论文部分内容阅读
红外检测技术具有远距离、不接触、不取样、不解体、准确、快速、直观等特点,广泛用于电力设备过热缺陷监测和诊断,对提高电力系统的稳定性具有重要意义。FAs TMatch(fast affine template matching)算法是一种基于灰度值的快速模板匹配算法,可在一幅图像中找到一个近似全局最优目标。文中综合利用可见光和红外图像,提出一种多目标定位方法。首先,通过改进的FAsT-Match算法在电力设备可见光图像中实现多目标定位;其次,利用红外图像和可见光图像之间存在近似仿射变换,求出目标在红外图像中的位置。实验结果表明文中方法的有效性。
Infrared detection technology with long-distance, non-contact, not sampling, non-disintegration, accurate, rapid and intuitive features, widely used in power equipment overheating defects monitoring and diagnosis, to improve the stability of the power system is of great significance. FAs TMatch (fast affine template matching) algorithm is a fast template matching algorithm based on gray value, which can find an approximate global optimal target in an image. In this paper, the comprehensive use of visible and infrared images, a multi-target positioning method. Firstly, multi-target localization is implemented in the visible light image of the power equipment through the improved FAsT-Match algorithm. Secondly, the approximate location of the target in the infrared image is obtained by using the approximate affine transformation between the infrared image and the visible light image. The experimental results show the effectiveness of the proposed method.