{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T15:14:24Z","timestamp":1782314064960,"version":"3.54.5"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T00:00:00Z","timestamp":1754352000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"DOI":"10.1007\/s44163-025-00455-x","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T07:37:40Z","timestamp":1754379460000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhanced urban driving scene segmentation using modified UNet with residual convolutions and attention guided skip connections"],"prefix":"10.1007","volume":"5","author":[{"given":"Siddhant","family":"Arora","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahaan","family":"Banerjee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nitish","family":"Katal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,5]]},"reference":[{"key":"455_CR1","doi-asserted-by":"crossref","unstructured":"Chen L, Yuchen L, Chao H, Yang X, Daxin T, Li L, Zhongxu H et al. Milestones in autonomous driving and intelligent vehicles\u2014part 1: Control, computing system design, communication, HD map, testing, and human behaviors.\u00a0IEEE Transactions on Systems, Man, and Cybernetics: Systems. 2023.","DOI":"10.1109\/TSMC.2023.3276218"},{"key":"455_CR2","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.isprsjprs.2022.12.021","volume":"196","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Carballo A, Yang H, Takeda K. Perception and sensing for autonomous vehicles under adverse weather conditions: a survey. ISPRS J Photogramm Remote Sens. 2023;196:146\u201377.","journal-title":"ISPRS J Photogramm Remote Sens"},{"issue":"11","key":"455_CR3","doi-asserted-by":"publisher","first-page":"11097","DOI":"10.1109\/JSEN.2023.3262134","volume":"23","author":"A Pandharipande","year":"2023","unstructured":"Pandharipande A, Cheng CH, Dauwels J, Gurbuz SZ, Ibanez-Guzman J, Li G, Piazzoni A, Wang P, Santra A. Sensing and machine learning for automotive perception: a review. IEEE Sens J. 2023;23(11):11097\u2013115.","journal-title":"IEEE Sens J"},{"issue":"2","key":"455_CR4","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.patrec.2008.04.005","volume":"30","author":"GJ Brostow","year":"2009","unstructured":"Brostow GJ, Fauqueur J, Cipolla R. Semantic object classes in video: a high-definition ground truth database. Pattern Recognit Lett. 2009;30(2):88\u201397.","journal-title":"Pattern Recognit Lett"},{"key":"455_CR5","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Philipp F, Thomas B, U-Net: Convolutional networks for biomedical image segmentation. In\u00a0Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, 2015, Proceedings, Part III 18, pp. 234\u2013241. Springer International Publishing, 2015.","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"5","key":"455_CR6","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1109\/LGRS.2018.2802944","volume":"15","author":"Z Zhang","year":"2018","unstructured":"Zhang Z, Liu Q, Wang Y. Road extraction by deep residual u-net. IEEE Geosci Remote Sens Lett. 2018;15(5):749\u201353.","journal-title":"IEEE Geosci Remote Sens Lett"},{"key":"455_CR7","unstructured":"Vaswani A, Noam S, Niki P, Jakob U, Llion J, Aidan NG, \u0141ukasz K, Illia P. Attention is all you need.\u00a0Adv Neural Inform Process Syst\u00a030 (2017)."},{"key":"455_CR8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73429-1","volume-title":"The 2005 DARPA grand challenge: the great robot race","author":"M Buehler","year":"2007","unstructured":"Buehler M, Karl I, Sanjiv S. The 2005 DARPA grand challenge: the great robot race, vol. 36. Springer; 2007."