卜瑞波,徐海祥,冯辉,余文曌.一种面向船舶智能航行的海上目标实时跟踪算法[J].,2020,60(1):30-35 |
一种面向船舶智能航行的海上目标实时跟踪算法 |
A real-time tracking algorithm of marine target for ship intelligent navigation |
|
DOI:10.7511/dllgxb202001005 |
中文关键词:智能船舶目标跟踪相关滤波高斯混合模型因式分解卷积 |
英文关键词:intelligent shiptarget trackingcorrelation filteringGaussian mixture modelfactorization convolution |
基金项目:国家自然科学基金资助项目(51879210);中央高校基本科研业务费专项资金资助项目(2019III0402019III132CG). |
|
摘要点击次数:420 |
全文下载次数:593 |
中文摘要: |
海上目标感知的准确性和实时性是实现船舶智能航行的前提和基础.为了满足以上要求,将有效卷积算子(ECO)引入海上船舶目标跟踪中.该算法以相关滤波为基础,响应最大值之处为目标船舶中心所在位置.获得中心位置之后,采用尺度滤波方法估计出船舶目标的最佳尺度,从而完成对目标当前帧的跟踪.利用因式分解卷积的方式分解卷积,降低数据维度,减少计算时间;采用高斯混合模型将样本分成不同类别,降低训练集样本冗余度;采用稀疏更新策略更新样本模型,防止过拟合问题.选取海洋环境下船舶不同运动场景作为实验样本,与几种常用跟踪算法对比,验证了ECO算法在海上船舶目标跟踪上的准确性和实时性. |
英文摘要: |
The accuracy and real-time performance of marine target perception are the premise and foundation of ship intelligent navigation. In order to meet the above requirements, the effective convolution operator (ECO) is introduced into the tracking of ship targets at sea. The algorithm is based on correlation filtering, and the maximum response value is the position of the center of the target ship. After obtaining the center position, the scale filtering method is used to estimate the optimal scale of the ship target, so as to complete the tracking of the current frame of the target. The convolution is decomposed by factorization convolution to reduce the data dimension and the calculation time, and the Gaussian mixture model is used to divide the samples into different categories to reduce the redundancy of the training set. The sparse update strategy is used to update the sample model to prevent the over-fitting problem. By selecting different ship motion scenes in marine environment as experimental samples and comparing with several commonly used tracking algorithms, the accuracy and real-time performance of ECO algorithm in marine ship target tracking are verified. |
查看全文查看/发表评论下载PDF阅读器 |
| --> 关闭 |