{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:04:30Z","timestamp":1787029470879,"version":"3.56.0"},"reference-count":57,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2017,2,24]],"date-time":"2017-02-24T00:00:00Z","timestamp":1487894400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-13-JS02-0005-01 (Asterix project)"],"award-info":[{"award-number":["ANR-13-JS02-0005-01 (Asterix project)"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>The geographic object-based image analysis (GEOBIA) framework has gained increasing interest for the last decade. One of its key advantages is the hierarchical representation of an image, where object topological features can be extracted and modeled in the form of structured data. We thus propose to use a structured kernel relying on the concept of bag of subpaths to directly cope with such features. The kernel can be approximated using random Fourier features, allowing it to be applied on a large structure size (the number of objects in the structured data) and large volumes of data (the number of pixels or regions for training). With the so-called scalable bag of subpaths kernel (SBoSK), we also introduce a novel multi-source classification approach performing machine learning directly on a hierarchical image representation built from two images at different resolutions under the GEOBIA framework. Experiments run on an urban classification task show that the proposed approach run on a single image improves the classification overall accuracy in comparison with conventional approaches from 2% to 5% depending on the training set size and that fusing two images allows a supplementary 4% accuracy gain. Additional evaluations on public available large-scale datasets illustrate further the potential of SBoSK, with overall accuracy rates improvement ranging from 1% to 11% depending on the considered setup.<\/jats:p>","DOI":"10.3390\/rs9030196","type":"journal-article","created":{"date-parts":[[2017,2,24]],"date-time":"2017-02-24T11:19:50Z","timestamp":1487935190000},"page":"196","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Scalable Bag of Subpaths Kernel for Learning on Hierarchical Image Representations and Multi-Source Remote Sensing Data Classification"],"prefix":"10.3390","volume":"9","author":[{"given":"Yanwei","family":"Cui","sequence":"first","affiliation":[{"name":"University Bretagne-Sud, UMR 6074, IRISA, F-56000 Vannes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laetitia","family":"Chapel","sequence":"additional","affiliation":[{"name":"University Bretagne-Sud, UMR 6074, IRISA, F-56000 Vannes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2384-8202","authenticated-orcid":false,"given":"S\u00e9bastien","family":"Lef\u00e8vre","sequence":"additional","affiliation":[{"name":"University Bretagne-Sud, UMR 6074, IRISA, F-56000 Vannes, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2017,2,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.isprsjprs.2013.09.014","article-title":"Geographic Object-Based Image Analysis\u2014Towards a new paradigm","volume":"87","author":"Blaschke","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.isprsjprs.2009.06.004","article-title":"Object based image analysis for remote sensing","volume":"65","author":"Blaschke","year":"2010","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2587","DOI":"10.1109\/TGRS.2006.875360","article-title":"A Multilevel Context-Based System for Classification of Very High Spatial Resolution Images","volume":"44","author":"Bruzzone","year":"2006","journal-title":"IEEE Trans. Geosci. Remote Sens"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2354","DOI":"10.1109\/TGRS.2003.815972","article-title":"A combined fuzzy pixel-based and object-based approach for classification of high-resolution multispectral data over urban areas","volume":"41","author":"Shackelford","year":"2003","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lef\u00e8vre, S., Chapel, L., and Merciol, F. (2014, January 24\u201327). Hyperspectral image classification from multiscale description with constrained connectivity and metric learning. Proceedings of the 6th International Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Lausanne, Switzerland.","DOI":"10.1109\/WHISPERS.2014.8077559"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1109\/TGRS.2014.2351395","article-title":"Pyramid of spatial relatons for scene-level land use classification","volume":"53","author":"Chen","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.isprsjprs.2016.03.004","article-title":"A spectral-structural bag-of-features scene classifier for very high spatial resolution remote sensing imagery","volume":"116","author":"Zhao","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1016\/j.isprsjprs.2008.01.007","article-title":"A framework of region-based spatial relations for non-overlapping features and its application in object based image analysis","volume":"63","author":"Liu","year":"2008","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1080\/17538947.2014.925517","article-title":"Spatial relationship-assisted classification from high-resolution remote sensing imagery","volume":"8","author":"Qiao","year":"2015","journal-title":"Int. J. Digit. Earth"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1109\/LGRS.2009.2014083","article-title":"Image mining using directional spatial constraints","volume":"7","author":"Aksoy","year":"2010","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Cui, Y., Chapel, L., and Lef\u00e8vre, S. (2016, January 21\u201324). Combining multiscale features for classification of hyperspectral images: A sequence based kernel approach. Proceedings of the 8th IEEE International Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Los Angeles, LA, USA.","DOI":"10.1109\/WHISPERS.2016.8071671"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Cui, Y., Chapel, L., and Lef\u00e8vre, S. (2015, January 13\u201315). A subpath kernel for learning hierarchical image representations. Proceedings of the International Workshop on Graph-Based Representations in Pattern Recognition, Beijing, China.","DOI":"10.1007\/978-3-319-18224-7_4"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1560","DOI":"10.1109\/JPROC.2015.2449668","article-title":"Multimodal classification of remote sensing images: A review and future directions","volume":"103","author":"Tuia","year":"2015","journal-title":"Proc. IEEE"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.1016\/j.asr.2008.11.008","article-title":"Hierarchical object oriented classification using very high resolution imagery and LIDAR data over urban areas","volume":"43","author":"Chen","year":"2009","journal-title":"Adv. Space Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1080\/19479830903561035","article-title":"Multi-source remote sensing data fusion: Status and trends","volume":"1","author":"Zhang","year":"2010","journal-title":"Int. J. Image Data Fusion"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Cui, Y., Lef\u00e8vre, S., Chapel, L., and Puissant, A. (2016, January 14\u201316). Combining Multiple Resolutions into Hierarchical Representations for kernel-based Image Classification. Proceedings of the International Conference on Geographic Object-Based Image Analysis, Enschede, The Netherlands.","DOI":"10.3990\/2.372"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1561\/0600000033","article-title":"Structured learning and prediction in computer vision","volume":"6","author":"Nowozin","year":"2011","journal-title":"Found. Trends Comput. Graph. Vis."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Volpi, M., and Ferrari, V. (2015, January 7\u201312). Semantic segmentation of urban scenes by learning local class interactions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Boston, MA, USA.","DOI":"10.1109\/CVPRW.2015.7301377"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4534","DOI":"10.1109\/TGRS.2012.2192741","article-title":"An overview and comparison of smooth labeling methods for land-cover classification","volume":"50","author":"Schindler","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2405","DOI":"10.1109\/JSTARS.2015.2407493","article-title":"Dynamic ensemble selection approach for hyperspectral image classification with joint spectral and spatial information","volume":"8","author":"Damodaran","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1016\/j.patcog.2011.03.035","article-title":"A spatial\u2013spectral kernel-based approach for the classification of remote-sensing images","volume":"45","author":"Fauvel","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"5975","DOI":"10.1080\/01431161.2010.512425","article-title":"Extended profiles with morphological attribute filters for the analysis of hyperspectral data","volume":"31","author":"Benediktsson","year":"2010","journal-title":"Int. J. Remote Sens."},{"key":"ref_23","unstructured":"Eisank, C., Dr\u0103gu\u0163, L., G\u00f6tz, J., and Blaschke, T. (July, January 29). Developing a semantic model of glacial landforms for object-based terrain classification\u2014The example of glacial cirques. Proceedings of the Geographic Object-Based Image Analysis (GEOBIA), Ghent, Belgium."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"491","DOI":"10.14358\/PERS.81.6.491","article-title":"A fuzzy spatial reasoner for multi-scale GEOBIA ontologies","volume":"81","author":"Argyridis","year":"2015","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_25","unstructured":"Yang, J., Yu, K., Gong, Y., and Huang, T. (2009, January 20\u201326). Linear spatial pyramid matching using sparse coding for image classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Yang, Y., and Newsam, S. (2010, January 2\u20135). Bag-of-visual-words and spatial extensions for land-use classification. Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems, San Jose, CA, USA.","DOI":"10.1145\/1869790.1869829"},{"key":"ref_27","first-page":"2211","article-title":"Multiple kernel learning algorithms","volume":"12","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1016\/j.isprsjprs.2016.10.011","article-title":"A robust multi-kernel change detection framework for detecting leaf beetle defoliation using Landsat 7 ETM+ data","volume":"122","author":"Anees","year":"2016","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1109\/LGRS.2005.857031","article-title":"Composite kernels for hyperspectral image classification","volume":"3","year":"2006","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1109\/LGRS.2009.2015341","article-title":"Multisource composite kernels for urban-image classification","volume":"7","author":"Tuia","year":"2010","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1822","DOI":"10.1109\/TGRS.2008.916201","article-title":"Kernel-based framework for multitemporal and multisource remote sensing data classification and change detection","volume":"46","year":"2008","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s10994-008-5086-2","article-title":"Graph kernels based on tree patterns for molecules","volume":"75","author":"Vert","year":"2009","journal-title":"Mach. Learn."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Harchaoui, Z., and Bach, F. (2007, January 14\u201321). Image classification with segmentation graph kernels. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Rio de Janeiro, Brazil.","DOI":"10.1109\/CVPR.2007.383049"},{"key":"ref_34","unstructured":"Vishwanathan, S., and Smola, A.J. (2004). Kernel Methods in Computational Biology, MIT Press."