Object tracking algorithm based on particle filter with color and texture feature

Ding, Dong-Sheng; Jiang, Zengru; Liu, Chengyuan

doi:10.1109/chicc.2016.7553983

Cited by 14 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we propose additive fusion with deterministic coefficients. Suppose β 1 is the deterministic coefficient of the feature p(z 1 | x) and β 2 is the deterministic coefficient of the feature p(z 2 | x). β 1 and β 2 are first normalised so that the sum of them is 1…”

Section: Feature Fusion With Deterministic Coefficientmentioning

confidence: 99%

“…To overcome the limitations of the traditional particle filter object-tracking method, and to improve tracking performance in the event of occlusion, many scholars have proposed improved particle filter methods. Ding et al [1] proposed an improved particle filter algorithm for object tracking that combined the colour and texture features of the object. They described the object feature using an improved colour histogram and local binary pattern (LBP) texture histogram and established a reference model for the object.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Anti‐occlusion particle filter object‐tracking method based on feature fusion

Huan

Bao

Wang

et al. 2018

IET Image Processing

View full text Add to dashboard Cite

Section: Feature Fusion With Deterministic Coefficientmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Anti‐occlusion particle filter object‐tracking method based on feature fusion

Huan

Bao

Wang

et al. 2018

IET Image Processing

View full text Add to dashboard Cite

“…Figure 9 show the test results of PFA. ZHU Su et al [26] in this paper the author proposed the two model novel robust MFT algorithm for saliency mapping. This paper also introduces PF for handing illumination variation, and occlusion.…”

Section: Table 1 Tracking Rate Different Algorithms C) Sec-c Occlusmentioning

confidence: 99%

Robust Visual Multi Target Trackers: A Review

E¹,

Rajgopal²

2018

IJEECS

View full text Add to dashboard Cite

<p>In this review paper, we address on the state-of-art process with visual object tracking in video surveillance, medical and military applications. In the present scenario number of algorithms and methods are used to track the object in the different scene, a robust visual object tracking remains a critical challenge. The challenges arise due to object motion from frame to frame with a change in appearance, structures, illumination, and occlusion. In this paper, at last, we outline the different algorithms, dataset, strength, and weakness of the different object tracker.</p>

show abstract

“…Second, the smallest error of the initial value might cause drastic changes in the solution, which is referred to as butterfly effects [4,5]. Although Bayesian state estimation techniques such as particle [6] and Kalman filter [7] filters might solve these problems, the important thing is that a single measurement might not be enough for accurately estimating the location of the object. Accordingly, some deep learning-based methods may be integrated with some object trackers in order to reduce these problems.…”

Section: Introductionmentioning

confidence: 99%

A motion parameters estimating method based on deep learning for visual blurred object tracking

Iraei

Faez

2021

IET Image Processing

View full text Add to dashboard Cite

Tracking the specific object in the blurred scenes is one of the challenging problems in computer vision and image processing. The accuracy and performance of trackers within the blur frames usually demonstrate a severe decrease. Accordingly, this problem needs to be corrected for better tracking results. Thus, this study seeks to present the best solution. To this end, a novel deep learning approach is proposed for object tracking in the presence of motion blur and fast motion. The hidden information in the blurring kernel is useful for tracking a specific blurred object through a series of consecutive frames. In this study, this matter is evaluated from a new perspective to solve the problems of blurred object tracking and objects with highly fast motions using a convolutional neural network (CNN) and a particle filter. Therefore, the proposed framework has two phases. First, the kernel leading to blurring is estimated by CNN, and then by a particle filter and the probability distribution of motion information that has been achieved by the kernel estimation the object is tracked. The results demonstrate that the suggested method can enhance the accuracy of tracking compared with the state-of-the-art, especially when the amount of blur is high.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

show abstract

Object tracking algorithm based on particle filter with color and texture feature

Cited by 14 publications

References 8 publications

Anti‐occlusion particle filter object‐tracking method based on feature fusion

Anti‐occlusion particle filter object‐tracking method based on feature fusion

Robust Visual Multi Target Trackers: A Review

A motion parameters estimating method based on deep learning for visual blurred object tracking

Contact Info

Product

Resources

About