Intelligent Trigonometric Particle Filter for visual tracking. (September 2022)

• Record Type: Journal Article
• Authors: Nenavath, Hathiram; Ashwini, K.; Jatoth, Ravi Kumar; Mirjalili, Seyedali
• Is Part Of: ISA transactions. Volume 128(2022)Part A
• Page Start: 460
• Page End: 476
• Publication Date: 2022-09
• Subjects: Particle filter (PF) -- Trigonometric Particle Filter (TPF) -- Visual tracking -- Sine Cosine Algorithm (SCA) -- Occlusion; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2021.09.014
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: Visual tracking is one of the pre-eminent tasks in several computer vision applications. Particle filter (PF) is extensively used in visual tracking for intelligent surveillance system applications, hugely significant. But the re-sampling procedure of PF will result in sample impoverishment, which will affect the precision of tracking simultaneously. In this paper, a new tracking technique, called Trigonometric Particle Filter (TPF), based on PF optimized by Sine Cosine Algorithm (SCA), which contains trigonometric sine and cosine functions, is proposed. An enhanced method for improving the number of target particles used in a Sine Cosine Algorithm for trigonometric particle filter includes SCA ahead of the re-sampling step. This step ensures a more extensive particle set Achievement of the proposed TPF tracker is inspected and assessed on Visual Tracker Benchmark (VOT) databases. The proposed TPF tracker is compared with evolutionary-based methods like the Spider monkey optimization assisted PF (SMO-PF), Firefly algorithm-based PF (FAPF) method, Particle swarm optimization-based PF (PSO-PF) and Particle filter, recent four correlation filter-based trackers, and also with other ten state-of-the-art tracking methods. We demonstrate that visual tracking using TPF delivers additional consistent and proficient tracking outcomes than compared trackers. Highlights: A new tracking technique, called TPF, based on PF optimized by SCA, is proposed. The SCA replaces the normal re-sampling process and improves the PF. TPF compared with evolutionary-based approaches and 10 other leading-edge methods. TPF visual tracking is more consistent and proficient than other trackers.