摘要
基于特征的图像匹配算法在图像处理系统中有重要的应用。文中以TMS320DM648型号的数字信号处理器(DSP)为核心,组建红外图像匹配系统。系统首先预处理红外图像,然后采用Sobel算法提取图像边缘,接着提取图像共生矩阵作为特征向量,最后找出匹配图片。试验表明,此系统在精度和速度方面都满足要求,是一套切实可行的方案。
The image matching algorithm based on the feature has an important application in the image processing system.In the paper,an infrared image matching system is set up and the digital signal processor（DSP）of TMS320DM648 model is used as the system core.Firstly,the system preprocesses the infrared image,then the Sobel algorithm is used to extract the image edge,calculates the image cooccurrence matrix as a feature vector.Finally,the matching pictures are obtained.The experiment results show that this system satisfies the requirements of precision and speed,and it is a feasible method.
作者
赵飞
潘丽杰
朱琪
Zhao Fei;Pan Lijie;Zhu Qi(Department of Advanced Manufacturing Technology,Yangtze Delta Region Institute of Tsinghua University Zhejiang,Jiaxing 314000,China)
出处
《单片机与嵌入式系统应用》
2018年第9期21-23,共3页
Microcontrollers & Embedded Systems
基金
集成自主探测器的分析型工业热像仪开发和应用(2013YQ470767)
