{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T21:31:31Z","timestamp":1775079091228,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T00:00:00Z","timestamp":1717459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T00:00:00Z","timestamp":1717459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Shandong Provincial Technology Innovation Guidance Plan","award":["YDZX2023085"],"award-info":[{"award-number":["YDZX2023085"]}]},{"name":"Science and Technology SMEs Innovation Capacity Improvement Project of Shandong","award":["2022TSGC1248"],"award-info":[{"award-number":["2022TSGC1248"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61801277"],"award-info":[{"award-number":["61801277"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Provincial Natural Science Foundation","doi-asserted-by":"crossref","award":["ZR2023MF025"],"award-info":[{"award-number":["ZR2023MF025"]}],"id":[{"id":"10.13039\/501100007129","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\/s11554-024-01483-z","type":"journal-article","created":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T17:01:54Z","timestamp":1717520514000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["ARF-YOLOv8: a novel real-time object detection model for UAV-captured images detection"],"prefix":"10.1007","volume":"21","author":[{"given":"YaLin","family":"Zeng","sequence":"first","affiliation":[]},{"given":"DongJin","family":"Guo","sequence":"additional","affiliation":[]},{"given":"WeiKai","family":"He","sequence":"additional","affiliation":[]},{"given":"Tian","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"ZhongTao","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,6,4]]},"reference":[{"key":"1483_CR1","doi-asserted-by":"publisher","first-page":"8085","DOI":"10.1109\/JSTARS.2022.3206399","volume":"15","author":"W Liu","year":"2022","unstructured":"Liu, W., Quijano, K., Crawford, M.M.: Yolov5-tassel: detecting tassels in rgb uav imagery with improved yolov5 based on transfer learning. IEEE J. Select. Top. Appl. Earth Observ. Remote Sens. 15, 8085\u20138094 (2022)","journal-title":"IEEE J. Select. Top. Appl. Earth Observ. Remote Sens."},{"issue":"12","key":"1483_CR2","doi-asserted-by":"publisher","first-page":"9511","DOI":"10.1007\/s00521-022-07104-9","volume":"34","author":"A Bouguettaya","year":"2022","unstructured":"Bouguettaya, A., Zarzour, H., Kechida, A., Taberkit, A.M.: Deep learning techniques to classify agricultural crops through UAV imagery: a review. Neural Comput. Appl. 34(12), 9511\u20139536 (2022)","journal-title":"Neural Comput. Appl."},{"key":"1483_CR3","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s41095-018-0116-x","volume":"4","author":"Y Lu","year":"2018","unstructured":"Lu, Y., Lu, J., Zhang, S., Hall, P.: Traffic signal detection and classification in street views using an attention model. Comput. Vis. Media 4, 253\u2013266 (2018)","journal-title":"Comput. Vis. Media"},{"key":"1483_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114937","volume":"178","author":"I Martinez-Alpiste","year":"2021","unstructured":"Martinez-Alpiste, I., Golcarenarenji, G., Wang, Q., Alcaraz-Calero, J.M.: Search and rescue operation using UAVs: a case study. Expert Syst. Appl. 178, 114937 (2021)","journal-title":"Expert Syst. Appl."},{"key":"1483_CR5","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"1483_CR6","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"1483_CR7","doi-asserted-by":"crossref","unstructured":"Cai, Z., Vasconcelos, N.: Cascade r-cnn: Delving into high quality object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6154\u20136162 (2018)","DOI":"10.1109\/CVPR.2018.00644"},{"key":"1483_CR8","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"1483_CR9","doi-asserted-by":"crossref","unstructured":"Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7263\u20137271 (2017)","DOI":"10.1109\/CVPR.2017.690"},{"key":"1483_CR10","unstructured":"Redmon, J., Farhadi, A.: Yolov3: an incremental improvement. arXiv preprint arXiv:1804.02767 (2018)"},{"key":"1483_CR11","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: Yolov4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)"},{"key":"1483_CR12","unstructured":"Jocher, G., Chaurasia, A., Stoken, A., Borovec, J., Kwon, Y., Fang, J., Michael, K., Montes, D., Nadar, J., Skalski, P., et al.: ultralytics\/yolov5: v6. 1-tensorrt, tensorflow edge tpu and openvino export and inference. Zenodo (2022)"},{"key":"1483_CR13","unstructured":"Li, C., Li, L., Jiang, H., Weng, K., Geng, Y., Li, L., Ke, Z., Li, Q., Cheng, M., Nie, W., et al.: Yolov6: a single-stage object detection framework for industrial applications. arXiv preprint arXiv:2209.02976 (2022)"},{"key":"1483_CR14","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: 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 (2023)","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"1483_CR15","unstructured":"Ultralytics: Ultralytics GitHub Repository. https:\/\/github.com\/ultralytics\/ultralytics Accessed 2023-06-06"},{"key":"1483_CR16","unstructured":"Agrawal, N., Prabhakaran, V., Wobber, T., Davis, J.D., Manasse, M., Panigrahy, R.: Design tradeoffs for {SSD} performance. In: 2008 USENIX Annual Technical Conference (USENIX ATC 08) (2008)"},{"key":"1483_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1483_CR18","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13, pp. 740\u2013755 . Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"1483_CR19","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s11263-014-0733-5","volume":"111","author":"M Everingham","year":"2015","unstructured":"Everingham, M., Eslami, S.A., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. Int. J. Comput. Vis. 111, 98\u2013136 (2015)","journal-title":"Int. J. Comput. Vis."},{"issue":"3","key":"1483_CR20","doi-asserted-by":"publisher","first-page":"188","DOI":"10.3390\/drones7030188","volume":"7","author":"L Zhao","year":"2023","unstructured":"Zhao, L., Zhu, M.: Ms-yolov7: Yolov7 based on multi-scale for object detection on UAV aerial photography. Drones 7(3), 188 (2023)","journal-title":"Drones"},{"issue":"5","key":"1483_CR21","doi-asserted-by":"publisher","first-page":"304","DOI":"10.3390\/drones7050304","volume":"7","author":"Y Li","year":"2023","unstructured":"Li, Y., Fan, Q., Huang, H., Han, Z., Gu, Q.: A modified yolov8 detection network for UAV aerial image recognition. Drones 7(5), 304 (2023)","journal-title":"Drones"},{"key":"1483_CR22","doi-asserted-by":"publisher","first-page":"1556","DOI":"10.1109\/TIP.2020.3045636","volume":"30","author":"S Deng","year":"2020","unstructured":"Deng, S., Li, S., Xie, K., Song, W., Liao, X., Hao, A., Qin, H.: A global-local self-adaptive network for drone-view object detection. IEEE Trans. Image Process. 30, 1556\u20131569 (2020)","journal-title":"IEEE Trans. Image Process."},{"issue":"15","key":"1483_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00521-021-06650-y","volume":"34","author":"L Guo","year":"2022","unstructured":"Guo, L., Yang, R., Zhong, Z., Zhang, R., Zhang, B.: Target recognition method of small UAV remote sensing image based on fuzzy clustering. Neural Comput. Appl. 34(15), 1\u201317 (2022)","journal-title":"Neural Comput. Appl."},{"key":"1483_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, X., Lyu, S., Wang, X., Zhao, Q.: Tph-yolov5: Improved yolov5 based on transformer prediction head for object detection on drone-captured scenarios. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2778\u20132788 (2021)","DOI":"10.1109\/ICCVW54120.2021.00312"},{"key":"1483_CR25","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"issue":"20","key":"1483_CR26","doi-asserted-by":"publisher","first-page":"17951","DOI":"10.1007\/s00521-022-07437-5","volume":"34","author":"L Yang","year":"2022","unstructured":"Yang, L., Fan, J., Song, S., Liu, Y.: A light defect detection algorithm of power insulators from aerial images for power inspection. Neural Comput. Appl. 34(20), 17951\u201317961 (2022)","journal-title":"Neural Comput. Appl."},{"key":"1483_CR27","unstructured":"Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., Adam, H.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"1483_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2022.104396","volume":"119","author":"A Amudhan","year":"2022","unstructured":"Amudhan, A., Sudheer, A.: Lightweight and computationally faster hypermetropic convolutional neural network for small size object detection. Image Vis. Comput. 119, 104396 (2022)","journal-title":"Image Vis. Comput."},{"issue":"9","key":"1483_CR29","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.: Lodnu: lightweight object detection network in UAV vision. J. Supercomput. 79(9), 10117\u201310138 (2023)","journal-title":"J. Supercomput."},{"key":"1483_CR30","doi-asserted-by":"crossref","unstructured":"Jiang, N., Yu, X., Peng, X., Gong, Y., Han, Z.: Sm+: Refined scale match for tiny person detection. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1815\u20131819 . IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9414162"},{"key":"1483_CR31","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.isprsjprs.2023.08.016","volume":"204","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Xu, C., Yang, W., He, G., Yu, H., Yu, L., Xia, G.-S.: Drone-based rgbt tiny person detection. ISPRS J. Photogramm. Remote. Sens. 204, 61\u201376 (2023)","journal-title":"ISPRS J. Photogramm. Remote. Sens."},{"issue":"3","key":"1483_CR32","doi-asserted-by":"publisher","first-page":"1104","DOI":"10.3390\/s22031104","volume":"22","author":"T Gandor","year":"2022","unstructured":"Gandor, T., Nalepa, J.: First gradually, then suddenly: understanding the impact of image compression on object detection using deep learning. Sensors 22(3), 1104 (2022)","journal-title":"Sensors"},{"key":"1483_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2023.108962","volume":"208","author":"R Li","year":"2023","unstructured":"Li, R., Shen, Y.: Yolosr-ist: a deep learning method for small target detection in infrared remote sensing images based on super-resolution and yolo. Signal Process. 208, 108962 (2023)","journal-title":"Signal Process."