},{"key":"455_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03991-1","volume-title":"The DARPA urban challenge: autonomous vehicles in city traffic","author":"M Buehler","year":"2009","unstructured":"Buehler M, Iagnemma K, Singh S. The DARPA urban challenge: autonomous vehicles in city traffic, vol. 56. Springer; 2009."},{"issue":"3","key":"455_CR10","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2020","unstructured":"Feng D, Haase-Sch\u00fctz C, Rosenbaum L, Hertlein H, Glaeser C, Timm F, Wiesbeck W, Dietmayer K. Deep multi-modal object detection and semantic segmentation for autonomous driving: datasets, methods, and challenges. IEEE Trans Intell Transp Syst. 2020;22(3):1341\u201360.","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"3","key":"455_CR11","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1109\/TITS.2013.2252427","volume":"14","author":"H Yoo","year":"2013","unstructured":"Yoo H, Yang U, Sohn K. Gradient-enhancing conversion for illumination-robust lane detection. IEEE Trans Intell Transp Syst. 2013;14(3):1083\u201394.","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"455_CR12","doi-asserted-by":"publisher","first-page":"107623","DOI":"10.1016\/j.patcog.2020.107623","volume":"111","author":"J Tang","year":"2021","unstructured":"Tang J, Li S, Liu P. A review of lane detection methods based on deep learning. Pattern Recognit. 2021;111:107623.","journal-title":"Pattern Recognit"},{"key":"455_CR13","doi-asserted-by":"crossref","unstructured":"Hou B, Ying L, Nam L, Yongxiong R, Lingzhi L. A survey of efficient deep learning models for moving object segmentation. APSIPA transactions on signal and information processing\u00a012, no. 1. 2023.","DOI":"10.1561\/116.00000140"},{"key":"455_CR14","doi-asserted-by":"crossref","unstructured":"Muhammad K, Tanveer H, Hayat U, Javier Del Ser, Mahdi R, Neeraj K, Mohammad H, Paolo B, Victor de HCA. Vision-based semantic segmentation in scene understanding for autonomous driving: Recent achievements, challenges, and outlooks.\u00a0IEEE Trans Intell Transp Syst (2022).","DOI":"10.1109\/TITS.2022.3207665"},{"key":"455_CR15","doi-asserted-by":"crossref","unstructured":"Long J, Evan S, Trevor D. Fully convolutional networks for semantic segmentation. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431\u20133440. 2015.","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"4","key":"455_CR16","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2017","unstructured":"Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFS. IEEE Trans Pattern Anal Mach Intell. 2017;40(4):834\u201348.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"12","key":"455_CR17","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. 2017;39(12):2481\u201395.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"2","key":"455_CR18","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/MITS.2023.3341952","volume":"16","author":"Y Wang","year":"2024","unstructured":"Wang Y, Han Z, Xing Y, Xu S, Wang J. A survey on datasets for the decision making of autonomous vehicles. IEEE Intell Transp Syst Magaz. 2024;16(2):23\u201340.","journal-title":"IEEE Intell Transp Syst Magaz"},{"key":"455_CR19","doi-asserted-by":"crossref","unstructured":"Cordts M, Mohamed O, Sebastian R, Timo R, Markus E, Rodrigo B, Uwe F, Stefan R, Bernt S. The cityscapes dataset for semantic urban scene understanding. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3213\u20133223. 2016.","DOI":"10.1109\/CVPR.2016.350"},{"issue":"3","key":"455_CR20","doi-asserted-by":"publisher","first-page":"3292","DOI":"10.1109\/TPAMI.2022.3179507","volume":"45","author":"Y Liao","year":"2022","unstructured":"Liao Y, Xie J, Geiger A. KITTI-360: a novel dataset and benchmarks for urban scene understanding in 2d and 3d. IEEE Trans Pattern Anal Mach Intell. 2022;45(3):3292\u2013310.