{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T15:27:37Z","timestamp":1776526057641,"version":"3.51.2"},"reference-count":100,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T00:00:00Z","timestamp":1741824000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T00:00:00Z","timestamp":1741824000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473288"],"award-info":[{"award-number":["62473288"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62403361"],"award-info":[{"award-number":["62403361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62233013"],"award-info":[{"award-number":["62233013"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Xiaomi Young Talents Program"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Auton. Intell. Syst."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Road scene parsing is a crucial capability for self-driving vehicles and intelligent road inspection systems. Recent research has increasingly focused on enhancing driving safety and comfort by improving the detection of both drivable areas and road defects. This article reviews state-of-the-art networks developed over the past decade for both general-purpose semantic segmentation and specialized road scene parsing tasks. It also includes extensive experimental comparisons of these networks across five public datasets. Additionally, we explore the key challenges and emerging trends in the field, aiming to guide researchers toward developing next-generation models for more effective and reliable road scene parsing.<\/jats:p>","DOI":"10.1007\/s43684-025-00096-y","type":"journal-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T03:04:13Z","timestamp":1741835053000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A glance over the past decade: road scene parsing towards safe and comfortable autonomous driving"],"prefix":"10.1007","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2593-6596","authenticated-orcid":false,"given":"Rui","family":"Fan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiale","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Long","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenshuo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohammud J.","family":"Bocus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sergey","family":"Vityazev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xieyuanli","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junhao","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stepan","family":"Andreev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huimin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alexander","family":"Dvorkovich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,13]]},"reference":[{"issue":"1","key":"96_CR1","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s43684-023-00047-5","volume":"3","author":"M. Weber","year":"2023","unstructured":"M. Weber, et al., Approach for improved development of advanced driver assistance systems for future smart mobility concepts. Auton. Intell. Syst. 3(1), 2 (2023)","journal-title":"Auton. Intell. Syst."},{"issue":"1","key":"96_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s43684-024-00071-z","volume":"4","author":"K. Yuan","year":"2024","unstructured":"K. Yuan, et al., Human feedback enhanced autonomous intelligent systems: a perspective from intelligent driving. Auton. Intell. Syst. 4(1), 1\u201310 (2024)","journal-title":"Auton. Intell. Syst."},{"key":"96_CR3","doi-asserted-by":"publisher","first-page":"1516","DOI":"10.1109\/TIP.2025.3540283","volume":"34","author":"C.W. Liu","year":"2025","unstructured":"C.W. Liu, et al., These maps are made by propagation: adapting deep stereo networks to road scenarios with decisive disparity diffusion. IEEE Trans. Image Process. 34, 1516\u20131528 (2025)","journal-title":"IEEE Trans. Image Process."},{"issue":"1","key":"96_CR4","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1007\/s43684-022-00025-3","volume":"2","author":"M.O. Macaulay","year":"2022","unstructured":"M.O. Macaulay, M. Shafiee, Machine learning techniques for robotic and autonomous inspection of mechanical systems and civil infrastructure. Auton. Intell. Syst. 2(1), 8 (2022)","journal-title":"Auton. Intell. Syst."