{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T17:07:38Z","timestamp":1773248858780,"version":"3.50.1"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T00:00:00Z","timestamp":1721865600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T00:00:00Z","timestamp":1721865600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62176110"],"award-info":[{"award-number":["62176110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1007\/s11554-024-01517-6","type":"journal-article","created":{"date-parts":[[2024,7,25]],"date-time":"2024-07-25T09:02:28Z","timestamp":1721898148000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["An improved YOLOv8 algorithm for small object detection in autonomous driving"],"prefix":"10.1007","volume":"21","author":[{"given":"Jie","family":"Cao","sequence":"first","affiliation":[]},{"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Liang","family":"Hou","sequence":"additional","affiliation":[]},{"given":"Ning","family":"Nan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,7,25]]},"reference":[{"key":"1517_CR1","doi-asserted-by":"publisher","unstructured":"Girshick R, Donahue J, Darrell T, et al.:Rich feature hierarchies for accurate object detection and semantic segmentation.2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014). https:\/\/doi.org\/10.1109\/cvpr.2014.81","DOI":"10.1109\/cvpr.2014.81"},{"key":"1517_CR2","doi-asserted-by":"publisher","unstructured":"Girshick R.Fast R-CNN. 2015 IEEE International Conference on Computer Vision (ICCV) (2015). https:\/\/doi.org\/10.1109\/iccv.2015.169","DOI":"10.1109\/iccv.2015.169"},{"key":"1517_CR3","doi-asserted-by":"crossref","unstructured":"Ren S, He K, Girshick R, et al.:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks.IEEE Transactions on Pattern Analysis and Machine Intelligence,1137\u20131149 (2017)","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"1517_CR4","doi-asserted-by":"publisher","unstructured":"Cai Z, Vasconcelos N.Cascade R-CNN: Delving into High Quality Object Detection.2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00644","DOI":"10.1109\/cvpr.2018.00644"},{"key":"1517_CR5","doi-asserted-by":"crossref","unstructured":"He K, Gkioxari G, Dollar P, et al.:Mask R-CNN. IEEE Transactions on Pattern Analysis and Machine Intelligence,386\u201397 (2020)","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"1517_CR6","doi-asserted-by":"publisher","unstructured":"Liu W, Anguelov D, Erhan D, et al.:SSD: Single Shot MultiBox Detector, Computer Vision\u2013ECCV,pp.21\u201337.Springer,Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"1517_CR7","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Goyal P, Girshick R, et al.:Focal Loss for Dense Object Detection.2017 IEEE International Conference on Computer Vision (ICCV) (2017). https:\/\/doi.org\/10.1109\/iccv.2017.324","DOI":"10.1109\/iccv.2017.324"},{"key":"1517_CR8","doi-asserted-by":"publisher","unstructured":"Tian Z, Shen C, Chen H, et al.:FCOS: Fully Convolutional One-Stage Object Detection.2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (2019). https:\/\/doi.org\/10.1109\/iccv.2019.00972","DOI":"10.1109\/iccv.2019.00972"},{"key":"1517_CR9","unstructured":"Duan K, Bai S, Xie L, et al.:CenterNet: Object Detection with Keypoint Triplets (2019)"},{"key":"1517_CR10","doi-asserted-by":"publisher","unstructured":"Redmon J, Divvala S, Girshick R, et al.:You Only Look Once: Unified, Real-Time Object Detection.2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016). https:\/\/doi.org\/10.1109\/cvpr.2016.91","DOI":"10.1109\/cvpr.2016.91"},{"key":"1517_CR11","doi-asserted-by":"publisher","unstructured":"Zhu X, Lyu S, Wang X, et al.:TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios.2021 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW) (2021). https:\/\/doi.org\/10.1109\/iccvw54120.2021.00312","DOI":"10.1109\/iccvw54120.2021.00312"},{"key":"1517_CR12","unstructured":"Ultralytics.YOLOv5.Github code (2020) https:\/\/github.com\/ultralytics\/YOLOv5"},{"key":"1517_CR13","unstructured":"Dong X, Yan S, Duan C.A lightweight vehicles detection network model based on YOLOv5"},{"key":"1517_CR14","doi-asserted-by":"publisher","unstructured":"Han K, Wang Y, Tian Q, et al.:GhostNet: More Features from Cheap Operations.2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.00165","DOI":"10.1109\/cvpr42600.2020.00165"},{"key":"1517_CR15","doi-asserted-by":"publisher","unstructured":"Woo S, Park J, Lee J-Y, et al.:CBAM: Convolutional Block Attention Module,ComputerVision\u2013ECCV, pp.3\u201319.Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1517_CR16","doi-asserted-by":"crossref","unstructured":"Zheng Z, Wang P, Liu W, et al.:Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression.Proceedings of the AAAI Conference on Artificial Intelligence, 12993\u20133000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"1517_CR17","unstructured":"Hamzenejadi M, Mohseni H.Fine-tuned YOLOv5 for real-time vehicle detection in UAV imagery: Architectural improvements and performance boost"},{"key":"1517_CR18","doi-asserted-by":"publisher","unstructured":"Hu J, Shen L, Sun G.Squeeze-and-Excitation Networks.2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00745","DOI":"10.1109\/cvpr.2018.00745"},{"key":"1517_CR19","unstructured":"Bie M, Liu Y, Li G, et al.:Real-time vehicle detection algorithm based on a lightweight You-Only-Look-Once (YOLOv5n-L) approach"},{"key":"1517_CR20","doi-asserted-by":"publisher","unstructured":"Chollet F.Xception: Deep Learning with Depthwise Separable Convolutions.