{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:17:05Z","timestamp":1767831425656,"version":"3.49.0"},"reference-count":31,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Road surface properties have a major impact on pavement\u2019s life service conditions. Nowadays, contactless techniques are widely used to monitor road surfaces due to their portability and high precision. Among the different possibilities, laser profilometers are widely used, even though they have two major drawbacks: spatial information is missed and the cost of the equipment is considerable. The scope of this work is to show the methodology used to develop a fast and low-cost system using images taken with a commercial camera to recover the height information of the road surface using Convolutional Neural Networks. Hence, the dataset was created ad hoc. Based on photometric theory, a closed black-box with four light sources positioned around the surface sample was built. The surface was provided with markers in order to link the ground truth measurements carried out with a laser profilometer and their corresponding intensity values. The proposed network was trained, validated and tested on the created dataset. Three loss functions where studied. The results showed the Binary Cross Entropy loss to be the most performing and the best overall on the reconstruction task. The methodology described in this study shows the feasibility of a low-cost system using commercial cameras based on Artificial Intelligence.<\/jats:p>","DOI":"10.3390\/s22176603","type":"journal-article","created":{"date-parts":[[2022,9,2]],"date-time":"2022-09-02T00:19:01Z","timestamp":1662077941000},"page":"6603","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Novel Methodology to Recover Road Surface Height Maps from Illuminated Scene through Convolutional Neural Networks"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0271-5475","authenticated-orcid":false,"given":"Gonzalo","family":"de Le\u00f3n","sequence":"first","affiliation":[{"name":"Department of Civil and Industrial Engineering (DICI), Engineering School, University of Pisa, Largo Lucio Lazzarino 1, 56126 Pisa, Italy"},{"name":"Joint Research Unit in Environmental Acoustics (UMRAE), Department of Planning, Mobility and Environment (AME), Universit\u00e9 Gustave Eiffel, CEREMA, F-44344 Bouguenais, France"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7182-909X","authenticated-orcid":false,"given":"Julien","family":"Cesbron","sequence":"additional","affiliation":[{"name":"Joint Research Unit in Environmental Acoustics (UMRAE), Department of Planning, Mobility and Environment (AME), Universit\u00e9 Gustave Eiffel, CEREMA, F-44344 Bouguenais, France"}]},{"given":"Philippe","family":"Klein","sequence":"additional","affiliation":[{"name":"Joint Research Unit in Environmental Acoustics (UMRAE), Department of Planning, Mobility and Environment (AME), Universit\u00e9 Gustave Eiffel-Lyon, CEREMA, F-69675 Lyon, France"}]},{"given":"Pietro","family":"Leandri","sequence":"additional","affiliation":[{"name":"Department of Civil and Industrial Engineering (DICI), Engineering School, University of Pisa, Largo Lucio Lazzarino 1, 56126 Pisa, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7354-8534","authenticated-orcid":false,"given":"Massimo","family":"Losa","sequence":"additional","affiliation":[{"name":"Department of Civil and Industrial Engineering (DICI), Engineering School, University of Pisa, Largo Lucio Lazzarino 1, 56126 Pisa, Italy"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"04015020","DOI":"10.1061\/(ASCE)TE.1943-5436.0000785","article-title":"Effects of pavement surface conditions on traffic crash severity","volume":"141","author":"Lee","year":"2015","journal-title":"J. Transp. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"\u017duraulis, V., Sivilevi\u010dius, H., \u0160abanovi\u010d, E., Ivanov, V., and Skrickij, V. (2021). Variability of gravel pavement roughness: An analysis of the impact on vehicle dynamic response and driving comfort. Appl. Sci., 11.","DOI":"10.20944\/preprints202107.0370.v1"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"S91","DOI":"10.1080\/14680629.2020.1735493","article-title":"Evaluation of tyre\/road noise and texture interaction on rubberised and conventional pavements using CPX and profiling measurements","volume":"21","author":"Teti","year":"2020","journal-title":"Road Mater. Pavement Des."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"124235","DOI":"10.1016\/j.conbuildmat.2021.124235","article-title":"Automated and contactless approaches for pavement surface texture measurement and analysis\u2014A review","volume":"301","author":"Jain","year":"2021","journal-title":"Constr. Build. Mater."},{"key":"ref_5","first-page":"3823","article-title":"A 3D envelopment procedure for tyre belt radiated noise level prediction","volume":"Volume 253","author":"Klein","year":"2016","journal-title":"Proceedings of the INTER-NOISE and NOISE-CON Congress and Conference Proceedings"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Surov\u1ef3, P., Yoshimoto, A., and Panagiotidis, D. (2016). Accuracy of reconstruction of the tree stem surface using terrestrial close-range photogrammetry. Remote Sens., 8.","DOI":"10.3390\/rs8020123"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1088\/0143-0807\/19\/2\/002","article-title":"The use of commercial CCD cameras as linear detectors in the physics undergraduate teaching laboratory","volume":"19","author":"Elliott","year":"1998","journal-title":"Eur. J. Phys."