摘要
针对复杂背景下的红外弱小目标的特征提取问题,提出了一种实用的红外目标的特征量提取算法。算法依据红外目标的辐射特性与背景之间的相关关系,得到目标的灰度和梯度特征量,通过融合处理,得到加权归一化的融合特征矢量。实验证明,这一融合特征矢量具有良好的稳定性和鲁棒性,同时该特征矢量计算量小,有利于工程实现。
This paper defines four features of a target based on IR radiation characteristics, The fusion feature was presened after the four features were normalized and weighted. Test results are found to be satisfactory. For the good stability and validity of the fusion feature, they can be used to IR point target recognition.
出处
《传感技术学报》
CAS
CSCD
北大核心
2005年第2期289-291,共3页
Chinese Journal of Sensors and Actuators
基金
海军十五预研项目(1010404010401)
关键词
目标特征
融合特征
特征提取
目标识别
character of target
fusion feature
feature extraction
target recognition
