Road Surface Classification with Images Captured From Low-cost Camera - Road Traversing Knowledge (RTK) Dataset

Thiago Rateke, Karla Aparecida Justen, Aldo von Wangenheim

Abstract


The type of road pavement directly influences the way vehicles are driven. It’s common to find papers that deal with path detection but don’t take into account major changes in road surface patterns. The quality of the road surface has a direct impact on the comfort and especially on the safety of road users. In emerging countries it’s common to find unpaved roads or roads with no maintenance. Unpaved or damaged roads also impact in higher fuel costs and vehicle maintenance. This kind of analysis can be useful for both road maintenance departments as well as for autonomous vehicle navigation systems to verify potential critical points. For the experiments accomplishment upon the surface types and quality classification, we present a new dataset, collected with a low-cost camera. This dataset has examples of good and bad asphalt (with potholes and other damages) other types of pavement and also many examples of unpaved roads (with and without potholes). We also provide several frames from our dataset manually sorted in surface types for tests accuracy verification. Our road type and quality classifier was done through a simple Convolutional Neural Network with few steps and presents promising results in different datasets.


Keywords


Road Surface Classification; Road Surface Quality Classification; Road dataset

Full Text:

PDF

References


FRISONI, R. et al. EU Road Surfaces: Economic and Safety Impact of the Lack of Regular Road Maintenance. [S.l.], 2014. Url: ⟨http://www.europarl.europa.eu/thinktank/ en/document.html?reference=IPOL STU(2014)529059⟩.

WANG, H.; REN, M.; YANG, J. Capitalizing on the boundary ratio prior for road detection. Multimedia Tools and Applications, v. 75, n. 19, p. 11999–12019, Oct 2016. Doi: ⟨https://doi.org/10.1007/s11042-016-3280-y⟩.

VALENTE, M.; STANCIULESCU, B. Real-time method for general road segmentation. In: 2017 IEEE Intelligent Vehicles Symposium (IV). [S.l.: s.n.], 2017. p. 443–447. Doi: ⟨https://doi.org/10.1109/IVS.2017.7995758⟩.

YUAN, Y.; JIANG, Z.; WANG, Q. Video-based road de- tection via online structural learning. Neurocomputing, v. 168, p. 336 – 347, 2015. Doi: ⟨http://dx.doi.org/10.1016/j.neucom. 2015.05.092⟩.

ZU, Z. et al. Real-time road detection with image tex- ture analysis-based vanishing point estimation. In: 2015 IEEE International Conference on Progress in Informatics and Computing (PIC). [S.l.: s.n.], 2015. p. 454–457. Doi: ⟨http://dx.doi.org/10.1109/PIC.2015.7489888⟩.

SHI, J. et al. A novel path segmentation method for autonomous road following. In: 2016 IEEE International Conference on Signal Processing, Communications and Com- puting (ICSPCC). [S.l.: s.n.], 2016. p. 1–6. Doi: ⟨http: //doi.acm.org/10.1109/ICSPCC.2016.7753701⟩.

RATEKE, T. et al. Passive vision region-based road de- tection: A literature review. ACM Comput. Surv., ACM, New York, NY, USA, v. 52, n. 2, p. 31:1–31:34, mar. 2019. Doi: ⟨http://doi.acm.org/10.1145/3311951⟩.

TEICHMANN, M. et al. Multinet: Real-time joint se- mantic reasoning for autonomous driving. 2018 IEEE Intel- ligent Vehicles Symposium (IV), p. 1013–1020, 2018. Doi: ⟨https://doi.org/10.1109/IVS.2018.8500504⟩.

SEEGER, C. et al. Towards road type classification with occupancy grids. In: IEEE Intelligent Vehicles Symposium 2016 Workshop: DeepDriving - Learning Representations for Intelligent Vehicles. [S.l.: s.n.], 2016. p. 1–4. Url: ⟨http: //iv2016.berkeleyvision.org/papers/seeger.pdf⟩.

