{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T13:48:59Z","timestamp":1790776139027,"version":"4.1.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031821554","type":"print"},{"value":"9783031821561","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-82156-1_9","type":"book-chapter","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T08:47:23Z","timestamp":1741078043000},"page":"108-122","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Semantic Segmentation of\u00a0Unmanned Aerial Vehicle Remote Sensing Images Using SegFormer"],"prefix":"10.1007","author":[{"given":"Vlatko","family":"Spasev","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2877-3430","authenticated-orcid":false,"given":"Ivica","family":"Dimitrovski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9648-4438","authenticated-orcid":false,"given":"Ivan","family":"Chorbev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0014-4229","authenticated-orcid":false,"given":"Ivan","family":"Kitanovski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,5]]},"reference":[{"issue":"12","key":"9_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: SegNet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., Kalinin, A.A.: Albumentations: fast and flexible image augmentations. Information 11(2), 125 (2020)","DOI":"10.3390\/info11020125"},{"key":"9_CR3","doi-asserted-by":"publisher","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.M. (eds.) Computer Vision \u2013 ECCV 2020. ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"issue":"4","key":"9_CR4","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834\u2013848 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"9_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"833","DOI":"10.1007\/978-3-030-01234-2_49","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833\u2013851. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_49"},{"key":"9_CR6","unstructured":"Cheng, B., Choudhuri, A., Misra, I., Kirillov, A., Girdhar, R., Schwing, A.G.: Mask2Former for video instance segmentation. arXiv preprint arXiv:2112.10764 (2021)"},{"key":"9_CR7","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.isprsjprs.2024.03.012","volume":"211","author":"J Cheng","year":"2024","unstructured":"Cheng, J., Deng, C., Su, Y., An, Z., Wang, Q.: Methods and datasets on semantic segmentation for unmanned aerial vehicle remote sensing images: a review. ISPRS J. Photogramm. Remote. Sens. 211, 1\u201334 (2024)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"9_CR9","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.jnca.2017.08.004","volume":"96","author":"M De Benedetti","year":"2017","unstructured":"De Benedetti, M., D\u2019Urso, F., Fortino, G., Messina, F., Pappalardo, G., Santoro, C.: A fault-tolerant self-organizing flocking approach for UAV aerial survey. J. Netw. Comput. Appl. 96, 14\u201330 (2017)","journal-title":"J. Netw. Comput. Appl."},{"key":"9_CR10","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.isprsjprs.2023.01.014","volume":"197","author":"I Dimitrovski","year":"2023","unstructured":"Dimitrovski, I., Kitanovski, I., Kocev, D., Simidjievski, N.: Current trends in deep learning for earth observation: an open-source benchmark arena for image classification. ISPRS J. Photogramm. Remote. Sens. 197, 18\u201335 (2023)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"9_CR11","doi-asserted-by":"crossref","unstructured":"Dimitrovski, I., Kitanovski, I., Panov, P., Kostovska, A., Simidjievski, N., Kocev, D.: AiTLAS: artificial intelligence toolbox for earth observation. Remote Sens. 15(9) (2023)","DOI":"10.3390\/rs15092343"},{"key":"9_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2024.3352926","volume":"21","author":"I Dimitrovski","year":"2024","unstructured":"Dimitrovski, I., Kitanovski, I., Simidjievski, N., Kocev, D.: In-domain self-supervised learning improves remote sensing image scene classification. IEEE Geosci. Remote Sens. Lett. 21, 1\u20135 (2024)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"9_CR13","doi-asserted-by":"publisher","unstructured":"Falcon, W.: The PyTorch Lightning team: PyTorch Lightning, March 2019. https:\/\/doi.org\/10.5281\/zenodo.3828935, https:\/\/github.com\/Lightning-AI\/lightning","DOI":"10.5281\/zenodo.3828935"},{"issue":"6","key":"9_CR14","doi-asserted-by":"publisher","first-page":"2547","DOI":"10.1109\/TNNLS.2020.3006524","volume":"32","author":"J