},{"issue":"1","key":"96_CR5","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1007\/s43684-021-00002-2","volume":"1","author":"M.A. Goodale","year":"2021","unstructured":"M.A. Goodale, Lessons from human vision for robotic design. Auton. Intell. Syst. 1(1), 2 (2021)","journal-title":"Auton. Intell. Syst."},{"key":"96_CR6","doi-asserted-by":"publisher","unstructured":"Y. Feng, et\u00a0al., SNE-RoadSegV2: advancing Heterogeneous Feature Fusion and Fallibility Awareness for Freespace Detection. IEEE Trans. Instrum. Meas. (2025). https:\/\/doi.org\/10.1109\/TIM.2025.3545498","DOI":"10.1109\/TIM.2025.3545498"},{"issue":"10","key":"96_CR7","doi-asserted-by":"publisher","first-page":"10750","DOI":"10.1109\/TCYB.2021.3064089","volume":"52","author":"H. Wang","year":"2021","unstructured":"H. Wang, et al., Dynamic fusion module evolves drivable area and road anomaly detection: a benchmark and algorithms. IEEE Trans. Cybern. 52(10), 10750\u201310760 (2021)","journal-title":"IEEE Trans. Cybern."},{"key":"96_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104047","volume":"151","author":"M. Rubagotti","year":"2022","unstructured":"M. Rubagotti, et al., Perceived safety in physical human\u2013robot interaction\u2014a survey. Robot. Auton. Syst. 151, 104047 (2022)","journal-title":"Robot. Auton. Syst."},{"issue":"1","key":"96_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s43684-024-00083-9","volume":"4","author":"X. Zhang","year":"2024","unstructured":"X. Zhang, et al., An intelligent surface roughness prediction method based on automatic feature extraction and adaptive data fusion. Auton. Intell. Syst. 4(1), 1\u201317 (2024)","journal-title":"Auton. Intell. Syst."},{"issue":"1","key":"96_CR10","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1007\/s43684-022-00037-z","volume":"2","author":"S. KC","year":"2022","unstructured":"S. KC, Enhanced pothole detection system using yolox algorithm. Auton. Intell. Syst. 2(1), 22 (2022)","journal-title":"Auton. Intell. Syst."},{"issue":"7","key":"96_CR11","doi-asserted-by":"publisher","first-page":"5163","DOI":"10.1109\/TIV.2024.3388726","volume":"9","author":"J. Li","year":"2024","unstructured":"J. Li, et al., RoadFormer: duplex transformer for RGB-normal semantic road scene parsing. IEEE Trans. Intell. Veh. 9(7), 5163\u20135172 (2024)","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"8","key":"96_CR12","doi-asserted-by":"publisher","first-page":"9920","DOI":"10.1109\/TITS.2024.3351209","volume":"25","author":"S. Guo","year":"2024","unstructured":"S. Guo, et al., UDTIRI: an online open-source intelligent road inspection benchmark suite. IEEE Trans. Intell. Transp. Syst. 25(8), 9920\u20139931 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"96_CR13","doi-asserted-by":"publisher","first-page":"897","DOI":"10.1109\/TIP.2019.2933750","volume":"29","author":"R. Fan","year":"2020","unstructured":"R. Fan, et al., Pothole detection based on disparity transformation and road surface modeling. IEEE Trans. Image Process. 29, 897\u2013908 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"96_CR14","first-page":"9716","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"M. Fan","year":"2021","unstructured":"M. Fan, et al., Rethinking BiSeNet for real-time semantic segmentation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), pp. 9716\u20139725"},{"key":"96_CR15","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1109\/IVS.2008.4621254","volume-title":"2008 IEEE Intelligent Vehicles Symposium (IV)","author":"A. Wedel","year":"2008","unstructured":"A. Wedel, et al., B-spline modeling of road surfaces for freespace estimation, in 2008 IEEE Intelligent Vehicles Symposium (IV) (IEEE, 2008), pp. 828\u2013833"},{"issue":"4","key":"96_CR16","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1109\/TITS.2009.2027223","volume":"10","author":"A. Wedel","year":"2009","unstructured":"A. Wedel, et al., B-spline modeling of road surfaces with an application to free-space estimation. IEEE Trans. Intell. Transp. Syst. 10(4), 572\u2013583 (2009)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"96_CR17","first-page":"2671","volume-title":"IEEE International Conference on Intelligent Transportation Systems (ITSC)","author":"A. Rasheed","year":"2015","unstructured":"A. Rasheed, et al., Stabilization of 3D pavement images for pothole metrology using the Kalman filter, in IEEE International Conference on Intelligent Transportation Systems (ITSC) (IEEE, 2015), pp. 2671\u20132676"},{"key":"96_CR18","first-page":"4885","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"G.L. Oliveira","year":"2016","unstructured":"G.L. Oliveira, et