A Review on Particle Swarm Optimization Algorithm and Its Variants to Human Motion Tracking

Abstract

Automatic human motion tracking in video sequences is one of the most frequently tackled tasks in computer vision community. The goal of human motion capture is to estimate the joints angles of human body at any time. However, this is one of the most challenging problem in computer vision and pattern recognition due to the high-dimensional search space, self-occlusion, and high variability in human appearance. Several approaches have been proposed in the literature using different techniques. However, conventional approaches such as stochastic particle filtering have shortcomings in computational cost, slowness of convergence, suffers from the curse of dimensionality and demand a high number of evaluations to achieve accurate results. Particle swarm optimization (PSO) is a population-based globalized search algorithm which has been successfully applied to address human motion tracking problem and produced better results in high-dimensional search space. This paper presents a systematic literature survey on the PSO algorithm and its variants to human motion tracking. An attempt is made to provide a guide for the researchers working in the field of PSO based human motion tracking from video sequences. Additionally, the paper also presents the performance of various model evaluation search strategies within PSO tracking framework for 3D pose tracking.

Two‐stage 3D model‐based UAV pose estimation: A comparison of methods for optimization

“…We can also use a different approach and combine a PF with PSO (Krzeszowski, Kwolek, & Wojciechowski, 2010) to perform local optimization, where each particle updates its state vector, taking into account its history and its neighbors. It has been applied, for example, to human motion tracking (Saini, Bt Awang Rambli, Zakaria, & Bt Sulaiman, 2014), image registration (Khan & Nystrom, 2010), object tracking (Zheng & Meng, 2007), and multi‐object tracking (Kwolek, 2013) using CV. When using a PF‐based approach, we have to obtain the likelihood function on each iteration.…”

Reconstruction of 3D human motion in real-time using particle swarm optimization with GPU-accelerated fitness function

“…As a result, our human model consists of several component objects, which are linked by joints. Such a coarse human models are frequently used in 3D motion reconstruction [5,35,40]. Figure 1 depicts a diagram of the system for real-time human motion tracking on the basis of OpenGL-based 3D model rendering and then projecting it to the camera views.…”

“…The system consists of three main ingredients, namely, OpenGL-based 3D model rendering, GPU-accelerated tracking, and image processing. The OpenGL module is universal since it can deliver the rendered models for all kinds of predict-evaluate trackers, such as particle filters [5,13] and particle swarm optimization [14,35]. The input for this module is transformation matrices, which are then used to obtain the 3D model in the required poses.…”

A Chaos-Enhanced Particle Swarm Optimization with Adaptive Parameters and Its Application in Maximum Power Point Tracking

“…Although particle swarm optimization rapidly searches the solution of many complex optimization problems, it suffers from premature convergence, trapping at a local minimum, the slowing down of convergence near the global optimum, and stagnation in a particular region of the problem space especially in a multimodal functions and high-dimensional problem space. If a particle is located at the position of the global best and the preceding velocity and weight inertia are non-zero, then the particle is moving away from that particular point [16,22]. Premature convergence happens if no particle moves and the previous velocities are near to zero.…”