基于细胞免疫的红外图像分割算法及FPGA实现  

Infrared Image Segmentation Algorithm Based on Cellular Immunity and Its FPGA Implementation

作　　者：李大华 王宇 高强 于晓 LI Da-hua;WANG Yu;GAO Qiang;YU Xiao(School of Electrical and Electronic Engineering, Tianjin University of Technology, Tianjin 300384, China;Tianjin Key Laboratory for Control Theory and Application in Complicated Systems, Tianjin 300384, China)

机构地区：[1]天津理工大学电气电子工程学院,天津300384 [2]天津市复杂系统控制理论与应用重点实验室,天津300384

出　　处：《红外》2020年第4期27-35,共9页Infrared

基　　金：国家自然科学基金(61502340);天津市自然科学基金(18JCQNJC01000);天津市教委科研计划项目(2018KJ133);天津市复杂系统控制理论及应用重点实验室开放基金(TJKL-CTACS-201907)。

摘　　要：在工业生产中,高温蒸汽管道通常用于输送高温蒸汽和高温工业废水等。但为了安全起见,管道通常被放置在环境比较复杂的地方,这不利于工人对管道进行检测与维护。如何快速地定位复杂背景下蒸汽管道的位置并对周围环境进行区分成了一个亟待解决的问题。由于最大类间方差(Otsu)算法不能满足上述要求,基于细胞免疫机制提出了一种改进的Otsu算法。根据红外图像中管道以及复杂背景的特征,该算法计算出两个不同的阈值,并将它们分别用于管道的提取与复杂背景的区分。借助QuartusⅡ软件搭建了基于现场可编程逻辑门阵别(Field Programmable Gate Array,FPGA)的软硬件系统,实现了数据通信传输,并对改进的Otsu算法进行了验证。实验结果表明,该算法在应用于管道红外图像时可以取得较好的效果。与几种边缘检测算子和经典Otsu算法相比,本文算法无论是用于管道的提取,还是用于复杂背景的区分,都具有较高的真阳性率(True Positive Rate,TPR)和较低的假阳性率(False Positive Rate,FPR)。In the industrial production,high temperature steam pipelines are usually used to transport high temperature steam and high temperature industrial waste water,etc.But the pipelines are often placed in complex environments for safety,which is not conducive to the inspection and maintenance of pipelines for the workers.How to quickly locate the location of the steam pipeline in the complex background and distinguish the surrounding environment has become an urgent problem to be solved.Because the Otsu algorithm cannot meet the requirements mentioned above,an improved Otsu algorithm is proposed based on the cellular immunity mechanism.According to the characteristics of the pipelines and the complex background in the infrared images,the algorithm calculates two different thresholds which can be used to extract the pipelines and distinguish the complex background.With the help of the QuartusⅡsoftware,a hardware and software system based on FPGA has been built to realize the data communication and transmission,and the improved Otsu algorithm has been verified.The experimental results show that the algorithm can be applied to the infrared images of the pipelines to obtain better effect.Compared with several edge detection operators and the classical Otsu algorithm,the improved algorithm has a higher true positive rate(TPR)and a lower false positive rate(FPR),both for the pipelines extraction and the complex background distinction.

关 键 词：红外图像 现场可编程逻辑门阵列 细胞免疫 阈值分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]