Biologically Inspired Optimization Methods for Image Registration in Visual Servoing of a Mobile Robot
Апстракт
Image registration (IR) represents image processing
technique that is suitable for use in Visual Servoing (VS). This
paper proposes the use of Biologically Inspired Optimization
(BIO) methods for IR in VS of nonholonomic mobile robot. The
comparison study of three different BIO methods is conducted,
namely Genetic Algorithm (GA), Particle Swarm Optimization
(PSO), and Grey Wolf Optimizer (GWO). The aforementioned
optimization algorithms utilized for IR are tested on 24 images of
manufacturing entities acquired by mobile robot stereo vision
system. The considered algorithms are implemented in the
MATLAB environment. The experimental results suggest
satisfactory geometrical alignment after IR, whilst GA and PSO
outperform GWO.
Кључне речи:
Image Registration / Nonholonomic Mobile Robot Visual Servoing / Biologically Inspired OptimizationИзвор:
Proceedings : 7th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2020), 28-29. September 2020, 2020, 715-720Финансирање / пројекти:
- MISSION4.0 - Deep Machine Learning and Swarm Intelligence-Based Optimization Algorithms for Control and Scheduling of Cyber-Physical Systems in Industry 4.0 (RS-ScienceFundRS-AI-6523109)
Колекције
Институција/група
Mašinski fakultetTY - CONF AU - Đokić, Lazar AU - Jokić, Aleksandar AU - Petrović, Milica AU - Miljković, Zoran PY - 2020 UR - https://machinery.mas.bg.ac.rs/handle/123456789/4235 AB - Image registration (IR) represents image processing technique that is suitable for use in Visual Servoing (VS). This paper proposes the use of Biologically Inspired Optimization (BIO) methods for IR in VS of nonholonomic mobile robot. The comparison study of three different BIO methods is conducted, namely Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Grey Wolf Optimizer (GWO). The aforementioned optimization algorithms utilized for IR are tested on 24 images of manufacturing entities acquired by mobile robot stereo vision system. The considered algorithms are implemented in the MATLAB environment. The experimental results suggest satisfactory geometrical alignment after IR, whilst GA and PSO outperform GWO. C3 - Proceedings : 7th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2020), 28-29. September 2020 T1 - Biologically Inspired Optimization Methods for Image Registration in Visual Servoing of a Mobile Robot EP - 720 SP - 715 UR - https://hdl.handle.net/21.15107/rcub_machinery_4235 ER -
@conference{ author = "Đokić, Lazar and Jokić, Aleksandar and Petrović, Milica and Miljković, Zoran", year = "2020", abstract = "Image registration (IR) represents image processing technique that is suitable for use in Visual Servoing (VS). This paper proposes the use of Biologically Inspired Optimization (BIO) methods for IR in VS of nonholonomic mobile robot. The comparison study of three different BIO methods is conducted, namely Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Grey Wolf Optimizer (GWO). The aforementioned optimization algorithms utilized for IR are tested on 24 images of manufacturing entities acquired by mobile robot stereo vision system. The considered algorithms are implemented in the MATLAB environment. The experimental results suggest satisfactory geometrical alignment after IR, whilst GA and PSO outperform GWO.", journal = "Proceedings : 7th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2020), 28-29. September 2020", title = "Biologically Inspired Optimization Methods for Image Registration in Visual Servoing of a Mobile Robot", pages = "720-715", url = "https://hdl.handle.net/21.15107/rcub_machinery_4235" }
Đokić, L., Jokić, A., Petrović, M.,& Miljković, Z.. (2020). Biologically Inspired Optimization Methods for Image Registration in Visual Servoing of a Mobile Robot. in Proceedings : 7th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2020), 28-29. September 2020, 715-720. https://hdl.handle.net/21.15107/rcub_machinery_4235
Đokić L, Jokić A, Petrović M, Miljković Z. Biologically Inspired Optimization Methods for Image Registration in Visual Servoing of a Mobile Robot. in Proceedings : 7th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2020), 28-29. September 2020. 2020;:715-720. https://hdl.handle.net/21.15107/rcub_machinery_4235 .
Đokić, Lazar, Jokić, Aleksandar, Petrović, Milica, Miljković, Zoran, "Biologically Inspired Optimization Methods for Image Registration in Visual Servoing of a Mobile Robot" in Proceedings : 7th International Conference on Electrical, Electronics and Computing Engineering (IcETRAN 2020), 28-29. September 2020 (2020):715-720, https://hdl.handle.net/21.15107/rcub_machinery_4235 .