al., Efficient deep models for monocular road segmentation, in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE, 2016), pp. 4885\u20134891"},{"key":"96_CR19","doi-asserted-by":"publisher","first-page":"1343","DOI":"10.1109\/ICRA.2017.7989159","volume-title":"2017 IEEE International Conference on Robotics and Automation (ICRA)","author":"L. Chen","year":"2017","unstructured":"L. Chen, et al., LiDAR-histogram for fast road and obstacle detection, in 2017 IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2017), pp. 1343\u20131348"},{"issue":"6","key":"96_CR20","doi-asserted-by":"publisher","first-page":"3025","DOI":"10.1109\/TIP.2018.2808770","volume":"27","author":"R. Fan","year":"2018","unstructured":"R. Fan, et al., Road surface 3D reconstruction based on dense subpixel disparity map estimation. IEEE Trans. Image Process. 27(6), 3025\u20133035 (2018)","journal-title":"IEEE Trans. Image Process."},{"issue":"8","key":"96_CR21","doi-asserted-by":"publisher","first-page":"3536","DOI":"10.1109\/TITS.2019.2931297","volume":"21","author":"A. Dhiman","year":"2019","unstructured":"A. Dhiman, R. Klette, Pothole detection using computer vision and learning. IEEE Trans. Intell. Transp. Syst. 21(8), 3536\u20133550 (2019)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"96_CR22","doi-asserted-by":"publisher","first-page":"8144","DOI":"10.1109\/TIP.2021.3112316","volume":"30","author":"R. Fan","year":"2021","unstructured":"R. Fan, et al., Graph attention layer evolves semantic segmentation for road pothole detection: a benchmark and algorithms. IEEE Trans. Image Process. 30, 8144\u20138154 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"96_CR23","first-page":"2532","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"C. Min","year":"2022","unstructured":"C. Min, et al., ORFD: a dataset and benchmark for off-road freespace detection, in IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2022), pp. 2532\u20132538"},{"key":"96_CR24","doi-asserted-by":"publisher","first-page":"7778","DOI":"10.1109\/ICRA48891.2023.10160470","volume-title":"2023 IEEE International Conference on Robotics and Automation (ICRA)","author":"B. Tian","year":"2023","unstructured":"B. Tian, et al., Unsupervised road anomaly detection with language anchors, in 2023 IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2023), pp. 7778\u20137785"},{"issue":"2","key":"96_CR25","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1109\/LRA.2019.2891028","volume":"4","author":"C. Lu","year":"2019","unstructured":"C. Lu, et al., Monocular semantic occupancy grid mapping with convolutional variational encoder\u2013decoder networks. IEEE Robot. Autom. Lett. 4(2), 445\u2013452 (2019)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"96_CR26","first-page":"340","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"R. Fan","year":"2020","unstructured":"R. Fan, et al., SNE-RoadSeg: incorporating surface normal information into semantic segmentation for accurate freespace detection, in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, Berlin, 2020), pp. 340\u2013356"},{"key":"96_CR27","first-page":"213","volume-title":"Proceedings of the Asian Conference on Computer Vision (ACCV)","author":"C. Hazirbas","year":"2017","unstructured":"C. Hazirbas, et al., FuseNet: incorporating depth into semantic segmentation via fusion-based CNN architecture, in Proceedings of the Asian Conference on Computer Vision (ACCV) (Springer, Berlin, 2017), pp. 213\u2013228"},{"key":"96_CR28","first-page":"1140","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"H. Wang","year":"2021","unstructured":"H. Wang, et al., SNE-RoadSeg+: rethinking depth-normal translation and deep supervision for freespace detection, in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE, 2021), pp. 1140\u20131145"},{"key":"96_CR29","first-page":"1693","volume-title":"IEEE International Conference on Intelligent Transportation Systems (ITSC)","author":"J. Fritsch","year":"2013","unstructured":"J. Fritsch, et al., A new performance measure and evaluation benchmark for road detection algorithms, in IEEE International Conference on Intelligent Transportation Systems (ITSC) (IEEE, 2013), pp. 1693\u20131700"},{"key":"96_CR30","unstructured":"Y. Cabon, et\u00a0al., Virtual KITTI 2. Comput. Res. Repos. (CoRR) (2020). arXiv:2001.10773"},{"key":"96_CR31","first-page":"3213","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"M. Cordts","year":"2016","unstructured":"M. Cordts, et al., The cityscapes dataset for semantic urban scene understanding, in IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2016), pp. 3213\u20133223"},{"issue":"1","key":"96_CR32","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K. Han","year":"2022","unstructured":"K. Han, et al., A survey on vision transformer. