Tracking of Traffic Monitoring Targets in Complicated Traffic Scene Based on MeanShift Algorithm

Jian You Zhao; Jian Cui

doi:10.4028/www.scientific.net/AMM.744-746.2012

Paper Titles

Research on Application of Pedestrian Throw Distance Formula in GA/T643-2006
p.1990

Research on Crossing Speed of Pedestrians Based on Dynamic Density
p.1995

Study of Steering Wheel Movement under Fatigue Driving and Drunk Driving Based on Sample Entropy
p.2001

Study on Cooperative Control Method among Large Flow and Long-Distance Intersections
p.2006

Tracking of Traffic Monitoring Targets in Complicated Traffic Scene Based on MeanShift Algorithm
p.2012

Vehicle-Pedestrian Accidents Characteristic Analysis and Study
p.2019

The Study on Urban Rail Transit Train Operation Simulation System Based on Timetable Control
p.2026

Wavelet Transform with Application in Roadside Landscape Design
p.2032

A Comparitive Analysis of Stop/Go Driving Behavior during the Amber Light at City Signalized Intersecdtions
p.2045

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 744-746Tracking of Traffic Monitoring Targets in...

Tracking of Traffic Monitoring Targets in Complicated Traffic Scene Based on MeanShift Algorithm

Abstract:

To avoid the the interference of busy backgrounds when tracking, detecting and recognizing moving targets in complicated traffic scene, an improved algorithm is proposed on the basis of the original MeanShift algorithm which use different colors of the centroid positions to identify the target. MeanShift algorithm can be used to calcucte the centroid position of each color in the monitoring area. Then the centroid positon of every color in every frame can be identified by analyzing spatial distribution and iteration. At last, establish weighting functions to increase the recognition accuracy so as to recognize and track the targets in complicated traffic scene. Experiments have shown that the improved algorithm is better than the traditional algorithm in identifying and tracking moving targets in the monitoring of complicated traffic scene.

You might also be interested in these eBooks

Advances in Civil Engineering and Transportation IV

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 744-746)

Pages:

2012-2018

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.744-746.2012

Citation:

Cite this paper

Online since:

March 2015

Authors:

Jian You Zhao*, Jian Cui

Keywords:

Distinguish Background, Meanshift, Target Tracking, Traffice Monitoring

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Welch G, Bishop G. An introduction to the kalman filters [C]. SIGGRAPH, (2007).

Google Scholar

[2] Ningsong Peng, Jie Yang, Zhi Liu. Mean-shift tracking algorithm automatically selects the kernel window width [J] Journal of Software, 2005, 16 (9): 1542-1550. in Chinese.

Google Scholar

[3] Jian Qin, Xiao-ping Zeng, Yongming Li. Nuclear power window width adaptive algorithm based on the boundary of the Mean-Shift [J] Journal of Software, 2009, 20 (7): 1726-1734. in Chinese.

DOI: 10.3724/sp.j.1001.2009.03315

Google Scholar

[4] Leykin A, Hammoud R. Robust multi-pedestrian tracking in thermal-visible surveillance videos [C]. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2006, 17(22): 136-143.

DOI: 10.1109/cvprw.2006.175

Google Scholar

[5] Mihaylova L, Loza A, Nikolov S, et al. The influence of multi-sensor video fusion on object tracking using a particle filters [C]. Workshop on Multiple Sensor Data Fusion, Dresden, Germany, (2006).

Google Scholar

[6] Arulampalam S, Maskell S, Gordon N, et al. A tutorial on particle filters for online nonlinear/non-gaussian bayesian tracking [J]. IEEE Transactions on Signal Processing, 2002, 50(2): 174-188.

DOI: 10.1109/78.978374

Google Scholar