{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:41:22Z","timestamp":1774629682922,"version":"3.50.1"},"reference-count":47,"publisher":"MDPI AG","issue":"15","license":[{"start":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T00:00:00Z","timestamp":1722384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"AEI","award":["PID2020-116448GB-I00"],"award-info":[{"award-number":["PID2020-116448GB-I00"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Popular geo-computer vision works make use of aerial imagery, with sizes ranging from 64 \u00d7 64 to 1024 \u00d7 1024 pixels without any overlap, although the learning process of deep learning models can be affected by the reduced semantic context or the lack of information near the image boundaries. In this work, the impact of three tile sizes (256 \u00d7 256, 512 \u00d7 512, and 1024 \u00d7 1024 pixels) and two overlap levels (no overlap and 12.5% overlap) on the performance of road classification models was statistically evaluated. For this, two convolutional neural networks used in various tasks of geospatial object extraction were trained (using the same hyperparameters) on a large dataset (containing aerial image data covering 8650 km2 of the Spanish territory that was labelled with binary road information) under twelve different scenarios, with each scenario featuring a different combination of tile size and overlap. To assess their generalisation capacity, the performance of all resulting models was evaluated on data from novel areas covering approximately 825 km2. The performance metrics obtained were analysed using appropriate descriptive and inferential statistical techniques to evaluate the impact of distinct levels of the fixed factors (tile size, tile overlap, and neural network architecture) on them. Statistical tests were applied to study the main and interaction effects of the fixed factors on the performance. A significance level of 0.05 was applied to all the null hypothesis tests. The results were highly significant for the main effects (p-values lower than 0.001), while the two-way and three-way interaction effects among them had different levels of significance. The results indicate that the training of road classification models on images with a higher tile size (more semantic context) and a higher amount of tile overlap (additional border context and continuity) significantly impacts their performance. The best model was trained on a dataset featuring tiles with a size of 1024 \u00d7 1024 pixels and a 12.5% overlap, and achieved a loss value of 0.0984, an F1 score of 0.8728, and an ROC-AUC score of 0.9766, together with an error rate of 3.5% on the test set.<\/jats:p>","DOI":"10.3390\/rs16152818","type":"journal-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T17:16:49Z","timestamp":1722446209000},"page":"2818","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Impact of Tile Size and Tile Overlap on the Prediction Performance of Convolutional Neural Networks Trained for Road Classification"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7713-7238","authenticated-orcid":false,"given":"Calimanut-Ionut","family":"Cira","sequence":"first","affiliation":[{"name":"Departamento de Ingenier\u00eda Topogr\u00e1fica y Cartograf\u00eda, E.T.S.I. en Topograf\u00eda, Geodesia y Cartograf\u00eda, Universidad Polit\u00e9cnica de Madrid, C\/Mercator 2, 28031 Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2307-8639","authenticated-orcid":false,"given":"Miguel-\u00c1ngel","family":"Manso-Callejo","sequence":"additional","affiliation":[{"name":"Departamento de Ingenier\u00eda Topogr\u00e1fica y Cartograf\u00eda, E.T.S.I. en Topograf\u00eda, Geodesia y Cartograf\u00eda, Universidad Polit\u00e9cnica de Madrid, C\/Mercator 2, 28031 Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7321-4590","authenticated-orcid":false,"given":"Naoto","family":"Yokoya","sequence":"additional","affiliation":[{"name":"Department of Complexity Science and Engineering, Graduate School of Frontier Sciences, University of Tokyo, 5-1-5 Kashiwanoha, Kashiwa-shi, Chiba 277-8561, Japan"},{"name":"Geoinformatics Team, RIKEN Center for Advanced Intelligence Project (AIP), Mitsui Building 15th Floor, 1-4-1 Nihonbashi, Ch\u016b\u014d-ku, Tokyo 103-0027, Japan"}]},{"given":"Tudor","family":"S\u0103l\u0103gean","sequence":"additional","affiliation":[{"name":"Department of Land Measurements and Exact Sciences, Faculty of Forestry and Cadastre, University of Agricultural Sciences and Veterinary Medicine Cluj-Napoca, 3-5 M\u0103n\u0103\u0219tur Street, 400372 Cluj-Napoca, Romania"},{"name":"Doctoral School, Technical University of