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 87\u2013110 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"96_CR33","first-page":"10012","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Z. Liu","year":"2021","unstructured":"Z. Liu, et al., Swin transformer: hierarchical vision transformer using shifted windows, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2021), pp. 10012\u201310022"},{"key":"96_CR34","first-page":"12077","volume":"34","author":"E. Xie","year":"2021","unstructured":"E. Xie, et al., 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."},{"issue":"10","key":"96_CR35","doi-asserted-by":"publisher","first-page":"12581","DOI":"10.1109\/TPAMI.2023.3282631","volume":"45","author":"K. Li","year":"2023","unstructured":"K. Li, et al., UniFormer: unifying convolution and self-attention for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(10), 12581\u201312600 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"96_CR36","first-page":"218","volume-title":"International Conference on 3D Vision (3DV)","author":"L. Lipson","year":"2021","unstructured":"L. Lipson, et al., RAFT-stereo: multilevel recurrent field transforms for stereo matching, in International Conference on 3D Vision (3DV) (IEEE, 2021), pp. 218\u2013227"},{"key":"96_CR37","first-page":"3061","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"M. Menze","year":"2015","unstructured":"M. Menze, A. Geiger, Object scene flow for autonomous vehicles, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2015), pp. 3061\u20133070"},{"issue":"3","key":"96_CR38","doi-asserted-by":"publisher","first-page":"5405","DOI":"10.1109\/LRA.2021.3067308","volume":"6","author":"R. Fan","year":"2021","unstructured":"R. Fan, et al., Three-filters-to-normal: an accurate and ultrafast surface normal estimator. IEEE Robot. Autom. Lett. 6(3), 5405\u20135412 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"96_CR39","first-page":"3354","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A. Geiger","year":"2012","unstructured":"A. Geiger, et al., Are we ready for autonomous driving? The KITTI vision benchmark suite, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2012), pp. 3354\u20133361"},{"key":"96_CR40","first-page":"16263","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"J. Li","year":"2022","unstructured":"J. Li, et al., Practical stereo matching via cascaded recurrent network with adaptive correlation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022), pp. 16263\u201316272"},{"key":"96_CR41","first-page":"1","volume-title":"Conference on Robot Learning (CoRL)","author":"A. Dosovitskiy","year":"2017","unstructured":"A. Dosovitskiy, et al., CARLA: an open urban driving simulator, in Conference on Robot Learning (CoRL) (2017), pp. 1\u201316. PMLR"},{"key":"96_CR42","first-page":"3431","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"J. Long","year":"2015","unstructured":"J. Long, et al., Fully convolutional networks for semantic segmentation, in IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2015), pp. 3431\u20133440"},{"key":"96_CR43","unstructured":"H. Wu, et\u00a0al., FastFCN: Rethinking dilated convolution in the backbone for semantic segmentation. Comput. Res. Repos. (CoRR) (2019). arXiv:1903.11816"},{"key":"96_CR44","volume-title":"The British Machine Vision Conference (BMVC)","author":"R.P. Poudel","year":"2019","unstructured":"R.P. Poudel, et al., Fast-SCNN: fast semantic segmentation network, in The British Machine Vision Conference (BMVC) (2019)"},{"key":"96_CR45","first-page":"19529","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"J. Xu","year":"2023","unstructured":"J. Xu, et al., PIDNet: a real-time semantic segmentation network inspired by PID controllers, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023), pp. 19529\u201319539"},{"key":"96_CR46","first-page":"6399","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A. Kirillov","year":"2019","unstructured":"A. Kirillov, et al., Panoptic feature pyramid networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019), pp. 6399\u20136408"},{"key":"96_CR47","first-page":"418","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"T. Xiao","year":"2018","unstructured":"T. Xiao, et al., Unified perceptual parsing for scene understanding, in Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 418\u2013434"},{"key":"96_CR48","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"L.-C. Florian","year":"2017","unstructured":"L.-C. Florian, et al., Rethinking atrous convolution for semantic image segmentation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017)"},{"key":"96_CR49","first-page":"801","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"L.-C. Chen","year":"2018","unstructured":"L.-C. Chen, et al., Encoder-decoder with atrous separable convolution for semantic image segmentation, in Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 801\u2013818"},{"key":"96_CR50","first-page":"3562","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"J. He","year":"2019","unstructured":"J. He, et al., Dynamic multi-scale filters for semantic segmentation, in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), pp. 3562\u20133572"},{"key":"96_CR51","first-page":"2881","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"H. Zhao","year":"2017","unstructured":"H. Zhao, et al., Pyramid scene parsing network, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017), pp. 2881\u20132890"},{"key":"96_CR52","first-page":"234","volume-title":"Medical Image Computing and Computer-Assisted Intervention (MICCAI)","author":"O. Ronneberger","year":"2015","unstructured":"O. Ronneberger, et al., U-net: convolutional networks for biomedical image segmentation, in Medical Image Computing and Computer-Assisted Intervention (MICCAI) (Springer, Berlin, 2015), pp. 234\u2013241"},{"key":"96_CR53","first-page":"5693","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"K. Sun","year":"2019","unstructured":"K. Sun, et al., Deep high-resolution representation learning for human pose estimation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019), pp. 5693\u20135703"},{"key":"96_CR54","first-page":"9799","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"A. Kirillov","year":"2020","unstructured":"A. Kirillov, et al., PointRend: image segmentation as rendering, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020), pp. 9799\u20139808"},{"key":"96_CR55","first-page":"593","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Z. Zhu","year":"2019","unstructured":"Z. Zhu, et al., Asymmetric non-local neural networks for semantic segmentation, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019), pp. 593\u2013602"},{"key":"96_CR56","first-page":"191","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"M. Yin","year":"2020","unstructured":"M. Yin, et al., Disentangled non-local neural networks, in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, Berlin, 2020), pp. 191\u2013207"},{"key":"96_CR57","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW)","author":"Y. Cao","year":"2019","unstructured":"Y. Cao, et al., GCNet: non-local networks meet squeeze-excitation networks and beyond, in Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW) (2019)"},{"key":"96_CR58","unstructured":"L. Huang, et\u00a0al., Interlaced sparse self-attention for semantic segmentation. Comput. Res. Repos. (CoRR) (2019). arXiv:1907.12273"},{"key":"96_CR59","first-page":"7794","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"X. Wang","year":"2018","unstructured":"X. Wang, et al., Non-local neural networks, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2018), pp. 7794\u20137803"},{"key":"96_CR60","first-page":"267","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"H. Zhao","year":"2018","unstructured":"H. Zhao, et al., PSANet: point-wise spatial attention network for scene sarsing, in Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 267\u2013283"},{"key":"96_CR61","first-page":"9167","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"X. Li","year":"2019","unstructured":"X. Li, et al., Expectation-maximization attention networks for semantic segmentation, in Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2019), pp. 9167\u20139176"},{"key":"96_CR62","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1109\/TIP.2020.3042065","volume":"30","author":"T. Wu","year":"2020","unstructured":"T. Wu, et al., CGNet: a light-weight context guided network for semantic segmentation. IEEE Trans. Image Process. 