{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:10:23Z","timestamp":1777705823317,"version":"3.51.4"},"reference-count":16,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"<jats:p>\u00a0Geo-localisation from a single aerial image for Uncrewed Aerial Vehicles (UAVs) is an alternative to other vision-based methods, such as visual Simultaneous Localisation and Mapping (SLAM), seeking robustness under GPS failure. Due to the success of deep learning and the fact that UAVs can carry a low-cost camera, we can train a Convolutional Neural Network (CNN) to predict position from a single aerial image. However, conventional CNN-based methods adapted to this problem require off-board training that involves high computational processing time and where the model can not be used in the same flight mission. In this work, we explore the use of continual learning via latent replay to achieve online training with a CNN model that learns during the flight mission GPS coordinates associated with single aerial images. Thus, the learning process repeats the old data with the new ones using fewer images. Furthermore, inspired by the sub-mapping concept in visual SLAM, we propose a multi-model approach to assess the advantages of using compact models learned continuously with promising results. On average, our method achieved a processing speed of 150 fps with an accuracy of 0.71 to 0.85, demonstrating the effectiveness of our methodology for geo-localisation applications.<\/jats:p>","DOI":"10.3233\/jifs-223627","type":"journal-article","created":{"date-parts":[[2023,4,7]],"date-time":"2023-04-07T11:37:48Z","timestamp":1680867468000},"page":"10369-10381","source":"Crossref","is-referenced-by-count":0,"title":["Continual learning for topological geo-localisation"],"prefix":"10.1177","volume":"44","author":[{"given":"Aldrich A.","family":"Cabrera-Ponce","sequence":"first","affiliation":[{"name":"Benemerita Universidad Autonoma de Puebla (BUAP), Puebla, Mexico"}]},{"given":"Manuel","family":"Martin-Ortiz","sequence":"additional","affiliation":[{"name":"Benemerita Universidad Autonoma de Puebla (BUAP), Puebla, Mexico"}]},{"given":"Jose","family":"Martinez-Carranza","sequence":"additional","affiliation":[{"name":"Instituto Nacional de Astrofisica Optica y Electronica (INAOE), Puebla, Mexico"}]}],"member":"179","reference":[{"key":"10.3233\/JIFS-223627_ref1","doi-asserted-by":"crossref","first-page":"37947","DOI":"10.1109\/ACCESS.2018.2854712","article-title":"Autonomous UAV flight control for GPSbased navigation","volume":"6","author":"Kwak","year":"2018","journal-title":"IEEE Access"},{"issue":"2","key":"10.3233\/JIFS-223627_ref4","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1080\/01691864.2015.1094409","article-title":"Indoor MAV auto-retrieval using fast 6D relocalisation","volume":"30","author":"Martinez-Carranza","year":"2016","journal-title":"Advanced Robotics"},{"issue":"8","key":"10.3233\/JIFS-223627_ref11","doi-asserted-by":"crossref","first-page":"1546","DOI":"10.1109\/TPAMI.2014.2299799","article-title":"Image geo-localization based on multiple nearest neighbour feature matching using generalized graphs","volume":"36","author":"Zamir","year":"2014","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"16","key":"10.3233\/JIFS-223627_ref12","first-page":"273","article-title":"Robust Underwater SLAM using Autonomous Relocalisation","volume":"54","author":"Willners","year":"2021","journal-title":"IFACPapersOn-Line"},{"issue":"10","key":"10.3233\/JIFS-223627_ref13","doi-asserted-by":"crossref","first-page":"2105","DOI":"10.3390\/app9102105","article-title":"A simultaneous localization and mapping (SLAM) framework for 2.5 D map building based on low-cost LiDAR and vision fusion","volume":"9","author":"Jiang","year":"2019","journal-title":"Applied Sciences"},{"issue":"5","key":"10.3233\/JIFS-223627_ref14","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1109\/TRO.2017.2705103","article-title":"Orb-slam2: An open-source slam system for monocular, stereo, and rgb-d cameras","volume":"33","author":"Mur-Artal","year":"2017","journal-title":"IEEE Transactions on Robotics"},{"issue":"2","key":"10.3233\/JIFS-223627_ref15","doi-asserted-by":"crossref","first-page":"149","DOI":"10.3390\/rs11020149","article-title":"Rapid relocation method for mobile robot based on improved ORB-SLAM2 algorithm","volume":"11","author":"Yang","year":"2019","journal-title":"Remote Sensing"},{"issue":"6","key":"10.3233\/JIFS-223627_ref20","doi-asserted-by":"crossref","first-page":"3007","DOI":"10.3390\/app12063007","article-title":"A Robust Localization System Fusion Vision-CNN Relocalization and Progressive Scan Matching for Indoor Mobile Robots","volume":"12","author":"Liu","year":"2022","journal-title":"Applied Sciences"},{"issue":"13","key":"10.3233\/JIFS-223627_ref23","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.3233\/JIFS-223627_ref27","doi-asserted-by":"crossref","first-page":"4615","DOI":"10.1109\/ACCESS.2019.2963056","article-title":"Incremental learning in deep convolutional neural networks using partial network sharing","volume":"8","author":"Sarwar","year":"2019","journal-title":"IEEE Access"},{"issue":"12","key":"10.3233\/JIFS-223627_ref30","doi-asserted-by":"crossref","first-page":"2935","DOI":"10.1109\/TPAMI.2017.2773081","article-title":"Learning without forgetting","volume":"40","author":"Li","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.3233\/JIFS-223627_ref33","doi-asserted-by":"crossref","unstructured":"Cabrera-Ponce A.A. , Martin-Ortiz M. , Martinez-Carranza J. , Continual Learning for Multi-camera Relocalisation, in: Mexican International Conference on Artificial Intelligence, Springer, 2021, pp. 289\u2013302.","DOI":"10.1007\/978-3-030-89817-5_22"},{"key":"10.3233\/JIFS-223627_ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-32833-153"},{"key":"10.3233\/JIFS-223627_ref40","doi-asserted-by":"crossref","unstructured":"Agarwal S. , Snavely N. , Seitz S.M. , Szeliski R. , Bundle adjustment in the large, in: European conference on computer vision, Springer, 2010, pp. 29\u201342.","DOI":"10.1007\/978-3-642-15552-9_3"},{"issue":"10","key":"10.3233\/JIFS-223627_ref41","doi-asserted-by":"crossref","first-page":"2585","DOI":"10.1007\/s10115-021-01605-0","article-title":"Model complexity of deep learning: A survey","volume":"63","author":"Hu","year":"2021","journal-title":"Knowledge and Information Systems"},{"issue":"Nov","key":"10.3233\/JIFS-223627_ref42","first-page":"463","article-title":"Rademacher and Gaussian complexities: Risk bounds and structural results","volume":"3","author":"Bartlett","year":"2002","journal-title":"Journal of Machine Learning Research"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-223627","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:45:20Z","timestamp":1777455920000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-223627"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":16,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/jifs-223627","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}