Bayesian sensor image fusion using local linear generative models
Bayesian sensor image fusion using local linear generative models
复制标题
DOI：
10.1117/1.1384886
复制
发表时间：
2001-07
影响因子：
1.3
通讯作者：
Ravi K. Sharma;T. Leen;M. Pavel
中科院分区：
文献类型：
--
作者：
Ravi K. Sharma;T. Leen;M. Pavel
提出了一种基于概率的多传感器图像融合方法。该方法基于图像形成模型，其中传感器图像是潜在真实场景（潜在变量）的有噪声的局部线性函数。然后，贝叶斯框架提供了传感器图像中真实场景的最大似然或最大后验估计。图像形成模型参数的最小二乘估计涉及（局部）二阶图像统计，并且与局部主成分分析有关。我们证明了该方法在可见光波段和红外传感器图像上的有效性。©2001美国光电仪器工程师学会。(DOI: 10.1117/1.1384886)
We present a probabilistic method for fusion of images pro- duced by multiple sensors. The approach is based on an image forma- tion model in which the sensor images are noisy, locally linear functions of an underlying true scene (latent variable). A Bayesian framework then provides for maximum-likelihood or maximum a posteriori estimates of the true scene from the sensor images. Least-squares estimates of the parameters of the image formation model involve (local) second-order image statistics, and are related to local principal-component analysis. We demonstrate the efficacy of the method on images from visible-band and infrared sensors. © 2001 Society of Photo-Optical Instrumentation Engineers. (DOI: 10.1117/1.1384886)