Fasting compressive sensing algorithm with context based on image sensor

MAO Zheng-chong; TANG Yu-yu; HAN Yi

doi:10.13873/J.1000-9787(2016)10-0131-04

Chinese

您当前的位置：

首页 >

文章列表页 >

Fasting compressive sensing algorithm with context based on image sensor

更新时间：2025-09-11

- Fasting compressive sensing algorithm with context based on image sensor
- Vol. 35, Issue 10, Pages: 131-134(2016)
- 作者机构：
  
  江南大学轻工过程先进控制教育部重点实验室
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2016)10-0131-04
  CLC： TP391.41
- Published：2016
- 稿件说明：
移动端阅览
[1]茅正冲,唐雨玉,韩毅.基于图像传感器的上下文快速压缩感知算法[J].传感器与微系统,2016,35(10):131-134.

MAO Zheng-chong, TANG Yu-yu, HAN Yi. Fasting compressive sensing algorithm with context based on image sensor[J]. 2016, 35(10): 131-134.
[1]茅正冲,唐雨玉,韩毅.基于图像传感器的上下文快速压缩感知算法[J].传感器与微系统,2016,35(10):131-134. DOI： 10.13873/J.1000-9787(2016)10-0131-04.

MAO Zheng-chong, TANG Yu-yu, HAN Yi. Fasting compressive sensing algorithm with context based on image sensor[J]. 2016, 35(10): 131-134. DOI： 10.13873/J.1000-9787(2016)10-0131-04.

摘要

针对快速压缩感知算法在目标被遮挡、光照变化较大时存在跟踪不稳定的问题

提出了基于图像传感器的上下文快速压缩感知跟踪（FCT）算法。新算法首先在Haar-like特征中引入时空上下文特征

通过目标周围的空间信息和时间上的递推关系协助估计目标的位置。通过改进的随机测量矩阵同时提取目标的纹理特征和灰度特征

加强了特征的稳定性

提高跟踪的准确性。通过方差分类器预判定候选样本

减少判定的次数

并减少错误的候选样本。改进的FCT算法对光照、旋转、尺度缩放都有良好的不变性

且不易发生跟踪漂移。实验证明:改进的FCT算法优于压缩感知跟踪（CT）算法和FCT算法。

Abstract

Aiming at problems that fast compressive tracking（ FCT）

algorithm has poor robustness in target occlusion and illumination changes

propose a FCT algorithm with context based on image sensors. First

the new algorithm introduces temporal and spatial context features in the Haar-like feature

and assists to estimate target position by spatial information around target and time recurrence relation. By improved random measurement matrix

extract simultaneously texture features and gray features of target

stability of feature is enhanced

accuracy of target tracking is improved. Pre-judge candidate sample by variance classifier

reduce number of decision

reduce number of wrong candidate samples. The improved FCT algorithm has good invariance for illumination

rotation and scale changes

tracking drift also not easy to happen. It can be proved that the improved FCT algorithm is superior to CT and FCT algorithms.

关键词

Keywords

references

视觉跟踪算法综述 [J]. 杨戈,刘宏. 智能系统学报 . 2010(02)

Discriminative subspace learning with sparse representation view-based model for robust visual tracking [J] . Yuan Xie,Wensheng Zhang,Yanyun Qu,Yinghua Zhang. Pattern Recognition . 2014 (3)

Collaborative object tracking model with local sparse representation [J] . Chengjun Xie,Jieqing Tan,Peng Chen,Jie Zhang,Lei He. Journal of Visual Communication and Image Representation . 2014 (2)

Object tracking [J] . Alper Yilmaz,Omar Javed,Mubarak Shah. ACM Computing Surveys （CSUR） . 2006 (4)

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Compressible data gathering scheme for reliability and energy consumption optimization

A multi-scale insulator tracking algorithm based on compressive sensing

Mobile data collection scheme based on compressive sensing in UWSNs

Clustering data gathering algorithm for wireless sensor networks based on compressive sensing

Virtual dark chamber test method based on CS

Related Author

LI Peng

WANG Jian-xin

AN Ning

YAN Bin

XIONG Jie

LI Peng

WANG Jian-xin

WANG Chong

Related Institution

School of Information Science and Engineering,Central South University

School of Automation Engineering,University of Electronic Science and Technology of China

School of Information System Engineering,Information Engineering University

School of Electronic Engineering,Naval University of Engineering

Tianjin Key Laboratory for Control Theory & Application in Complicated System

⁰