CNT. Pesquisa CNT de Rodovias 2016. Relato ́rio Geren- cial. [S.l.], 2018. v. 20. Url: ⟨https://pesquisarodovias.cnt.org. br/Home⟩.

Cabral, F. S. et al. An automatic survey system for paved and unpaved road classification and road anomaly detection using smartphone sensor. In: 2018 IEEE Inter- national Conference on Service Operations and Logistics, and Informatics (SOLI). [S.l.: s.n.], 2018. p. 65–70. Doi: ⟨https://doi.org/10.1109/SOLI.2018.8476788⟩.

TARIQ, H.; MAZHAR, S.; HAMEED, H. Road quality classification for road repair authorities and regular drivers, using an on-board data logger: Poster abstract. In: Pro- ceedings of the 17th ACM/IEEE International Conference on Information Processing in Sensor Networks. Piscataway, NJ, USA: IEEE Press, 2018. (IPSN ’18), p. 142–143. Doi: ⟨https://doi.org/10.1109/IPSN.2018.00034⟩.

Kang, B.; Choi, S. Pothole detection system using 2d lidar and camera. In: 2017 Ninth International Conference on Ubiquitous and Future Networks (ICUFN). [S.l.: s.n.], 2017. p. 744–746. Doi: ⟨https://doi.org/10.1109/ICUFN.2017. 7993890⟩.

Yu, X.; Salari, E. Pavement pothole detection and sever- ity measurement using laser imaging. In: 2011 IEEE INTER- NATIONAL CONFERENCE ON ELECTRO/INFORMATION TECHNOLOGY. [S.l.: s.n.], 2011. p. 1–5. Doi: ⟨http://doi. acm.org/10.1109/EIT.2011.5978573⟩.

COMMISSION, I. E. SAFETY OF LASER PRODUCTS. Part 1: Equipment classification, requirements and user’s guide. [S.l.]: Geneva : International Electrotechnical Commis- sion, 2001, 2001.

STANDARD, A. N. American National Standard for Safe use of Lasers Outdoors. Orlando, FL, 2005.

HERGHELEGIU, P.; BURLACU, A.; CARAIMAN, S. Negative obstacle detection for wearable assistive devices for visually impaired. In: 2017 21st International Conference on System Theory, Control and Computing (ICSTCC). [S.l.: s.n.], 2017. p. 564–570. Doi: ⟨http://doi.acm.org/10.1109/ICSTCC. 2017.8107095⟩.

KARUNASEKERA, H. et al. Stereo vision based nega- tive obstacle detection. In: 2017 13th IEEE International Conference on Control Automation (ICCA). [S.l.: s.n.], 2017. p. 834–838. Doi: ⟨https://doi.org/10.1109/ICCA.2017. 8003168⟩.

MAEDA, H. et al. Road damage detection and classifi- cation using deep neural networks with smartphone images. Computer-Aided Civil and Infrastructure Engineering, v. 33, n. 12, p. 1127–1141, 2018. Doi: ⟨https://doi.org/10.1111/mice. 12387⟩.

ERIKSSON, J. et al. The pothole patrol: Using a mobile sensor network for road surface monitoring. In: Proceedings of the 6th International Conference on Mobile Systems, Ap- plications, and Services. New York, NY, USA: ACM, 2008. (MobiSys ’08), p. 29–39. Doi: ⟨http://doi.acm.org/10.1145/ 1378600.1378605⟩.

KOCH, C.; BRILAKIS, I. Pothole detection in as- phalt pavement images. Advanced Engineering Informat- ics, v. 25, n. 3, p. 507 – 515, 2011. Special Section: En- gineering informatics in port operations and logistics, doi: ⟨https://doi.org/10.1016/j.aei.2011.01.002⟩.