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"455_CR21","doi-asserted-by":"crossref","unstructured":"Huang X, Xinjing C, Qichuan G, Binbin C, Dingfu Z, Peng W, Yuanqing L, Ruigang Y. The apolloscape dataset for autonomous driving. In\u00a0Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 954\u2013960. 2018.","DOI":"10.1109\/CVPRW.2018.00141"},{"key":"455_CR22","doi-asserted-by":"crossref","unstructured":"Caesar H, Varun B, Alex HL, Sourabh V, Venice EL, Qiang X, Anush K, Yu P, Giancarlo B, Oscar B. nuscenes: A multimodal dataset for autonomous driving. In\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631. 2020.","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"455_CR23","doi-asserted-by":"publisher","first-page":"14076","DOI":"10.1109\/ACCESS.2022.3147495","volume":"10","author":"T Turay","year":"2022","unstructured":"Turay T, Vladimirova T. Toward performing image classification and object detection with convolutional neural networks in autonomous driving systems: a survey. IEEE Access. 2022;10:14076\u2013119.","journal-title":"IEEE Access"},{"key":"455_CR24","doi-asserted-by":"crossref","unstructured":"Chen L-C, Yukun Z, George P, Florian S, Hartwig A. Encoder-decoder with atrous separable convolution for semantic image segmentation. In\u00a0Proceedings of the European conference on computer vision (ECCV), pp. 801\u2013818. 2018.","DOI":"10.1007\/978-3-030-01234-2_49"},{"issue":"11","key":"455_CR25","doi-asserted-by":"publisher","first-page":"3145","DOI":"10.1007\/s13042-019-01005-5","volume":"10","author":"S Ghosh","year":"2019","unstructured":"Ghosh S, Pal A, Jaiswal S, Santosh KC, Das N, Nasipuri M. SegFast-V2: semantic image segmentation with less parameters in deep learning for autonomous driving. Int J Mach Learn Cybernet. 2019;10(11):3145\u201354.","journal-title":"Int J Mach Learn Cybernet"},{"key":"455_CR26","doi-asserted-by":"publisher","first-page":"36776","DOI":"10.1109\/ACCESS.2020.2975640","volume":"8","author":"W Wang","year":"2020","unstructured":"Wang W, Yongjian F, Pan Z, Li X, Zhuang Y. Real-time driving scene semantic segmentation. IEEE Access. 2020;8:36776\u201388.","journal-title":"IEEE Access"},{"key":"455_CR27","doi-asserted-by":"publisher","first-page":"15084","DOI":"10.1109\/ACCESS.2021.3052791","volume":"9","author":"B Olimov","year":"2021","unstructured":"Olimov B, Kim J, Paul A. REF-Net: robust, efficient, and fast network for semantic segmentation applications using devices with limited computational resources. IEEE Access. 2021;9:15084\u201398.","journal-title":"IEEE Access"},{"issue":"1","key":"455_CR28","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1109\/TIV.2022.3176860","volume":"8","author":"J Fan","year":"2022","unstructured":"Fan J, Wang F, Chu H, Xiao H, Cheng Y, Gao B. Mlfnet: multi-level fusion network for real-time semantic segmentation of autonomous driving. IEEE Trans Intell Vehicles. 2022;8(1):756\u201367.","journal-title":"IEEE Trans Intell Vehicles"},{"key":"455_CR29","doi-asserted-by":"crossref","unstructured":"Sellat Q, Sukant KB, Rojalina P, Ankit V, Sandeep K, Rabindra KB. Intelligent semantic segmentation for self-driving vehicles using deep learning. Computational Intelligence and Neuroscience\u00a02022 (2022).","DOI":"10.1155\/2022\/6390260"},{"key":"455_CR30","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1016\/j.neunet.2022.10.034","volume":"157","author":"X Xiao","year":"2023","unstructured":"Xiao X, Zhao Y, Zhang F, Luo B, Lingli Y, Chen B, Yang C. BASeg: boundary aware semantic segmentation for autonomous driving. Neural Networks. 2023;157:460\u201370.","journal-title":"Neural Networks"},{"key":"455_CR31","doi-asserted-by":"crossref","unstructured":"Zhang H, Yujie D, Yixuan P, Shenqi L, Chengxu L, Kaipeng Z, Xueming Q. HF-HRNet: a simple hardware friendly high-resolution network. IEEE Trans Circuits Syst V Technol. 