Fu","year":"2020","unstructured":"Fu, J., Liu, J., Jiang, J., Li, Y., Bao, Y., Lu, H.: Scene segmentation with dual relation-aware attention network. IEEE Trans. Neural Netw. Learn. Syst. 32(6), 2547\u20132560 (2020)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Funk, F., St\u00fctz, P.: A passive cloud detection system for UAV: weather situation mapping with imaging sensors. In: 2017 IEEE Aerospace Conference, pp. 1\u201312 (2017)","DOI":"10.1109\/AERO.2017.7943915"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Green, D.R., Hagon, J.J., G\u00f3mez, C., Gregory, B.J.: Using low-cost UAVs for environmental monitoring, mapping, and modelling: examples from the coastal zone. In: Coastal Management, pp. 465\u2013501. Academic Press (2019)","DOI":"10.1016\/B978-0-12-810473-6.00022-4"},{"key":"9_CR17","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s13735-017-0141-z","volume":"7","author":"Y Guo","year":"2018","unstructured":"Guo, Y., Liu, Y., Georgiou, T., Lew, M.S.: A review of semantic segmentation using deep neural networks. Int. J. Multimedia Inf. Retrieval 7, 87\u201393 (2018)","journal-title":"Int. J. Multimedia Inf. Retrieval"},{"key":"9_CR18","unstructured":"He, W., Li, J., Cao, W., Zhang, L., Zhang, H.: Building extraction from remote sensing images via an uncertainty-aware network. arXiv preprint arXiv:2307.12309 (2023)"},{"key":"9_CR19","unstructured":"Kamilaris, A., Prenafeta-Bold\u00fa, F.X.: Disaster monitoring using unmanned aerial vehicles and deep learning. arXiv preprint arXiv:1807.11805 (2018)"},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Kemker, R., Salvaggio, C., Kanan, C.: Algorithms for semantic segmentation of multispectral remote sensing imagery using deep learning. ISPRS J. Photogramm. Remote Sens. (2018)","DOI":"10.1016\/j.isprsjprs.2018.04.014"},{"key":"9_CR21","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431\u20133440 (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"9_CR22","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"9_CR23","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.isprsjprs.2020.05.009","volume":"165","author":"Y Lyu","year":"2020","unstructured":"Lyu, Y., Vosselman, G., Xia, G.S., Yilmaz, A., Yang, M.Y.: UAVid: a semantic segmentation dataset for UAV imagery. ISPRS J. Photogramm. Remote. Sens. 165, 108\u2013119 (2020)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"9_CR24","doi-asserted-by":"crossref","unstructured":"Merdjanovska, E., Kitanovski, I., Kokalj, \u017d., Dimitrovski, I., Kocev, D.: Crop type prediction across countries and years: Slovenia, Denmark and The Netherlands. In: IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium, pp. 5945\u20135948. IEEE (2022)","DOI":"10.1109\/IGARSS46834.2022.9884623"},{"key":"9_CR25","first-page":"102456","volume":"102","author":"LP Osco","year":"2021","unstructured":"Osco, L.P., et al.: A review on deep learning in UAV remote sensing. Int. J. Appl. Earth Obs. Geoinf. 102, 102456 (2021)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"9_CR26","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"9_CR27","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/JSTARS.2022.3219724","volume":"16","author":"F Safavi","year":"2023","unstructured":"Safavi, F., Rahnemoonfar, M.: Comparative study of real-time semantic segmentation networks in aerial images during flooding events. IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens. 16, 4\u201320 (2023)","journal-title":"IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens."},{"key":"9_CR28","unstructured":"Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., LeCun, Y.: OverFeat: integrated recognition, localization and detection using convolutional networks (2014)"},{"key":"9_CR29","doi-asserted-by":"crossref","unstructured":"Spasev, V., Dimitrovski, I., Kitanovski, I., Chorbev, I.: Semantic segmentation of remote sensing images: definition, methods, datasets and applications. In: ICT Innovations 2023. Learning: Humans, Theory, Machines, and Data, pp. 127\u2013140 (2024)","DOI":"10.1007\/978-3-031-54321-0_9"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7262\u20137272 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"9_CR31","first-page":"1","volume":"19","author":"L Wang","year":"2022","unstructured":"Wang, L., Li, R., Duan, C., Zhang, C., Meng, X., Fang, S.: