{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,16]],"date-time":"2026-11-16T19:48:03Z","timestamp":1794858483222,"version":"4.9.1"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,18]],"date-time":"2026-02-18T00:00:00Z","timestamp":1771372800000},"content-version":"vor","delay-in-days":18,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-37938-5","type":"journal-article","created":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T12:46:14Z","timestamp":1769863574000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Real-time object detection for unmanned aerial vehicles based on vision transformer and edge computing"],"prefix":"10.1038","volume":"16","author":[{"given":"Wenyao","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ken","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,1,31]]},"reference":[{"issue":"3","key":"37938_CR1","doi-asserted-by":"publisher","first-page":"2835","DOI":"10.1109\/TITS.2022.3224325","volume":"24","author":"Y Chen","year":"2023","unstructured":"Chen, Y., Zhang, H., Wang, L. & Wu, Q. A survey on vision-based UAV navigation. IEEE Trans. Intell. Transp. Syst. 24 (3), 2835\u20132854. https:\/\/doi.org\/10.1109\/TITS.2022.3224325 (2023).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"2","key":"37938_CR2","doi-asserted-by":"publisher","first-page":"98","DOI":"10.3390\/drones7020098","volume":"7","author":"Y Zhang","year":"2023","unstructured":"Zhang, Y., Yuan, Y., Feng, Y. & Lu, X. UAV swarms in urban environments: A survey of emerging trends and challenges. Drones 7 (2), 98. https:\/\/doi.org\/10.3390\/drones7020098 (2023).","journal-title":"Drones"},{"issue":"4","key":"37938_CR3","doi-asserted-by":"publisher","first-page":"3553","DOI":"10.1109\/JIOT.2022.3215698","volume":"10","author":"K Li","year":"2023","unstructured":"Li, K., Ni, W., Tovar, E. & Jamalipour, A. On-board deep learning in UAV-based applications: opportunities and challenges. IEEE Internet Things J. 10 (4), 3553\u20133575. https:\/\/doi.org\/10.1109\/JIOT.2022.3215698 (2023).","journal-title":"IEEE Internet Things J."},{"key":"37938_CR4","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: Transformers for image recognition at scale. In Proceedings of the International Conference on Learning Representations (ICLR). (2021). https:\/\/doi.org\/10.48550\/arXiv.2010.11929","DOI":"10.48550\/arXiv.2010.11929"},{"issue":"10s","key":"37938_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3505244","volume":"54","author":"S Khan","year":"2022","unstructured":"Khan, S. et al. Transformers in vision: A survey. ACM Comput. Surveys. 54 (10s), 1\u201341. https:\/\/doi.org\/10.1145\/3505244 (2022).","journal-title":"ACM Comput. Surveys"},{"issue":"5","key":"37938_CR6","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","volume":"3","author":"W Shi","year":"2016","unstructured":"Shi, W., Cao, J., Zhang, Q., Li, Y. & Xu, L. Edge computing: vision and challenges. IEEE Internet Things J. 3 (5), 637\u2013646. https:\/\/doi.org\/10.1109\/JIOT.2016.2579198 (2016).","journal-title":"IEEE Internet Things J."},{"key":"37938_CR7","doi-asserted-by":"publisher","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 (CVPR) 779\u2013788. (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.91","DOI":"10.1109\/CVPR.2016.91"},{"key":"37938_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2021.3138849","volume":"60","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Yuan, Y., Feng, Y. & Lu, X. Cascade det: A universal cascade detection framework for small objects in drone-captured scenes. IEEE Trans. Geosci. Remote Sens. 60, 1\u201313. https:\/\/doi.org\/10.1109\/TGRS.2021.3138849 (2021).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"37938_CR9","doi-asserted-by":"publisher","first-page":"28456","DOI":"10.1109\/ACCESS.2023.3258741","volume":"11","author":"Z Xu","year":"2023","unstructured":"Xu, Z., Wu, W., Qi, L. & Lu, X. Efficient vision Transformers for edge devices: A survey. IEEE Access. 