HUIDROM, L.; DAS, L. K.; SUD, S. Method for au- tomated assessment of potholes, cracks and patches from road surface video clips. Procedia - Social and Behavioral Sciences, v. 104, p. 312 – 321, 2013. 2nd Conference of Transportation Research Group of India (2nd CTRG), doi: ⟨https://doi.org/10.1016/j.sbspro.2013.11.124⟩.

TEDESCHI, A.; BENEDETTO, F. A real-time automatic pavement crack and pothole recognition system for mobile android-based devices. Advanced Engineering Informatics, v. 32, p. 11 – 25, 2017. Doi: ⟨https://doi.org/10.1016/j.aei. 2016.12.004⟩.

BANHARNSAKUN, A. Hybrid abc-ann for pave- ment surface distress detection and classification. Interna- tional Journal of Machine Learning and Cybernetics, v. 8, n. 2, p. 699–710, Apr 2017. Doi: ⟨https://doi.org/10.1007/ s13042-015-0471-1⟩.

WANG, X. et al. Facial expression recognition with deep learning. In: Proceedings of the 10th International Conference on Internet Multimedia Computing and Service. New York, NY, USA: ACM, 2018. (ICIMCS ’18), p. 10:1–10:4. Doi: ⟨http://doi.acm.org/10.1145/3240876.3240908⟩.

Vo, A. T.; Tran, H. S.; Le, T. H. Advertisement im- age classification using convolutional neural network. In: 2017 9th International Conference on Knowledge and Sys- tems Engineering (KSE). [S.l.: s.n.], 2017. p. 197–202. Doi: ⟨https://doi.org/10.1109/KSE.2017.8119458⟩.

Li, Y. et al. Sleep posture classification with multi- stream cnn using vertical distance map. In: 2018 Interna- tional Workshop on Advanced Image Technology (IWAIT). [S.l.: s.n.], 2018. p. 1–4. Doi: ⟨https://doi.org/10.1109/IWAIT. 2018.8369761⟩.

SACHAN, A. Tensorflow Tutorial 2: im- age classifier using convolutional neural network. 2017. Url: ⟨https://cv-tricks.com/tensorflow-tutorial/ training-convolutional-neural-network-for-image-classification/ ⟩.

GEIGER, A. et al. Vision meets robotics: The kitti dataset. Int. J. Rob. Res., Sage Publications, Inc., Thousand Oaks, CA, USA, v. 32, n. 11, p. 1231–1237, sep 2013. Doi: ⟨http://dx.doi.org/10.1177/0278364913491297⟩.

SHINZATO, P. Y. et al. Carina dataset: An emerging- country urban scenario benchmark for road detection systems. In: 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC). [S.l.: s.n.], 2016. p. 41–46. Doi: ⟨http://dx.doi.org/10.1109/ITSC.2016.7795529⟩.

BROSTOW, G. J.; FAUQUEUR, J.; CIPOLLA, R. Se- mantic object classes in video: A high-definition ground truth database. Pattern Recognition Letters, v. 30, n. 2, p. 88 – 97, 2009. Doi: ⟨https://doi.org/10.1016/j.patrec.2008.04.005⟩.

Cordts, M. et al. The cityscapes dataset for semantic urban scene understanding. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [S.l.: s.n.], 2016. p. 3213–3223. Doi: ⟨https://doi.org/10.1109/CVPR. 2016.350⟩.

ZANIN, M. et al. diplodoc road stereo se- quence. 2013. Url: ⟨https://tev.fbk.eu/databases/ diplodoc-road-stereo-sequence⟩.

SHANG, E. et al. Offroadscene: An open database for unstructured road detection algorithms. In: 2013 International Conference on Computer Sciences and Applications. [S.l.: s.n.], 2013. p. 779–783. Doi: ⟨http://dx.doi.org/10.1109/CSA. 2013.186⟩.




DOI: https://doi.org/10.22456/2175-2745.91522

Copyright (c) 2019 Thiago Rateke, Karla Aparecida Justen, Aldo von Wangenheim

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Indexing databases:
        

Acknowledgments: