为及时发现和跟踪小型渔船、救生艇等弱小目标，提高海上救援和应急响应的效率和准确性，研究基于视觉传达技术的船舶图像中弱小目标检测方法。通过中值滤波算法去除船舶图像中的噪声，改善船舶图像质量，将去噪后的船舶图像应用于基于门限直方图均衡的船舶图像增强方法中，在该方法处理下，增强船舶图像对比度；之后利用视觉传达技术，对船舶图像中的弱小目标亮度进行调整，并根据亮度调整结果分割目标边缘，从而实现弱小目标检测。经实验验证，该方法可在保证图像边缘清晰的情况下实现图像去噪与增强，提高了船舶图像质量，同时该方法具有较高的背景抑制因子与信杂比率增益，在检测过程中可有效分割弱小目标与背景，实现良好的弱小目标检测。
To timely detect and track small and weak targets such as small fishing boats and lifeboats, and improve the efficiency and accuracy of maritime rescue and emergency response, a method for detecting small and weak targets in ship images based on visual communication technology is studied. By using median filtering algorithm to remove noise from ship images and improve the quality of ship images, the denoised ship images are applied to a ship image enhancement method based on threshold histogram equalization. Under this method, the contrast of ship images is enhanced. Afterwards, visual communication technology is used to adjust the brightness of small and weak targets in ship images, and based on the brightness adjustment results, target edges are segmented to achieve detection of small and weak targets. Through experimental verification, this method can achieve image denoising and enhancement while ensuring clear image edges, improving the quality of ship images. At the same time, this method has a high background suppression factor and signal-to-noise ratio gain, and can effectively segment weak targets and backgrounds during the detection process, achieving good detection of weak targets.
2023,45(22): 198-201 收稿日期：2023-8-28
DOI：10.3404/j.issn.1672-7649.2023.22.038
分类号：TP391
作者简介：谢凌云(1990-),女,硕士,讲师,研究方向为视觉传达设计及图像处理
参考文献：
[1] 崔宗勇, 王晓雅, 施君南, 等. 基于中心点回归的大场景SAR图像船舶检测方法[J]. 电波科学学报, 2022, 37(1): 153-161.
CUI Zong-yong, WANG Xiao-ya, SHI Jun-nan, et al. Ship detection in large scene SAR images based on target center point regression[J]. Chinese Journal of Radio Science, 2022, 37(1): 153-161.
[2] 马啸, 邵利民, 金鑫, 等. 基于改进Mask R-CNN的可见光图像中船舶目标检测方法[J]. 北京理工大学学报, 2021, 41(7): 734-744.
MA Xiao, SHAO Li-min, JIN Xin, et al. Ship target detection in optical images based on improved mask R-CNN[J]. Transactions of Beijing Institute of Technology, 2021, 41(7): 734-744.
[3] 谢兆哲, 程永强, 吴昊, 等. 基于Toeplitz矩阵特征值分解的SAR图像船舶目标检测方法[J]. 信号处理, 2023, 39(3): 496-504.
XIE Zhao-zhe, CHENG Yong-qiang, 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.