2024.","DOI":"10.1109\/TCSVT.2024.3377365"},{"issue":"9","key":"455_CR32","doi-asserted-by":"publisher","first-page":"4997","DOI":"10.1109\/TCSVT.2023.3246999","volume":"33","author":"H Zhang","year":"2023","unstructured":"Zhang H, Lai S, Wang Y, Da Z, Dun Y, Qian X. Scgnet: shifting and cascaded group network. IEEE Trans Circuits Syst V Technol. 2023;33(9):4997\u20135008.","journal-title":"IEEE Trans Circuits Syst V Technol"},{"key":"455_CR33","doi-asserted-by":"crossref","unstructured":"Peng H, Siyu X, Mingjun C, Hongyang L, Qin S. DCN-Deeplabv3+: a novel road segmentation algorithm based on improved Deeplabv3+.\"\u00a0IEEE Access\u00a0(2024).","DOI":"10.1109\/ACCESS.2024.3416468"},{"key":"455_CR34","doi-asserted-by":"crossref","unstructured":"Wang Z, Zhihao L, Bin Z, Guizhen Y, Wenwen L. SwinURNet: hybrid transformer-cnn architecture for real-time unstructured road segmentation. IEEE Trans Instrum Meas. 2024.","DOI":"10.1109\/TIM.2024.3470042"},{"issue":"1","key":"455_CR35","doi-asserted-by":"publisher","first-page":"6110","DOI":"10.1038\/s41598-025-90518-x","volume":"15","author":"T Li","year":"2025","unstructured":"Li T, Cui Z, Zhang H. Semantic segmentation feature fusion network based on transformer. Sci Rep. 2025;15(1):6110.","journal-title":"Sci Rep"},{"key":"455_CR36","doi-asserted-by":"crossref","unstructured":"Suryanto N, Andro AA, Ahmada YK, Derry P, Yongsu K, Howon K. Cityscape-Adverse: Benchmarking Robustness of Semantic Segmentation with Realistic Scene Modifications via Diffusion-Based Image Editing. IEEE Access. 2025.","DOI":"10.1109\/ACCESS.2025.3537981"},{"issue":"1","key":"455_CR37","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1038\/s41598-024-84685-6","volume":"15","author":"B Ye","year":"2025","unstructured":"Ye B, Xue R, Qianlong W. A hybrid attention multi-scale fusion network for real-time semantic segmentation. Sci Rep. 2025;15(1):872.","journal-title":"Sci Rep"},{"key":"455_CR38","doi-asserted-by":"publisher","first-page":"110698","DOI":"10.1016\/j.patcog.2024.110698","volume":"156","author":"H Zhang","year":"2024","unstructured":"Zhang H, Ma Y, Zhang K, Zheng N, Lai S. FMGNet: An efficient feature-multiplex group network for real-time vision task. Pattern Recognit. 2024;156:110698.","journal-title":"Pattern Recognit"},{"key":"455_CR39","unstructured":"Zhang H, Yongqiang M, Wenqi S, Ping L, Nanning Z, Kaipeng Z. HRVMamba: high-resolution visual state space model for dense prediction.\"\u00a0arXiv preprint arXiv:2410.03174\u00a0(2024)."},{"key":"455_CR40","unstructured":"Bengio Y, Ian G, Aaron C. Deep learning. Vol. 1. Cambridge, MA, USA: MIT press, 2017. https:\/\/www.deeplearningbook.org\/"}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00455-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-025-00455-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-025-00455-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:17:50Z","timestamp":1757351870000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-025-00455-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,5]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["455"],"URL":"https:\/\/doi.org\/10.1007\/s44163-025-00455-x","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,5]]},"assertion":[{"value":"29 January 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study did not require ethical approval as it did not involve human participants, animals, or sensitive data.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors consent to the publication of this manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to publish"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interest"}}],"article-number":"198"}}