An improved anti-occlusion automobile and pedestrian stability tracking method

ZHANG Chuanwei; LI Bo; YANG Mengyue; ZENG Hongjun; WANG Rui

doi:10.13873/J.1000-9787(2020)10-0042-03

Chinese

您当前的位置：

首页 >

文章列表页 >

An improved anti-occlusion automobile and pedestrian stability tracking method

更新时间：2025-09-11

- An improved anti-occlusion automobile and pedestrian stability tracking method
- Issue 10, Pages: 42-44(2020)
- 作者机构：
  
  西安科技大学机械工程学院
- 作者简介：
- 基金信息：
- DOI：10.13873/J.1000-9787(2020)10-0042-03
  CLC： TN713;TP391.41
- Published：2020
- 稿件说明：
移动端阅览
ZHANG Chuanwei, LI Bo, YANG Mengyue, et al. An improved anti-occlusion automobile and pedestrian stability tracking method[J]. 2020, (10): 42-44.
DOI：

ZHANG Chuanwei, LI Bo, YANG Mengyue, et al. An improved anti-occlusion automobile and pedestrian stability tracking method[J]. 2020, (10): 42-44. DOI： 10.13873/J.1000-9787(2020)10-0042-03.

摘要

针对行人被遮挡、汽车与行人相对速度较大使得汽车行人跟踪算法无法继续跟踪的问题

设计实现了一种改进的抗遮挡汽车行人稳定跟踪方法。即在核相关滤波器(KCF)跟踪算法的基础上引入方向梯度直方图(HOG)和尺度不变特征变换(SIFT)特征。当视频帧中的目标行人没有出现或部分出现时

提取当前帧的SIFT特征与HOG特征

采用主成分分析(PCA)降维技术进行多特征降维

通过串行组合的方式来构造HOG和SIFT融合特征集

生成HOG-SIFT特征模板。利用形成的特征模板与下一帧中的HOGSIFT特征进行匹配

对行人进行快速重新定位跟踪。视频序列对比实验结果表明:改进算法较跟踪—学习—检测(TLD)

CSK和KCF算法跟踪准确度分别提高了24.1%

15.8%

2.2%。

Abstract

Aiming at the problem that the automobile and pedestrian tracking algorithm can not continue to track because of the pedestrian is sheltered and the high relative speed between automobile and pedestrian

an improved anti-occlusion automobile and pedestrian tracking method is designed and realized

which introduces the histogram of oriented gradient（ HOG） and scale-invariant feature transform（ SIFT） feature on the basis of kernel correlation filter（ KCF） tracking algorithm. When the target pedestrian in the video frame does not appear or partially appears

the SIFT feature and HOG feature of the current frame are extracted. Principal component analysis（ PCA）dimension reduction technology is used to reduce the dimension of multi-feature. Then the fusion feature set of HOG and SIFT is constructed by serial combination

and the feature template HOG-SIFT is generated. By matching the generated feature template with the HOG-SIFT feature in the next frame

pedestrians can be quickly repositioned and tracked. The result of video sequence comparison experiment show that

compared with TLD

CSK and KCF

the tracking accuracy of this algorithm is improved by 24. 1 %

15. 8 % and 2. 2 %

respectively.

关键词

Keywords

references

Views

175

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Spatio-temporal action detection algorithm based on dual-branch feature fusion

Research on target detection based on multi-stage feature pyramid network

Traffic sign recognition algorithm based on double-channel CNN

Analysis method of ECG fusion feature for BSN

Improved CNN based on three-channel fitting for forest fire recognition algorithm

Related Author

MA Li

LU Yuanmeng

GAO Hangbiao

GUAN Zhibin

LIANG Liming

QIAN Yanqun

XIONG Wen

LAN Zhimin

Related Institution

School of Communication and Information Engineering,Xi’an University of Science and Technology

School of Electrical Engineering and Automation, Jiangxi University of Science and Technology

College of Physics and Information Engineering,Fuzhou University

Robot Technology Used for Special Environment Key Laboratory of Sichuan Province

School of Information Engineering,Southwest University of Science and Technology

⁰