TY - GEN

T1 - Semantic Image Segmentation Methods in the Duckietown Project

AU - Lanchukovskaya, Kristina S.

AU - Shabalina, Dasha E.

AU - Liakh, Tatiana V.

N1 - Publisher Copyright: © 2022 IEEE.

PY - 2022

Y1 - 2022

N2 - The article focuses on evaluation of the applicability of existing semantic segmentation algorithms for the Duckietown simulator. Duckietown is an open research project in the field of autonomously controlled robots. The article explores classical semantic image segmentation algorithms. Their analysis for applicability in Duckietown is carried out. With the help of them, we want to make a dataset for training neural networks. The following was investigated: edge-detection techniques, threshold algorithms, region growing, segmentation algorithms based on clustering, neural networks. The article also reviewed networks designed for semantic image segmentation and machine learning frameworks, taking into account all the limitations of the Duckietown simulator. Experiments were conducted to evaluate the accuracy of semantic segmentation algorithms on such classes of Duckietown objects as road and background. Based on the results of the analysis, region growing algorithms and clustering algorithms were selected and implemented. Experiments were conducted to evaluate the accuracy on such classes of Duckietown objects as road, background and traffic signs. After evaluating the accuracy of the algorithms considered, it was decided to use Color segmentation, Mean Shift, Thresholding algorithms and Segmentation of signs by April-tag for image preprocessing. For neural networks, experiments were conducted to evaluate the accuracy of semantic segmentation algorithms on such classes of Duckietown objects as road and background. After evaluating the accuracy of the algorithms considered, it was decided to select the DeepLab-v3 neural network. Separate module was created for semantic image segmentation in Duckietown.

AB - The article focuses on evaluation of the applicability of existing semantic segmentation algorithms for the Duckietown simulator. Duckietown is an open research project in the field of autonomously controlled robots. The article explores classical semantic image segmentation algorithms. Their analysis for applicability in Duckietown is carried out. With the help of them, we want to make a dataset for training neural networks. The following was investigated: edge-detection techniques, threshold algorithms, region growing, segmentation algorithms based on clustering, neural networks. The article also reviewed networks designed for semantic image segmentation and machine learning frameworks, taking into account all the limitations of the Duckietown simulator. Experiments were conducted to evaluate the accuracy of semantic segmentation algorithms on such classes of Duckietown objects as road and background. Based on the results of the analysis, region growing algorithms and clustering algorithms were selected and implemented. Experiments were conducted to evaluate the accuracy on such classes of Duckietown objects as road, background and traffic signs. After evaluating the accuracy of the algorithms considered, it was decided to use Color segmentation, Mean Shift, Thresholding algorithms and Segmentation of signs by April-tag for image preprocessing. For neural networks, experiments were conducted to evaluate the accuracy of semantic segmentation algorithms on such classes of Duckietown objects as road and background. After evaluating the accuracy of the algorithms considered, it was decided to select the DeepLab-v3 neural network. Separate module was created for semantic image segmentation in Duckietown.

KW - artificial intelligence

KW - computer vision

KW - duckiebots

KW - Duckietown

KW - neural networks

KW - OpenCV

KW - robotics

KW - semantic image segmentation

UR - http://www.scopus.com/inward/record.url?scp=85137355503&partnerID=8YFLogxK

UR - https://www.mendeley.com/catalogue/934fb053-9fef-3b12-ad3b-46ab03d879bd/

U2 - 10.1109/EDM55285.2022.9855168

DO - 10.1109/EDM55285.2022.9855168

M3 - Conference contribution

AN - SCOPUS:85137355503

SN - 9781665498043

T3 - International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices, EDM

SP - 611

EP - 617

BT - Proceedings of the 2022 IEEE 23rd International Conference of Young Professionals in Electron Devices and Materials, EDM 2022

PB - IEEE Computer Society

T2 - 23rd IEEE International Conference of Young Professionals in Electron Devices and Materials, EDM 2022

Y2 - 30 June 2022 through 4 July 2022

ER -