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.195","DOI":"10.1109\/cvpr.2017.195"},{"key":"1517_CR21","doi-asserted-by":"publisher","unstructured":"Tan M, Pang R, Le Q V.EfficientDet: Scalable and Efficient Object Detection.2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR) (2020). https:\/\/doi.org\/10.1109\/cvpr42600.2020.01079","DOI":"10.1109\/cvpr42600.2020.01079"},{"key":"1517_CR22","unstructured":"Kang L, Lu Z, Meng L, et al.:YOLO-FA: Type-1 fuzzy attention based YOLO detector for vehicle detection"},{"key":"1517_CR23","unstructured":"Ultralytics.YOLOv8.Github code (2023) https:\/\/github.com\/ultralytics\/YOLOv8"},{"key":"1517_CR24","doi-asserted-by":"crossref","unstructured":"Sunkara R, Luo T.No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects (2022)","DOI":"10.1007\/978-3-031-26409-2_27"},{"key":"1517_CR25","doi-asserted-by":"publisher","unstructured":"Dai X, Chen Y, Xiao B, et al.:Dynamic Head: Unifying Object Detection Heads with Attentions.2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2021).https:\/\/doi.org\/10.1109\/cvpr46437.2021.00729","DOI":"10.1109\/cvpr46437.2021.00729"},{"key":"1517_CR26","doi-asserted-by":"publisher","unstructured":"Bodla N, Singh B, Chellappa R, et al.:Soft-NMS \u2014 Improving Object Detection with One Line of Code.2017 IEEE International Conference on Computer Vision (ICCV) (2017).https:\/\/doi.org\/10.1109\/iccv.2017.593","DOI":"10.1109\/iccv.2017.593"},{"key":"1517_CR27","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-Y.YOLOv4: Optimal speed and accuracy of object detection. Cornell University - arXiv,Cornell University \u2013 arXiv (2020)"},{"key":"1517_CR28","doi-asserted-by":"publisher","unstructured":"Lin T-Y, Dollar P, Girshick R, et al.:Feature Pyramid Networks for Object Detection.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017).https:\/\/doi.org\/10.1109\/cvpr.2017.106","DOI":"10.1109\/cvpr.2017.106"},{"key":"1517_CR29","doi-asserted-by":"crossref","unstructured":"Chen X, Zhao Y, Qin Y, et al.:PANet: Perspective-aware network with dynamic receptive fields and self-distilling supervision for crowd counting. SSRN Electronic Journal (2022)","DOI":"10.2139\/ssrn.4194721"},{"key":"1517_CR30","unstructured":"Ge Z, Liu S, Wang F, et al.:YOLOX: Exceeding YOLO Series in 2021 (2021)"},{"key":"1517_CR31","unstructured":"Redmon J, Farhadi A.YOLOv3: An Incremental Improvement.arXiv: Computer Vision and Pattern Recognition,arXiv: Computer Vision and Pattern Recognition (2018)"},{"key":"1517_CR32","doi-asserted-by":"crossref","unstructured":"Wang J, Chen Y, Dong Z, et al.: Improved YOLOv5 network for real-time multi-scale traffic sign detection.Neural Computing and Applications,7853\u20137865 (2023)","DOI":"10.1007\/s00521-022-08077-5"},{"key":"1517_CR33","doi-asserted-by":"publisher","unstructured":"Nishiyama T, Kumagai A, Kamiya K, et al.:SILU: Strategy Involving Large-scale Unlabeled Logs for Improving Malware Detector.2020 IEEE Symposium on Computers and Communications (ISCC) (2020).https:\/\/doi.org\/10.1109\/iscc50000.2020.9219571","DOI":"10.1109\/iscc50000.2020.9219571"},{"key":"1517_CR34","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, et al.:Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence,1904\u20131916 (2015)","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"1517_CR35","doi-asserted-by":"crossref","unstructured":"Neubeck A, Gool L V: Efficient Non-Maximum Suppression.18th International Conference on Pattern Recognition (ICPR\u201906),850\u2013855 (2006)","DOI":"10.1109\/ICPR.2006.479"},{"key":"1517_CR36","unstructured":"Li X, Wang W, Wu L, et al.:Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection.Cornell University - arXiv,Cornell University \u2013 arXiv (2020)"},{"key":"1517_CR37","unstructured":"Yu F, Xian W, Chen Y, et al.:BDD100K: a diverse driving video database with scalable annotation tooling. arXiv: Computer Vision and Pattern Recognition (2018)"},{"key":"1517_CR38","unstructured":"Wang C, He W, Nie Y, et al.:Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism.ArXiv (2023)"},{"key":"1517_CR39","unstructured":"Wang Z, Li C, Xu H, et al.:Mamba YOLO: SSMs-Based YOLO For Object Detection.arXiv preprint arXiv:240605835 (2024)"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01517-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01517-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01517-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T16:33:47Z","timestamp":1724776427000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01517-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,25]]},"references-count":39,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["1517"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01517-6","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,7,25]]},"assertion":[{"value":"29 February 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 July 2024","order":3,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"138"}}