},{"key":"1483_CR34","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., Sun, J.: Yolox: exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)"},{"key":"1483_CR35","doi-asserted-by":"crossref","unstructured":"Feng, C., Zhong, Y., Gao, Y., Scott, M.R., Huang, W.: Tood: task-aligned one-stage object detection. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3490\u20133499 . IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.00349"},{"key":"1483_CR36","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1483_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., Hu, Q.: 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 (2020)","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"1483_CR38","doi-asserted-by":"crossref","unstructured":"Hou, Q., Zhou, D., Feng, J.: Coordinate attention for efficient mobile network design. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13713\u201313722 (2021)","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"1483_CR39","unstructured":"Liu, Y., Shao, Z., Hoffmann, N.: Global attention mechanism: retain information to enhance channel-spatial interactions. arXiv preprint arXiv:2112.05561 (2021)"},{"key":"1483_CR40","doi-asserted-by":"crossref","unstructured":"Rezatofighi, H., Tsoi, N., Gwak, J., Sadeghian, A., Reid, I., Savarese, S.: Generalized intersection over union: a metric and a loss for bounding box regression. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 658\u2013666 (2019)","DOI":"10.1109\/CVPR.2019.00075"},{"key":"1483_CR41","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Liu, W., Li, J., Ye, R., Ren, D.: Distance-iou loss: faster and better learning for bounding box regression. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 12993\u201313000 (2020)","DOI":"10.1609\/aaai.v34i07.6999"},{"key":"1483_CR42","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","volume":"506","author":"Y-F Zhang","year":"2022","unstructured":"Zhang, Y.-F., Ren, W., Zhang, Z., Jia, Z., Wang, L., Tan, T.: Focal and efficient iou loss for accurate bounding box regression. Neurocomputing 506, 146\u2013157 (2022)","journal-title":"Neurocomputing"},{"key":"1483_CR43","unstructured":"Gevorgyan, Z.: Siou loss: more powerful learning for bounding box regression. arXiv preprint arXiv:2205.12740 (2022)"},{"key":"1483_CR44","unstructured":"Wang, J., Xu, C., Yang, W., Yu, L.: A normalized gaussian wasserstein distance for tiny object detection. arXiv preprint arXiv:2110.13389 (2021)"},{"key":"1483_CR45","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Liao, H.-Y.M., Wu, Y.-H., Chen, P.-Y., Hsieh, J.-W., Yeh, I.-H.: Cspnet: a new backbone that can enhance learning capability of CNN. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 390\u2013391 (2020)","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"1483_CR46","doi-asserted-by":"publisher","unstructured":"Du, D., Zhu, P., Wen, L., Bian, O.: Visdrone-det2019: the vision meets drone object detection in image challenge results. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 213\u2013226. https:\/\/doi.org\/10.1109\/ICCVW.2019.00030 (2019)","DOI":"10.1109\/ICCVW.2019.00030"},{"issue":"3","key":"1483_CR47","doi-asserted-by":"publisher","first-page":"1320","DOI":"10.1109\/TCSVT.2022.3210207","volume":"33","author":"J Leng","year":"2022","unstructured":"Leng, J., Mo, M., Zhou, Y., Gao, C., Li, W., Gao, X.: Pareto refocusing for drone-view object detection. IEEE Trans. Circ. Syst. Video Technol. 33(3), 1320\u20131334 (2022)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"issue":"3","key":"1483_CR48","first-page":"1","volume":"40","author":"S Zeng","year":"2023","unstructured":"Zeng, S., Yang, W., Jiao, Y., Geng, L., Chen, X.: Sca-yolo: a new small object detection model for UAV images. Vis. Comput. 40(3), 1\u201317 (2023)","journal-title":"Vis. Comput"},{"issue":"14","key":"1483_CR49","doi-asserted-by":"publisher","first-page":"3141","DOI":"10.3390\/electronics12143141","volume":"12","author":"Y Zeng","year":"2023","unstructured":"Zeng, Y., Zhang, T., He, W., Zhang, Z.: Yolov7-uav: an unmanned aerial vehicle image object detection algorithm based on improved yolov7. Electronics 12(14), 3141 (2023)","journal-title":"Electronics"},{"key":"1483_CR50","doi-asserted-by":"crossref","unstructured":"Meethal, A., Granger, E., Pedersoli, M.: Cascaded zoom-in detector for high resolution aerial images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2045\u20132054 (2023)","DOI":"10.1109\/CVPRW59228.2023.00198"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01483-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-024-01483-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-024-01483-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,27]],"date-time":"2024-08-27T16:23:09Z","timestamp":1724775789000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-024-01483-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,4]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["1483"],"URL":"https:\/\/doi.org\/10.1007\/s11554-024-01483-z","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,4]]},"assertion":[{"value":"7 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 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 that they have no confict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"107"}}