{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,8]],"date-time":"2026-02-08T08:43:35Z","timestamp":1770540215492,"version":"3.49.0"},"reference-count":64,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T00:00:00Z","timestamp":1678320000000},"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>As a crucial component of the autonomous driving task, the vehicle target detection algorithm directly impacts driving safety, particularly in inclement weather situations, where the detection precision and speed are significantly decreased. This paper investigated the You Only Look Once (YOLO) algorithm and proposed an enhanced YOLOv4 for real-time target detection in inclement weather conditions. The algorithm uses the Anchor-free approach to tackle the problem of YOLO preset anchor frame and poor fit. It better adapts to the detected target size, making it suitable for multi-scale target identification. The improved FPN network transmits feature maps to unanchored frames to expand the model's sensory field and maximize the utilization of model feature data. Decoupled head detecting head to increase the precision of target category and location prediction. The experimental dataset BDD-IW was created by extracting specific labeled photos from the BDD100K dataset and fogging some of them to test the proposed method's practical implications in terms of detection precision and speed in Inclement weather conditions. The proposed method is compared to advanced target detection algorithms in this dataset. Experimental results indicated that the proposed method achieved a mean average precision of 60.3%, which is 5.8 percentage points higher than the original YOLOv4; the inference speed of the algorithm is enhanced by 4.5 fps compared to the original, reaching a real-time detection speed of 69.44 fps. The robustness test results indicated that the proposed model has considerably improved the capacity to recognize targets in inclement weather conditions and has achieved high precision in real-time detection.<\/jats:p>","DOI":"10.3389\/fnbot.2023.1058723","type":"journal-article","created":{"date-parts":[[2023,3,9]],"date-time":"2023-03-09T07:21:29Z","timestamp":1678346489000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":30,"title":["Real-time vehicle target detection in inclement weather conditions based on YOLOv4"],"prefix":"10.3389","volume":"17","author":[{"given":"Rui","family":"Wang","sequence":"first","affiliation":[]},{"given":"He","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Zhengwei","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yaming","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Guowei","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yuxin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hua","family":"Li","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2023,3,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1016\/j.jvcir.2013.08.001","article-title":"Image-based on-road vehicle detection using cost-effective histograms of oriented gradients","volume":"24","author":"Arr\u00f3spide","year":"2013","journal-title":"J. Vis. Commun. Image Rep."},{"key":"B2","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 [Preprint]. arXiv: 2004.10934"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2017\/5627281","article-title":"Vehicle detection based on deep dual-vehicle deformable part models","volume":"2017","author":"Cai","year":"2017","journal-title":"J. Sensor."},{"key":"B4","doi-asserted-by":"publisher","first-page":"5047","DOI":"10.1007\/s12652-020-02085-w","article-title":"Inception-SSD: An improved single shot detector for vehicle detection","volume":"13","author":"Chen","year":"2020","journal-title":"J. Ambient. Intell. Human. Comput"},{"key":"B5","first-page":"13728","article-title":"\u201cRepVGG: Making VGG-style convnets great again,\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ding","year":"2021"},{"key":"B6","first-page":"303","article-title":"\u201cOTA: Optimal transport assignment for object detection,\u201d","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ge","year":""},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2107.08430","article-title":"Yolox: Exceeding yolo series in 2021","author":"Ge","year":"","journal-title":"arXiv [Preprint]. arXiv: 2107.08430"},{"key":"B8","doi-asserted-by":"crossref","first-page":"7029","DOI":"10.1109\/CVPR.2019.00720","article-title":"\u201cNAS-FPN: Learning scalable feature pyramid architecture for object detection,\u201d","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Ghiasi","year":"2019"},{"key":"B9","doi-asserted-by":"publisher","first-page":"25985","DOI":"10.1007\/s11042-021-10954-5","article-title":"On-road vehicle detection in varying weather conditions using faster R-CNN with several region proposal networks","volume":"80","author":"Ghosh","year":"2021","journal-title":"Multimed. Tools Appl"},{"key":"B10","first-page":"1440","article-title":"\u201cFast R-CNN,\u201d","volume-title":"2015 IEEE International Conference on Computer Vision","author":"Girshick","year":"2015"},{"key":"B11","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","article-title":"Region-based convolutional networks for accurate object detection and segmentation","volume":"38","author":"Girshick","year":"2015","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B12","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1049\/itr2.12190","article-title":"A domain-adaptive method with cycle perceptual consistency adversarial networks for vehicle target detection in foggy weather","volume":"16","author":"Guo","year":"2022","journal-title":"IET Intell. Transp. Syst."},{"key":"B13","doi-asserted-by":"publisher","first-page":"52","DOI":"10.3390\/jimaging7030052","article-title":"A review of detection and removal of raindrops in automotive vision systems","volume":"7","author":"Hamzeh","year":"2021","journal-title":"J. Imag."},{"key":"B14","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1016\/j.egyr.2021.10.039","article-title":"Insulator detection and damage identification based on improved lightweight YOLOv4 network","volume":"7","author":"Han","year":"2021","journal-title":"Energy Rep."