11, 28456\u201328478. https:\/\/doi.org\/10.1109\/ACCESS.2023.3258741 (2023).","journal-title":"IEEE Access."},{"issue":"2","key":"37938_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3303848","volume":"52","author":"Y Rizk","year":"2019","unstructured":"Rizk, Y., Awad, M. & Tunstel, E. W. Cooperative heterogeneous multi-robot systems: A survey. ACM Comput. Surveys. 52 (2), 1\u201331. https:\/\/doi.org\/10.1145\/3303848 (2019).","journal-title":"ACM Comput. Surveys"},{"key":"37938_CR11","doi-asserted-by":"publisher","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems (Vol. 25, pp. 1097\u20131105. (2012). https:\/\/doi.org\/10.1145\/3065386","DOI":"10.1145\/3065386"},{"key":"37938_CR12","unstructured":"Vaswani, A. et al. Attention is all you need. In Advances in Neural Information Processing Systems (Vol. 30, pp. 5998\u20136008. (2017). https:\/\/proceedings.neurips.cc\/paper\/7181-attention-is-all-you-need"},{"key":"37938_CR13","doi-asserted-by":"publisher","unstructured":"Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. In Proceedings of the International Conference on Learning Representations (ICLR). (2015). https:\/\/doi.org\/10.48550\/arXiv.1409.0473","DOI":"10.48550\/arXiv.1409.0473"},{"key":"37938_CR14","doi-asserted-by":"publisher","unstructured":"Touvron, H. et al. Training data-efficient image transformers & distillation through attention. In Proceedings of the International Conference on Machine Learning (ICML) 10347\u201310357. (2021). https:\/\/doi.org\/10.48550\/arXiv.2012.12877","DOI":"10.48550\/arXiv.2012.12877"},{"key":"37938_CR15","doi-asserted-by":"publisher","unstructured":"Vaswani, A. et al. Scaling local self-attention for parameter efficient visual backbones. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 12894\u201312904. (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.01270","DOI":"10.1109\/CVPR46437.2021.01270"},{"issue":"1","key":"37938_CR16","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MC.2017.9","volume":"50","author":"M Satyanarayanan","year":"2017","unstructured":"Satyanarayanan, M. The emergence of edge computing. Computer 50 (1), 30\u201339. https:\/\/doi.org\/10.1109\/MC.2017.9 (2017).","journal-title":"Computer"},{"issue":"4","key":"37938_CR17","doi-asserted-by":"publisher","first-page":"2322","DOI":"10.1109\/COMST.2017.2745201","volume":"19","author":"Y Mao","year":"2017","unstructured":"Mao, Y., You, C., Zhang, J., Huang, K. & Letaief, K. B. A survey on mobile edge computing: the communication perspective. IEEE Commun. Surv. Tutorials. 19 (4), 2322\u20132358. https:\/\/doi.org\/10.1109\/COMST.2017.2745201 (2017).","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"37938_CR18","doi-asserted-by":"publisher","unstructured":"Jacob, B. et al. Quantization and training of neural networks for efficient integer-arithmetic-only inference. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2704\u20132713. (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00286","DOI":"10.1109\/CVPR.2018.00286"},{"key":"37938_CR19","doi-asserted-by":"publisher","unstructured":"He, Y., Liu, P., Wang, Z., Hu, Z. & Yang, Y. Filter pruning via geometric median for deep convolutional neural networks acceleration. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 4340\u20134349. (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00447","DOI":"10.1109\/CVPR.2019.00447"},{"key":"37938_CR20","doi-asserted-by":"publisher","unstructured":"Hinton, G., Vinyals, O. & Dean, J. