基于DSP和FPGA的多目标跟踪系统
首发时间:2008-11-14
摘要:为了解决空中多目标跟踪中数据存储量、运算量大与实时处理之间的矛盾,本文先采用适合硬件移植的自适应分割算法和自适应中小目标判决算法将图像处理成二值图像,然后提出了数据访问次数少,运算量小的改进的轮廓跟踪算法对二值图像进行轮廓跟踪,标记出所有目标,最后进行OSD显示。算法在DM643和Xilinx XC2S300E平台上实现,实验结果表明在40ms内可以完成720×576视场中的多达3个目标的跟踪、显示。
For information in English, please click here
Multi-target tracking on DSP&FPGA
Abstract:In order to resolve the conflict between excessive data storage, time expensive computation and real-time image processing in aerial multi-target tracing, we adopt the auto-adaptive division algorithm and auto-adaptive small target determine method to process the image into a 0-1 image. Then a method is proposed based on edge tracing to mark all the targets. Finally do the OSD task. The algorithm is implemented on the platform of DM643+Xilinx XC2S300E. Experimental results show that up to 3 targets in 720×576 image can be processed and displayed within 40ms.
Keywords: DSP FPGA edge-tracing multi-target tracing
基金:
论文图表:
引用
No.2569135424112266****
同行评议
共计0人参与
勘误表
基于DSP和FPGA的多目标跟踪系统
评论
全部评论0/1000