Civil Engineering Bucharest, 122-124 Lacul Tei Blvd., Sector 2, 020396 Bucharest, Romania"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4521-5403","authenticated-orcid":false,"given":"Ana-Cornelia","family":"Badea","sequence":"additional","affiliation":[{"name":"Doctoral School, Technical University of Civil Engineering Bucharest, 122-124 Lacul Tei Blvd., Sector 2, 020396 Bucharest, Romania"},{"name":"Department of Topography and Cadastre, Faculty of Geodesy, Technical University of Civil Engineering Bucharest, 122-124 Lacul Tei Blvd., Sector 2, 020396 Bucharest, Romania"}]}],"member":"1968","published-online":{"date-parts":[[2024,7,31]]},"reference":[{"key":"ref_1","unstructured":"Rigollet, P. (2015). 18.657: Mathematics of Machine Learning, Massachusetts Institute of Technology. Available online: https:\/\/ocw.mit.edu\/courses\/18-657-mathematics-of-machine-learning-fall-2015\/."},{"key":"ref_2","unstructured":"Cira, C.-I. (2022). Contribution to Object Extraction in Cartography: A Novel Deep Learning-Based Solution to Recognise, Segment and Post-Process the Road Transport Network as a Continuous Geospatial Element in High-Resolution Aerial Orthoimagery. [Ph.D. Thesis, Universidad Polit\u00e9cnica de Madrid]. Available online: http:\/\/oa.upm.es\/70152."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet Large Scale Visual Recognition Challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"Int. J. Comput. Vis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1007\/978-3-030-32475-9_14","article-title":"Evaluation of Transfer Learning Techniques with Convolutional Neural Networks (CNNs) to Detect the Existence of Roads in High-Resolution Aerial Imagery","volume":"Volume 1051","author":"Florez","year":"2019","journal-title":"Applied Informatics"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"108316","DOI":"10.1016\/j.dib.2022.108316","article-title":"Dataset Containing Orthoimages Tagged with Road Information Covering Approximately 8650 Km2 of the Spanish Territory (SROADEX)","volume":"42","author":"Cira","year":"2022","journal-title":"Data Brief"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Reina, G.A., Panchumarthy, R., Thakur, S.P., Bastidas, A., and Bakas, S. (2020). Systematic Evaluation of Image Tiling Adverse Effects on Deep Learning Semantic Segmentation. Front. Neurosci., 14.","DOI":"10.3389\/fnins.2020.00065"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"100850","DOI":"10.1016\/j.imu.2022.100850","article-title":"Model Architecture and Tile Size Selection for Convolutional Neural Network Training for Non-Small Cell Lung Cancer Detection on Whole Slide Images","volume":"28","author":"Lee","year":"2022","journal-title":"Inform. Med. Unlocked"},{"key":"ref_8","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings, San Diego, CA, USA."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cira, C.-I., Alcarria, R., Manso-Callejo, M.-\u00c1., and Serradilla, F. (2020). A Deep Learning-Based Solution for Large-Scale Extraction of the Secondary Road Network from High-Resolution Aerial Orthoimagery. Appl. Sci., 10.","DOI":"10.3390\/app10207272"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Cira, C.-I., Manso-Callejo, M.-\u00c1., Alcarria, R., Bordel S\u00e1nchez, B.B., and Gonz\u00e1lez Matesanz, J.G. (2023). State-Level Mapping of the Road Transport Network from Aerial Orthophotography: An End-to-End Road Extraction Solution Based on Deep Learning Models Trained for Recognition, Semantic Segmentation and Post-Processing with Conditional Generative Learning. Remote Sens., 15.","DOI":"10.3390\/rs15082099"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Unel, F.O., Ozkalayci, B.O., and Cigla, C. (2019, January 16\u201320). The Power of Tiling for Small Object Detection. Proceedings of the 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA.","DOI":"10.1109\/CVPRW.2019.00084"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Akyon, F.C., Onur Altinuc, S., and Temizel, A. (2022, January 16). Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection. Proceedings of the 2022 IEEE International Conference on Image Processing (ICIP), Bordeaux, France.","DOI":"10.1109\/ICIP46576.2022.9897990"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.media.2019.07.003","article-title":"Holistic Decomposition Convolution for Effective Semantic Segmentation of Medical Volume Images","volume":"57","author":"Zeng","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_14","first-page":"35","article-title":"Overlap Training to Mitigate Inconsistencies Caused by Image Tiling in CNNs","volume":"Volume 12498","author":"Bramer","year":"2020","journal-title":"Artificial Intelligence XXXVII"},{"key":"ref_15","unstructured":"Abrahams, E., Snow, T., Siegfried, M.R., and P\u00e9rez, F. (2024). A Concise Tiling Strategy for Preserving Spatial Context in Earth Observation Imagery. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Chun, C., and Ryu, S.-K. (2019). Road Surface Damage Detection Using Fully Convolutional Neural Networks and Semi-Supervised Learning. Sensors, 19.","DOI":"10.3390\/s19245501"},{"key":"ref_17","unstructured":"Maeda, H., Sekimoto, Y., Seto, T., Kashiyama, T., and Omata, H. (2018). Road Damage Detection Using Deep Neural Networks with Images Captured Through a Smartphone. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liang, H., Lee, S.-C., and Seo, S. (2022). Automatic Recognition of Road Damage Based on Lightweight Attentional Convolutional Neural Network. Sensors, 22.","DOI":"10.3390\/s22249599"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Rajendran, T., Mohamed Imtiaz, N., Jagadeesh, K., and Abdul Kareem, D. (2022, January 20\u201322). Road Obstacles Detection Using Convolution Neural Network and Report Using IoT. Proceedings of the 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India.","DOI":"10.1109\/ICSSIT53264.2022.9716337"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1267","DOI":"10.1007\/s12205-024-1066-8","article-title":"Benchmark Study on a Novel Online Dataset for Standard Evaluation of Deep Learning-Based Pavement Cracks Classification Models","volume":"28","author":"Zhang","year":"2024","journal-title":"KSCE J. Civ. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"105098","DOI":"10.1016\/j.autcon.2023.105098","article-title":"Extended Efficient Convolutional Neural Network for Concrete Crack Detection with Illustrated Merits","volume":"156","author":"Fu","year":"2023","journal-title":"Autom. Constr."},{"key":"ref_22","first-page":"e02378","article-title":"Deep Learning Techniques for Multi-Class Classification of Asphalt Damage Based on Hamburg-Wheel Tracking Test Results","volume":"19","year":"2023","journal-title":"Case Stud. Constr. Mater."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, L., Peng, B., Tang, D., and Li, Y. (2022). Road Extraction Based on Improved Convolutional Neural Networks with Satellite Images. Appl. Sci., 12.","DOI":"10.3390\/app122110800"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1007\/s12524-022-01532-9","article-title":"Improved Road Detection Algorithm Based on Fusion of Deep Convolutional Neural Networks and Random Forest Classifier on VHR Remotely-Sensed Images","volume":"50","author":"Fakhri","year":"2022","journal-title":"J. Indian. Soc. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1007\/978-3-030-34110-7_10","article-title":"Road Detection of Remote Sensing Image Based on Convolutional Neural Network","volume":"Volume 11902","author":"Zhao","year":"2019","journal-title":"Image and Graphics"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1186\/s13640-019-0426-7","article-title":"Research on Road Extraction of Remote Sensing Image Based on Convolutional Neural Network","volume":"2019","author":"Jiang","year":"2019","journal-title":"J. Image Video Proc."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Higuchi, R., and Fujimoto, Y. (2020, January 14). Road and Intersection Detection Using Convolutional Neural Network. Proceedings of the 2020 IEEE 16th International Workshop on Advanced Motion Control (AMC), Kristiansand, Norway.","DOI":"10.1109\/AMC44022.2020.9244357"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Eltaher, F., Miralles-Pechu\u00e1n, L., Courtney, J., and Mckeever, S. (2023, January 27\u201331). Detecting Road Intersections from Satellite Images Using Convolutional Neural Networks. Proceedings of the 38th ACM\/SIGAPP Symposium on Applied Computing, Tallinn, Estonia.","DOI":"10.1145\/3555776.3578728"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/s11370-020-00343-6","article-title":"RCNet: Road Classification Convolutional Neural Networks for Intelligent Vehicle System","volume":"14","author":"Dewangan","year":"2021","journal-title":"Intel. Serv. Robot."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"109597","DOI":"10.1016\/j.apacoust.2023.109597","article-title":"Road Type Classification Using Deep Learning for Tire-Pavement Interaction Noise Data in Autonomous Driving Vehicle","volume":"212","author":"Lee","year":"2023","journal-title":"Appl. Acoust."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Cira, C.I., Alcarria, R., Manso-Callejo, M.