热红外目标的多标度分形识别模型

Thermal Infrared Target Recognition Using Multi-scale Fractal Model

利用机载热红外成像光谱仪(TASI)获取的热红外图像,进行了温度与比辐射率分离,然后采用多标度分形模型进行阈值分割,建立了一种新的热红外影像目标探测方法。实验结果表明,温度的空间分布具有多标度分形特征,即对lgL(r)与lgr进行分段拟合。利用多标度分形模型提取的温度阈值进行城市热红外影像的精细目标识别,并成功提取了建筑物目标。

Using the thermal infrared image acquired by thermal airborne hyperspectral imager（TASI）,temperature and emissivity are separated.And target fine recognition based on temperature image using multi-scale fractal model was studied.Experimental results show that there is a positive correlation between fractal dimension and complexity of temperature spatial heterogeneity.Spatial distribution of temperature has a character of multi-scale fractal.Multi-scale fractal method was used to extract the thresholds,and extract the edge feature of building successfully.This method has an important value on classification,information extraction,and scale effect.