摘要
为了自动确定遥感图像分割的最佳阈值,本文提出了一种改进的自适应遗传算法,并利用该算法对二维Otsu图像阈值分割函数进行了全局优化,提高了分割阈值的求解速度。该算法能够根据个体适应度大小和群体的分散程度自动调整遗传控制参数,从而能够在保持群体多样性的同时加快收敛速度,克服基本遗传算法的收敛性差、易早熟问题。实验结果表明,该算法具有良好的收敛速度和稳定性,达到较好的图像分割效果,大大缩短了计算时间。
In order to automatically determine the best remote sensing image segmentation threshold,this paper presents an im- proved adaptive genetic algorithm,and uses the method of two-dimensional image segmentation Otsu evaluation function which is a global optimization and can raise the speed of the threshold value of the division.The improved A GA can preserve the multifamily of population and the astringency of the algorithm and can overcome the problems of poor astringency and premature occurrence in Simple Ge...
出处
《测绘科学》
CSCD
北大核心
2008年第S1期247-248,267,共3页
Science of Surveying and Mapping
关键词
遥感图像
自适应遗传算法
图像分割
阈值
OTSU法
remote sensing image
Adaptive Genetic Algorithm（AGA）
image segmentation
threshold
OTSU method