\u00c1., and Serradilla, F. (2019). A Deep Convolutional Neural Network to Detect the Existence of Geospatial Elements in High-Resolution Aerial Imagery. Proceedings, 19.","DOI":"10.3390\/proceedings2019019017"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Cira, C.-I., D\u00edaz-\u00c1lvarez, A., Serradilla, F., and Manso-Callejo, M.-\u00c1. (2023). Convolutional Neural Networks Adapted for Regression Tasks: Predicting the Orientation of Straight Arrows on Marked Road Pavement Using Deep Learning and Rectified Orthophotography. Electronics, 12.","DOI":"10.3390\/electronics12183980"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Cira, C.-I., Alcarria, R., Manso-Callejo, M.-\u00c1., and Serradilla, F. (2020). A Framework Based on Nesting of Convolutional Neural Networks to Classify Secondary Roads in High Resolution Aerial Orthoimages. Remote Sens., 12.","DOI":"10.3390\/rs12050765"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"de la Fuente Castillo, V., D\u00edaz-\u00c1lvarez, A., Manso-Callejo, M.-\u00c1., and Serradilla Garc\u00eda, F. (2020). Grammar Guided Genetic Programming for Network Architecture Search and Road Detection on Aerial Orthophotography. Appl. Sci., 10.","DOI":"10.20944\/preprints202005.0002.v1"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Alshaikhli, T., Liu, W., and Maruyama, Y. (2019). Automated Method of Road Extraction from Aerial Images Using a Deep Convolutional Neural Network. Appl. Sci., 9.","DOI":"10.3390\/app9224825"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, X., Sun, Y., and Zhang, P. (2018). Road Centerline Extraction from Very-High-Resolution Aerial Image and LiDAR Data Based on Road Connectivity. Remote Sens., 10.","DOI":"10.3390\/rs10081284"},{"key":"ref_37","unstructured":"(2024, March 10). Centro Nacional de Informaci\u00f3n Geogr\u00e1fica, Instituto Geogr\u00e1fico Nacional Plan Nacional de Ortofotograf\u00eda A\u00e9rea. Available online: https:\/\/pnoa.ign.es\/."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Fischer, H. (2011). A History of the Central Limit Theorem: From Classical to Modern Probability Theory, Springer.","DOI":"10.1007\/978-0-387-87857-7"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"7968","DOI":"10.1109\/JSTARS.2021.3101934","article-title":"First Dataset of Wind Turbine Data Created at National Level with Deep Learning Techniques from Aerial Orthophotographs with a Spatial Resolution of 0.5 m\/Pixel","volume":"14","author":"Cira","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_40","first-page":"103563","article-title":"Assessment of the Large-Scale Extraction of Photovoltaic (PV) Panels with a Workflow Based on Artificial Neural Networks and Algorithmic Postprocessing of Vectorization Results","volume":"125","author":"Cira","year":"2023","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_41","unstructured":"Agarap, A.F. (2018). Deep Learning Using Rectified Linear Units (ReLU). arXiv."},{"key":"ref_42","unstructured":"Kingma, D.P., and Ba, J. (2015, January 7\u20139). Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings, San Diego, CA, USA."},{"key":"ref_43","unstructured":"Chollet, F. (2020, May 14). Keras. Available online: https:\/\/github.com\/fchollet\/keras."},{"key":"ref_44","unstructured":"Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016, January 2\u20134). TensorFlow: A System for Large-Scale Machine Learning. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation, Savannah, GA, USA."},{"key":"ref_45","unstructured":"Manso Callejo, M.A., Cira, C.-I., Iturrioz, T., and Serradilla Garcia, F. (2024, March 20). Train and Evaluation Code, Road Classification Models and Test Set of the Paper \u201cImpact of Image Resolution and Image Overlap on the Prediction Performance of Convolutional Neural Networks Trained for Road Classification\u201d. Available online: https:\/\/zenodo.org\/records\/10835684."},{"key":"ref_46","unstructured":"(2024, March 18). IBM Corp IBM SPSS Statistics for Macintosh. Available online: https:\/\/www.ibm.com\/support\/pages\/ibm-spss-statistics-29-documentation."},{"key":"ref_47","unstructured":"Lee, D.D., Sugiyama, M., Luxburg, U., Guyon, I., and Garnett, R. (2016, January 5\u201310). Understanding the Effective Receptive Field in Deep Convolutional Neural Networks. Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/15\/2818\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T15:27:26Z","timestamp":1760110046000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/16\/15\/2818"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,31]]},"references-count":47,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["rs16152818"],"URL":"https:\/\/doi.org\/10.3390\/rs16152818","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,31]]}}}