{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T11:00:50Z","timestamp":1784804450488,"version":"3.55.0"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T00:00:00Z","timestamp":1730246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"The Key Research and Development Project in Xinjiang Uygul Autonomous Region","award":["No.2022B01006"],"award-info":[{"award-number":["No.2022B01006"]}]},{"name":"This research was funded by The National Natural Science Foundation of China","award":["No.62162059"],"award-info":[{"award-number":["No.62162059"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1007\/s11227-024-06611-x","type":"journal-article","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:17:28Z","timestamp":1730301448000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["LightUAV-YOLO: a lightweight object detection model for unmanned aerial vehicle image"],"prefix":"10.1007","volume":"81","author":[{"given":"Yifan","family":"Lyu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianze","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aixun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,30]]},"reference":[{"issue":"1","key":"6611_CR1","doi-asserted-by":"publisher","first-page":"9711","DOI":"10.1038\/s41598-023-36868-w","volume":"13","author":"X Jia","year":"2023","unstructured":"Jia X, Tong Y, Qiao H, Li M, Tong J, Liang B (2023) Fast and accurate object detector for autonomous driving based on improved yolov5. Sci Rep 13(1):9711","journal-title":"Sci Rep"},{"issue":"14","key":"6611_CR2","doi-asserted-by":"publisher","first-page":"21627","DOI":"10.1007\/s11042-023-14696-4","volume":"82","author":"Y Teja","year":"2023","unstructured":"Teja Y (2023) Static object detection for video surveillance. Multimed Tools Appl 82(14):21627\u201321639","journal-title":"Multimed Tools Appl"},{"key":"6611_CR3","doi-asserted-by":"crossref","unstructured":"Zhao H, Zhang H, Zhao Y (2023) Yolov7-Sea: Object Detection of Maritime UAV Images Based on Improved yolov7. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 233\u2013238","DOI":"10.1109\/WACVW58289.2023.00029"},{"issue":"17","key":"6611_CR4","doi-asserted-by":"publisher","first-page":"3664","DOI":"10.3390\/electronics12173664","volume":"12","author":"X Zhai","year":"2023","unstructured":"Zhai X, Huang Z, Li T, Liu H, Wang S (2023) Yolo-drone: an optimized yolov8 network for tiny uav object detection. Electronics 12(17):3664","journal-title":"Electronics"},{"key":"6611_CR5","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"6611_CR6","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"6611_CR7","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster r-cnn: Towards real-time object detection with region proposal networks. Adv Neural Inform Process Syst 28"},{"key":"6611_CR8","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You Only Look Once: Unified, Real-Time Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"6611_CR9","doi-asserted-by":"crossref","unstructured":"Redmon J, Farhadi A(2017) Yolo9000: Better, Faster, Stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7263\u20137271","DOI":"10.1109\/CVPR.2017.690"},{"key":"6611_CR10","unstructured":"Redmon J, Farhadi A (2018) Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767"},{"key":"6611_CR11","unstructured":"Bochkovskiy A, Wang C-Y, Liao H-YM(2020) Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934"},{"key":"6611_CR12","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-YM(2023) Yolov7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7464\u20137475","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"6611_CR13","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu C-Y, Berg AC (2016) Ssd: Single Shot Multibox Detector. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I 14, pp 21\u201337 . Springer","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"6611_CR14","doi-asserted-by":"crossref","unstructured":"Diwan T, Anirudh G, Tembhurne JV (2023) Object detection using yolo: challenges, architectural successors, datasets and applications. Multimed Tools Appl 82(6):9243\u20139275","DOI":"10.1007\/s11042-022-13644-y"},{"issue":"6","key":"6611_CR15","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.3390\/rs15061687","volume":"15","author":"Q Zhao","year":"2023","unstructured":"Zhao Q, Liu B, Lyu S, Wang C, Zhang H (2023) Tph-yolov5++: boosting object detection on drone-captured scenarios with cross-layer asymmetric transformer. Remote Sens 15(6):1687","journal-title":"Remote Sens"},{"key":"6611_CR16","doi-asserted-by":"crossref","unstructured":"Du D, Qi Y, Yu H, Yang Y, Duan K, Li G, Zhang W, Huang Q, Tian Q (2018) The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking. In: Proceedings of the European Conference on Computer Vision (ECCV)","DOI":"10.1007\/978-3-030-01249-6_23"},{"key":"6611_CR17","doi-asserted-by":"crossref","unstructured":"Cao Y, He Z, Wang L, Wang W, Yuan Y, Zhang D, Zhang J, Zhu P, Van\u00a0Gool L, Han J (2021) Visdrone-det2021: The Vision Meets Drone Object Detection Challenge Results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 2847\u20132854","DOI":"10.1109\/ICCVW54120.2021.00319"},{"key":"6611_CR18","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Doll\u00e1r P, Girshick R, He K, Hariharan B, Belongie S (2017) Feature Pyramid Networks for Object Detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 2117\u20132125","DOI":"10.1109\/CVPR.2017.106"},{"key":"6611_CR19","doi-asserted-by":"crossref","unstructured":"Liu S, Qi L, Qin H, Shi J, Jia J (2018) Path Aggregation Network for Instance Segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 8759\u20138768","DOI":"10.1109\/CVPR.2018.00913"},{"key":"6611_CR20","doi-asserted-by":"crossref","unstructured":"Kong T, Sun F, Tan C, Liu H, Huang W (2018) Deep Feature Pyramid Reconfiguration for Object Detection. In: Proceedings of the European Conference on Computer Vision (ECCV), pp 169\u2013185","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"6611_CR21","doi-asserted-by":"crossref","unstructured":"Pang J, Chen K, Shi J, Feng H, Ouyang W, Lin D (2019) Libra r-cnn: Towards Balanced Learning for Object Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 821\u2013830","DOI":"10.1109\/CVPR.2019.00091"},{"key":"6611_CR22","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le QV (2020) Efficientdet: Scalable and Efficient Object Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10781\u201310790","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"6611_CR23","unstructured":"Chen Q, Wang Y, Yang T, Zhang X, Cheng J, Sun J (2011) You Only Look One-Level Feature. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 13039\u201313048"},{"issue":"6","key":"6611_CR24","doi-asserted-by":"publisher","first-page":"4505","DOI":"10.1007\/s00371-023-03095-3","volume":"40","author":"Y-l Li","year":"2024","unstructured":"Li Y-l, Feng Y, Zhou M-l, Xiong X-c, Wang Y-h, Qiang B-h (2024) Dma-yolo: multi-scale object detection method with attention mechanism for aerial images. The Visual Comput 40(6):4505\u20134518","journal-title":"The Visual Comput"},{"issue":"8","key":"6611_CR25","doi-asserted-by":"publisher","first-page":"526","DOI":"10.3390\/drones7080526","volume":"7","author":"Z Zhang","year":"2023","unstructured":"Zhang Z (2023) Drone-yolo: an efficient neural network method for target detection in drone images. Drones 7(8):526","journal-title":"Drones"},{"key":"6611_CR26","doi-asserted-by":"crossref","unstructured":"Zhong R, Peng E, Li Z, Ai Q, Han T, Tang Y (2024) Spd-yolov8: an small-size object detection model of uav imagery in complex scene. The J Supercomput 1\u201321","DOI":"10.1007\/s11227-024-06121-w"},{"issue":"3","key":"6611_CR27","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.1007\/s00371-023-02886-y","volume":"40","author":"S Zeng","year":"2024","unstructured":"Zeng S, Yang W, Jiao Y, Geng L, Chen X (2024) Sca-yolo: a new small object detection model for uav images. The Visual Comput 