: Models, Methods & Applications (2017)
Wang, Y., Wang, C., Zhang, H., Dong, Y., Wei, S.: A SAR dataset of ship detection for deep learning under complex backgrounds. Remote Sensing, 11(7) (2020)
Li Jianwei, Q., Changwen, P.S., Bing, D.: Ship target detection in SAR images based on convolutional neural network. Syst. Eng. Electron. Technol. 40(9), 7 (2018)
Changhua, H., Chen, C., Chuan, H., Hong, P., Jianxun, Z.: Small target detection of ships. In: SAR images based on deep convolutional neural networks (3) (2022)
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. arXiv e-prints (2018)
Xiaoling, Z., Tianwen, Z., Jun, S., Shunjun, W.: High-speed and high-precision SAR ship detection based on deep separation convolutional neural network. J. Radar 8(6), 11 (2019)
Wang, Y., Wang, C., Zhang, H., Dong, Y., Wei, S.: Automatic ship detection based on retinanet using multi-resolution gaofen-3 imagery. Remote Sens., 11(5) (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. IEEE (2016)
Tan, M., Le, Q.V.: Efficientnet: rethinking model scaling for convolutional neural networks (2019)
Abadi, M., Barham, P., Chen, J., Chen, Z., Zhang, X.: A system for large-scale machine learning. USENIX Association, Tensorflow (2016)
Lin, T.Y., Dollar, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. IEEE Computer Society (2017)
Bochkovskiy, A., Wang, C.Y., Liao, H.: YOLOv4: optimal speed and accuracy of object detection (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, B., Zhu, Y., Wang, C., Wang, X. (2023). Synthetic Aperture Radar Image Ship Detection Based on YOLO-SARshipNet. In: Liang, Q., Wang, W., Liu, X., Na, Z., Zhang, B. (eds) Communications, Signal Processing, and Systems. CSPS 2022. Lecture Notes in Electrical Engineering, vol 873. Springer, Singapore. https://doi.org/10.1007/978-981-99-1260-5_1
Download citation
DOI: https://doi.org/10.1007/978-981-99-1260-5_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-1259-9
Online ISBN: 978-981-99-1260-5
eBook Packages: EngineeringEngineering (R0)