| 采用监督特征学习的红外小目标检测 |
| |
| 引用本文： | 许庆晗,金立左,费树岷.采用监督特征学习的红外小目标检测[J].东南大学学报(自然科学版),2011,41(5):1008-1012. |
| |
| 作者姓名： | 许庆晗 金立左 费树岷 |
| |
| 作者单位： | 东南大学自动化学院,南京,210096 |
| |
| 基金项目： | 航空科学基金资助项目(20080169003) |
| |
| 摘 要： | 为了改善大尺寸图像下红外小目标检测的检测率与速度,提出一种采用监督特征学习的检测算法.通过分析小目标邻域图像的分布特点,定义一种基于灰度分布的统计特征,用以描述目标与非目标的邻域的灰度分布差异.以局部灰度极大值区域为训练样本,通过有监督学习提取对目标区分能力最强的特征.随后,在特征空间设计级联结构的多分类器,采用逻辑斯...
|
| 关 键 词： | 小目标检测 灰度分布特征 相关向量机 |
Small infrared target detection via supervised feature learning |
| |
| Xu Qinghan,Jin Lizuo,Fei Shumin.Small infrared target detection via supervised feature learning[J].Journal of Southeast University(Natural Science Edition),2011,41(5):1008-1012. |
| |
| Authors: | Xu Qinghan Jin Lizuo Fei Shumin |
| |
| Institution: | Xu Qinghan Jin Lizuo Fei Shumin(School of Automation,Southeast University,Nanjing 210096,China) |
| |
| Abstract: | A supervised feature learning method is proposed for improving the detection probability and detection speed of small infrared target detection.Through analyzing the traits of small targets' neighborhood image,a statistical feature based on gray intensity distribution is defined for describing the difference between the targets and nontargets' neighborhood.Intensity extrema on global images are considered as training samples,and then a feature with the highest discriminability is extracted by supervised lea... |
| |
| Keywords: | small target detection feature of gray intensity distribution relevance vector machine |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