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531. (2015). https:\/\/doi.org\/10.48550\/arXiv.1503.02531","DOI":"10.48550\/arXiv.1503.02531"},{"key":"37938_CR21","doi-asserted-by":"publisher","first-page":"154714","DOI":"10.1109\/ACCESS.2019.2949098","volume":"7","author":"X Jiang","year":"2019","unstructured":"Jiang, X., Hadid, A., Pang, Y., Granger, E. & Feng, X. Deep learning-based face detection and recognition on mobile devices. IEEE Access. 7, 154714\u2013154735. https:\/\/doi.org\/10.1109\/ACCESS.2019.2949098 (2019).","journal-title":"IEEE Access."},{"issue":"12","key":"37938_CR22","doi-asserted-by":"publisher","first-page":"7405","DOI":"10.1109\/TGRS.2016.2601622","volume":"54","author":"G Cheng","year":"2016","unstructured":"Cheng, G., Zhou, P. & Han, J. Learning rotation-invariant convolutional neural networks for object detection in VHR optical remote sensing images. IEEE Trans. Geosci. Remote Sens. 54 (12), 7405\u20137415. https:\/\/doi.org\/10.1109\/TGRS.2016.2601622 (2016).","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"3","key":"37938_CR23","doi-asserted-by":"publisher","first-page":"87","DOI":"10.3390\/drones8030087","volume":"8","author":"M Xie","year":"2024","unstructured":"Xie, M. & Jean, N. Low altitude thermal airborne platform for tracking and monitoring of wildlife in open-canopy landscapes. Drones 8 (3), 87. https:\/\/doi.org\/10.3390\/drones8030087 (2024).","journal-title":"Drones"},{"issue":"8","key":"37938_CR24","doi-asserted-by":"publisher","first-page":"2238","DOI":"10.3390\/s20082238","volume":"20","author":"M Liu","year":"2020","unstructured":"Liu, M. et al. UAV-YOLO: small object detection on unmanned aerial vehicle perspective. Sensors 20 (8), 2238. https:\/\/doi.org\/10.3390\/s20082238 (2020).","journal-title":"Sensors"},{"key":"37938_CR25","doi-asserted-by":"publisher","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 (CVPR) 7464\u20137475. (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00721","DOI":"10.1109\/CVPR52729.2023.00721"},{"issue":"12","key":"37938_CR26","doi-asserted-by":"publisher","first-page":"3948","DOI":"10.3390\/s24123948","volume":"24","author":"Z Wang","year":"2024","unstructured":"Wang, Z. et al. UAV-assisted mobile edge computing: dynamic trajectory design and resource allocation. Sensors 24 (12), 3948. https:\/\/doi.org\/10.3390\/s24123948 (2024).","journal-title":"Sensors"},{"issue":"3","key":"37938_CR27","doi-asserted-by":"publisher","first-page":"3175","DOI":"10.1364\/OE.449787","volume":"30","author":"J Zhang","year":"2022","unstructured":"Zhang, J., Xing, W., Xing, M. & Sun, G. Terahertz image reconstruction based on compressed sensing and inverse Fresnel diffraction. Opt. Express. 30 (3), 3175\u20133195. https:\/\/doi.org\/10.1364\/OE.449787 (2022).","journal-title":"Opt. Express"},{"key":"37938_CR28","doi-asserted-by":"publisher","unstructured":"Tian, Z., Shen, C., Chen, H. & He, T. FCOS: Fully convolutional one-stage object detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) 9627\u20139636. (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00972","DOI":"10.1109\/ICCV.2019.00972"},{"key":"37938_CR29","doi-asserted-by":"publisher","unstructured":"Bodla, N., Singh, B., Chellappa, R. & Davis, L. S. Soft-NMS: Improving object detection with one line of code. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) 5561\u20135569. (2017). https:\/\/doi.org\/10.1109\/ICCV.2017.593","DOI":"10.1109\/ICCV.2017.593"},{"key":"37938_CR30","doi-asserted-by":"publisher","unstructured":"Lin, T. Y. et al. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2117\u20132125. (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.106","DOI":"10.1109\/CVPR.2017.106"},{"key":"37938_CR31","doi-asserted-by":"publisher","unstructured":"Liu, Z. et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) 10012\u201310022. (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"37938_CR32","doi-asserted-by":"publisher","unstructured":"Kirillov, A., Girshick, R., He, K. & Doll\u00e1r, P. Panoptic feature pyramid networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 6399\u20136408. (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00656","DOI":"10.1109\/CVPR.2019.00656"},{"key":"37938_CR33","doi-asserted-by":"publisher","first-page":"7389","DOI":"10.1109\/TIP.2020.3002345","volume":"29","author":"T Kong","year":"2020","unstructured":"Kong, T. et al. FoveaBox: Beyound anchor-based object detection. IEEE Trans. Image Process. 