{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T23:17:27Z","timestamp":1778195847076,"version":"3.51.4"},"reference-count":35,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T00:00:00Z","timestamp":1638403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Unsupervised image classification methods conventionally use the spatial information of pixels to reduce the effect of speckled noise in the classified map. To extract this spatial information, they employ a predefined geometry, i.e., a fixed-size window or segmentation map. However, this coding of geometry lacks the necessary complexity to accurately reflect the spatial connectivity within objects in a scene. Additionally, there is no unique mathematical formula to determine the shape and scale applied to the geometry, being parameters that are usually estimated by expert users. In this paper, a novel geometry-led approach using Vector Agents (VAs) is proposed to address the above drawbacks in unsupervised classification algorithms. Our proposed method has two primary steps: (1) creating reliable training samples and (2) constructing the VA model. In the first step, the method applies the statistical information of a classified image by k-means to select a set of reliable training samples. Then, in the second step, the VAs are trained and constructed to classify the image. The model is tested for classification on three high spatial resolution images. The results show the enhanced capability of the VA model to reduce noise in images that have complex features, e.g., streets, buildings.<\/jats:p>","DOI":"10.3390\/rs13234896","type":"journal-article","created":{"date-parts":[[2021,12,6]],"date-time":"2021-12-06T03:10:38Z","timestamp":1638760238000},"page":"4896","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Using Vector Agents to Implement an Unsupervised Image Classification Algorithm"],"prefix":"10.3390","volume":"13","author":[{"given":"Kambiz","family":"Borna","sequence":"first","affiliation":[{"name":"Civil Engineering and Land Surveying Department, Unitec Institute of Technology, Auckland 1025, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7738-2308","authenticated-orcid":false,"given":"Antoni B.","family":"Moore","sequence":"additional","affiliation":[{"name":"School of Surveying, University of Otago, Dunedin 9054, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Azadeh","family":"Noori Hoshyar","sequence":"additional","affiliation":[{"name":"School of Engineering, IT and Physical Sciences, Federation University Australia, Brisbane, QLD 4000, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascal","family":"Sirguey","sequence":"additional","affiliation":[{"name":"School of Surveying, University of Otago, Dunedin 9054, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,12,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2113","DOI":"10.1080\/01431160512331337844","article-title":"Combining spectral and spatial information into hidden Markov models for unsupervised image classification","volume":"26","author":"Tso","year":"2005","journal-title":"Int. J. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Madhu, A., Kumar, A., and Jia, P. (2021). Exploring Fuzzy Local Spatial Information Algorithms for Remote Sensing Image Classification. Remote Sens., 13.","DOI":"10.3390\/rs13204163"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/LGRS.2007.905119","article-title":"A context-sensitive clustering technique based on graph-cut initialisation and expectation-maximisation algorithm","volume":"5","author":"Tyagi","year":"2008","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Madubedube, A., Coetzee, S., and Rautenbach, V. (2021). A Contributor-Focused Intrinsic Quality Assessment of OpenStreetMap in Mozambique Using Unsupervised Machine Learning. ISPRS Int. J. Geo-Inf., 10.","DOI":"10.3390\/ijgi10030156"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1793","DOI":"10.1016\/j.asr.2008.02.012","article-title":"Classification of hyperspectral remote-sensing data with primal SVM for small-sized training dataset problem","volume":"41","author":"Chi","year":"2008","journal-title":"Adv. Space Res."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Ragettli, S., Herberz, T., and Siegfried, T. (2018). An Unsupervised Classification Algorithm for Multi-Temporal Irrigated Area Mapping in Central Asia. Remote Sens., 10.","DOI":"10.3390\/rs10111823"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.isprsjprs.2014.08.006","article-title":"Automatic histogram-based fuzzy C-means clustering for remote sensing imagery","volume":"97","author":"Ghaffarian","year":"2014","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Tarabalka, Y., Chanussot, J., Benediktsson, J.A., Angulo, J., and Fauvel, M. (2008). Segmentation and classification of hyperspectral data using watershed. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium, IEEE.","DOI":"10.1109\/IGARSS.2008.4779432"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1080\/2150704X.2014.973075","article-title":"A fuzzy local neighbourhood-attraction-based information c-means clustering algorithm for very high spatial resolution imagery classification","volume":"5","author":"Zheng","year":"2014","journal-title":"Remote Sens. Lett."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"3672","DOI":"10.1109\/TGRS.2016.2524557","article-title":"Spectral\u2013Spatial Sparse Subspace Clustering for Hyperspectral Remote Sensing Images","volume":"54","author":"Zhang","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Cui, W., Zhang, D., He, X., Yao, M., Wang, Z., Hao, Y., Li, J., Wu, W., Cui, W., and Huang, J. (2019). Multi-Scale Remote Sensing Semantic Analysis Based on a Global Perspective. ISPRS Int. J. Geo-Inf., 8.","DOI":"10.3390\/ijgi8090417"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1109\/LGRS.2012.2231662","article-title":"A spatial clustering method with edge weighting for image segmentation","volume":"10","author":"Li","year":"2013","journal-title":"Geosci. Remote Sens. Lett."