为获取海上移动目标的位置信息，精准掌握其移动轨迹，研究支持向量机的海上移动目标位置跟踪方法。采集海上移动目标的连续帧图像，构建2个样本数据集组成训练集，从训练集中提取海上移动目标图像的边缘特征和局部灰度最大值特征，构建特征向量集训练排序支持向量机，获取学习排序函数，输入海上移动目标的图像帧及原始位置，通过排序支持向量机计算排序函数分值，确定目标位置，并不断重复该过程以实现连续的位置跟踪。实验结果显示，所提方法可以有效提取用于表征海上移动目标的边缘特征以及局部灰度最大值特征，实现移动目标位置的准确跟踪，并生成其位置移动轨迹。
To obtain the position information of moving targets at sea and accurately grasp their movement trajectory, a method for tracking the position of moving targets at sea using support vector machines is studied. Collect continuous frame images of moving targets at sea, construct two sample datasets to form a training set, extract edge features and local grayscale maximum features of moving target images from the training set, construct a feature vector set to train a sorting support vector machine, obtain a learning sorting function, input the image frames and original positions of moving targets at sea, calculate the sorting function score through the sorting support vector machine, determine the target position, and repeat the process continuously to achieve continuous position tracking. The experimental results show that the proposed method can effectively extract edge features and local grayscale maximum features used to characterize moving targets at sea, achieve accurate tracking of the position of the moving target, and generate its position movement trajectory.
2024,46(22): 178-181 收稿日期：2024-3-23
DOI：10.3404/j.issn.1672-7649.2024.22.032
分类号：TP18
作者简介：彭晓雷(1982-),男,硕士,高级实验师,研究方向为光电、电子及智能化
参考文献：
[1] 杨迪, 李振瑜, 郭帅, 等. 天基低轨海上移动目标成像搜索任务调度[J]. 航空学报, 2023, 44(15): 347-366+4.
YANG Di, LI Zhenyu, GUO Shuai, et al. Space-based LEO-observation search planning for maritime moving targets[J]. Acta Aeronautica ET Astronautica Sinica, 2023, 44(15): 347-366+4.
[2] 龙君芳, 马琳娟, 李庆珍. 基于KPCA和结构化支持向量机的视频目标跟踪[J]. 南京理工大学学报, 2023, 47(5): 671-677.
LONG Junfang, MA Linjuan, LI Qingzhen. Video object tracking based on KPCA and structured support vector machine[J]. Journal of Nanjing University of Science and Technology, 2023, 47(5): 671-677.
[3] 赵一鉴, 林利, 王茜蒨, 等. 基于大地距离计算相似度的海上目标轨迹预测[J]. 计算机应用, 2023, 43(11): 3594-3598.
ZHAO Yijian, LIN Li, WANG Qianqian, et al. Trajectory prediction of sea targets based on geodetic distance similarity[J]. Journal of Computer Applications, 2023, 43(11): 3594-3598.
[4] 任文娟, 杨战鹏, 许光銮, 等. 海上动目标身份置信度融合计算模型[J]. 系统工程与电子技术, 2023, 45(4): 1082-1089.
REN Wenjuan, YANG Zhanpeng, XU Guangluan, et al. Fusion calculation model of sea moving target identity confidence[J]. Systems Engineering and Electronics, 2023, 45(4): 1082-1089.
[5] 孙帅, 吕红光, 黄骁. 遮挡环境下基于航海雷达的舰船目标跟踪方法研究[J]. 中国舰船研究, 2024, 19(1): 55-61.
SUN Shuai, LV Hongguang, HUANG Xiao. Ship target tracking for marine radar in occluded environments[J]. Chinese Journal of Ship Research, 2024, 19(1): 55-61.
[6] 初庆栋, 尹羿博, 龚小旋, 等. 基于双偶极向量场的欠驱动无人船目标跟踪制导方法[J]. 中国舰船研究, 2022, 17(4): 32-37.
CHU Qingdong, YIN Yibo, GONG Xiaoxuan, et al. Method for target tracking and guidance of under-actuated unmanned surface vehicle based on two-dimensional dipolar vector field[J]. Chinese Journal of Ship Research, 2022, 17(4): 32-37.