29, 7389\u20137398. https:\/\/doi.org\/10.1109\/TIP.2020.3002345 (2020).","journal-title":"IEEE Trans. Image Process."},{"key":"37938_CR34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.08295","author":"M Nagel","year":"2021","unstructured":"Nagel, M. et al. A white paper on neural network quantization. ArXiv Preprint arXiv:2106 08295. https:\/\/doi.org\/10.48550\/arXiv.2106.08295 (2021).","journal-title":"ArXiv Preprint arXiv:2106 08295"},{"key":"37938_CR35","unstructured":"Frankle, J. & Carbin, M. The lottery ticket hypothesis: Finding sparse, trainable neural networks. In Proceedings of the International Conference on Learning Representations (ICLR). (2019). https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"37938_CR36","unstructured":"Vanholder, H. Efficient inference with TensorRT. GPU Technology Conference. (2016). https:\/\/developer.nvidia.com\/tensorrt"},{"key":"37938_CR37","doi-asserted-by":"publisher","unstructured":"Liu, L., Li, H. & Gruteser, M. Edge assisted real-time object detection for mobile augmented reality. In Proceedings of the 25th Annual International Conference on Mobile Computing and Networking 1\u201316. (2019). https:\/\/doi.org\/10.1145\/3300061.3300116","DOI":"10.1145\/3300061.3300116"},{"issue":"11","key":"37938_CR38","doi-asserted-by":"publisher","first-page":"7380","DOI":"10.1109\/TPAMI.2021.3119563","volume":"44","author":"P Zhu","year":"2021","unstructured":"Zhu, P. et al. Detection and tracking Meet drones challenge. IEEE Trans. Pattern Anal. Mach. Intell. 44 (11), 7380\u20137399. https:\/\/doi.org\/10.1109\/TPAMI.2021.3119563 (2021).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37938_CR39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.02976","author":"C Li","year":"2022","unstructured":"Li, C. et al. YOLOv6: A single-stage object detection framework for industrial applications. ArXiv Preprint arXiv:2209 02976. https:\/\/doi.org\/10.48550\/arXiv.2209.02976 (2022).","journal-title":"ArXiv Preprint arXiv:2209 02976"},{"issue":"2","key":"37938_CR40","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","volume":"11","author":"A Buslaev","year":"2020","unstructured":"Buslaev, A. et al. Albumentations: fast and flexible image augmentations. Information 11 (2), 125. https:\/\/doi.org\/10.3390\/info11020125 (2020).","journal-title":"Information"},{"key":"37938_CR41","doi-asserted-by":"publisher","unstructured":"Lin, T. Y. et al. Microsoft COCO: Common objects in context. In Proceedings of the European Conference on Computer Vision (ECCV) 740\u2013755. (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"37938_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3259032","volume":"72","author":"T Ye","year":"2023","unstructured":"Ye, T., Zhao, Z., Luo, H. & Liu, H. Real-time object detection network in UAV-vision based on CNN and transformer. IEEE Trans. Instrum. Meas. 72, 1\u201313. https:\/\/doi.org\/10.1109\/TIM.2023.3259032 (2023).