摘要
本文将红外目标提取阈值的计算问题看作系统状态估计问题,提出了一种基于序贯蒙特卡罗方法的红外目标提取算法。在序贯蒙特卡罗方法框架下,建立关于灰度—方差加权信息熵和像素点灰度值的阈值状态空间;建立随机漂移状态转移模型;综合了红外图像中灰度、信息熵、梯度、像素点的空间位置等信息,提出了定量描述红外目标分割效果的评价函数,并以此作为系统的观测模型;最后,将粒子的加权平均做为分割阈值的估计值。实验结果表明,该方法是有效且稳健的。
A novel algorithm on infrared target extraction based on Sequential Monte Carlo Algorithm is proposed in this paper. We analyzed and solved the problem of the infrared target segmentation in the view of state estimation, and computed the threshold value adaptively by optimal estimation of a dynamic system. In the framework of Particle Filter, the threshold state space is established on the Gray-variance Weighted Information Entropy and the gray value of each pixel. The state transition model is chosen as random-drift model. As for the observation probability model, a novel objective function, integrating gray, entropy, gradient and spatial distribution of pixels, is proposed for both the quantitive evaluation of the segmentation and the weight of each particle in the particle set. Finally, the estimation for segmentation threshold is the weighted average of all the particles. The experimental results show the effectiveness of the proposed algorithm.
出处
《微型电脑应用》
2008年第4期55-59,1,共5页
Microcomputer Applications
基金
国家自然科学基金(60675023)
关键词
序贯蒙特卡罗方法
灰度-方差加权信息熵
红外目标分割评价函数
目标提取
Sequential Monte Carlo Method
Gray-variance Weighted Information Entropy
Objective function for infrared target segmentation
Target extraction
