Implementation and analysis of template matching for image registration on DevKit-8500D

详细信息    查看全文

• 作者：Kartikey Thakar ; Divyang Kapadia ; Fenil Natali ; Jignesh Sarvaiya ; ^{jns@eced.svnit.ac.in}
• 关键词：Image registration ; OpenCV ; DevKit-8500D ; Template matching
• 刊名：Optik - International Journal for Light and Electron Optics
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：130
• 期：Complete
• 页码：935-944
• 全文大小：2880 K
• 卷排序：130

文摘

Image registration is a fundamental task in image processing used to match two different images of same object acquired under different situations and at different times. Implementation of image registration can be intensity value based or feature based. Implementing intensity based image registration technique with reduced time delay on embedded platform DevKit-8500D is presented in this paper. DevKit-8500D is used due to its compatibility for higher programming language such as C/C++ and hardware availability of on-board DSP making it adequate for image and video processing. Template matching on resized images by computation of cross-correlation is used for registration purpose to reduce the computational delay of whole process. A comparison between normal and resized images is also presented to show errors produced in results due to resizing operation and to emphasize on reduced amount of time-delay.