为了及时发现行驶过程中船舶并及时避开，提出基于视觉传达技术的船舶图像弱小目标跟踪方法。使用视觉传达技术对获取的船舶图像进行去噪处理，采用TDLMS算法通过对去噪后的船舶图像使用模板卷积，检测弱小目标。在此基础上引入模板压缩及空心法进行TDLMS算法改进，提升船舶图像背景预测精度，获取精准船舶图像弱小目标检测结果，并使用直线模型对弱小目标进行跟踪。引入卡尔曼滤波算法对弱小目标的运动轨迹进行预测更新，实现船舶图像弱小目标的实时跟踪。实验结果表明：视觉传达技术的应用可显著提升船舶图像质量，该方法可以有效实现船舶弱小目标不同运行状态下的准确跟踪。
In order to timely detect and avoid ships during their travel, a tracking method for small and weak targets in ship images based on visual communication technology is studied. Using visual communication technology to denoise the obtained ship image, the TDLMS algorithm is used to detect weak and small targets in the ship image by using template convolution on the denoised ship image. Based on this, template compression and hollow method are introduced to improve the TDLMS algorithm, improve the background prediction accuracy of the ship image, obtain accurate detection results of weak and small targets in the ship image, and track weak and small targets using a straight line model, Introducing the Kalman filtering algorithm to predict and update the motion trajectory of small and weak targets, achieving real-time tracking of small and weak targets in ship images. The experimental results show that the application of visual communication technology can significantly improve the quality of ship images, and this method can effectively achieve accurate tracking of small and weak targets in different operating states of ships.
2023,45(21): 205-208 收稿日期：2023-3-27
DOI：10.3404/j.issn.1672-7649.2023.21.040
分类号：TP391
基金项目：广西自治区科学技术委员会基金项目 （2021KY0786）
作者简介：伍玉彬（1987-），男，硕士，副教授，主要研究方向为艺术设计及数字媒体艺术
参考文献：
[1] 林迅, 姚力波, 孙炜玮, 等. 碎云环境下GF-4卫星对运动船舶的目标跟踪[J]. 航天返回与遥感, 2021, 42(5): 127-139.LIN Xun, YAO Libo, SUN Weiwei, et al. A Method for Moving Ship Target Tracking of GF-4 under the Condition of Broken Cloud[J]. Spacecraft Recovery & Remote Sensing, 2021, 42(5): 127-139.
[2] 王俐云, 方峰, 伊成俊, 等. GEO遥感卫星在船舶目标检测跟踪中的应用分析[J]. 航天器工程, 2021, 30(5): 133-139.WANG Liyun, FANG Feng, YI Chengjun, et al. Application Research of GEO Remote Sensing Satellite in Ship Detection and Tracking[J]. Spacecraft Engineering, 2021, 30(5): 133-139.
[3] 刘坤, 于晟焘. 基于卷积神经网络的云雾遮挡船舶目标识别[J]. 控制与决策, 2021, 36(3): 661-668.LIU Kun, YU Sheng-tao. Obscured ship target recognition based on convolutional neural network[J]. Control and Decision, 2021, 36(3): 661-668.
[4] 胡晋山, 付昱凯, 康建荣, 等. 一种改进的小波域均值滤波算法[J]. 测绘科学, 2021, 46(9): 55-60.HU Jinshan, FU Yukai, KANG Jianrong, et al. An improved wavelet domain mean filtering algorithm[J]. Science of Surveying and Mapping, 2021, 46(9): 55-60.
[5] 董凌宇, 单瑞, 刘慧敏, 等. 基于分形纹理特征的侧扫声呐图像沉船识别方法研究[J]. 海洋地质与第四纪地质, 2021, 41(4): 232-239.DONG Lingyu, SHAN Rui, LIU Huimin, et al. Shipwreck identification with side scan sonar image based on fractal texture[J]. Marine Geology & Quaternary Geology, 2021, 41(4): 232-239.
[6] 戴礼灿, 刘欣, 张海瀛, 等. 基于卡尔曼滤波算法展开的飞行目标轨迹预测[J]. 系统工程与电子技术, 2023, 45(6): 1814-1820.DAI Lican, LIU Xin, ZHANG Haiying, et al. Flight target track prediction based on Kalman filter algorithm unfolding[J]. Systems Engineering and Electronics, 2023, 45(6): 1814-1820.