30, 1169\u20131179 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"96_CR63","volume-title":"International Conference on Learning Representations (ICLR)","author":"A. Dosovitskiy","year":"2020","unstructured":"A. Dosovitskiy, et al., An image is worth 16\u00a0\u00d7 16 words: transformers for image recognition at scale, in International Conference on Learning Representations (ICLR) (2020)"},{"key":"96_CR64","first-page":"6881","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"S. Zheng","year":"2021","unstructured":"S. Zheng, et al., Rethinking semantic segmentation from a sequence-to-sequence perspective with transformers, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021), pp. 6881\u20136890"},{"key":"96_CR65","first-page":"213","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"N. Carion","year":"2020","unstructured":"N. Carion, et al., End-to-end object detection with transformers, in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, Berlin, 2020), pp. 213\u2013229"},{"key":"96_CR66","first-page":"9355","volume":"34","author":"X. Chu","year":"2021","unstructured":"X. Chu, et al., Twins: revisiting the design of spatial attention in vision transformers. Adv. Neural Inf. Process. Syst. 34, 9355\u20139366 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"96_CR67","first-page":"12179","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"R. Ranftl","year":"2021","unstructured":"R. Ranftl, et al., Vision transformers for dense prediction, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2021), pp. 12179\u201312188"},{"key":"96_CR68","first-page":"173","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Y. Yuan","year":"2020","unstructured":"Y. Yuan, et al., Object-contextual representations for semantic segmentation, in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, Berlin, 2020), pp. 173\u2013190"},{"key":"96_CR69","first-page":"10326","volume":"34","author":"W. Zhang","year":"2021","unstructured":"W. Zhang, et al., K-Net: towards unified image segmentation. Adv. Neural Inf. Process. Syst. 34, 10326\u201310338 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"96_CR70","first-page":"17864","volume":"34","author":"B. Cheng","year":"2021","unstructured":"B. Cheng, et al., 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":"96_CR71","first-page":"1290","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"B. Cheng","year":"2022","unstructured":"B. Cheng, et al., Masked-attention mask transformer for universal image segmentation, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022), pp. 1290\u20131299"},{"key":"96_CR72","first-page":"5108","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"Q. Ha","year":"2017","unstructured":"Q. Ha, et al., MFNet: towards real-time semantic segmentation for autonomous vehicles with multi-spectral scenes, in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE, 2017), pp. 5108\u20135115"},{"issue":"3","key":"96_CR73","doi-asserted-by":"publisher","first-page":"2576","DOI":"10.1109\/LRA.2019.2904733","volume":"4","author":"Y. Sun","year":"2019","unstructured":"Y. Sun, et al., RTFNet: RGB-thermal fusion network for semantic segmentation of urban scenes. IEEE Robot. Autom. Lett. 4(3), 2576\u20132583 (2019). https:\/\/doi.org\/10.1109\/LRA.2019.2904733","journal-title":"IEEE Robot. Autom. Lett."},{"key":"96_CR74","first-page":"376","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"J.M. Alvarez","year":"2012","unstructured":"J.M. Alvarez, et al., Road scene segmentation from a single image, in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, Berlin, 2012), pp. 376\u2013389"},{"issue":"3","key":"96_CR75","doi-asserted-by":"publisher","first-page":"101","DOI":"10.5772\/63561","volume":"13","author":"L. Xiao","year":"2016","unstructured":"L. Xiao, et al., Monocular road detection using structured random forest. Int. J. Adv. Robot. Syst. 13(3), 101 (2016)","journal-title":"Int. J. Adv. Robot. Syst."},{"key":"96_CR76","volume-title":"International Conference on Computer Vision Theory and Applications (VISAPP)","author":"C.-A. Brust","year":"2015","unstructured":"C.