{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T01:21:56Z","timestamp":1782004916973,"version":"3.54.5"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T00:00:00Z","timestamp":1740009600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Key R&D Program of Shandong Province","award":["2023CXGC010111"],"award-info":[{"award-number":["2023CXGC010111"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Aiming at the problems of low detection accuracy and redundant model parameters in the current road scene detection, a RADNet-based road scene detection algorithm is proposed. In this algorithm, an efficient backbone structure CSPResRepBlock is designed to enable the model to obtain more comprehensive target information. Secondly, a multi-feature fusion progressive pyramid is designed to significantly alleviate the elimination of target feature information during the feature fusion process. Meanwhile, a new decoupling head structure called Efficient Dynamic DCNv2 Head is designed, which significantly improves the model\u2019s sensitivity to deformation or edge blurring features. In addition, a structured pruning algorithm is introduced to achieve network acceleration by automatically analyzing complex structural couplings and correctly removing parameters. Finally, experiments on the BDD100K dataset show that the RADNet\u00a0algorithm improves the average detection accuracy mAP50 by 6.3% and reduces the number of parameters by 68.6% and the computational effort by 30.3% compared to Yolov8s. The inference speed of the model is 114.1 FPS. The model\u2019s generalizability was evaluated using four additional publicly available datasets. These results show that the RADNet\u00a0algorithm is effective and superior for the task of autopilot target detection.<\/jats:p>","DOI":"10.1093\/comjnl\/bxaf002","type":"journal-article","created":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T15:25:18Z","timestamp":1739373918000},"page":"763-774","source":"Crossref","is-referenced-by-count":1,"title":["RADNet: a highly and robust dynamic network for object detection in complex road scenes"],"prefix":"10.1093","volume":"68","author":[{"given":"Wenyang","family":"Zhao","sequence":"first","affiliation":[{"name":"Institute of Automation, Qilu University of Technology (Shandong Academy of Sciences) , Jinan ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyao","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Qilu University of Technology (Shandong Academy of Sciences) , Jinan ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Qilu University of Technology (Shandong Academy of Sciences) , Jinan ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,2,20]]},"reference":[{"key":"2025071900315903300_ref1","first-page":"12","article-title":"Overview on key technology of perceptual system on self-driving vehicles","volume":"57","author":"Yi-Fan","year":"2016","journal-title":"Autoelectr Parts"},{"key":"2025071900315903300_ref2","doi-asserted-by":"crossref","first-page":"4224","DOI":"10.1109\/TII.2018.2822828","article-title":"Object classification using CNN-based fusion of vision and LIDAR in autonomous vehicle environment","volume":"14","author":"Gao","year":"2018","journal-title":"IEEE Trans Industr Inform"},{"key":"2025071900315903300_ref3","doi-asserted-by":"crossref","first-page":"6468","DOI":"10.1109\/TNNLS.2021.3136866","article-title":"An interacting multiple model for trajectory prediction of intelligent vehicles in typical road traffic scenario","volume":"34","author":"Gao","year":"2023","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2025071900315903300_ref4","first-page":"1","article-title":"An improved SSD-like deep network-based object detection method for indoor scenes","volume":"72","author":"Ni","year":"2023","journal-title":"IEEE Trans Instrum Meas"},{"key":"2025071900315903300_ref5","first-page":"21","volume-title":"SSD: single shot multibox detector. Amsterdam, the Netherlands, October 11\u201314, 2016","author":"Liu","year":"2016"},{"key":"2025071900315903300_ref6","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025071900315903300_ref7","first-page":"1","article-title":"Yolov3: an incremental improvement","volume-title":"Computer Vision and Pattern Recognition","author":"Farhadi","year":"2018"},{"key":"2025071900315903300_ref8","first-page":"13029","article-title":"Scaled-yolov4: scaling cross stage partial network","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2021"},{"key":"2025071900315903300_ref9","volume-title":"YOLOv5","author":"Bochkovskiy","year":"2020"},{"key":"2025071900315903300_ref10","article-title":"YOLOv6: a single-stage object detection framework for industrial applications","author":"Li","year":"2022"},{"key":"2025071900315903300_ref11","volume-title":"YOLOv8","author":"Bochkovskiy","year":"2023"},{"key":"2025071900315903300_ref12","doi-asserted-by":"crossref","first-page":"580","DOI":"10.1109\/CVPR.2014.81","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","volume-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition","author":"Girshick","year":"2014"},{"key":"2025071900315903300_ref13","first-page":"1440","article-title":"Fast R-CNN","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Girshick","year":"2015"},{"key":"2025071900315903300_ref14","doi-asserted-by":"crossref","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":"2016","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2025071900315903300_ref15","first-page":"2961","article-title":"Mask R-CNN","volume-title":"2017 IEEE International Conference on Computer Vision","author":"He","year":"2017"},{"key":"2025071900315903300_ref16","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/s11263-013-0620-5","article-title":"Selective search for object recognition","volume":"104","author":"Uijlings","year":"2013","journal-title":"Int J Comput Vis"},{"key":"2025071900315903300_ref17","article-title":"Yolox: exceeding yolo series in 2021","author":"Ge","year":"2021"},{"key":"2025071900315903300_ref18","first-page":"7464","article-title":"YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wang","year":"2023"},{"key":"2025071900315903300_ref19","first-page":"1751","article-title":"Research on object detection method in driving scenario based on improved YOLOv4","volume-title":"2022 IEEE Information Technology and Mechatronics Engineering Conference","author":"Wang","year":"2022"},{"key":"2025071900315903300_ref20","doi-asserted-by":"crossref","first-page":"1427","DOI":"10.1007\/s13369-022-06874-7","article-title":"DW-YOLO: