Improved Object Tracking with Particle Filter and Mean Shift

Bai, Kejia; Liu, Wei Ming

doi:10.1109/ical.2007.4338601

Cited by 16 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interesting implementation of this scheme has been proposed in (Cai et al, 2006) where the data association problem is formulated and the MS algorithm is "embedded seamlessly" into the particle filter algorithm: the deterministic MS -induced particle bias with a superimposed Gaussian distribution is considered as a new proposal distribution. Other related hybrid particle filters combined with the MS have been proposed in (Bai & Liu (2007); Cai et al (2006); Han et al (2004); Shan et al (2007)).…”

Section: Video Tracking Overview 21 Deterministic Methodsmentioning

confidence: 99%

Structural Information Approaches to Object Tracking in Video Sequences

Loza¹,

Mihaylova²,

Wang³

et al. 2011

Object Tracking

View full text Add to dashboard Cite

Section: Video Tracking Overview 21 Deterministic Methodsmentioning

confidence: 99%

Structural Information Approaches to Object Tracking in Video Sequences

Loza¹,

Mihaylova²,

Wang³

et al. 2011

Object Tracking

View full text Add to dashboard Cite

“…Third, approaches were proposed which belong to the serial category (Maggio and Cavallaro, 2005;Wang et al, 2007;Bai and Liu, 2007;Liu et al, 2008;Khan et al, 2011), consisting of three stages:…”

Section: Introductionmentioning

confidence: 99%

Anadvanced integrated framework for moving object tracking

Choe

Wang

Liu

et al. 2014

J. Zhejiang Univ. - Sci. C

View full text Add to dashboard Cite

This paper first introduces the concept of a geogram that captures richer features to represent the objects. The spatiogram contains some moments upon the coordinates of the pixels corresponding to each bin, while the geogram contains information about the perimeter of grouped regions in addition to features in the spatiogram. Then we consider that a convergence process of mean shift is divided into obvious dynamic and steady states, and introduce a hybrid technique of feature description, to control the convergence process. Also, we propose a spline resampling to control the balance between computational cost and accuracy of particle filtering. Finally, we propose a boosting-refining approach, which is boosting the particles positioned in the ill-posed condition instead of eliminating the ill-posed particles, to refine the particles. It enables the estimation of the object state to obtain high accuracy. Experimental results show that our approach has promising discriminative capability in comparison with the state-of-the-art approaches.

show abstract

“…Researchers have done much research on visual tracking and proposed many effective methods. Particle filter [2] is a powerful and reliable method for visual tracking because it neither limits to the linear tracking system nor restricts the noise to be Gaussian. However, it exposes several difficult issues such as particle degeneracy, computational complexity and sample impoverishment.…”

Section: Introductionmentioning

confidence: 99%

A Visual Tracking Based on Particle Filter of Multi-Algorithm Fusion

Sun

2014

AMM

View full text Add to dashboard Cite

A novel visual tracking algorithm based on particle filter with multi-algorithm fusion is proposed. Mean shift is employed to make particles distribute more reasonably in order to maintain tracking accuracy by using fewer particles, and the genetic evolution ideas is introduced to increase the diversity of samples by applying selection, crossover and mutation operator to achieve particles resampling. The experiments show that the tracking performance of the proposed method, compared with Mean Shift Embedded Particle Filter (MSEPF), is significantly improved.

show abstract

Improved Object Tracking with Particle Filter and Mean Shift

Cited by 16 publications

References 12 publications

Structural Information Approaches to Object Tracking in Video Sequences

Structural Information Approaches to Object Tracking in Video Sequences

Anadvanced integrated framework for moving object tracking

A Visual Tracking Based on Particle Filter of Multi-Algorithm Fusion

Contact Info

Product

Resources

About