针对海洋环境的复杂性以及舰船目标的多样性，研究基于视觉传达的舰船航行图像中多目标检测方法，及时发现潜在的安全隐患。将舰船航行图像从RGB颜色空间转换到CIE Lab模式空间，应用改进HFT（超复数傅里叶变换）模型有效提取舰船多目标显著区域。利用加权处理和Otsu算法划分多层显著区域，并基于先验信息确定舰船多目标候选区域。采用模糊C均值聚类算法对候选区域进行分割，实现舰船多目标的精准检测。实验结果表明，该方法可在云雾覆盖、海洋杂波、船舶尾迹等多种复杂环境下准确检测舰船多目标，具有较高的鲁棒性和实用性。
In response to the complexity of the marine environment and the diversity of ship targets, a multi object detection method based on visual communication in ship navigation images is studied to timely discover potential safety hazards. Convert ship navigation images from RGB color space to CIE Lab mode space, and apply an improved HFT (Hypercomplex Fourier Transform) model to effectively extract multi-target salient regions of ships. Using weighted processing and Otsu algorithm to partition multi-layer salient regions, and determining multi-target candidate regions for ships based on prior information. Using fuzzy C-means clustering algorithm to segment candidate regions and achieve accurate detection of multiple targets on ships. The experimental results show that this method can accurately detect multiple targets of ships in various complex environments such as cloud and fog coverage, ocean clutter, and ship wake, and has high robustness and practicality.
2024,46(16): 170-173 收稿日期：2024-02-17
DOI：10.3404/j.issn.1672-7649.2024.16.029
分类号：TP391.4
基金项目：江西省教育厅科学技术研究项目（GJJ2203103）
作者简介：吴军良（1981 – ），男，副教授，研究方向为软件工程及算法设计
参考文献：
[1] 郑子阳, 张婷, 刘兆英, 等. 基于旋转损失函数RCIoU的SAR图像舰船目标检测方法[J]. 山东大学学报(工学版), 2022, 52(2): 15–22.
ZHENG Ziyang , ZHANG Ting , LIU Zhaoying , et al. Ship target detection in SAR images based on RCIoU loss function[J]. Journal of Shandong University(Engineering Science) , 2022, 52(2): 15–22.
[2] 周旗开, 张伟, 李东锦, 等. 基于改进YOLOv5s的光学遥感图像舰船分类检测方法[J]. 激光与光电子学进展, 2022, 59(16): 476–483.
ZHOU Qikai , ZHANG Wei , LI Dongjin , et al. Ship classification and detection method for optical remote sensing images based on improved YOLOv5s [J]. Laser & Optoelectronics Progress, 2022, 59(16): 476–483.
[3] 扈琪, 胡绍海, 刘帅奇. 基于多层显著性模型的SAR图像舰船目标检测[J]. 系统工程与电子技术, 2024, 46(2): 478–487.
HU Qi , HU Shaohai , LIU Shuaiqi . Ship detection in SAR image based on multi-layer saliency model[J]. Systems Engineering and Electronics, 2024, 46(2): 478–487.
[4] 严荣慧, 谢海成, 花敏恒, 等. 基于运动与表象特征的广域船舶目标识别方法[J]. 中国舰船研究, 2022, 17(1): 227–234.
YAN Ronghui, XIE Haicheng, HUA Minheng, et al. Wide-area ship target recognition method based on motion and appearance features[J]. Chinese Journal of Ship Research, 2022, 17(1): 227–234.
[5] 贾晓雅, 汪洪桥, 杨亚聃, 等. 基于YOLO框架的无锚框SAR图像舰船目标检测[J]. 系统工程与电子技术, 2022, 44(12): 3703–3709.
JIA Xiaoya , WANG Hongqiao , YANG Yadan , et al. Anchor free SAR image ship target detection method based on the YOLO framework[J]. Systems Engineering and Electronics, 2022, 44(12): 3703–3709.
[6] 谢兆哲, 程永强, 吴昊, 等. 基于Toeplitz矩阵特征值分解的SAR图像舰船目标检测方法[J]. 信号处理, 2023, 39(3): 496–504.
XIE Zhaozhe , CHENG Yongqiang , WU Hao , et al. Ship target detection method in sar imagery based on eigenvalue decomposition of the toeplitz matrix[J]. Journal of Signal Processing, 2023, 39(3): 496–504.
[7] 张学思, 张婷, 刘兆英, 等. 基于轻量型卷积神经网络的海面红外显著性目标检测方法[J]. 山东大学学报(工学版), 2022, 52(2): 41–49.
ZHANG Xuesi , ZHANG Ting , LIU Zhaoying , et al. Infrared salient object detection of sea background based on lightweight CNN[J]. Journal of Shandong University(Engineering Science), 2022, 52(2): 41–49.
