A particle filter for joint detection and tracking of color objects

Czyz, J.; Ristić, Branko; Macq, Benoı̂t

doi:10.1016/j.imavis.2006.07.027

Cited by 115 publications

(82 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The setting of other parameters in the particle filter framework, such as σ in the Gaussian filter and A and W in the motion model, can be found in Ref. [22].…”

Section: Methodsmentioning

confidence: 99%

Robust Tracking Using Particle Filter with a Hybrid Feature

Zhao¹,

Satoh

Takauji

et al. 2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Xinyue ZHAO†a) , Yutaka SATOH † †b) , Hidenori TAKAUJI † † †c) , Nonmembers, and Shun'ichi KANEKO †d) , Member SUMMARY This paper presents a novel method for robust object tracking in video sequences using a hybrid feature-based observation model in a particle filtering framework. An ideal observation model should have both high ability to accurately distinguish objects from the background and high reliability to identify the detected objects. Traditional features are better at solving the former problem but weak in solving the latter one. To overcome that, we adopt a robust and dynamic feature called Grayscale Arranging Pairs (GAP), which has high discriminative ability even under conditions of severe illumination variation and dynamic background elements. Together with the GAP feature, we also adopt the color histogram feature in order to take advantage of traditional features in resolving the first problem. At the same time, an efficient and simple integration method is used to combine the GAP feature with color information. Comparative experiments demonstrate that object tracking with our integrated features performs well even when objects go across complex backgrounds.

show abstract

“…The setting of other parameters in the particle filter framework, such as σ in the Gaussian filter and A and W in the motion model, can be found in Ref. [22].…”

Section: Methodsmentioning

confidence: 99%

Robust Tracking Using Particle Filter with a Hybrid Feature

Zhao¹,

Satoh

Takauji

et al. 2012

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…Similarly, Boosted Particle filtering (BPF) [12] uses proposal distributions with a mixture model that contains contributions from a detector and the target dynamic model. In [13], the target state is augmented with an existence variable to model the number of targets in the Bayesian estimation. This leads to a hybrid estimation problem solved using a jump Markov model [14], as one component of the state vector is discrete valued, while the rest are continuous valued.…”

Section: A Target Tracking: Related Workmentioning

confidence: 99%

“…To solve this problem, instead of using the existence variable and the jump Markov model [13], [16], we employ clustering of the particles. The prediction step remains the same as in the case of single targets as defined in Eq.…”

Section: B Multi-sensor Multi-target Track-before-detectmentioning

confidence: 99%

Multi-camera track-before-detect

Taj

Cavallaro

2009

2009 Third ACM/IEEE International Conference on Distributed Smart Cameras (ICDSC)

View full text Add to dashboard Cite

Abstract-We present a novel multi-camera multi-target fusion and tracking algorithm for noisy data. Information fusion is an important step towards robust multi-camera tracking and allows us to reduce the effect of projection and parallax errors as well as of the sensor noise. Input data from each camera view are projected on a top-view through multi-level homographic transformations. These projected planes are then collapsed onto the top-view to generate a detection volume. To increase track consistency with the generated noisy data we propose to use a track-before-detect particle filter (TBD-PF) on a 5D statespace. TBD-PF is a Bayesian method which extends the target state with the signal intensity and evaluates each image segment against the motion model. This results in filtering components belonging to noise only and enables tracking without the need of hard thresholding the signal. We demonstrate and evaluate the proposed approach on real multi-camera data from a basketball match.

show abstract

“…During the fifty years of research and development, the target tracking has been largely used in various areas [2]. One camera can detect limited area, it is difficult to track target with multiple perspectives, and long time and wide range, so using multiple cameras become inevitable.…”

Section: Introductionmentioning

confidence: 99%

Multi-camera tracking algorithm study based on information fusion

Wang¹,

Li²,

Wen³

2016

Proceedings of the 2016 International Conference on Advanced Electronic Science and Technology (AEST 2016)

View full text Add to dashboard Cite

Abstract. Intelligent video surveillance technology is a part of pattern recognition used for analyzing, extracting and recognizing behavior characteristics of a moving target basing on computer algorithms. The target tracking algorithm combines particle filter and Mean-shift in overlapping multi-camera environment on the intelligent video surveillance system. Multicamera tracking is studied using a fusion of SURF characteristics, color characteristics and geometric characteristic in Matlab. Experimental results show that the method of tracking between multiple cameras has good accuracy and stability.

show abstract

A particle filter for joint detection and tracking of color objects

Cited by 115 publications

References 23 publications

Robust Tracking Using Particle Filter with a Hybrid Feature

Robust Tracking Using Particle Filter with a Hybrid Feature

Multi-camera track-before-detect

Multi-camera tracking algorithm study based on information fusion

Contact Info

Product

Resources

About