基于图像放大影响的多模板相关跟踪算法

目标实时跟踪算法是图像处理技术中的一个非常重要的应用，该算法将提供的原始目标怍为基准图像进行序列跟踪。实时跟踪算法有很多种，大多是基于图像匹配算法的跟踪方法，其中比较常用的为单模板相关跟踪。该文通过对图像放大对相关跟踪影响的分析，计算了单模板相关跟踪的最小图像放大率。针对单模板存在的问题提出了多模板跟踪算法，根据目标莉背景的位置分布提出了五模板相关跟踪，并给出了多模板跟踪算法中的相关结果置信度的计算方法，同时根据最终的相关位置给出了跟踪点的计算方法，仿真试验证明优于单模板跟踪算法。

Object Real-time Tracking Arithmetic in complex background

Object Real -time Tracking Arithmetic is one of the most important methods in graphics transaction area. This arithmetic provides a sequence tracking method to track original object as a standard image. There are various tracking arithmetics. Most of them are based on image matching method. The author analyses the effect of correlation tracking by zooming image and calculates the least rate of image magnifying in single template correlation tracking, On this condition the author provides a new multi - template tracking arithmetic and the way of calculating track- ing point. She delivers a new Five - template correlation method to calculate the correlative result reliability by the position of the object and the background. At the same time an improved algorithm which can calculate the correlative position is provided in this thesis. Emulation proved the multi - template correlation tracking is superior to single template correlation tracking.