Particle filter algorithm based on adaptive resampling strategy

Yao

2023

JMSE

Due to the complexity of the underwater environment, tracking underwater targets via traditional particle filters is a challenging task. To resolve the problem that the tracking accuracy of a traditional particle filter is low due to the sample impoverishment caused by resampling, in this paper, a new tracking algorithm using Harris-hawks-optimized particle filters (HHOPF) is proposed. At the same time, the problem of particle filter underwater target feature construction and underwater target scale transformation is addressed, the corrected background-weighted histogram method is introduced into underwater target feature recognition, and the scale filter is combined to realize target scaling transformation during tracking. In addition, to enhance the computational speed of underwater target tracking, this paper constructs a nonlinear escape energy using the Harris hawks algorithm in order to balance the exploration and exploitation processes. Based on the proposed HHOPF tracker, we performed detection and evaluation using the Underwater Object Tracking (UOT100) vision database. The proposed method is compared with evolution-based tracking algorithms and particle filters, as well as with recent tracker-based correlation filters and some other state-of-the-art tracking methods. By comparing the results of tracking using the test data sets, it is determined that the presented algorithm improves the overlap accuracy and tracking accuracy by 11% compared with other algorithms. The experiments demonstrate that the presented HHOPF visual tracking provides better tracking results.

Section: Improved Particle Filter Based On Sample Impoverishmentmentioning

confidence: 99%

Particle Filter Based on Harris Hawks Optimization Algorithm for Underwater Visual Tracking

Yao

2023

JMSE

Lecture Notes in Electrical Engineering

“…But it is elusive to get satisfactory estimation results when the dimension of state vector is greater than three. It had been proved that Particle Filter (PF) [7], which approximates the posterior PDF by generating a large number of particles randomly, could achieve very high precision long as the number of particles meets the requirement. But large number of particles may cause an enormous amount of calculation, thus limiting the widely use of PF in practical application.…”

Section: Introductionmentioning

confidence: 99%

Cubature Kalman Filter Based on Strong Tracking

Zhang

Zhao

et al. 2015

To improve the ability of dealing with inaccurate of model and statistic characteristics of noise, as well as the abrupt change of state of cubature Kalman filter (CKF), a new nonlinear filter, called Cubature Kalman Filter based on strong tracking (CKF-ST), is proposed in this paper. Inspired by the idea of strong tracking, a time-variant factor is introduced into the recursive process of cubature Kalman filter such that the filter gain can be updated along with the measured values, thus endowing CKF-ST powerful ability to deal with abrupt changes of state. Meanwhile, such merits of CKF as high accuracy and being easy to implement can be entirely preserved in CKF-ST. Simulation results on one classical examples demonstrate that CKF-ST is overall superior to CKF and other filters involved, especially when target motion changes suddenly.

“…Two common methods to deal with degeneracy are: Resampling. Good choice of importance density. Resampling is a method by which particles with small weights are eliminated from the state vector estimate and are replaced with particles having large weights. The authors in [12–15] present systematic resampling, adaptive resampling, residual resampling, multinomial resampling, and stratified resampling methodologies, respectively. Nonetheless, these resampling methods partially solve the particle degeneracy problem.…”

Section: Introductionmentioning

confidence: 99%

Spider monkey optimisation assisted particle filter for robust object tracking

Rohilla

Sikri

Kapoor

2017

IET Computer Vision

Particle filters (PFs) are sequential Monte Carlo methods that use particle representation of state-space model to implement the recursive Bayesian filter for non-linear and non-Gaussian systems. Owing to this property, PFs have been extensively used for object tracking in recent years. Although PFs provide a robust object tracking framework, they suffer from shortcomings. Particle degeneracy and particle impoverishment brought by the resampling step result in abysmal construction of posterior probability density function (PDF) of the state. To overcome these problems, this work amalgamates two characteristics of population-based heuristic optimisation algorithms: exploration and exploitation with PF implementing dynamic resampling method. The aim of optimisation is to distribute particles in high-likelihood area according to the cognitive effect and improve quality of particles, while the objective of dynamic resampling is to maintain diversity in the particle set. This work uses very efficient spider monkey optimisation to achieve this. Furthermore, to test the efficiency of the proposed algorithm, experiments were carried out on one-dimensional state estimation problem, bearing only tracking problem, standard videos and synthesised videos. Metrics obtained show that the proposed algorithm outplays simple PF, particle swarm optimisation based PF, and cuckoo search based PF, and effectively handles different challenges inherent in object tracking.