},{"key":"B15","doi-asserted-by":"publisher","first-page":"4230","DOI":"10.1109\/TITS.2020.3014013","article-title":"Vehicle detection and tracking in adverse weather using a deep learning framework","volume":"22","author":"Hassaballah","year":"2020","journal-title":"IEEE Trans. Intell. Transport Syst."},{"key":"B16","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"\u201cDeep residual learning for image recognition,\u201d","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2505","DOI":"10.1109\/TTE.2021.3080690","article-title":"A feature fusion method to improve the driving obstacle detection under foggy weather","volume":"7","author":"He","year":"2021","journal-title":"IEEE Trans. Transport. Elect."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1704.04861","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv [Preprint]. arXiv: 1704.04861"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1109\/TITS.2018.2838132","article-title":"SINet: A scale-insensitive convolutional neural network for fast vehicle detection","volume":"20","author":"Hu","year":"2018","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"B20","doi-asserted-by":"publisher","first-page":"2748","DOI":"10.3390\/electronics11172748","article-title":"Traffic management: Multi-scale vehicle detection in varying weather conditions using yolov4 and spatial pyramid pooling network","volume":"11","author":"Humayun","year":"2022","journal-title":"Electronics."},{"key":"B21","first-page":"784","article-title":"\u201cAcquisition of localization confidence for accurate object detection,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Jiang","year":"2018"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1016","DOI":"10.1177\/03611981211005470","article-title":"Development of a novel convolutional neural network architecture named RoadweatherNet for trajectory-level weather detection using SHRP2 naturalistic driving data","volume":"2675","author":"Khan","year":"2021","journal-title":"Transp. Res. Rec"},{"key":"B23","doi-asserted-by":"publisher","first-page":"7389","DOI":"10.1109\/TIP.2020.3002345","article-title":"Foveabox: Beyound anchor-based object detection","volume":"29","author":"Kong","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"B24","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1109\/TSMC.2018.2872891","article-title":"Feature selection based on tensor decomposition and object proposal for night-time multiclass vehicle detection","volume":"49","author":"Kuang","year":"2018","journal-title":"IEEE Trans. Syst. Man. Cybernet. Syst."},{"key":"B25","first-page":"734","article-title":"\u201cCornernet: Detecting objects as paired keypoints,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision","author":"Law","year":"2018"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.02976","article-title":"YOLOv6: A single-stage object detection framework for industrial applications","author":"Li","year":"2022","journal-title":"arXiv [Preprint]. arXiv: 2209.02976"},{"key":"B27","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B28","doi-asserted-by":"crossref","first-page":"8759","DOI":"10.1109\/CVPR.2018.00913","article-title":"\u201cPath aggregation network for instance segmentation,\u201d","volume-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2018"},{"key":"B29","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"\u201cSsd: Single shot multibox detector,\u201d","volume-title":"Computer Vision-ECCV 2016: 14th European Conference","author":"Liu","year":"2016"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.3390\/rs14071544","article-title":"Enhancing front-vehicle detection in large vehicle fleet management","volume":"14","author":"Mu","year":"2022","journal-title":"Remot. Sens."},{"key":"B31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/SoutheastCon45413.2021.9401941","article-title":"A review of the impacts of defogging on deep learning-based object detectors in self-driving cars","volume":"2021","author":"Ogunrinde","year":"2021","journal-title":"SoutheastCon"},{"key":"B32","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/CVPR.2016.91","article-title":"\u201cYou only look once: unified, real-time object detection,\u201d","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition","author":"Redmon","year":"2016"},{"key":"B33","first-page":"6517","article-title":"\u201cYOLO9000: Better, faster, stronger,\u201d","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition","author":"Redmon","year":"2017"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1804.02767","article-title":"Yolov3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv [Preprint]"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"B36","article-title":"\u201cDriver assistance in fog environment based on convolutional neural networks (CNN),\u201d","volume-title":"The Proceedings of the Third International Conference on Smart City Applications","author":"Samir","year":"2018"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1409.1556","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv [Preprint]. arXiv:1409.1556"},{"key":"B38","first-page":"11560","article-title":"\u201cRevisiting the sibling head in object detector,\u201d","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Song","year":"2020"},{"key":"B39","first-page":"5686","article-title":"\u201cDeep high-resolution representation learning for human pose estimation,\u201d","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Sun","year":"2019"},{"key":"B40","article-title":"\u201cEfficientnet: rethinking model scaling for convolutional neural networks,\u201d","volume-title":"International Conference on Machine Learning","author":"Tan","year":"2019"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1093\/ijlct\/ctac084","article-title":"Vehicle detection method with low-carbon technology in haze weather based on deep neural network","volume":"17","author":"Tao","year":"2022","journal-title":"Int. J. Low-Carbon Technol."