Color Feature-Based Object Tracking through Particle Swarm Optimization with Improved Inertia Weight

Guo, Siqiu; Zhang, Tao; Song, Yujiang; Qian, Feng

doi:10.3390/s18041292

Cited by 10 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…High-speed KCF tracker [16] is concerned with the adaptive ability to the problems of scale and obscurity, besides the incredible tracking speed of up to 170 fps. A particle swarm tracking algorithm is based on the increasing inertia weight PSO [17] or the method using color features [18]. Te algorithm has the advantage of global tracking, so it can deal with shortcomings as the tracker falls into the local problem.…”

Section: Introductionmentioning

confidence: 99%

An Improvement of the Camshift Human Tracking Algorithm Based on Deep Learning and the Kalman Filter

Nguyen

Chu

Phan

et al. 2023

Journal of Robotics

View full text Add to dashboard Cite

Automated human tracking in real time has been applied in many areas such as security, surveillance, traffic control, and robots. In this paper, an improvement of the Camshift human tracking algorithm based on deep learning and the Kalman filter is proposed. To detail an approach by using YOLOv4-tiny to detect a human in real time, Camshift is used to track a particular person and the Kalman filter is applied to enhance the performance of this algorithm in case of occlusion, noise, and different light conditions. The experiments show that the combination of YOLOv4-tiny and the improved Camshift algorithm raises the standard of speed as well as robustness. The proposed algorithm is suitable for running in real time and adapts well to the same color and different light conditions.

show abstract

Section: Introductionmentioning

confidence: 99%

An Improvement of the Camshift Human Tracking Algorithm Based on Deep Learning and the Kalman Filter

Nguyen

Chu

Phan

et al. 2023

Journal of Robotics

View full text Add to dashboard Cite

show abstract

“…PSO was selected because it has mainly been applied to continuous‐discrete nonlinear optimization and has been used by many studies . In addition, Guo et al and Zhou et al also proved that this approach can be applied in color‐ and illumination‐related research. Similar to some studies, this article also applied general PSO algorithm for minimizing CSI value, since it can be implemented easily in the military research organizations.…”

Section: Introductionmentioning

confidence: 99%

A metaheuristic‐based approach to optimizing color design for military camouflage using particle swarm optimization

Lin

Prasetyo

2019

Color Research & Application

View full text Add to dashboard Cite

Enhancing an existing military camouflage is an important component during the assessment of military camouflage. The current study proposed a new and practical approach to enhancing the undetectability of a military camouflage using particle swarm optimization (PSO). Eight different locations (20 × 50 pixels) in the one swamp background were selected to be the place of a human-shaped target. The PSO would generate newly proposed camouflage as an empirical parameter based on the lower and the upper bounds from selected four different colors in swamp background. The predictive algorithm was applied to adjust the optimum shift of %L*, %a*, and %b* from the original to the empirical parameter. Thirty participants were recruited to evaluate the original and newly proposed camouflages. Paired sample t test indicates that the newly proposed military camouflage had a significant lower camouflage similarity index value and a longer detection time. The PSO shows to be a method with good results; however, a comprehensive study using multiple backgrounds and patterns would be required to generalize the methodology to other background environments or camouflage patterns. K E Y W O R D Scamouflage similarity index, detection time, military camouflage, particle swarm optimization, target search

show abstract

“…Object tracking is a challenging problem and its difficulties can arise due to object appearance changes, illumination changes, occlusion, and so on. In the past few decades, most researchers have taken their efforts on color-image-based tracking methods [1,2,3], and have achieved a great progress. However, the intrinsic character of color image is that it is obtained by color camera at the cost of losing information by projecting 3D to 2D, which makes the features extracted from it easily influenced by the changes of illumination.…”

Section: Introductionmentioning

confidence: 99%

Visual Tracking Applying Depth Spatiogram and Multi-feature Data

Dastjerdi¹,

Ahmad²

2019

9th International Conference on Advances in Computing and Information Technology (ACITY 2019)

View full text Add to dashboard Cite

Object tracking, in general, is a promising technology that can be utilized in a wide variety of applications. It is a challenging problem and its difficulties in tracking objects may fail when confronted with challenging scenarios such as similar background color, occlusion, illumination variation, or background clutter. A number of ongoing challenges still remain and an improvement on accuracy can be obtained with additional processing of information. Hence, utilizing depth information can potentially be exploited to boost the performance of traditional object tracking algorithms. Therefore, a large trend in this paper is to integrate depth data with other features in tracking to improve the performance of tracking algorithm and disambiguate occlusions and overcome other challenges such as illumination artifacts. For this, we use the basic idea of many trackers which consists of three main components of the reference model, i.e., object modeling, object detection and localization, and model updating. However, there are major improvements in our system. Our forth component, occlusion handling, utilizes the depth spatiogram of target and occluder to localize the target and occluder. The proposed research develops an efficient and robust way to keep tracking the object throughout video sequences in the presence of significant appearance variations and severe occlusions. The proposed method is evaluated on the Princeton RGBD tracking dataset and the obtained results demonstrate the effectiveness of the proposed method.

show abstract

Color Feature-Based Object Tracking through Particle Swarm Optimization with Improved Inertia Weight

Cited by 10 publications

References 35 publications

An Improvement of the Camshift Human Tracking Algorithm Based on Deep Learning and the Kalman Filter

An Improvement of the Camshift Human Tracking Algorithm Based on Deep Learning and the Kalman Filter

A metaheuristic‐based approach to optimizing color design for military camouflage using particle swarm optimization

Visual Tracking Applying Depth Spatiogram and Multi-feature Data

Contact Info

Product

Resources

About