Design of Embedded Real-Time Large Size SAR Image Ship Detection System

doi:10.3778/j.issn.1002-8331.2209-0287

Abstract

Abstract: In applications of real-time ship detection in large size synthetic aperture radar (SAR) images after real-time imaging of spaceborne or airborne high-resolution SAR, it is difficult for traditional FPGA+DSP embedded system to realize both of the SAR imaging process and the artificial intelligence-based ship detection in real-time for large size SAR images. In this paper, a large size SAR images oriented real-time ship detection system on 3U VPX FPGA+GPU is proposed and a YOLOv5s based ship detection model is proposed as well, which applies L2-norm sparsity penalty scaling factor control method for lightweight. The average detection accuracy of the proposed lightweight ship detection model is 0.968, where the number of the parameters of the model is reduced by 47.39%, and the computational cost is reduced by 18.67%. The lightweight ship detection model is applied to the embedded ship real-time detection system for large size SAR images. For the typical large size images application scenario of 10 km×10 km, the embedded real-time detection system is designed and implemented by utilizing multi-threading and GPU-based many-core parallel programming. Performance evaluation are conducted on a public SAR image data set. Experimental results verify that the proposed system is able to meet the requirements of the real-time ship detection for large size SAR images under different resolutions.

Key words: synthetic aperture radar (SAR) , YOLOv5s, lightweight, graphics processing unit (GPU) , real-time ship detection

摘要： 针对星载或机载高分辨率合成孔径雷达（synthetic aperture radar，SAR）实时成像后的大幅宽SAR图像舰船实时检测的应用需求，传统的基于FPGA+DSP的嵌入式系统很难同时实现SAR成像处理和基于人工智能技术的大幅宽SAR图像舰船实时检测，为此设计了一种基于3U VPX FPGA+GPU架构的大幅宽SAR图像嵌入式舰船实时检测系统；提出了一种基于YOLOv5s的舰船检测模型，采用基于L2-范数稀疏性惩罚的缩放因子控制法进行轻量化，轻量化舰船检测模型的参数量减小了47.39%，计算量减少了18.67%，平均检测精度为0.968；将轻量化舰船检测模型应用于大幅宽SAR图像嵌入式舰船实时检测系统，并针对典型的10 km×10 km的大幅宽图像应用场景，设计开发基于多线程技术和基于GPU的众核并行计算技术的大幅宽SAR图像嵌入式实时检测系统软件；通过公开的SAR数据集进行功能验证和性能评估，该系统能够满足不同分辨率的大幅宽SAR图像舰船实时检测需求。

关键词: 合成孔径雷达（SAR）, YOLOv5s, 轻量化, 图形处理器（GPU）, 实时舰船检测

LU Tianyu, XU Zhan, CUI Hongyuan, GONG Hao, WANG Cheng. Design of Embedded Real-Time Large Size SAR Image Ship Detection System[J]. Computer Engineering and Applications, 2024, 60(1): 301-309.

陆天宇, 徐湛, 崔红元, 龚昊, 王琤. 大幅宽SAR图像嵌入式舰船实时检测系统设计[J]. 计算机工程与应用, 2024, 60(1): 301-309.

References

[1] ZHAO K, ZHOU Y, CHEN X. A dense connection based SAR ship detection network[C]//2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2020: 669-673.
[2] CHAI B, CHEN L, SHI H, et al. Marine ship detection method for SAR image based on improved Faster RCNN[C]//2021 SAR in Big Data Era (BIGSARDATA), 2021: 1-4.
[3] XU X, ZHANG X, ZHANG T. SAR ship detection using YOLOv5 algorithm with anchor boxes cluster[C]//2022 IEEE International Geoscience and Remote Sensing Symposium, 2022: 2139-2142.
[4] 王毓玮, 史国友, 林佳木. 基于改进Faster R-CNN的SAR舰船图像检测[J]. 船舶工程, 2021, 43(8): 29-33.
WANG Y W, SHI G Y, LIN J M. SAR ship image detection based on improved Faster R-CNN[J]. Ship Engineering, 2021, 43(8): 29-33.
[5] GUO Y, CHEN S, ZHAN R, et al. SAR ship detection based on YOLOv5 using CBAM and BiFPN[C]//2022 IEEE International Geoscience and Remote Sensing Symposium, 2022: 2147-2150.
[6] BENGIO Y, COURVILLE A, VINCENT P. Representation learning: a review and new perspectives[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(8): 1798-1828.
[7] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[8] GIRSHICK R. Fast R-CNN[C]//Proceedings of the IEEE International Conference on Computer Vision, 2015: 1440-1448.
[9] REN S, HE K, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[10] HE K, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[C]//2017 IEEE International Conference on Computer Vision (ICCV), 2017: 2980-2988.
[11] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real?time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016: 779-788.
[12] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference Computer Vision, 2016: 21-37.
[13] REDMON J, FARHADI A. YOLO9000: better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017: 6517-6525.
[14] REDMON J, FARHADI A. YOLOv3: an incremental improvement[J]. arXiv:1804.02767, 2018.
[15] BOCHKOVSKIY A, WANG C Y, LIAO H Y M. YOLOv4: optimal speed and accuracy of object detection[J]. arXiv:2004.10934, 2020.
[16] 张晓玲, 张天文, 师君, 等. 基于深度分离卷积神经网络的高速高精度SAR舰船检测[J]. 雷达学报, 2019, 8(6): 841-851.
ZHANG X L, ZHANG T W, SHI J, et al. High-speed and high-accurate SAR ship detection based on a depthwise separable convolution neural network[J]. Journal of Radars, 2019, 8(6): 841-851.
[17] 谭显东, 彭辉. 改进YOLOv5的SAR图像舰船目标检测[J]. 计算机工程与应用, 2022, 58(4): 247-254.
TAN X D, PENG H. Improved YOLOv5 ship target detection in SAR image[J]. Computer Engineering and Applications, 2022, 58(4): 247-254.
[18] 李磊, 徐国伟, 李文婧, 等. 基于深度学习的舰船目标检测算法与硬件加速[J]. 计算机应用, 2021, 41(S1): 162-166.
LI L, XU G W, LI W J, et al. Ship target detection algorithm based on deep learning and hardware acceleration[J]. Journal of Computer Applications, 2021, 41(S1): 162-166.
[19] 张天文, 张晓玲. 一种大场景SAR图像中舰船检测虚警抑制方法[J]. 现代雷达, 2022, 44(2): 1-8.
ZHANG T W, ZHANG X L. A false alarm suppression method for ship detection in large-scene SAR image[J]. Modern Radar, 2022, 44(2): 1-8.
[20] 周玉金, 谢宜壮, 乔婷婷, 等. 基于Jetson TX2的SAR船只目标检测实现[J]. 信号处理, 2022, 38(2): 426-431.
ZHOU Y J, XIE Y Z, QIAO T T, et al. Implementation of SAR ship target detection based on Jetson TX2[J]. Journal of Signal Processing, 2022, 38(2): 426-431.
[21] LIU Z, LI J, SHEN Z, et al. Learning efficient convolutional networks through network slimming[C]//2017 IEEE International Conference on Computer Vision (ICCV), 2017: 2755-2763.
[22] LI J, QU C, SHAO J. Ship detection in SAR images based on an improved faster R-CNN[C]//2017 SAR in Big Data Era: Models, Methods and Applications (BIGSARDATA), 2017: 1-6.