{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T08:20:59Z","timestamp":1791447659944,"version":"4.3.3"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T00:00:00Z","timestamp":1701648000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>The visual perception model is critical to autonomous driving systems. It provides the information necessary for self-driving cars to make decisions in traffic scenes. We propose a lightweight multi-task network (Mobip) to simultaneously perform traffic object detection, drivable area segmentation, and lane line detection. The network consists of a shared encoder for feature extraction and two decoders for handling detection and segmentation tasks collectively. By using MobileNetV2 as the backbone and an extremely efficient multi-task architecture to implement the perception model, our network has great advantages in inference speed. The performance of the multi-task network is verified on a challenging public Berkeley Deep Drive(BDD100K) dataset. The model achieves an inference speed of 58 FPS on NVIDIA Tesla V100 while still maintaining competitive performance on all three tasks compared to other multi-task networks. Besides, the effectiveness and efficiency of the multi-task architecture are verified via ablative studies.<\/jats:p>","DOI":"10.3389\/fnbot.2023.1291875","type":"journal-article","created":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T06:10:47Z","timestamp":1701670247000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Mobip: a lightweight model for driving perception using MobileNet"],"prefix":"10.3389","volume":"17","author":[{"given":"Minghui","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,12,4]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2004.10934","article-title":"YOLOv4: optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1109\/TMI.2006.880587","article-title":"Generalized overlap measures for evaluation and validation in medical image analysis","volume":"25","author":"Crum","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B3","first-page":"580","article-title":"\u201cRich feature hierarchies for accurate object detection and semantic segmentation,\u201d","volume-title":"in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Girshick","year":"2014"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2208.11434","article-title":"YOLOPv2: better, faster, stronger for panoptic driving perception","author":"Han","year":"2022","journal-title":"arXiv"},{"key":"B5","first-page":"732","article-title":"\u201cRethinking channel dimensions for efficient model design,\u201d","volume-title":"Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition","author":"Han","year":"2021"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","article-title":"Spatial pyramid pooling in deep convolutional networks for visual recognition","volume":"37","author":"He","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B7","first-page":"1013","article-title":"\u201cLearning lightweight lane detection cnns by self attention distillation,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Hou","year":"2019"},{"key":"B8","first-page":"1314","article-title":"\u201cSearching for mobilenetv3,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Howard","year":"2019"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.3390\/agriculture12101659","article-title":"An attention mechanism-improved YOLOv7 object detection algorithm for hemp duck count estimation","volume":"12","author":"Jiang","year":"2022","journal-title":"Agriculture"},{"key":"B10","first-page":"2117","article-title":"\u201cFeature pyramid networks for object detection,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Lin","year":""},{"key":"B11","first-page":"2980","article-title":"\u201cFocal loss for dense object detection,\u201d","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Lin","year":""},{"key":"B12","first-page":"8759","article-title":"\u201cPath aggregation network for instance segmentation,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2018"},{"key":"B13","first-page":"3431","article-title":"Fully convolutional networks for semantic segmentation,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Long","year":"2015"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1608.03983","article-title":"SGDR: stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016","journal-title":"arXiv"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIV.2023.3270878","article-title":"Real-time memory efficient multitask learning model for autonomous driving","author":"Miraliev","year":"2023","journal-title":"IEEE Trans. Intell. Veh"},{"key":"B16","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1016\/j.neucom.2022.01.005","article-title":"Review the state-of-the-art technologies of semantic segmentation based on deep learning","volume":"493","author":"Mo","year":"2022","journal-title":"Neurocomputing"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.02147","article-title":"ENet: a deep neural network architecture for real-time semantic segmentation","author":"Paszke","year":"2016","journal-title":"arXiv"},{"key":"B18","unstructured":"PyTorch: an imperative style, high-performance deep learning library32\n            PaszkeA.\n            GrossS.\n            MassaF.\n            LererA.\n            BradburyJ.\n            ChananG.