-A. Brust, et al., Convolutional patch networks with spatial prior for road detection and urban scene understanding, in International Conference on Computer Vision Theory and Applications (VISAPP) (2015)"},{"key":"96_CR77","first-page":"4","volume-title":"Proceedings of the British Machine Vision Conference (BMVC)","author":"D. Levi","year":"2015","unstructured":"D. Levi, et al., StixelNet: a deep convolutional network for obstacle detection and road segmentation, in Proceedings of the British Machine Vision Conference (BMVC), vol.\u00a01 (2015), p.\u00a04"},{"issue":"1","key":"96_CR78","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1109\/TMECH.2021.3061077","volume":"27","author":"R. Fan","year":"2021","unstructured":"R. Fan, et al., Learning collision-free space detection from stereo images: homography matrix brings better data augmentation. IEEE\/ASME Trans. Mechatron. 27(1), 225\u2013233 (2021)","journal-title":"IEEE\/ASME Trans. Mechatron."},{"issue":"8","key":"96_CR79","doi-asserted-by":"publisher","first-page":"9909","DOI":"10.1109\/TITS.2024.3359242","volume":"25","author":"H. Zhou","year":"2024","unstructured":"H. Zhou, et al., Exploiting low-level representations for ultra-fast road segmentation. IEEE Trans. Intell. Transp. Syst. 25(8), 9909\u20139919 (2024)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"96_CR80","first-page":"801","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"L.-C. Chen","year":"2018","unstructured":"L.-C. Chen, et al., Encoder-decoder with atrous separable convolution for semantic image segmentation, in Proceedings of the European Conference on Computer Vision (ECCV) (2018), pp. 801\u2013818"},{"key":"96_CR81","first-page":"770","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"K. He","year":"2016","unstructured":"K. He, et al., Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016), pp. 770\u2013778"},{"key":"96_CR82","first-page":"1019","volume-title":"IEEE Intelligent Vehicles Symposium (IV)","author":"L. Caltagirone","year":"2017","unstructured":"L. Caltagirone, et al., Fast LIDAR-based road detection using fully convolutional neural networks, in IEEE Intelligent Vehicles Symposium (IV) (IEEE, 2017), pp. 1019\u20131024"},{"issue":"5","key":"96_CR83","doi-asserted-by":"publisher","first-page":"1769","DOI":"10.1109\/TCSI.2018.2881162","volume":"66","author":"Y. Lyu","year":"2018","unstructured":"Y. Lyu, et al., ChipNet: real-time LiDAR processing for drivable region segmentation on an FPGA. IEEE Trans. Circuits Syst. 66(5), 1769\u20131779 (2018)","journal-title":"IEEE Trans. Circuits Syst."},{"key":"96_CR84","first-page":"6144","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"S. Gu","year":"2019","unstructured":"S. Gu, et al., Two-view fusion based convolutional neural network for urban road detection, in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE, 2019), pp. 6144\u20136149"},{"key":"96_CR85","doi-asserted-by":"publisher","first-page":"3832","DOI":"10.1109\/ICRA.2019.8793585","volume-title":"2019 International Conference on Robotics and Automation (ICRA)","author":"S. Gu","year":"2019","unstructured":"S. Gu, et al., Road detection through CRF based LiDAR-camera fusion, in 2019 International Conference on Robotics and Automation (ICRA) (IEEE, 2019), pp. 3832\u20133838"},{"key":"96_CR86","first-page":"13308","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"S. Gu","year":"2021","unstructured":"S. Gu, et al., A cascaded LiDAR-camera fusion network for road detection, in IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2021), pp. 13308\u201313314"},{"issue":"10","key":"96_CR87","doi-asserted-by":"publisher","first-page":"3349","DOI":"10.1109\/TPAMI.2020.2983686","volume":"43","author":"J. Wang","year":"2020","unstructured":"J. Wang, et al., Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"96_CR88","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.robot.2018.11.002","volume":"111","author":"L. Caltagirone","year":"2019","unstructured":"L. Caltagirone, et al., LiDAR\u2013camera fusion for road detection using fully convolutional neural networks. Robot. Auton. Syst. 111, 125\u2013131 (2019)","journal-title":"Robot. Auton. Syst."