Semantic Image Segmentation in Duckietown
https://doi.org/10.25205/1818-7900-2021-19-3-26-39
Abstract
The article is devoted to evaluation of the applicability of existing semantic segmentation algorithms for the “Duckietown” simulator. The article explores classical semantic segmentation algorithms as well as ones based on neural networks. We also examined machine learning frameworks, taking into account all the limitations of the “Duckietown” simulator. According to the research results, we selected neural network algorithms based on U-Net, SegNet, DeepLab-v3, FC-DenceNet and PSPNet networks to solve the segmentation problem in the “Duckietown” project. U-Net and SegNet have been tested on the “Duckietown” simulator.
About the Authors
D. E. Shabalina
Novosibirsk State University
Russian Federation
Russian Federation
Daria E. Shabalina, Bachelor Student
Novosibirsk
K. S. Lanchukovskaya
Novosibirsk State University
Russian Federation
Russian Federation
Kristina S. Lanchukovskaya, Bachelor Student
Novosibirsk
T. V. Liakh
Novosibirsk State University
Russian Federation
Russian Federation
Tatyana V. Lyakh, Candidate of Sciences (Engineering)
Novosibirsk
K. V. Chaika
Saint Petersburg Electrotechnical University; Mobile Robot Algorithms Laboratory “JetBrains Research”
Russian Federation
Russian Federation
Konstantin V. Chaika, Post-Graduate Student
St. Petersburg
References
1. Sharma Y. Adoption of next generation robotics: A case study on Amazon. Pune, 2017, 15 p.
2. Csurka G., Larlus D., Perronnin F. What is a good evaluation measure for semantic segmentation. Meylan, 2013, 11 p.
3. Zuenko E. A., Shulunova A. A. Automated Segmentation of the Lateral Ventricles from MRI Image. Vestnik NSU. Series: Information Technologies, 2017, vol. 15, no. 4, pp. 22–31. (in Russ.) DOI 10.25205/1818-7900-2017-15-4-22-31
4. Musatyan S. A., Lomakin A. V., Sartasov S. Yu., Popyvanov L. K., Monakhov I. B., Chizhova A. S. Methods for segmentation of medical images. In: Proceedings of the Institute for System Programming of the Russian Academy of Sciences. Moscow, 2018. (in Russ.) DOI 10.15514/ISPRAS-2018-30(4)-12
5. Gorbacheva V. A., Krivorotova I. A., Markelov A. O., Kotlyarova E. V. Semantic segmentation of satellite images of airports using convolutional neural networks. Moscow, 2019. 10 p. (in Russ.)
6. Ozmen A., Akman E. T. Edge detection using steerable filters and CNN. In: 11th European Signal Processing Conference. Toulouse, 2002, pp. 1–4.
7. Pestunov I., Rylov S., Berikov V. Hierarchical Ensemble Clustering Algorithm for Multispectral Image Segmentation. In: Proceedings 9th Open German-Russian Workshop on Pattern Recognition and Image Understanding (OGRW-2014). Koblenz, Uni. of Koblenz-Landau Press, 2015, pp. 123–127.
8. Rylov S. A., Melnikov P. V., Pestunov I. A. Spectral and texture classification of high spatial resolution hyperspectral images. Interexpo GEO-Siberia, 2016, vol. 4, no. 1, pp. 78–84. (in Russ.)
9. Chichvarin N. V. Threshold methods. Moscow, 2016. (in Russ.)
10. Lutsenko M. T., Ulyanychev N. V., Semichevskaya N. P. Automatic system for object recognition in microscopic images of biological samples. Blagoveshchensk, 1999. (in Russ.)
11. Pestunov I. A., Sinyavsky Yu. N. Clustering algorithms in satellite images segmentation tasks. Vestnik KSU, 2012, vol. 52, no. 4/2, pp. 110–125. (in Russ.)
12. Li B., Shi Y., Qi Z., Chen Z. A Survey on Semantic Segmentation. Beijing, 2018. DOI 10.1109/ICDMW.2018.00176
13. Noh H., Hong S., Han B. Learning deconvolution network for semantic segmentation. Pohang, 2015.
14. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Berlin, 2015.
15. Badrinarayanan V., Kendall A., Cipolla R. SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, vol. 39, no. 12, pp. 2481–2495. DOI 10.1109/TPAMI.2016.2644615
16. Emelyanov A. V. Analysis of Semantic Image Segmentation Methods Based on Neural Networks. Moscow, 2019. (in Russ.)
17. Chen L., Papandreou G., Kokkinos I., Murphy K., Yuille A. L. DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, vol. 40, no. 4, pp. 834–848. DOI 10.1109/TPAMI.2017.2699184
18. Zhou J., Hao M., Zhang D., Zou P., Zhang W. Fusion PSPnet Image Segmentation Based Method for Multi-Focus Image Fusion. IEEE Photonics Journal, 2019, vol. 11, no. 6, pp. 1–12. DOI 10.1109/JPHOT.2019.2950949
19. Paszke A. ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation. Ithaca, 2016, 10 p.
20. Zhao H., Qi X., Shen X., Shi J., Jia J. ICNet for Real-Time Semantic Segmentation on HighResolution Images. Hong Kong, 2018, 16 p.
21. Chaurasia A., Culurciello E. LinkNet: Exploiting encoder representations for efficient semantic segmentation. EEE Visual Communications and Image Processing (VCIP), 2017, pp. 1–4. DOI 10.1109/VCIP.2017.8305148
22. Emelyanov A. V., Galiahmetov D. G. Analysis of Semantic Image Segmentation Methods in Real Time Based on Neural Networks. Moscow, 2020. (in Russ.)
23. Mehta S., Rastegari M., Caspi A., Shapiro L., Hajishirzi H. ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation. Seattle, 2018, 29 p.
24. Romera E., Alvarez J. M., Bergasa L. M., Arroyo R. ERFNet: Efficient Residual Factorized ConvNet for Real-time Semantic Segmentation. IEEE Transactions on Intelligent Transportation Systems, 2018, vol. 19, no. 1, pp. 263–272. DOI 10.1109/TITS.2017.2750080
25. Brahimi S., Aoun N. B., Chokri B. A., Benoit A., Lambert P. Multiscale Fully Convolutional DenseNet for Semantic Segmentation. Pilsen, 2018.
26. Li X. Examining the spatial distribution and temporal change of the green view index in New York City using Google Street View images and deep learning. Philadelphia, 2020, 16 p.
27. Tóth Z. Deep Learning-based Semantic Segmentation in Simulation and Real-World for Autonomous Vehicles. URL: https://smartlabai.medium.com/deep-learning-based-semanticsegmentation-in-simulation-and-real-world-for-autonomous-vehicles-e7fe25cef816 (accessed 31.03.2021).
28. Ajrapetov A. E., Kovalenko A. A. Research of the generative adversarial network. Polytechnic Youth Journal of the Moscow State Technical University. N. E. Bauman, 2018, no. 10. (in Russ.) DOI 10.18698/2541-8009-2018-10-380
Review
For citations:
Shabalina D.E., Lanchukovskaya K.S., Liakh T.V., Chaika K.V. Semantic Image Segmentation in Duckietown. Vestnik NSU. Series: Information Technologies. 2021;19(3):26-39. (In Russ.) https://doi.org/10.25205/1818-7900-2021-19-3-26-39
Views:
422
Email this article 