基于最大類間方差法的圖像分割系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)

摘 要：在現(xiàn)代戰(zhàn)爭(zhēng)中，快速而有效的對(duì)攻擊目標(biāo)進(jìn)行識(shí)別和跟蹤對(duì)獲取戰(zhàn)爭(zhēng)主動(dòng)權(quán)起著很重要的作用，而要達(dá)到這個(gè)目的，就需要從目標(biāo)圖像中準(zhǔn)確的分割出目標(biāo)。在圖像分割中，閾值的選取至關(guān)重要。最大類間方差法是一種常用而有效的圖像分割算法，并已在許多實(shí)時(shí)場(chǎng)合中采用。為滿足高速場(chǎng)合的要求，本文采用Altera公司的Cyclone II 系列的FPGA實(shí)現(xiàn)類間方差的計(jì)算。實(shí)驗(yàn)結(jié)果表明，本設(shè)計(jì)能夠?qū)崟r(shí)穩(wěn)定的對(duì)目標(biāo)分割提取，分割效果良好。

關(guān)鍵詞：圖像分割；最大類間方差；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

基于最大類間方差法的圖像分割系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)-哈爾濱工業(yè)大學(xué)-王暕來(lái).pdf