\n          Adv. Neural Inf. Process. Syst2019"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.4271\/2020-01-5179","volume-title":"Research on Application and Testing of Autonomous Driving in Ports","author":"Qin","year":"2020"},{"key":"B20","first-page":"10428","article-title":"\u201cDesigning network design spaces,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Radosavovic","year":"2020"},{"key":"B21","first-page":"779","article-title":"\u201cYou only look once: unified, real-time object detection,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Redmon","year":"2016"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767","article-title":"YOLOv3: an incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv"},{"key":"B23","doi-asserted-by":"publisher","first-page":"115","DOI":"10.4236\/jcc.2022.101006","article-title":"Overview of object detection algorithms using convolutional neural networks","volume":"10","author":"Ren","year":"2022","journal-title":"J. Comput. Commun"},{"key":"B24","unstructured":"Faster R-CNN: towards real-time object detection with region proposal networks28\n            RenS.\n            HeK.\n            GirshickR.\n            SunJ.\n          27295650Adv. Neural Inf. Process. Syst2015"},{"key":"B25","first-page":"234","article-title":"\u201cU-Net: convolutional networks for biomedical image segmentation,\u201d","volume-title":"Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18","author":"Ronneberger","year":"2015"},{"key":"B26","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1007\/978-3-031-05359-7_15","article-title":"\u201cInvestigating the requirements of automated vehicles for port-internal logistics of containers,\u201d","volume-title":"International Conference on Dynamics in Logistics","author":"Rose","year":"2022"},{"key":"B27","first-page":"4510","article-title":"\u201cMobileNetv2: inverted residuals and linear bottlenecks,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Sandler","year":"2018"},{"key":"B28","doi-asserted-by":"crossref","first-page":"240","DOI":"10.1007\/978-3-319-67558-9_28","article-title":"\u201cGeneralised dice overlap as a deep learning loss function for highly unbalanced segmentations,\u201d","volume-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017, Qu\u00e9bec City, QC, Canada, September 14, Proceedings 3","author":"Sudre","year":"2017"},{"key":"B29","article-title":"\u201cEfficientnet: rethinking model scaling for convolutional neural networks,\u201d","volume-title":"Proceedings of International Conference on Machine Learning","author":"Tan","year":"2019"},{"key":"B30","doi-asserted-by":"crossref","first-page":"1013","DOI":"10.1109\/IVS.2018.8500504","article-title":"\u201cMultinet: real-time joint semantic reasoning for autonomous driving,\u201d","volume-title":"2018 IEEE Intelligent Vehicles Symposium (IV)","author":"Teichmann","year":"2018"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.09035","article-title":"Hybridnets: end-to-end perception network","author":"Vu","year":"2022","journal-title":"arXiv"},{"key":"B32","first-page":"7464","article-title":"\u201cYOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2023"},{"key":"B33","doi-asserted-by":"publisher","first-page":"10750","DOI":"10.1109\/TCYB.2021.3064089","article-title":"Dynamic fusion module evolves drivable area and road anomaly detection: a benchmark and algorithms","volume":"52","author":"Wang","year":"2021","journal-title":"IEEE Trans. Cybern"},{"key":"B34","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1007\/s11633-022-1339-y","article-title":"YOLOP: you only look once for panoptic driving perception","volume":"19","author":"Wu","year":"2022","journal-title":"Mach. Intell. Res"},{"key":"B35","first-page":"2636","article-title":"\u201cBDD100K: a diverse driving dataset for heterogeneous multitask learning,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yu","year":"2020"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1710.09412","article-title":"mixup: beyond empirical risk minimization","author":"Zhang","year":"2017","journal-title":"arXiv"},{"key":"B37","first-page":"2881","article-title":"\u201cPyramid scene parsing network,\u201d","volume-title":"ProceeEdings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Zhao","year":"2017"},{"key":"B38","doi-asserted-by":"publisher","first-page":"12993","DOI":"10.1609\/aaai.v34i07.6999","article-title":"Distance-iou loss: faster and better learning for bounding box regression","volume":"34","author":"Zheng","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B39","first-page":"2582","article-title":"\u201cRethinking semantic segmentation: a prototype view,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhou","year":"2022"},{"key":"B40","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/TVT.2019.2949603","article-title":"Robust lane detection from continuous driving scenes using deep neural networks","volume":"69","author":"Zou","year":"2019","journal-title":"IEEE Trans. Veh. Technol"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1291875\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,4]],"date-time":"2023-12-04T06:11:16Z","timestamp":1701670276000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1291875\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,4]]},"references-count":40,"alternative-id":["10.3389\/fnbot.2023.1291875"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1291875","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,4]]},"article-number":"1291875"}}