A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images. IEEE Geosci. Remote Sens. Lett. 19, 1\u20135 (2022)","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"9_CR32","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.isprsjprs.2022.06.008","volume":"190","author":"L Wang","year":"2022","unstructured":"Wang, L., et al.: UNetFormer: a UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery. ISPRS J. Photogramm. Remote. Sens. 190, 196\u2013214 (2022)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"key":"9_CR33","first-page":"103661","volume":"127","author":"S Wang","year":"2024","unstructured":"Wang, S., Hu, Q., Wang, S., Zhao, P., Li, J., Ai, M.: Category attention guided network for semantic segmentation of fine-resolution remote sensing images. Int. J. Appl. Earth Obs. Geoinf. 127, 103661 (2024)","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"issue":"2","key":"9_CR34","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1016\/j.cviu.2010.10.002","volume":"115","author":"D Weinland","year":"2011","unstructured":"Weinland, D., Ronfard, R., Boyer, E.: A survey of vision-based methods for action representation, segmentation and recognition. Comput. Vis. Image Underst. 115(2), 224\u2013241 (2011)","journal-title":"Comput. Vis. Image Underst."},{"key":"9_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"9_CR36","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR37","unstructured":"Yamazaki, K., et\u00a0al.: AerialFormer: multi-resolution transformer for aerial image segmentation. arXiv preprint arXiv:2306.06842 (2023)"},{"key":"9_CR38","doi-asserted-by":"publisher","first-page":"134503","DOI":"10.1109\/ACCESS.2021.3115950","volume":"9","author":"J Yang","year":"2021","unstructured":"Yang, J., Ding, Z., Wang, L.: The programming model of air-ground cooperative patrol between multi-UAV and police car. IEEE Access 9, 134503\u2013134517 (2021)","journal-title":"IEEE Access"},{"key":"9_CR39","doi-asserted-by":"publisher","first-page":"114417","DOI":"10.1016\/j.eswa.2020.114417","volume":"169","author":"X Yuan","year":"2021","unstructured":"Yuan, X., Shi, J., Gu, L.: A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Syst. Appl. 169, 114417 (2021)","journal-title":"Expert Syst. Appl."},{"issue":"6","key":"9_CR40","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.3390\/rs13061221","volume":"13","author":"H Zhang","year":"2021","unstructured":"Zhang, H., Wang, L., Tian, T., Yin, J.: A review of unmanned aerial vehicle low-altitude remote sensing (UAV-LARS) use in agricultural monitoring in china. Remote Sens. 13(6), 1221 (2021)","journal-title":"Remote Sens."},{"issue":"8","key":"9_CR41","doi-asserted-by":"publisher","first-page":"824","DOI":"10.3390\/rs9080824","volume":"9","author":"Y Zhang","year":"2017","unstructured":"Zhang, Y., Yuan, X., Li, W., Chen, S.: Automatic power line inspection using UAV images. Remote Sens. 9(8), 824 (2017)","journal-title":"Remote Sens."},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2881\u20132890 (2017)","DOI":"10.1109\/CVPR.2017.660"},{"key":"9_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/978-3-030-01240-3_17","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Zhao","year":"2018","unstructured":"Zhao, H., et al.: PSANet: point-wise spatial attention network for scene parsing. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 270\u2013286. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_17"}],"container-title":["Communications in Computer and Information Science","Intelligent Systems and Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-82156-1_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T08:47:35Z","timestamp":1741078055000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-82156-1_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031821554","9783031821561"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-82156-1_9","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"5 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Systems and Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Istanbul","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"T\u00fcrkiye","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ispr22024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ispr2024.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}