基于DSP+FPGA框架的实时目标跟踪系统设计

高文; 朱明; 刘剑; 汤洋

doi:null

您当前的位置：

首页 >

文章列表页 >

基于DSP+FPGA框架的实时目标跟踪系统设计

成像技术与图像处理 | 更新时间：2020-08-12

- 基于DSP+FPGA框架的实时目标跟踪系统设计
- Desigen of real-time target tracking system based on DSP+FPGA
- 液晶与显示 2014年29卷第4期页码：611-616
- 作者机构：
  
  中国科学院长春光学精密机械与物理研究所, 吉林长春 130033
- 作者简介：
- 基金信息：
  
  中国科学院航空光学成像与测量重点实验室开放基金（No.Y2HC1SR121）()
- DOI：
  中图分类号： TP394.1;TH691.9
- 收稿日期：2014-02-15，
  
  修回日期：2014-04-22，
  
  纸质出版日期：2014-08-05
- 稿件说明：
移动端阅览
高文, 朱明, 刘剑, 汤洋. 基于DSP+FPGA框架的实时目标跟踪系统设计[J]. 液晶与显示, 2014,29(4): 611-616

GAO Wen, ZHU Ming, LIU Jian, TANG Yang. Desigen of real-time target tracking system based on DSP+FPGA[J]. , 2014,29(4): 611-616
高文, 朱明, 刘剑, 汤洋. 基于DSP+FPGA框架的实时目标跟踪系统设计[J]. 液晶与显示, 2014,29(4): 611-616 DOI：

GAO Wen, ZHU Ming, LIU Jian, TANG Yang. Desigen of real-time target tracking system based on DSP+FPGA[J]. , 2014,29(4): 611-616 DOI：

摘要

随着我国武器研制水平的不断提高，高速度、高机动能力的武器装备越来越多，为了使型号武器中的目标跟踪器对于目标大尺度变化、速度快等情况有很好的鲁棒性，本文设计了一款基于DSP+FPGA的实时目标跟踪系统。针对均值漂移算法不适用于快速运动目标等限制情况使用多级金字塔进行了改进，采用背景加权的核直方图建立目标模板从而减小跟踪框中背景对于跟踪的影响，并将整个算法进行了优化以在嵌入式系统上实时实现。实验结果表明，本文设计的实时目标跟踪系统对于目标的快速运动、尺度变化以及一定程度的模糊均有很好的跟踪结果。每帧的平均处理时间为13.5 ms，满足实际工程的实时性和稳定性要求。

Abstract

Along with the weapon research development

more and more weaponry with high speed and high mobility are equipped in our country. In order to make target tracker of the weapons have good robustness under the situation of the target scale changed and high speed

a real-time target tracking system based on DSP+FPGA was designed. The MeanShift Algorithm was improved by using multi-level pyramid and the background weighted kernel histogram

which can reduce the influence of background in the tracking box

then the whole algorithm was optimized to implement on the embedded system in real time. The experimental results show that the design of the real-time target tracking system is robust for the rapid motion of the target

scale changing

and some degree of fuzzy. The average processing time per frame was 13.5 ms

which can meet the engineering requirements of real-time and stability.

关键词

Keywords

references

贺柏根,刘剑,马天玮. 基于DSP+FPGA的实时图像去雾增强系统设计[J]. 液晶与显示,2013,28(6):968-972. He B G, Liu J, Ma T W. Real-time image defogging and enhanced system designed based on DSP+FPGA [J]. Chinese Journal of Liquid Crystals and Displays, 2013, 28(6):968-972.(in Chinese)[2] 朱秋平,颜佳,张虎,等.基于压缩感知的多特征实时跟踪[J]. 光学精密工程,2013,21(2):437-444. Zhu Q P, Yan J, Zhang H, et al. Real-time tracking using multiple features based on compressive sensing [J].Optics and Precision Engineering,2013,21(2):437-444.(in Chinese)[3] 龚俊亮,何昕,魏仲慧,等. 采用改进辅助粒子滤波的红外多目标跟踪[J]. 光学精密工程,2012,20(2):413- 421. Gong JL,He X,Wei Z H,et al. Multiple infrared target tracking using improved auxiliary particle filter[J]. Opt. Precision Eng.,2012,20(2):413-421. (in Chinese)[4] 张云峰. 基于DSP的实时图像拼接技术[J]. 液晶与显示,2013,28(6):963-967. Zhang Y F. Realtime image mosaic technology based on DSP[J].Chinese Journal of Liquid Crystals and Displays,2013,28(6): 963- 967.(in Chinese)[5] 苏可心,韩广良,孙海江.基于SURF的抗视角变换图像匹配算法[J]. 液晶与显示,2013,28(4):626-632. Su K X, Han G L, Sun H J. Anti-viewpoint changing image matching algorithm based on SURF [J]. Chinese Journal of Liquid Crystals and Displays, 2013, 28(4):.626-632.(in Chinese)[6] Roweis S. EM algorithms for PCA and SPCA [M]//Advances in Neural Information Processing Systems,MIT Press,1997: 626-632.[7] 孙晓燕,常发亮. 梯度特征稀疏表示目标跟踪[J]. 光学精密工程,2013,21(12):3191-3197. Sun X Y, Chang F L. Object tracking based on sparse representation of gradient feature [J]. Opt.Precision Eng., 2013,21(12):3191-3197.(in Chinese)[8] 王丽佳,贾松敏,王爽,等. 采用改进Mean Shift算法的移动机器人行人跟踪[J]. 光学精密工程,2013,21(9):2364-2370. Wang L J, Jia S M, Wang S, et al. Person tracking of a mobile robot using improved Mean Shift [J]. Opt. Precision Eng., 2013,21(9):2364-2370. (in Chinese)[9] 匡金骏,柴毅,熊庆宇.结合标准对冲与核函数稀疏分类的目标跟踪[J]. 光学精密工程, 2012, 20(11): 2540- 2547. Kuang J J, Chai Y, Xiong Q Y. Visual object tracking combined normal hedge and kernel sparse representation classification[J].Opt. Precision Eng., 2012, 20(11): 2540- 2547.(in Chinese)[10] Comaniciu D, Ramesh V, Meer P. Kernel-based object tracking[J]. IEEE Transaction on pattern analysis and machine intelligence, 2003,25(5):564-577.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

高分辨率多传感器融合图像跟踪系统的设计与实现

高速弹丸位置坐标自动测量系统设计

基于CPCI总线的FPGA+DSP架构通用视频图像处理系统的设计

基于DSP+FPGA平台的复杂背景目标检测与跟踪

基于DSP+FPGA的实时图像去雾增强系统设计