{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:16:08Z","timestamp":1778285768132,"version":"3.51.4"},"reference-count":30,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T00:00:00Z","timestamp":1747699200000},"content-version":"vor","delay-in-days":139,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Image Processing"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Drones, due to their high efficiency and flexibility, have been widely applied. However, small objects captured by drones are easily affected by various conditions, resulting in suboptimal surveying performance. While the YOLO series has achieved significant success in detecting large targets, it still faces challenges in small target detection. To address this, we propose an innovative model, AMFE\u2010YOLO, aimed at overcoming the bottlenecks in small target detection. Firstly, we introduce the AMFE module to focus on occluded targets, thereby improving detection capabilities in complex environments. Secondly, we design the SFSM module to merge shallow spatial information from the input features with deep semantic information obtained from the neck, enhancing the representation ability of small target features and reducing noise. Additionally, we implement a novel detection strategy that introduces an auxiliary detection head to identify very small targets. Finally, we reconfigured the detection head, effectively addressing the issue of false positives in small\u2010object detection and improving the precision of small object detection. AMFE\u2010YOLO outperforms methods like YOLOv10 and YOLOv11 in terms of mAP on the VisDrone2019 public dataset. Compared to the original YOLOv8s, the average precision improved by 5.5%, while the model parameter size was reduced by 0.7\u00a0M.<\/jats:p>","DOI":"10.1049\/ipr2.70110","type":"journal-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T02:10:57Z","timestamp":1747793457000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["AMFE\u2010YOLO: A Small Object Detection Model for Drone Images"],"prefix":"10.1049","volume":"19","author":[{"given":"Qi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science Nanjing University of Information Science and Technology  Nanjing China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0430-6612","authenticated-orcid":false,"given":"Chengxin","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science Nanjing University of Information Science and Technology  Nanjing China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2025,5,20]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.3390\/s24196209"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3339235"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3462745"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs16040644"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs14020420"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"e_1_2_8_8_1","unstructured":"XYuan Z.Zheng Y.Li et\u00a0al. \u201cStrip R\u2010CNN: Large Strip Convolution for Remote Sensing Object Detection.\u201d Preprint arXiv January 7 2025: arXiv:2501.03775."},{"key":"e_1_2_8_9_1","unstructured":"J.Liu L.Plotegher E.Roura C. S.deJunior andS.He \u201cReal\u2010Time Detection for Small UAVs: Combining YOLO and Multi\u2010Frame Motion Analysis \u201d arXiv October 10 2024: arXiv:2411.02582."},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23167190"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3461172"},{"key":"e_1_2_8_12_1","unstructured":"J.RedmonandA.Farhadi \u201cYOLOv3: An Incremental Improvement\u201d preprint arXiv April 8 2018: arXiv:1804.02767."},{"key":"e_1_2_8_13_1","unstructured":"A.Bochkovskiy C.\u2010Y.Wang andH.\u2010Y. M.Liao \u201cYOLOv4: Optimal Speed and Accuracy of Object Detection\u201d preprint arXiv April 23 2020 arXiv:2004.10934."},{"key":"e_1_2_8_14_1","unstructured":"J.NelsonandJ.Solawetz \u201cYOLOv5 is Here\u201d State\u2010of\u2010the\u2010Art Object Detection at 140 FPS published June 7 2020 https:\/\/blog.roboflow.com\/yolov5\u2010is\u2010here."},{"key":"e_1_2_8_15_1","unstructured":"C.Li L.Li H.Jiang et\u00a0al. \u201cYOLOv6: A Single\u2010Stage Object Detection Framework for Industrial Applications\u201d preprint arXiv Sepember 7 2022 arXiv:2209.02976."},{"key":"e_1_2_8_16_1","doi-asserted-by":"crossref","unstructured":"C.Wang A.Bochkovskiy andH. Y. M.Liao \u201cYOLOv7: Trainable Bag\u2010of\u2010Freebies Sets New State\u2010of\u2010the\u2010Art for Real\u2010Time Object Detectors\u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2023)7464\u20137475.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3382245"},{"key":"e_1_2_8_18_1","doi-asserted-by":"crossref","unstructured":"J.Chen S. \u2010H. Kao H. He et\u00a0al. \u201cRun Don't Walk: Chasing Higher FLOPS for Faster Neural Networks\u201d inProceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (IEEE 2023) 12021\u201312031.","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"e_1_2_8_19_1","doi-asserted-by":"crossref","unstructured":"Y.Yang \u201cDrone\u2010View Object Detection Based on the Improved YOLOv5\u201d inProceedings of the 2022 IEEE International Conference on Electrical Engineering Big Data and Algorithms (EEBDA) (IEEE 2022) 612\u2013617.","DOI":"10.1109\/EEBDA53927.2022.9744741"},{"key":"e_1_2_8_20_1","unstructured":"Z.Chen A.Geng J.Jiang J.Lu andD.Wu \u201cInfra\u2010YOLO: Efficient Neural Network Structure With Model Compression for Real\u2010Time Infrared Small Object Detection \u201d preprint arXiv August 14 2024: arXiv:2408.07455."},{"key":"e_1_2_8_21_1","unstructured":"C.Li A.Zhou andA.Yao \u201cOmni\u2010Dimensional Dynamic Convolution\u201d preprint arXiv september 16 2022."},{"key":"e_1_2_8_22_1","unstructured":"Z.Liu Z.Hao K.Han Y.Tang andY.Wang \u201cGhostNetV3: Exploring the Training Strategies for Compact Models\u201d preprint arXiv April 22 2024: arXiv:2404.11202."},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"e_1_2_8_24_1","unstructured":"H.Li J.Li H.Wei Z.Liu Z.Zhan andQ.Ren \u201cSlim\u2010Neck by GSConv: A Better Design Paradigm of Detector Architectures for Autonomous Vehicles\u201d preprint arXiv June 6 2022: arXiv:2206.02424."},{"key":"e_1_2_8_25_1","unstructured":"Z.Ge S.Liu F.Wang Z.Li andJ.Sun \u201cYOLOX: Exceeding YOLO Series in 2021\u201d preprint arXiv July 18 2021."},{"key":"e_1_2_8_26_1","unstructured":"D.Du P.Zhu L.Wen et\u00a0al. \u201cVisdrone\u2010Det2019: The Vision Meets Drone Object Detection in Image Challenge Results\u201d inProceedings of the IEEE\/CVF ICCV Workshops (IEEE 2019) 213\u2013226."},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-92344-7"},{"key":"e_1_2_8_29_1","doi-asserted-by":"crossref","unstructured":"S.Tang S.Zhang andY.Fang \u201cHIC\u2010YOLOv5: Improved YOLOv5 for Small Object Detection \u201d in2024 IEEE International Conference on Robotics and Automation (ICRA). (IEEE 2024) 6614\u20136619.","DOI":"10.1109\/ICRA57147.2024.10610273"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/drones8070276"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402097"}],"container-title":["IET Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70110","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/full-xml\/10.1049\/ipr2.70110","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/ipr2.70110","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T23:50:12Z","timestamp":1778284212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/ipr2.70110"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1049\/ipr2.70110"],"URL":"https:\/\/doi.org\/10.1049\/ipr2.70110","archive":["Portico"],"relation":{},"ISSN":["1751-9659","1751-9667"],"issn-type":[{"value":"1751-9659","type":"print"},{"value":"1751-9667","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"assertion":[{"value":"2025-01-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-05-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70110"}}