40(3):1787\u20131803","journal-title":"The Visual Comput"},{"key":"6611_CR28","doi-asserted-by":"crossref","unstructured":"Gong Y, Yu X, Ding Y, Peng X, Zhao J, Han Z (2021) Effective Fusion Factor in fpn for Tiny Object Detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 1160\u20131168","DOI":"10.1109\/WACV48630.2021.00120"},{"key":"6611_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103752","volume":"90","author":"M Wang","year":"2023","unstructured":"Wang M, Yang W, Wang L, Chen D, Wei F, KeZiErBieKe H, Liao Y (2023) Fe-yolov5: feature enhancement network based on yolov5 for small object detection. J Vis Commun Image Rep 90:103752","journal-title":"J Vis Commun Image Rep"},{"key":"6611_CR30","unstructured":"Li C, Li L, Jiang H, Weng K, Geng Y, Li L, Ke Z, Li Q, Cheng M, Nie W, et al (2022) Yolov6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976"},{"key":"6611_CR31","doi-asserted-by":"crossref","unstructured":"Ghiasi G, Lin T-Y, Le QV (2019) Nas-fpn: Learning Scalable Feature Pyramid Architecture for Object Detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 7036\u20137045","DOI":"10.1109\/CVPR.2019.00720"},{"key":"6611_CR32","doi-asserted-by":"crossref","unstructured":"Li Y, Chen Y, Wang N, Zhang Z (2019) Scale-Aware Trident Networks for Object Detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 6054\u20136063","DOI":"10.1109\/ICCV.2019.00615"},{"key":"6611_CR33","unstructured":"Chen K, Cao Y, Loy CC, Lin D, Feichtenhofer C (2020) Feature pyramid grids. arXiv preprint arXiv:2004.03580"},{"key":"6611_CR34","unstructured":"Xu X, Jiang Y, Chen W, Huang Y, Zhang Y, Sun, X (2022) Damo-yolo: a report on real-time object detection design. arXiv preprint arXiv:2211.15444"},{"key":"6611_CR35","doi-asserted-by":"crossref","unstructured":"Yang G, Lei J, Zhu Z, Cheng S, Feng Z, Liang R (2023) Afpn: Asymptotic Feature Pyramid Network for Object Detection. In: 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp 2184\u20132189 . IEEE","DOI":"10.1109\/SMC53992.2023.10394415"},{"key":"6611_CR36","doi-asserted-by":"crossref","unstructured":"Fan Q, Li Y, Deveci M, Zhong K, Kadry S (2024) Lud-yolo: a novel lightweight object detection network for unmanned aerial vehicle. Inform Sci 121366","DOI":"10.1016\/j.ins.2024.121366"},{"issue":"9","key":"6611_CR37","doi-asserted-by":"publisher","first-page":"10117","DOI":"10.1007\/s11227-023-05065-x","volume":"79","author":"N Chen","year":"2023","unstructured":"Chen N, Li Y, Yang Z, Lu Z, Wang S, Wang J (2023) Lodnu: lightweight object detection network in uav vision. The J Supercompu 79(9):10117\u201310138","journal-title":"The J Supercompu"},{"key":"6611_CR38","doi-asserted-by":"crossref","unstructured":"Hu J, Shen L, Sun G (2018) Squeeze-and-Excitation Networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7132\u20137141","DOI":"10.1109\/CVPR.2018.00745"},{"key":"6611_CR39","unstructured":"Liu Y, Shao Z, Hoffmann N (2021) Global attention mechanism: Retain information to enhance channel-spatial interactions. arXiv preprint arXiv:2112.05561"},{"key":"6611_CR40","doi-asserted-by":"crossref","unstructured":"Woo S, Park J, Lee J-Y, Kweon IS (2018) Cbam: Convolutional Block Attention Module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"6611_CR41","doi-asserted-by":"crossref","unstructured":"Wang Q, Wu B, Zhu P, Li P, Zuo W, Hu Q (2020) Eca-net: Efficient Channel Attention for Deep Convolutional Neural Networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 11534\u201311542","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"6611_CR42","unstructured":"Yang L, Zhang R-Y, Li L, Xie X (2021) Simam: A Simple, Parameter-Free Attention Module for Convolutional Neural Networks. In: International Conference on Machine Learning, pp 11863\u201311874 . PMLR"},{"key":"6611_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.106442","volume":"123","author":"D Wan","year":"2023","unstructured":"Wan D, Lu R, Shen S, Xu T, Lang X, Ren Z (2023) Mixed local channel attention for object detection. Eng Appl Artif Intell 123:106442","journal-title":"Eng Appl Artif Intell"},{"key":"6611_CR44","doi-asserted-by":"crossref","unstructured":"Yang M, He D, Fan M, Shi B, Xue X, Li F, Ding E, Huang J (2021) Dolg: Single-Stage Image Retrieval With Deep Orthogonal Fusion of Local and Global Features. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 11772\u201311781","DOI":"10.1109\/ICCV48922.2021.01156"},{"issue":"7","key":"6611_CR45","doi-asserted-by":"publisher","first-page":"1655","DOI":"10.1109\/TPAMI.2018.2846566","volume":"41","author":"F Radenovi\u0107","year":"2018","unstructured":"Radenovi\u0107 F, Tolias G, Chum O (2018) Fine-tuning cnn image retrieval with no human annotation. IEEE Trans Pattern Anal Mach Intell 41(7):1655\u20131668","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"6611_CR46","doi-asserted-by":"crossref","unstructured":"Yu W, Yang T, Chen C (2021) Towards Resolving the Challenge of Long-Tail Distribution in UAV Images for Object Detection. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp 3258\u20133267","DOI":"10.1109\/WACV48630.2021.00330"},{"key":"6611_CR47","doi-asserted-by":"crossref","unstructured":"Albaba BM, Ozer S (2021) Synet: An Ensemble Network for Object Detection in UAV Images. In: 2020 25th International Conference on Pattern Recognition (ICPR), pp 10227\u201310234 . IEEE","DOI":"10.1109\/ICPR48806.2021.9412847"},{"key":"6611_CR48","doi-asserted-by":"crossref","unstructured":"Du D, Zhu P, Wen L, Bian X, Lin H, Hu Q, Peng T, Zheng J, Wang X, Zhang Y (2019) Visdrone-det2019: The Vision Meets Drone Object Detection in Image Challenge Results. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, pp 0\u20130","DOI":"10.1109\/ICCVW.2019.00031"},{"issue":"7","key":"6611_CR49","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.3390\/s20071861","volume":"20","author":"H Zhao","year":"2020","unstructured":"Zhao H, Zhou Y, Zhang L, Peng Y, Hu X, Peng H, Cai X (2020) Mixed yolov3-lite: a lightweight real-time object detection method. Sensors 20(7):1861","journal-title":"Sensors"},{"key":"6611_CR50","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-Cam: Visual Explanations from Deep Networks Via Gradient-Based Localization. In: Proceedings of the IEEE International Conference on Computer Vision, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"6611_CR51","doi-asserted-by":"crossref","unstructured":"Zhang Y, Wu C, Guo W, Zhang T, Li W (2023) Cfanet: efficient detection of uav image based on cross-layer feature aggregation. IEEE Transactions on Geoscience and Remote Sensing","DOI":"10.1109\/TGRS.2023.3273314"},{"key":"6611_CR52","doi-asserted-by":"crossref","unstructured":"Du B, Huang Y, Chen J, Huang D (2023) Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 13435\u201313444","DOI":"10.1109\/CVPR52729.2023.01291"},{"key":"6611_CR53","doi-asserted-by":"crossref","unstructured":"Shi Y, Wang C, Xu S, Yuan M-D, Liu F, Zhang L (2024) Deformable convolution-guided multiscale feature learning and fusion for uav object detection. IEEE Geoscience and Remote Sensing Letters","DOI":"10.1109\/LGRS.2024.3362890"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06611-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-024-06611-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-024-06611-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:22:44Z","timestamp":1730301764000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-024-06611-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,30]]},"references-count":53,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["6611"],"URL":"https:\/\/doi.org\/10.1007\/s11227-024-06611-x","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"value":"0920-8542","type":"print"},{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,30]]},"assertion":[{"value":"10 October 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No potential conflict of interest was reported by the authors.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"105"}}