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

Siqiu Guo,Feng Qian,Tao Zhang,Yulong Song

doi:10.3390/s18041292

Abstract

This paper presents a particle swarm tracking algorithm with improved inertia weight based on color features. The weighted color histogram is used as the target feature to reduce the contribution of target edge pixels in the target feature, which makes the algorithm insensitive to the target non-rigid deformation, scale variation, and rotation. Meanwhile, the influence of partial obstruction on the description of target features is reduced. The particle swarm optimization algorithm can complete the multi-peak search, which can cope well with the object occlusion tracking problem. This means that the target is located precisely where the similarity function appears multi-peak. When the particle swarm optimization algorithm is applied to the object tracking, the inertia weight adjustment mechanism has some limitations. This paper presents an improved method. The concept of particle maturity is introduced to improve the inertia weight adjustment mechanism, which could adjust the inertia weight in time according to the different states of each particle in each generation. Experimental results show that our algorithm achieves state-of-the-art performance in a wide range of scenarios.

Highlights

In recent years, object tracking technology has been a hot topic in the field of computer vision.For decades, a large number of scholars worldwide have been engaged in the study of object tracking algorithms [1,2,3,4,5,6]
A weighted color histogram unit circle used as the target feature description
Particle swarm optimization is used normalized to optimize to a unit circle is used as the target feature description

Summary

Introduction

A large number of scholars worldwide have been engaged in the study of object tracking algorithms [1,2,3,4,5,6]. The algorithms representative of the traditional object tracking field include the centroid tracking algorithm, the related tracking algorithm, the gate tracking algorithm, the optical flow algorithm, and the mean-shift tracking algorithm. The centroid tracking algorithm and the gate tracking algorithm have satisfactory real-time performance and low complexity, but their stability is poor. The related tracking algorithm and the optical flow algorithm have satisfactory stability, but they have difficulty guaranteeing real-time. The mean-shift tracking algorithm is more susceptible to the background, which is problematic since it is easy to lose the target in a complex environment. Most of the solutions are confined to a specific environment and require a large amount of research

Methods

Results

Conclusion