{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T19:01:52Z","timestamp":1778698912336,"version":"3.51.4"},"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2021,10,19]],"date-time":"2021-10-19T00:00:00Z","timestamp":1634601600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004480","name":"Natural Science Foundation of Shanxi Province","doi-asserted-by":"publisher","award":["201901d111258"],"award-info":[{"award-number":["201901d111258"]}],"id":[{"id":"10.13039\/501100004480","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Applied Basic Research Key Project of Shanxi","award":["201801d221179"],"award-info":[{"award-number":["201801d221179"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>The security of car driving is of interest due to the growing number of motor vehicles and frequent occurrence of road traffic accidents, and the combination of advanced driving assistance system (ADAS) and vehicle-road cooperation can prevent more than 90% of traffic accidents. Lane detection, as a vital part of ADAS, has poor real-time performance and accuracy in multiple scenarios, such as road damage, light changes, and traffic jams. Moreover, the sparse pixels of lane lines on the road pose a tremendous challenge to the task of lane line detection. In this study, we propose a model that fuses non bottleneck skip residual connections and an improved attention pyramid (IAP) to effectively obtain contextual information about real-time scenes and improve the robustness and real-time performance of current lane detection models. The proposed model modifies the efficient residual factorized pyramid scene parsing network (ERF-PSPNet) and utilizes skip residual connections in non bottleneck-1D modules. A decoder with an IAP provides high-level feature maps with pixel-level attention. We add an auxiliary segmenter and a lane predictor side-by-side after the encoder, the former for lane prediction and the latter to assist with semantic segmentation for classification purposes, as well as to solve the gradient disappearance problem. On the CULane dataset, the<jats:italic>F1<\/jats:italic>metric reaches 92.20% in the normal scenario, and the<jats:italic>F1<\/jats:italic>metric of the model is higher than the<jats:italic>F1<\/jats:italic>metrics of other existing models, such as ERFNet-HESA, ENet_LGAD, and DSB+LDCDI, in normal, crowded, night, dazzling light and no line scenarios; in addition, the mean<jats:italic>F1<\/jats:italic>of the nine scenarios reached 74.10%, the runtime (time taken to test 100 images) of the model was 5.88 ms, and the number of parameters was 2.31M, which means that the model achieves a good trade-off between real-time performance and accuracy compared to the current best results (i.e., a running time of 13.4 ms and 0.98M parameters).<\/jats:p>","DOI":"10.1371\/journal.pone.0252755","type":"journal-article","created":{"date-parts":[[2021,10,21]],"date-time":"2021-10-21T03:26:07Z","timestamp":1634786767000},"page":"e0252755","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":9,"title":["Real-time lane detection model based on non bottleneck skip residual connections and attention pyramids"],"prefix":"10.1371","volume":"16","author":[{"given":"Lichao","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6202-8258","authenticated-orcid":true,"given":"Xiuzhi","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1374-5285","authenticated-orcid":true,"given":"Lihu","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoming","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2021,10,19]]},"reference":[{"key":"pone.0252755.ref001","unstructured":"Ammar A, Venkatraman S, Abawajy J and Alazab M. An optimal transportation routing approach using GIS-based dynamic traffic flows, in ICMTA: Proceedings of the International Conference on Management Technology and Applications, Research Publishing Services, Singapore. 2010; 172\u2013178."},{"issue":"99","key":"pone.0252755.ref002","first-page":"1","article-title":"CANintelliIDS: Detecting In-vehicle intrusion attacks on a controller area network using CNN and attention-based GRU","author":"AR Javed","year":"2021","journal-title":"IEEE Transactions on Network Science and Engineering"},{"key":"pone.0252755.ref003","article-title":"Anomaly detection in automated vehicles using multistage attention-based convolutional neural network","author":"AR Javed","year":"2020","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"1","key":"pone.0252755.ref004","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3358797","article-title":"Driving lane detection on smartphones using deep neural networks","volume":"16","author":"B Ravi","year":"2020","journal-title":"ACM Transactions on Sensor Networks"},{"key":"pone.0252755.ref005","doi-asserted-by":"crossref","first-page":"105584","DOI":"10.1016\/j.knosys.2020.105584","article-title":"Attention deep neural network for lane marking detection","volume":"194","author":"DG Xiao","year":"2020","journal-title":"Knowledge-based systems"},{"key":"pone.0252755.ref006","doi-asserted-by":"crossref","unstructured":"Chen PR, Lo SY, Hang HM, Chan SW, Lin JJ. Efficient road lane marking detection with deep learning. 