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.ymssp.2016.02.011","article-title":"Photogrammetry and optical methods in structural dynamics\u2014A review","volume":"86","author":"Baqersad","year":"2017","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_9","unstructured":"Xiong, Y., and Shafer, S.A. (1993, January 15\u201317). Depth from focusing and defocusing. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, New York, NY, USA."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1117\/12.956740","article-title":"Photometric stereo: A reflectance map technique for determining surface orientation from image intensity","volume":"Volume 155","author":"Woodham","year":"1979","journal-title":"Proceedings of the Image Understanding Systems and Industrial Applications I"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.patrec.2013.12.013","article-title":"Error analysis of photometric stereo with colour lights","volume":"48","author":"Klaudiny","year":"2014","journal-title":"Pattern Recognit. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1561\/0600000065","article-title":"A survey of photometric stereo techniques","volume":"9","author":"Ackermann","year":"2015","journal-title":"Found. Trends\u00ae Comput. Graph. Vis."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1061\/(ASCE)0733-947X(2007)133:7(433)","article-title":"Mean profile depth of pavement surface macrotexture using photometric stereo techniques","volume":"133","author":"Gendy","year":"2007","journal-title":"J. Transp. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/j.measurement.2018.05.109","article-title":"Optimization of the photometric stereo method for measuring pavement texture properties","volume":"127","author":"Alamdarlo","year":"2018","journal-title":"Measurement"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1007\/BF02478259","article-title":"A logical calculus of the ideas immanent in nervous activity","volume":"5","author":"McCulloch","year":"1943","journal-title":"Bull. Math. Biophys."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1126\/science.aaa8415","article-title":"Machine learning: Trends, perspectives, and prospects","volume":"349","author":"Jordan","year":"2015","journal-title":"Science"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","article-title":"Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions","volume":"8","author":"Alzubaidi","year":"2021","journal-title":"J. Big Data"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Fukushima, K., and Miyake, S. (1982). Neocognitron: A self-organizing neural network model for a mechanism of visual pattern recognition. Competition and Cooperation in Neural Nets, Springer.","DOI":"10.1007\/978-3-642-46466-9_18"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, J., Robles-Kelly, A., You, S., and Matsushita, Y. (2019, January 15\u201320). Learning to minify photometric stereo. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00775"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Ikehata, S. (2018, January 8\u201314). CNN-PS: CNN-based photometric stereo for general non-convex surfaces. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01267-0_1"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1021\/ci0342472","article-title":"The problem of overfitting","volume":"44","author":"Hawkins","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"ref_22","unstructured":"(2018). Standard Test Method for Measuring the Longitudinal Profile of Traveled Surfaces with an Accelerometer Established Inertial Profiling Reference (Standard No. ASTM E950\/E950m-09)."},{"key":"ref_23","first-page":"444","article-title":"Decentering distortion of lenses","volume":"32","author":"Brown","year":"1966","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_24","unstructured":"(2019). Characterization of Pavement Texture by Use of Surface Profiles\u2014Part 1: Determination of Mean Profile Depth (Standard No. ISO 13473-1:2019)."},{"key":"ref_25","unstructured":"Hamet, J.F., and Klein, P. (2005). Use of Road Texture Profiles as Input Data for Tyre\/Road Models. 2D Profiles Pre-Processing Procedures for Smoothing and Peaks Removal, INRETS. Technical Report, SILVIA-INRETS-019-WP2."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.procir.2021.05.057","article-title":"Fast development cycle for the design of industrial grippers","volume":"100","author":"Jorg","year":"2021","journal-title":"Procedia CIRP"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"013002","DOI":"10.1117\/1.3533326","article-title":"Calibrating light sources by using a planar mirror","volume":"20","author":"Shen","year":"2011","journal-title":"J. Electron. Imaging"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.1109\/34.888718","article-title":"A flexible new technique for camera calibration","volume":"22","author":"Zhang","year":"2000","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.neucom.2022.04.127","article-title":"Recent Advances on Loss Functions in Deep Learning for Computer Vision","volume":"497","author":"Tian","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_30","unstructured":"Creswell, A., Arulkumaran, K., and Bharath, A.A. (2017). On denoising autoencoders trained to minimise binary cross-entropy. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Leach, R. (2013). Characterisation of Areal Surface Texture, Springer.","DOI":"10.1007\/978-3-642-36458-7"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6603\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:21:40Z","timestamp":1760142100000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6603"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":31,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["s22176603"],"URL":"https:\/\/doi.org\/10.3390\/s22176603","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,1]]}}}