{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T16:01:21Z","timestamp":1772812881015,"version":"3.50.1"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686547","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T00:00:00Z","timestamp":1772582400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,4]]},"abstract":"<jats:p>Aerial image object detection faces the challenge of dense distribution of small objects, which are difficult to be detected due to too few features, damaging the whole detection performance in the complex scenes. To address this issue, we propose a Small Target Detection Transformer (ST-DETR) based on the RT-DETR architecture to implement the systematic optimization tailored for aerial scenarios. Specifically, we first introduce a cross-scale feature fusion module to enhance multi-scale representation with hierarchical feature integration, effectively improving the model\u2019s recognition capability for objects with different sizes. Then we propose a novel Wise-MPDIoU loss function to leverage the dynamic weighting mechanism to heighten the subtle differences among bounding boxes with similar aspect ratios, thus significantly improving bounding box regression. Finally, we establish a dedicated small object detection head based on the P2 layer to more accurately extract fine-grained textures and spatial features crucial for small target localization. Experimental results on the SkyFusion aerial object detection dataset demonstrate that our proposed ST-DETR achieving 4.7% mAP50 and 2.3% mAP50:95 gains over the baseline model RT-DETR, and its detection accuracy also outperforms other popular models, validating its effectiveness and robustness for small object detection in complex aerial images.<\/jats:p>","DOI":"10.3233\/faia260003","type":"book-chapter","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:19:52Z","timestamp":1772792392000},"source":"Crossref","is-referenced-by-count":0,"title":["Small Target Detection Algorithm in Aerial Images Based on Improved RT-DETR"],"prefix":"10.3233","author":[{"given":"Haoran","family":"Yu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Jianghan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, Jianghan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","Machine Learning and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA260003","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:19:52Z","timestamp":1772792392000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA260003"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,4]]},"ISBN":["9781643686547"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia260003","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,4]]}}}