A Dynamic Approach for Railway Semantic Segmentation
Abstract
Railway semantic segmentation is the task of highlighting rail blades in images taken from the ego-view of the train. Solving this task allows for further image processing on the rails, which can be used for more complex problems such as switch or fault detection. In this paper we approach the railway semantic segmentation using two deep architectures from the U-Net family, U-Net and ResUNet++, using the most comprehensive dataset available at the time of writing from the railway scene, namely RailSem19. We also investigate the effects of image augmentations and different training dataset sizes, as well as the performance of the models on dark images. We have compared our solution to other approaches and obtained competitive results with larger scores.
References
[2] Clifton, A., Pappu, A., Reddy, S., Yu, Y., Karlgren, J., Carterette, B., and Jones, R. The spotify podcast dataset. arXiv preprint arXiv:2004.04270 (2020), 1–4.
[3] Delbouys, R., Hennequin, R., Piccoli, F., Royo-Letelier, J., and Moussallam, M. Music mood detection based on audio and lyrics with deep neural net. In Proceedings of the 19th International Society for Music Information Retrieval Conference, ISMIR 2018, Paris, France, September 23-27, 2018 (2018), pp. 370–375.
[4] Dey, R., and Salem, F. M. Gate-variants of gated recurrent unit (GRU) neural networks. In IEEE 60th International Midwest Symposium on Circuits and Systems, MWS-CAS 2017, Boston, MA, USA, August 6-9, 2017 (2017), IEEE, pp. 1597–1600.
[5] Hevner, K. Experimental studies of the elements of expression in music. The American Journal of Psychology 48, 2 (1936), 246–268.
[6] Kamm, T., Hermansky, H., and Andreou, A. G. Learning the mel-scale and optimal vtn mapping. In Center for Language and Speech Processing, Workshop (1997), pp. 1–8.
[7] Li, T., and Ogihara, M. Detecting emotion in music. CiteSeer (2003), 1–3.
[8] Lidy, T., and Schindler, A. Parallel convolutional neural networks for music genre and mood classification. MIREX2016 (2016), 1–4.
[9] Liu, T., Han, L., Ma, L., and Guo, D. Audio-based deep music emotion recognition. AIP Conference Proceedings 1967, 1 (2018), 040021.
[10] Malik, M., Adavanne, S., Drossos, K., Virtanen, T., Ticha, D., and Jarina, R. Stacked convolutional and recurrent neural networks for music emotion recognition. CoRR abs/1706.02292 (2017).
[11] Peeters, G. A generic training and classification system for mirex08 classification tasks: audio music mood, audio genre, audio artist and audio tag. In Proceedings of the International Symposium on Music Information Retrieval (ISMIR’08) (2008), Citeseer.
[12] Petrescu, A. Spotify dataset. https://github.com/AndreiPetrescu99/SpotifyDataset.git/, 2022.
[13] Raju, A., R.S, D., Gurang, D., Kirthika, R., and Rubeena, S. Ai based music recommendation system using deep learning algorithms. IOP Conference Series: Earth and Environmental Science 785 (06 2021), 012013.
[14] Russell, J. A. A circumplex model of affect. Journal of personality and social psychology 39, 6 (1980), 1161.
[15] Tan, K., Villarino, M., and Maderazo, C. Automatic music mood recognition using russell’s twodimensional valence-arousal space from audio and lyrical data as classified using svm and na¨ıve bayes. IOP Conference Series: Materials Science and Engineering 482 (03 2019), 012019.
[16] Yang, G. Research on music content recognition and recommendation technology based on deep learning. Security and Communication Networks 2022 (03 2022), Article ID 7696840.
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Transfer of copyright agreement: When the article is accepted for publication, I, as the author and the representative of the coauthors, hereby agree to transfer to Studia Universitatis Babes-Bolyai, Series Informatica, all rights, including those pertaining to electronic forms and transmissions, under existing copyright laws, except for the following, which the authors specifically retain: the authors can use the material however they want as long as it fits the NC ND terms of the license. The authors have all rights for reuse according to the below license.