an efficient object detector for drones and self-driving vehicles","volume":"48","author":"Chen","year":"2023","journal-title":"Arab J Sci Eng"},{"key":"2025071900315903300_ref21","doi-asserted-by":"crossref","first-page":"8471","DOI":"10.3390\/s23208471","article-title":"Object detection in adverse weather for autonomous driving through data merging and YOLOv8","volume":"23","author":"Kumar","year":"2023","journal-title":"Sensors"},{"key":"2025071900315903300_ref22","first-page":"032073","article-title":"Research on a pedestrian detection algorithm based on improved SSD network","author":"Dong","year":"2021","journal-title":"J Phys: Conf Ser"},{"key":"2025071900315903300_ref23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10489-019-01511-7","article-title":"Small traffic sign detection from large image","volume":"50","author":"Liu","year":"2020","journal-title":"Appl Intell"},{"key":"2025071900315903300_ref24","first-page":"16091","article-title":"Depgraph: towards any structural pruning","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Fang","year":"2023"},{"key":"2025071900315903300_ref25","first-page":"13733","article-title":"RepVGG: making VGG-style ConvNets great again","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ding","year":"2021"},{"key":"2025071900315903300_ref26","first-page":"2184","article-title":"AFPN: asymptotic feature pyramid network for object detection","volume-title":"2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","author":"Yang"},{"key":"2025071900315903300_ref27","first-page":"12021","article-title":"Run, don\u2019t walk: chasing higher FLOPS for faster neural networks","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2023"},{"key":"2025071900315903300_ref28","first-page":"1","article-title":"Deep & cross network for ad click predictions","volume-title":"2017 ADKDD\u201917, Halifax, 13\u201317 August","author":"Wang","year":"2017"},{"key":"2025071900315903300_ref29","first-page":"9308","article-title":"Deformable ConvNets v2: more deformable, better results","volume-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhu","year":"2019"},{"key":"2025071900315903300_ref30","first-page":"2636","article-title":"BDD100K: a diverse driving dataset for heterogeneous multitask learning","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yu","year":"2020"},{"key":"2025071900315903300_ref31","article-title":"SODA10M: towards large-scale object detection benchmark for autonomous driving","author":"Han","year":"2021"},{"key":"2025071900315903300_ref32","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW.2019.00030","article-title":"VisDrone-DET2019: the vision meets drone object detection in image challenge results","volume-title":"2019 IEEE\/CVF International Conference on Computer Vision Workshops","author":"Du","year":"2019"},{"key":"2025071900315903300_ref33","doi-asserted-by":"crossref","first-page":"380","DOI":"10.1109\/TMM.2019.2929005","article-title":"WiderPerson: a diverse dataset for dense pedestrian detection in the wild","volume":"22","author":"Zhang","year":"2020","journal-title":"IEEE Trans Multimed"},{"key":"2025071900315903300_ref34","article-title":"CCTSDB 2021: a more comprehensive traffic sign detection benchmark","volume":"12","author":"Zhang"},{"key":"2025071900315903300_ref35","article-title":"Yolov10: real-time end-to-end object detection","author":"Wang","year":"2024"},{"key":"2025071900315903300_ref46","first-page":"16965","article-title":"DETRs beat YOLOs on real-time object detection","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Zhao","year":"2024"},{"key":"2025071900315903300_ref36","first-page":"14420","article-title":"EfficientViT: memory efficient vision transformer with cascaded group attention","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Liu","year":"2023"},{"key":"2025071900315903300_ref37","first-page":"16133","article-title":"ConvNeXt V2: co-designing and scaling ConvNets with masked autoencoders","volume-title":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Woo","year":"2023"},{"key":"2025071900315903300_ref38","first-page":"10781","article-title":"EfficientDet: scalable and efficient object detection","volume-title":"2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Tan","year":"2020"},{"key":"2025071900315903300_ref39","article-title":"Gold-YOLO: efficient object detector via gather-and-distribute mechanism","volume":"36","author":"Wang","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025071900315903300_ref40","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1007\/s11554-024-01436-6","article-title":"Slim-neck by GSConv: a lightweight-design for real-time detector architectures","volume":"21","author":"Li","journal-title":"J Real-Time Image Proc"},{"key":"2025071900315903300_ref41","first-page":"2763","article-title":"GraphFPN: graph feature pyramid network for object detection","volume-title":"2021 IEEE\/CVF International Conference on Computer Vision","author":"Zhao","year":"2021"},{"key":"2025071900315903300_ref42","first-page":"13713","article-title":"Coordinate attention for efficient mobile network design","volume-title":"2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hou","year":"2021"},{"key":"2025071900315903300_ref43","first-page":"3","article-title":"CBAM: convolutional block attention module","volume-title":"2018 European Conference on Computer Vision","author":"Woo","year":"2018"},{"key":"2025071900315903300_ref44","first-page":"7132","article-title":"Squeeze-and-excitation networks","volume-title":"2018 IEEE Conference on Computer Vision and Pattern Recognition","author":"Hu","year":"2018"},{"key":"2025071900315903300_ref45","first-page":"11863","volume-title":"SimAM: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks","author":"Yang","year":"2021"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/advance-article-pdf\/doi\/10.1093\/comjnl\/bxaf002\/62005554\/bxaf002.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/advance-article-pdf\/doi\/10.1093\/comjnl\/bxaf002\/62005554\/bxaf002.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T04:32:12Z","timestamp":1752899532000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/68\/7\/763\/8025940"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,20]]},"references-count":46,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,2,20]]},"published-print":{"date-parts":[[2025,7,16]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxaf002","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,2,20]]}}}