摘要
针对传统相关跟踪算法中存在的一些问题,在分析多种模板更新算法的基础上,提出一种基于直方图信息的模板更新策略。同时给出一种简单实用的轨迹预测方法来解决遮挡问题。为了解决算法复杂性及满足工程实时性,设计了以高性能的DSP芯片TMS320C6416为核心处理器,结合大规模可编程逻辑器件CPLD进行逻辑控制以及现场可编程门阵列FPGA对采集的视频数字图像做预处理的实时目标识别跟踪处理平台。实验结果证明该系统快速、稳定、鲁棒性强。
In the view of problems of conventional target tracking algorithms, a novel template image updating strategy based on information of gray histogram is presented. In addition, a simple and efficient track prediction method is proposed. The real-time target track processing system is designed which is constructed by the high performance DSP chipset TMS320C6416 as the core digital processor, the huge reprogrammable logic chipset CPLD as the system logic control and the field reprogrammable array FPGA as the image preprocessing chipset to sampled video digital image. The experimental results show that the system is efficient, effective, and robust.
出处
《电子器件》
EI
CAS
2006年第2期416-419,共4页
Chinese Journal of Electron Devices
基金
中科院长春光学精密机械与物理研究所二期创新基金资助(C05702z)