【作者】 朱明； 刘微； 胡硕；

【Author】 Zhu Ming, Liu Wei, Hu Shuo(Image Processing Laboratory,changchun Institute of Optics Fine Mechanics and Physics,Chinese Academy of Sciences, Jilin Changchun 130033, China)

【机构】 中国科学院长春光学精密机械与物理研究所；

【摘要】 为了在各种机载小型光电平台上加装电视跟踪器,实现对观测目标的自动跟踪与测量,设计了一种高性能小型电视跟踪器(10cm×10cm×2cm),取的了较好的跟踪效果。该型电视跟踪器在硬件结构上采用DSP+FPGA的线性流水阵列结构,以高性能的DSP芯片TMS320C6416为核心处理器,结合现场可编程门阵列FPGA对采集的视频字图像做预处理的实现高性能小型电视跟踪器的设计。同时根据空对地的复杂背景情况,采用基于遗传算法的快速图像相关匹配算法,实现了对各种目标的稳定跟踪。本文介绍了该电视跟踪器的硬件组成、工作原理和所采用图像相关匹配算法。更多还原

【Abstract】 This paper will describe a miniature embed video tracker composed by DSP + FPGA architecture. The architecture has an optimal relation cost/efficiency, modularity, application based dynamic re-programmability that makes possible used in the very small space (10cm×10cm×2cm) .The hardware and software foundations of design the video tracker was expatiated. According to the demands military and civil project, a real high-performance miniature embed video tracker was designed.the hardware of a miniature embed video tracker used height-performance DSP (TMS320C6416) to realize the real-time digital image processing algorithm, in the same time it used field programmable gate array FPGA to preprocess the image. A method of fast image template matching algorithm based on evolutionary algorithm is proposed. Taken advance of virtue of fast searching of EA, the method can achieve high computing efficiency and good matching results.更多还原