},{"issue":"3","key":"96_CR89","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1109\/JAS.2019.1911459","volume":"6","author":"Z. Chen","year":"2019","unstructured":"Z. Chen, et al., Progressive LiDAR adaptation for road detection. IEEE\/CAA J. Autom. Sin. 6(3), 693\u2013702 (2019)","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"96_CR90","doi-asserted-by":"publisher","unstructured":"A.A. Khan, et\u00a0al., LRDNet: Lightweight LiDAR Aided Cascaded Feature Pools for Free Road Space Detection. IEEE Trans. Multimed., 1\u201313 (2022). https:\/\/doi.org\/10.1109\/TMM.2022.3230330","DOI":"10.1109\/TMM.2022.3230330"},{"key":"96_CR91","first-page":"11124","volume-title":"IEEE International Conference on Robotics and Automation (ICRA)","author":"Y. Chang","year":"2022","unstructured":"Y. Chang, et al., Fast road segmentation via uncertainty-aware symmetric network, in IEEE International Conference on Robotics and Automation (ICRA) (IEEE, 2022), pp. 11124\u201311130"},{"key":"96_CR92","first-page":"2706","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","author":"H. Wang","year":"2020","unstructured":"H. Wang, et al., Applying surface normal information in drivable area and road anomaly detection for ground mobile robots, in IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE, 2020), pp. 2706\u20132711"},{"key":"96_CR93","first-page":"191","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"M. Yin","year":"2020","unstructured":"M. Yin, et al., Disentangled non-local neural networks, in Proceedings of the European Conference on Computer Vision (ECCV) (Springer, Berlin, 2020), pp. 191\u2013207"},{"key":"96_CR94","first-page":"9167","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"X. Li","year":"2019","unstructured":"X. Li, et al., Expectation-maximization attention networks for semantic segmentation, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2019), pp. 9167\u20139176"},{"key":"96_CR95","first-page":"7262","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"R. Strudel","year":"2021","unstructured":"R. Strudel, et al., Segmenter: transformer for semantic segmentation, in Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2021), pp. 7262\u20137272"},{"issue":"8","key":"96_CR96","doi-asserted-by":"publisher","first-page":"5386","DOI":"10.1109\/TCSVT.2022.3146305","volume":"32","author":"L. Sun","year":"2022","unstructured":"L. Sun, et al., Pseudo-LiDAR-based road detection. IEEE Trans. Circuits Syst. Video Technol. 32(8), 5386\u20135398 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"96_CR97","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3448251","author":"J. Huang","year":"2024","unstructured":"J. Huang, et al., RoadFormer+: delivering RGB-X scene parsing through scale-aware information decoupling and advanced heterogeneous feature fusion. IEEE Trans. Intell. Veh. (2024). https:\/\/doi.org\/10.1109\/TIV.2024.3448251","journal-title":"IEEE Trans. Intell. Veh."},{"key":"96_CR98","first-page":"876","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","author":"J.-Y. Sun","year":"2019","unstructured":"J.-Y. Sun, et al., Reverse and boundary attention network for road segmentation, in Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW) (2019), pp. 876\u2013885"},{"key":"96_CR99","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3456299","author":"Z. Huang","year":"2024","unstructured":"Z. Huang, et al., Online, target-free LiDAR-camera extrinsic calibration via cross-modal mask matching. IEEE Trans. Intell. Veh. (2024). https:\/\/doi.org\/10.1109\/TIV.2024.3456299","journal-title":"IEEE Trans. Intell. Veh."},{"issue":"2","key":"96_CR100","doi-asserted-by":"publisher","first-page":"3940","DOI":"10.1109\/TIV.2024.3357056","volume":"9","author":"Z. Wu","year":"2024","unstructured":"Z. Wu, et al., S3M-Net: Joint learning of semantic segmentation and stereo matching for autonomous driving. IEEE Trans. Intell. Veh. 9(2), 3940\u20133951 (2024)","journal-title":"IEEE Trans. Intell. Veh."}],"container-title":["Autonomous Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43684-025-00096-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43684-025-00096-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43684-025-00096-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T03:39:01Z","timestamp":1741837141000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43684-025-00096-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,13]]},"references-count":100,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["96"],"URL":"https:\/\/doi.org\/10.1007\/s43684-025-00096-y","relation":{},"ISSN":["2730-616X"],"issn-type":[{"value":"2730-616X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,13]]},"assertion":[{"value":"10 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"8"}}