光学学报, 2015, 35 (7): 0715004, 网络出版: 2015-06-26   

基于空间距离改进的视觉显著性弱小目标检测 下载: 546次

Small Target Detection Based on Visual Saliency Improved by Spatial Distance
作者单位
国防科学技术大学电子科学与工程学院, 湖南 长沙 410073
摘要
在人类视觉系统(HVS)中,占据重要部分的是对比度值而不是亮度。现有的基于HVS的红外弱小目标检测算法可以有效提高目标信噪比和检测率,但也存在虚警率较高、易受噪声影响等问题。针对这些问题,提出一种基于空间距离改进的视觉显著性红外弱小目标检测算法。用目标所在像素块均值与其周围像素块加权和的比值来加权目标点灰度,得到一幅显著图。在计算周围像素的灰度加权和时,将视觉注意机制中关键因素之一的空间关系考虑进去,根据空间距离加权计算,较远的地方分配较小的权值。实验表明,本文算法不仅可以降低虚警率,而且抗噪能力也比较强。
Abstract
In human visual system (HVS), is the contrast value occupies the most important part rather than the brightness. The existing infrared small target detection algorithm based on HVS can get a higher signal to noise ratio and detection rate, but it also has shortcomings of higher false alarm rate and easily effected by noise. Considering those shortcomings, An infrared small target detection algorithm based on visual saliency improved by spatial distance is proposed. The gray value of target is weighted by the ratio of the target pixel block and its surrounding blocks, and a saliency map is got. Spatial distance is one of the most important factors in visual attention mechanism and is used in the calculation of the weighted sum of the surrounding blocks. Smaller weight value is distributed to fruther distance according to the weighted space distance. Experimental results show that the proposed algorithm can not only get a lower false alarm rate, but also has robustness for noise.

杨林娜, 安玮, 林再平, 李安冬. 基于空间距离改进的视觉显著性弱小目标检测[J]. 光学学报, 2015, 35(7): 0715004. Yang Linna, An Wei, Lin Zaiping, Li Andong. Small Target Detection Based on Visual Saliency Improved by Spatial Distance[J]. Acta Optica Sinica, 2015, 35(7): 0715004.

本文已被 13 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!