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Miao, Z., and Shi, W. (2016). A New Methodology for Spectral-Spatial Classification of Hyperspectral Images. J. Sens., 1\u201312.","DOI":"10.1155\/2016\/1538973"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1006\/cviu.2001.0951","article-title":"Pham, Spatial Models for Fuzzy Clustering","volume":"84","author":"Dzung","year":"2001","journal-title":"Comput. Vis. Image Underst."},{"key":"ref_15","first-page":"339","article-title":"An automated object-based approach for the multiscale image segmentation of forest scenes","volume":"7","author":"Hay","year":"2005","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4625","DOI":"10.1080\/01431160701241746","article-title":"Optimisation in multi-scale segmentation of high-resolution satellite images for artificial feature recognition","volume":"28","author":"Tian","year":"2007","journal-title":"Int. J. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"105073","DOI":"10.1016\/j.catena.2020.105073","article-title":"An object based image analysis applied for volcanic and glacial landforms mapping in Sahand Mountain, Iran","volume":"198","author":"Feizizadeh","year":"2021","journal-title":"Catena"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"59415973","DOI":"10.1080\/01431161.2010.512312","article-title":"Multi-resolution region-based clustering for urban analysis","volume":"31","author":"Kurtz","year":"2010","journal-title":"Int. J. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"4151","DOI":"10.1016\/j.patcog.2012.05.006","article-title":"Unsupervised segmentation and classification of cervical cell images","volume":"45","author":"Aksoy","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.media.2008.06.014","article-title":"A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme","volume":"13","author":"Hesheng","year":"2009","journal-title":"Med. Image Anal."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Fang, B., Chen, G., Chen, J., Ouyang, G., Kou, R., and Wang, L. (2021). CCT: Conditional Co-Training for Truly Unsupervised Remote Sensing Image Segmentation in Coastal Areas. Remote Sens., 13.","DOI":"10.3390\/rs13173521"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.patcog.2017.03.012","article-title":"Unsupervised hierarchical image segmentation through fuzzy entropy maximization","volume":"68","author":"Yin","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Hay, G.J., and Castilla, G. (2008). Geographic Object-Based Image Analysis (GEOBIA): A new name for a new discipline. Object-Based Image Analysis, Springer.","DOI":"10.1007\/978-3-540-77058-9_4"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Baatz, M., Hoffmann, C., and Willhauck, G. (2008). Progressing from object-based to object-oriented image analysis. Object-Based Image Analysis, Springer.","DOI":"10.1007\/978-3-540-77058-9_2"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.isprsjprs.2013.09.014","article-title":"Geographic object-based image analysis\u2013towards a new paradigm","volume":"87","author":"Blaschke","year":"2014","journal-title":"ISPRS J. Photogramm. Remote"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.patcog.2017.08.030","article-title":"Remote sensing image analysis by aggregation of segmentation-classification collaborative agents","volume":"73","year":"2018","journal-title":"Pattern Recognit."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1080\/19479832.2015.1015459","article-title":"Towards a framework for agent-based image analysis of remote-sensing data","volume":"6","author":"Hofmann","year":"2015","journal-title":"Int. J. Image Data Fusion"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1080\/13658810512331325139","article-title":"Geographic automata systems","volume":"19","author":"Torrens","year":"2005","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1016\/j.compenvurbsys.2007.08.003","article-title":"The dynamic geometry of geographical vector agents","volume":"31","author":"Hammam","year":"2007","journal-title":"Comput. Environ. Urban Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/1961189.1961199","article-title":"LIBSVM: A Library for Support Vector Machines","volume":"3","author":"Chang","year":"2011","journal-title":"ACM Trans. Intell. Systems Technol."},{"key":"ref_31","unstructured":"Marceau, D., and Benenson, I. (2011). Geographical Vector Agent-Based Simulation for Agricultural Land Use Modelling. Advanced Geosimulation Models, Available online: http:\/\/www.casa.ucl.ac.uk\/Advanced%20Geosimulation%20Models.pdf."},{"key":"ref_32","unstructured":"Howe, T. (2006). Containing agents: Contexts, projections, and agents. Proceedings of the Agent Conference on Social Agents: Results and Prospects, Argonne National Laboratory."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1080\/14498596.2014.915588","article-title":"Towards a vector agent modelling approach for remote sensing image classification","volume":"59","author":"Borna","year":"2014","journal-title":"J. Spat. Sci."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1111\/tgis.12226","article-title":"An Intelligent Geospatial Processing Unit for Image Classification Based on Geographic Vector Agents (GVAs)","volume":"20","author":"Borna","year":"2016","journal-title":"Trans. GIS"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.cageo.2012.12.007","article-title":"Object oriented image analysis based on multi-agent recognition system","volume":"54","author":"Mahmoudi","year":"2013","journal-title":"Comput. Geosci."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/23\/4896\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:38:55Z","timestamp":1760168335000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/23\/4896"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,2]]},"references-count":35,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["rs13234896"],"URL":"https:\/\/doi.org\/10.3390\/rs13234896","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,2]]}}}