基于加权场景先验的海上红外弱小目标检测
投稿时间:2019-03-11  修订日期:2019-03-11  点此下载全文
引用本文:
摘要点击次数: 55
全文下载次数: 0
作者单位E-mail
潘胜达 上海海事大学 sdpan@shmtu.edu.cn 
张 素 上海海事大学 1207904890@qq.com 
赵明 上海海事大学  
安博文 上海海事大学  
基金项目:国家自然科学基金(Nos. 61302132,61504078,41701523);
中文摘要:为了提高海上红外弱小目标检测的检测精度和实时性,提出了一种基于加权场景先验的红外弱小目标检测方法。该方法首先利用目标的稀疏特性以及海面场景的非局部自相关特性,将目标和背景的分离问题转化为恢复低秩和稀疏矩阵的鲁棒主成分分析(Robust Principal Component Analysis,RPCA)问题。之后,将海面背景的先验特征信息通过加权核范数的方式加入模型,加快算法中目标和背景图像块矩阵的分解速度。最后,通过引入交替方向乘子法(ADMM)算法进一步加速求解的迭代速度。实验结果表明:该算法能有效地提高目标检测准确率,算法实时性较原算法提高了120%。
中文关键词:图像处理  弱小目标检测  加权场景先验  加权核范数  交替方向乘子法
 
Infrared small target detection based onweighted scene prior
Abstract:To further improve the detection accuracy and real-time performance of infrared small target detection at sea, a new method based on weighted scene priors is introduced. Firstly, using the sparse characteristics of the target and the non-local self-correlation characteristics of the sea background, the target-background separation problem is modeled as a robust low-rank matrix recovery problem. Moreover, the prior information of sea background is added into the model by weighted nuclear norm to accelerate the decomposition of target and background images matrix in the algorithm. Finally, the alternating direction method of multipliers (ADMM) is introduced to further accelerate the iteration speed of the solution. The experimental results show that the proposed algorithm can effectively improve the accuracy of target detection. The real-time performance of the algorithm is improved by 120% compared with the original algorithm.
keywords:image  processing,dim  and small  target detection,weighted  scene prior,ADMM
  查看/发表评论  下载PDF阅读器

版权所有:《红外与毫米波学报》编辑部