Object tracking with occlusion handling using mean shift, Kalman filter and Edge Histogram

Iraei, Iman; Faez, Karim

doi:10.1109/pria.2015.7161637

Cited by 12 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Volleyball is both physically and conceptually estimated by event units, because the true value of physical states is impossible to obtain. During an event cell, if the ball track has a continuous curve without sharp gaps and all projected 2D image coordinates are within the area of the ball in the image frame, we determine that the ball tracking of the event cell is successful [25]. To visualize the tracking results, we selected a test sequence and plotted the tracked 3D track in the figure, figure 10.…”

Section: ) Color/grayscale Figuresmentioning

confidence: 99%

Notice of Violation of IEEE Publication Principles: Study on Sports Volleyball Tracking Technology Based on Image Processing and 3D Space Matching

2020

IEEE Access

View full text Add to dashboard Cite

The tracking technology of the 3D space position of the target is of great use to the analysis and understanding of professional volleyball match, but there are many factors that affect the volleyball tracking rate in the competition. In this paper, the image processing technology is combined with 3D spatial matching technology, and a sports volleyball tracking system framework is established with particle filter, which improves the accuracy of volleyball tracking more effectively. This article begins with a 3D tracking volleyball workflow diagram and selects using particle filters to improve tracking success rates. Secondly, the paper puts forward the similarity estimation method according to the characteristics of volleyball itself, mainly the similarity estimation of the base and HSV color space, to solve the problem of the supercomputing of real-time tracking. Finally, the results of the simulation experiment can be seen that the method can greatly improve the tracking success rate, high efficiency and high accuracy of the characteristics of the dynamic video sports volleyball tracking, has an unpredictable application development value.INDEX TERMS Image processing, 3D spatial matching, particle filters, tracking technology.

show abstract

Section: ) Color/grayscale Figuresmentioning

confidence: 99%

Notice of Violation of IEEE Publication Principles: Study on Sports Volleyball Tracking Technology Based on Image Processing and 3D Space Matching

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Object tracking has various applications such as in security and surveillance systems which use visual data [14], self-driving cars [15], traffic management [16], improved medical therapy, customer behavior analysis [17], interactive game design, design of futuristic video effects, etc. Many algorithms like Mean-shift [18], Camshift [19] etc were developed for this purpose, but it is found that they do not show efficient real-time performance.…”

Section: Literature Surveymentioning

confidence: 99%

Real-Time Tracking of Moving Objects through Efficient Scale Space Adaptation and Normalized Correlation Filtering

Ali

Ghosh

Chaudhuri

2023

Preprint

View full text Add to dashboard Cite

The field of real-time mobile object tracking is a crucial aspect of computer vision. Despite numerous algorithms proposed for efficient tracking, the high computational complexity presents challenges in achieving real-time performance. This paper presents a novel approach by introducing an adaptive search region proposal block that works in tandem with Mean Shift and Unscented Kalman Filter. The block efficiently searches the region of the estimated object location. The dynamic changes in the appearance and size of a moving target make tracking difficult, but the proposed Multi-scale Template Matching technique addresses this challenge by utilizing the Normalized Cross-Correlation method in the adaptive search region. This optimization results in a reduced computational complexity and an increased frame rate of 53.4 FPS. Additionally, the approach leads to a 50.3% decrease in error rate and improved precision and success rates of 76% and 79% respectively. Comparisons with various state-of-the-art trackers show that the proposed algorithm achieves the best results in terms of precision, success rate, and object tracking error.

show abstract

“…(7) According to Equation (7), the motion vectors of m p and m q in Cartesian coordinates are defined as (u p − v p ) and (u q − v q ), respectively, where l 𝜖S l and 𝜃𝜖S 𝜃 , and N (p) is the neighborhood of p. The energy function should be minimized to obtain a good performance. Meanwhile, the first term enforces choosing the higher confidence of the motion kernel for each pixel, and the second term encourages the smoothness of the nearby motion kernels.…”

Section: Blur Kernel Optimizationmentioning

confidence: 99%

“…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

Self Cite

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 with occlusion handling using mean shift, Kalman filter and Edge Histogram

Cited by 12 publications

References 11 publications

Notice of Violation of IEEE Publication Principles: Study on Sports Volleyball Tracking Technology Based on Image Processing and 3D Space Matching

Notice of Violation of IEEE Publication Principles: Study on Sports Volleyball Tracking Technology Based on Image Processing and 3D Space Matching

Real-Time Tracking of Moving Objects through Efficient Scale Space Adaptation and Normalized Correlation Filtering

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

Contact Info

Product

Resources

About