2018 IEEE 23rd International Conference on Digital Signal Processing(DSP), Shanghai, China, 2018; 1\u20135.","DOI":"10.1109\/ICDSP.2018.8631673"},{"issue":"19","key":"pone.0252755.ref007","doi-asserted-by":"crossref","first-page":"9161","DOI":"10.1007\/s00500-018-3607-x","article-title":"A robust lane detection method based on hyperbolic model","volume":"23","author":"WH Li","year":"2019","journal-title":"Soft Computing"},{"issue":"12","key":"pone.0252755.ref008","doi-asserted-by":"crossref","first-page":"4043","DOI":"10.1109\/TITS.2018.2791572","article-title":"Robust lane detection and tracking for real-time applications","volume":"19","author":"C Lee","year":"2018","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"2","key":"pone.0252755.ref009","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1007\/s12239-020-0027-6","article-title":"Lane detection and trajectory tracking control of autonomous vehicle based on model predictive control","volume":"21","author":"JJ Hu","year":"2020","journal-title":"International Journal of Automotive Technology"},{"key":"pone.0252755.ref010","article-title":"An efficient lane line detection method based on computer vision","author":"HG Zhu","year":"2021","journal-title":"Journal of Physics: Conference Series. Forthcoming"},{"key":"pone.0252755.ref011","article-title":"Hand gesture classification using a novel CNN-crow search algorithm","author":"TR Gadekallu","year":"2021","journal-title":"Complex & Intelligent Systems"},{"key":"pone.0252755.ref012","doi-asserted-by":"crossref","first-page":"101748","DOI":"10.1016\/j.cose.2020.101748","article-title":"Image-Based malware classification using ensemble of CNN architectures (IMCEC)","volume":"92","author":"D Vasan","year":"2020","journal-title":"Computers & Security"},{"key":"pone.0252755.ref013","doi-asserted-by":"crossref","first-page":"150833","DOI":"10.1109\/ACCESS.2019.2947574","article-title":"Multi-lane detection based on deep convolutional neural network","volume":"7","author":"C Fan","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0252755.ref014","doi-asserted-by":"crossref","first-page":"173148","DOI":"10.1109\/ACCESS.2019.2957053","article-title":"Improved lane detection with multilevel features in branch convolutional neural networks","volume":"7","author":"WJ Yang","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0252755.ref015","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1016\/j.neucom.2021.01.100","article-title":"Label-guided attention distillation for lane segmentation","volume":"438","author":"ZK Liu","year":"2021","journal-title":"Neurocomputing"},{"key":"pone.0252755.ref016","first-page":"1394","article-title":"Lane detection in low-light conditions using an efficient data enhancement: light conditions style transfer","author":"T Liu","year":"2020","journal-title":"IEEE Intelligent Vehicles Symposium"},{"key":"pone.0252755.ref017","article-title":"End-to-End lane marker detection via row-wise classification","author":"S Yoo","year":"2020","journal-title":"arXiv: 2005.08630v1"},{"key":"pone.0252755.ref018","article-title":"Heatmap-based vanishing point boosts lane detection","author":"YB Liu","year":"2020","journal-title":"arXiv: 2007.15602v1"},{"key":"pone.0252755.ref019","article-title":"Robust lane detection via expanded self attention","author":"M Lee","year":"2021","journal-title":"arXiv: 2102.07037v1"},{"key":"pone.0252755.ref020","doi-asserted-by":"crossref","first-page":"16473","DOI":"10.1007\/s11042-019-7475-x","article-title":"A lane detection network based on IBN and attention","volume":"79","author":"WH Li","year":"2019","journal-title":"Multimed Tools Applications"},{"issue":"6","key":"pone.0252755.ref021","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1049\/iet-its.2017.0143","article-title":"Lane detection method based on lane structural analysis and CNNs","volume":"12","author":"YY Ye","year":"2018","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"pone.0252755.ref022","doi-asserted-by":"crossref","unstructured":"He KM, Zhang XY, Ren SQ, Sun J. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Las Vegas: IEEE, 2016; 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"01","key":"pone.0252755.ref023","first-page":"40","article-title":"Semantic segmentation of landing environment for unmanned helicopter based on improved ERFNet","volume":"60","author":"J Liu","year":"2020","journal-title":"Telecommunication Engineering"},{"issue":"1","key":"pone.0252755.ref024","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","article-title":"Efficient convNet for real-time semantic segmentation","volume":"19","author":"E Romera","year":"2018","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"pone.0252755.ref025","doi-asserted-by":"crossref","unstructured":"Romera E, Alvarez JM, Bergasa LM, Arroyo R. Efficient convNet for real-time semantic segmentation. IEEE Intelligent Vehicles Symposium (IV). Los Angeles, CA, USA. 2017; 1789\u20131794.","DOI":"10.1109\/IVS.2017.7995966"},{"issue":"5","key":"pone.0252755.ref026","doi-asserted-by":"crossref","first-page":"1506","DOI":"10.3390\/s18051506","article-title":"Unifying terrain awareness for the visually impaired through real-time semantic segmentation","volume":"18","author":"KL Yang","year":"2018","journal-title":"Sensors"},{"key":"pone.0252755.ref027","doi-asserted-by":"crossref","unstructured":"Zhao HS, Shi JP, Qi XJ, Jia J. Pyramid scene parsing network. IEEE Conference on Computer Vision and Pattern Recognition, Hawaii: CVPR, 2017; 6230\u20136239.","DOI":"10.1109\/CVPR.2017.660"},{"issue":"10","key":"pone.0252755.ref028","first-page":"2501","article-title":"Super-resolution reconstruction of deep residual network with multi-level skip connections","volume":"41","author":"XQ Zhao","year":"2019","journal-title":"Journal of Electronics & Information Technology"},{"key":"pone.0252755.ref029","unstructured":"Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. Proceedings of the 32nd International Conference on International Conference on Machine Learning. 2015; 37(10): 448\u2013456."},{"key":"pone.0252755.ref030","doi-asserted-by":"crossref","first-page":"8865","DOI":"10.1109\/ACCESS.2018.2890394","article-title":"Recurrent models of visual co-attention for person re-identification","volume":"7","author":"L Lin","year":"2019","journal-title":"IEEE ACCESS"},{"issue":"2","key":"pone.0252755.ref031","first-page":"416","article-title":"Review of visual attention detection","volume":"30","author":"WG Wang","year":"2019","journal-title":"Journal of Software"},{"issue":"11","key":"pone.0252755.ref032","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.3390\/rs11111349","article-title":"Oceanic eddy identification using an AI scheme","volume":"11","author":"GJ Xu","year":"2019","journal-title":"Remote Sensing"},{"issue":"09","key":"pone.0252755.ref033","first-page":"1882","article-title":"Multi-scenario lane line detection with auxiliary loss","volume":"25","author":"LC Chen","year":"2019","journal-title":"Journal of Image and Graphics"},{"key":"pone.0252755.ref034","doi-asserted-by":"crossref","unstructured":"Pan XG, Shi JP, Luo P. Spatial as deep: spatial CNN for traffic scene understanding. 32nd AAAI Conference on Artificial Intelligence, AAAI, New Orleans. 2018; 7276\u20137283.","DOI":"10.1609\/aaai.v32i1.12301"},{"key":"pone.0252755.ref035","article-title":"LaneNet: Real-time lane detection networks for autonomous driving","author":"Z Wang","year":"2018","journal-title":"arXiv:1807.01726v1"},{"key":"pone.0252755.ref036","article-title":"A review on deep learning techniques applied to semantic segmentation","author":"A GGarcia-Garcia","year":"2017","journal-title":"arXiv:1704.06857v1"},{"issue":"04","key":"pone.0252755.ref037","first-page":"606","article-title":"Semantic segmentation of tennis scene based on series atrous convolution neural network","volume":"32","author":"YY Li","year":"2020","journal-title":"Journal of Computer-Aided Design & Computer Graphics"},{"key":"pone.0252755.ref038","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-5617-6","volume-title":"Information Retrieval: Uncertainty and Logics","author":"F Crestani","year":"1998"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0252755","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,13]],"date-time":"2023-01-13T02:56:43Z","timestamp":1673578603000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0252755"}},"subtitle":[],"editor":[{"given":"Thippa Reddy","family":"Gadekallu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,10,19]]},"references-count":38,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,10,19]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0252755","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,10,19]]}}}