},{"key":"ref_35","unstructured":"Kimura, D., and Kashima, H. (July, January 26). Fast Computation of Subpath Kernel for Trees. Proceedings of the 29th International Conference on Machine Learning, Edinburgh, UK."},{"key":"ref_36","unstructured":"Cuturi, M. (July, January 28). Fast global alignment kernels. Proceedings of the 28th International Conference on Machine Learning, Bellevue, WA, USA."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1258","DOI":"10.1109\/TPAMI.2015.2477823","article-title":"Scale space graph representation and kernel matching for non rigid and textured 3D shape retrieval","volume":"38","author":"Garro","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_38","unstructured":"Yang, T., Li, Y.F., Mahdavi, M., Jin, R., and Zhou, Z.H. (2012, January 3\u20136). Nystr\u00f6m method vs random fourier features: A theoretical and empirical comparison. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_39","unstructured":"Rahimi, A., and Recht, B. (2007, January 3\u20136). Random features for large-scale kernel machines. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_40","unstructured":"Rahimi, A., and Recht, B. (2009, January 7\u201310). Weighted sums of random kitchen sinks: Replacing minimization with randomization in learning. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_41","first-page":"1","article-title":"How to scale up kernel methods to be as good as deep neural nets","volume":"14","author":"Lu","year":"2014","journal-title":"arXiv"},{"key":"ref_42","unstructured":"Bo, L., and Sminchisescu, C. (2009, January 7\u201310). Efficient match kernel between sets of features for visual recognition. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_43","unstructured":"Haussler, D. (1999). Convolution Kernels on Discrete Structures, University of California. Technical Report."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Shawe-Taylor, J., and Cristianini, N. (2004). Kernel Methods for Pattern Analysis, Cambridge University Press.","DOI":"10.1017\/CBO9780511809682"},{"key":"ref_45","first-page":"1","article-title":"On the error of random Fourier features","volume":"15","author":"Sutherland","year":"2015","journal-title":"arXiv"},{"key":"ref_46","unstructured":"Collins, M., and Duffy, N. (2001, January 3\u20138). Convolution kernels for natural language. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e1nchez, J., and Mensink, T. (2010, January 5\u201311). Improving the fisher kernel for large-scale image classification. Proceedings of the European Conference on Computer Vision, Heraklion, Greece.","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Tolias, G., Avrithis, Y., and J\u00e9gou, H. (2013, January 1\u20138). To aggregate or not to aggregate: Selective match kernels for image search. Proceedings of the IEEE International Conference on Computer Vision, Sydney, Australia.","DOI":"10.1109\/ICCV.2013.177"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1016\/j.patcog.2011.07.017","article-title":"Extraction of complex patterns from multiresolution remote sensing images: A hierarchical top-down methodology","volume":"45","author":"Kurtz","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Tilton, J.C. (1998, January 6\u201310). Image segmentation by region growing and spectral clustering with a natural convergence criterion. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Seattle, WA, USA.","DOI":"10.1109\/IGARSS.1998.703645"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1016\/j.compenvurbsys.2012.01.003","article-title":"Knowledge-based region labeling for remote sensing image interpretation","volume":"36","author":"Forestier","year":"2012","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: A library for support vector machines","volume":"2","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"2147","DOI":"10.1109\/JSTARS.2014.2298876","article-title":"Automatic framework for spectral\u2013spatial classification based on supervised feature extraction and morphological attribute profiles","volume":"7","author":"Ghamisi","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1109\/LGRS.2014.2329713","article-title":"Semisupervised Classification of Remote Sensing Images with Hierarchical Spatial Similarity","volume":"12","author":"Huo","year":"2015","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"2335","DOI":"10.1109\/TGRS.2014.2358934","article-title":"A survey on spectral\u2013spatial classification techniques based on attribute profiles","volume":"53","author":"Ghamisi","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Tuia, D., Volpi, M., and Moser, G. (2016, January 10\u201315). Getting pixels and regions to agree with conditional random fields. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, Beijing, China.","DOI":"10.1109\/IGARSS.2016.7729851"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Perronnin, F., S\u00e9nchez, J., and Xerox, Y.L. (2010, January 13\u201318). Large-scale image categorization with explicit data embedding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.","DOI":"10.1109\/CVPR.2010.5539914"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/9\/3\/196\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:29:08Z","timestamp":1760207348000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/9\/3\/196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,2,24]]},"references-count":57,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2017,3]]}},"alternative-id":["rs9030196"],"URL":"https:\/\/doi.org\/10.3390\/rs9030196","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,2,24]]}}}