摘 要：在现代战争中，快速而有效的对攻击目标进行识别和跟踪对获取战争主动权起着很重要的作用，而要达到这个目的，就需要从目标图像中准确的分割出目标。在图像分割中，阈值的选取至关重要。最大类间方差法是一种常用而有效的图像分割算法，并已在许多实时场合中采用。为满足高速场合的要求，本文采用Altera公司的Cyclone II 系列的FPGA实现类间方差的计算。实验结果表明，本设计能够实时稳定的对目标分割提取，分割效果良好。
关键词：图像分割；最大类间方差；FPGA
Implementation of image segmentation system
based on Otsu method
WANG Jian-lai YANG Chun-ling
(Electrical Engineering, Harbin Institute of Technology, Harbin, 150001)
Abstract: In the modern war, recognizing and tracking the target rapidly and effectively is of vital importance for acquiring war initiative. For the sake, it is necessary to segment the target from the image accurately. In image segmentation, threshold selection is very important. The Otsu’s method is an effective algorithm for image segmentation, and has been widely employed in various real-time applications. In this paper, an implementation on FPGA of Altera's Cyclone II series for the BCVC (Between Class Variance Computation) of Otsu’s method is presented to meet these high speed requirements. The experimental results indicate that the system can obtain a good performance of image segmentation.
Keywords: Image segmentation; Maximum between class variance; FPGA
