An Experimental Comparison of Swarm Optimization Based Abrupt Motion Tracking Methods

et al. 2020

J Image Video Proc.

Self Cite

In view of the problem that the conventional tracker does not adapt to abrupt motion, we propose a tracking algorithm based on the hybrid extended ant lion optimizer with sine cosine algorithm (EALO-SCA) in this paper. Firstly, the multiple elites is used to replace the single elite in the standard ant lion optimizer (ALO). The extended ALO (EALO) can enhance the global exploration ability, which can handle abrupt motion. Secondly, considering that sine cosine algorithm (SCA) has strong local exploitation operator, a hybrid EALO-SCA tracker is proposed using the advantages of both EALO and SCA. The proposed approach can improve tracking accuracy and efficiency. Finally, extensive experimental results in both quantitative and qualitative measures prove that the proposed algorithm is very competitive compared to 7 state-of-the-art trackers, especially for abrupt motion tracking.

show abstract

Section: Introductionmentioning

confidence: 99%

Hybridizing extended ant lion optimizer with sine cosine algorithm approach for abrupt motion tracking

et al. 2020

J Image Video Proc.

Self Cite

show abstract

“…In this case, the conventional tracker cannot track effectively. To address the issue, many methods have been proposed subsequently, including detection based tracking methods [9], [10], stochastic sampling based tracking methods [11], [12], optimization based tracking methods [13], [14], etc.…”

Section: Introductionmentioning

confidence: 99%

“…These hybrid optimization algorithms can effectively balance exploration and exploitation for dealing with visual tracking. In addition, we have been focusing on hybrid algorithm to solve abrupt motion tracking [13], [14], [29]. Zhang et al [29] proposed an extended kernel correlation filter (KCF) tracker based on simulated annealing method and designed a unified framework to track smooth or abrupt motion simultaneously.…”

Section: Introductionmentioning

confidence: 99%

Hybridizing Teaching-Learning-Based Optimization With Adaptive Grasshopper Optimization Algorithm for Abrupt Motion Tracking

et al. 2019

IEEE Access

Self Cite

Aiming at the problem that conventional tracking algorithms are difficult to deal with abrupt motion efficiently, an optimization algorithm called hybrid Teaching-learning-based optimization with Adaptive Grasshopper Optimization Algorithm (TLGOA) is proposed in this paper. Firstly, the non-linear strategy based on tangent function is used to replace the linear mechanism in the standard Grasshopper Optimization Algorithm (GOA). The improved adaptive GOA (AGOA) can avoid the local trapping problem and enhance the global optimization ability, which can handle the problem of abrupt motion. Secondly, considering that Teaching-learning-based optimization (TLBO) has obviously local exploitation operator and fast convergence, a hybrid TLGOA tracker is designed by combining the advantages of both AGOA and TLBO. The approach can enable better tracking accuracy and efficiency. Finally, extensive experimental results show that the proposed algorithm has obvious advantages over other algorithms, and also prove that TLGOA tracker is very competitive compared to other state-of-the-art trackers, especially for abrupt motion tracking. INDEX TERMS Visual tracking, abrupt motion, grasshopper optimization algorithm, teaching-learningbased optimization.

show abstract

Visual Tracking with Levy Flight Grasshopper Optimization Algorithm

Pattern Recognition and Computer Vision

et al. 2019