摘要
提出了一种基于可见光成像序列的海上运动目标的快速检测方法。该方法先在静态图像中分割出感兴趣区域,继而仅在感兴趣区域中应用变形的时间差分法来检测运动目标。在感兴趣区域分割阶段,引入视觉注意力机制,通过构造金字塔结构以及迭代的小尺寸倒三角低通模板运算成功地滤除了海面波浪噪声。在此基础上,检测并分析外边缘,在单帧图像中快速实现了感兴趣区域的分割。大量实验表明,该方法具有实时性好、鲁棒性强等特点。
This paper introduces a novel method of detecting the moving maritime objects in video sequences.Those regions of interest are quickly segmented first and then a modified temporal differencing method is applied to detecting the moving objects. On the process of image segmentation,visual attention architecture is imported,the maritime noises are filtered successfully by building pyramid structure and making low-pass inversed triangular filter of small mask iteratively.Then those regions of interest are segmented successfully and quickly via boundary detection and analysis.Many experimental results show that the proposed real-time system produces satisfying results in various maritime video sequences.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第14期213-216,共4页
Computer Engineering and Applications
基金
国家自然科学基金(No.60175008)
国家创新研究群体资助项目(No.60024301)
厦门大学985二期信息创新平台项目资助~~
关键词
金字塔结构
滤噪
图像分割
运动目标检测
时间差分
pyramid structure
noise removal
image segmentation
moving objects detection
temporal differencing