},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2205.13764","article-title":"Fully convolutional one-stage 3D object detection on LiDAR range images","author":"Tian","year":"2022","journal-title":"arXiv [Preprint]. arXiv: 2205.13764"},{"key":"B43","unstructured":"YOLOv52020"},{"key":"B44","doi-asserted-by":"crossref","first-page":"1879","DOI":"10.1109\/ICCV.2011.6126456","article-title":"\u201cSegmentation as selective search for object recognition,\u201d","volume-title":"2011 International Conference on Computer Vision","author":"van de Sande","year":"2011"},{"key":"B45","first-page":"241","article-title":"\u201cImage deraining and denoising convolutional neural network for autonomous driving,\u201d","volume-title":"2021 International Conference on High Performance Big Data and Intelligent Systems","author":"Wang","year":"2021"},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1155\/2021\/9218137","article-title":"\u201cA real-time object detector for autonomous vehicles based on YOLOv4,\u201d","volume-title":"Computational Intelligence and Neuroscience 2021","author":"Wang","year":"2021"},{"key":"B47","first-page":"p. 1607","article-title":"\u201cVehicle detection in severe weather based on pseudo-visual search and HOG-LBP feature fusion,\u201d","volume-title":"Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, Vol. 236","author":"Wang","year":"2022"},{"key":"B48","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/4235.585893","article-title":"No free lunch theorems for optimization","volume":"1","author":"Wolpert","year":"1997","journal-title":"IEEE Trans. Evolut. Comput."},{"key":"B49","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.18280\/ts.380419","article-title":"Vehicle classification and counting system using YOLO object detection technology","volume":"38","author":"Wu","year":"2021","journal-title":"Traitement du Signal"},{"key":"B50","first-page":"10183","article-title":"\u201cRethinking classification and localization for object detection,\u201d","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wu","year":"2020"},{"key":"B51","first-page":"5987","article-title":"\u201cAggregated residual transformations for deep neural networks,\u201d","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition","author":"Xie","year":"2017"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.16250","article-title":"PP-YOLOE: An evolved version of YOLO","author":"Xu","year":"2022","journal-title":"arXiv [Preprint]. arXiv:2203.16250"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1845","DOI":"10.1109\/TITS.2016.2617202","article-title":"An enhanced Viola-Jones vehicle detection method from unmanned aerial vehicles imagery","volume":"18","author":"Xu","year":"2016","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"B54","doi-asserted-by":"publisher","first-page":"910","DOI":"10.3390\/e23070910","article-title":"Robust vehicle speed measurement based on feature information fusion for vehicle multi-characteristic detection","volume":"23","author":"Yang","year":"2021","journal-title":"Entropy"},{"key":"B55","doi-asserted-by":"publisher","first-page":"475","DOI":"10.3390\/info11100475","article-title":"Traffic sign detection method based on improved SSD","volume":"11","author":"You","year":"2020","journal-title":"Information."},{"key":"B56","doi-asserted-by":"crossref","first-page":"2633","DOI":"10.1109\/CVPR42600.2020.00271","article-title":"\u201cBDD100K: A diverse driving dataset for heterogeneous multitask learning,\u201d","volume-title":"2020 IEEE\/CVF Conference on Computer Vision Pattern Recognition (CVPR)","author":"Yu","year":"2020"},{"key":"B57","doi-asserted-by":"publisher","first-page":"103514","DOI":"10.1016\/j.autcon.2020.103514","article-title":"A real-time detection approach for bridge cracks based on YOLOv4-FPM","volume":"122","author":"Yu","year":"2021","journal-title":"Automat. Const."},{"key":"B58","doi-asserted-by":"crossref","first-page":"325","DOI":"10.1007\/978-3-030-20873-8_21","article-title":"\u201cComprehensive feature enhancement module for single-shot object detector,\u201d","volume-title":"Computer Vision-ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2\u20136, 2018, Revised Selected Papers, Part V 14","author":"Zhao","year":"2019"},{"key":"B59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10723-021-09594-8","article-title":"Dim target detection method based on deep learning in complex traffic environment","volume":"20","author":"Zheng","year":"2022","journal-title":"J. Grid Comput."},{"key":"B60","doi-asserted-by":"publisher","first-page":"3604","DOI":"10.1109\/TVT.2020.2969427","article-title":"Detecting motion blurred vehicle logo in IoV using filter-DeblurGAN and VL-YOLO","volume":"69","author":"Zhou","year":"2020","journal-title":"IEEE Trans. Vehicular Technol."},{"key":"B61","volume-title":"Objects as points","author":"Zhou","year":""},{"key":"B62","first-page":"850","article-title":"\u201cBottom-up object detection by grouping extreme and center points,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhou","year":""},{"key":"B63","first-page":"840","article-title":"\u201cFeature selective anchor-free module for single-shot object detection,\u201d","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhu","year":"2019"},{"key":"B64","first-page":"2778","article-title":"\u201cTPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios,\u201d","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision Workshops","author":"Zhu","year":"2021"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1058723\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T01:04:06Z","timestamp":1729040646000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2023.1058723\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,9]]},"references-count":64,"alternative-id":["10.3389\/fnbot.2023.1058723"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2023.1058723","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,9]]},"article-number":"1058723"}}