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"37938_CR43","doi-asserted-by":"publisher","unstructured":"Chen, C., Zheng, Z., Ding, X., Huang, Y. & Dou, Q. Harmonizing transferability and discriminability for adapting object detectors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 8869\u20138878. (2021). https:\/\/doi.org\/10.1109\/CVPR46437.2021.00876","DOI":"10.1109\/CVPR46437.2021.00876"},{"key":"37938_CR44","unstructured":"Wang, X., Huang, T. E., Darrell, T., Gonzalez, J. E. & Yu, F. Frustratingly simple few-shot object detection. In Proceedings of the International Conference on Machine Learning (ICML) 9919\u20139928. (2020). https:\/\/proceedings.mlr.press\/v119\/wang20j.html"},{"key":"37938_CR45","doi-asserted-by":"publisher","unstructured":"Mueller, M., Smith, N. & Ghanem, B. A benchmark and simulator for UAV tracking. In Proceedings of the European Conference on Computer Vision (ECCV) 445\u2013461. (2016). https:\/\/doi.org\/10.1007\/978-3-319-46448-0_27","DOI":"10.1007\/978-3-319-46448-0_27"},{"key":"37938_CR46","doi-asserted-by":"publisher","unstructured":"Huang, X., Ge, Z., Jie, Z. & Yoshie, O. NMS by representative region: Towards crowded pedestrian detection by proposal pairing. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 10750\u201310759. (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01076","DOI":"10.1109\/CVPR42600.2020.01076"},{"issue":"6","key":"37938_CR47","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39 (6), 1137\u20131149. https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031 (2017).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37938_CR48","unstructured":"Tan, M. & Le, Q. EfficientNet: Rethinking model scaling for convolutional neural networks. In Proceedings of the International Conference on Machine Learning (ICML) 6105\u20136114. (2019). https:\/\/proceedings.mlr.press\/v97\/tan19a.html"},{"key":"37938_CR49","doi-asserted-by":"publisher","unstructured":"Carion, N. et al. End-to-end object detection with transformers. In Proceedings of the European Conference on Computer Vision (ECCV) 213\u2013229. (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"37938_CR50","unstructured":"Jocher, G., Chaurasia, A. & Qiu, J. Ultralytics YOLOv8. GitHub repository. (2023). https:\/\/github.com\/ultralytics\/ultralytics"},{"key":"37938_CR51","doi-asserted-by":"publisher","unstructured":"Tan, M., Pang, R. & Le, Q. V. EfficientDet: Scalable and efficient object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 10781\u201310790. (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.01079","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"37938_CR52","doi-asserted-by":"publisher","unstructured":"Zhao, Y. et al. DETRs beat YOLOs on real-time object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 16965\u201316974. (2024). https:\/\/doi.org\/10.1109\/CVPR52733.2024.01605","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"37938_CR53","doi-asserted-by":"publisher","unstructured":"Amdahl, G. M. Validity of the single processor approach to achieving large scale computing capabilities. In Proceedings of the April 18\u201320, 1967, Spring Joint Computer Conference 483\u2013485. (1967). https:\/\/doi.org\/10.1145\/1465482.1465560","DOI":"10.1145\/1465482.1465560"},{"key":"37938_CR54","doi-asserted-by":"publisher","unstructured":"Wang, C. Y., Yeh, I. H. & Liao, H. Y. M. YOLOv9: Learning what you want to learn using programmable gradient information. In Proceedings of the European Conference on Computer Vision (ECCV) 1\u201321. (2024). https:\/\/doi.org\/10.1007\/978-3-031-72751-1_1","DOI":"10.1007\/978-3-031-72751-1_1"},{"key":"37938_CR55","unstructured":"Wang, A. et al. YOLOv10: Real-time end-to-end object detection. In Advances in Neural Information Processing Systems (NeurIPS) (Vol. 37. (2024). https:\/\/arxiv.org\/abs\/2405.14458"},{"key":"37938_CR56","doi-asserted-by":"publisher","first-page":"117774","DOI":"10.1016\/j.engappai.2025.117774","volume":"144","author":"M Bakirci","year":"2025","unstructured":"Bakirci, M. Performance evaluation of low-power and lightweight object detectors for real-time monitoring in resource-constrained drone systems. Eng. Appl. Artif. Intell. 144, 117774. https:\/\/doi.org\/10.1016\/j.engappai.2025.117774 (2025).","journal-title":"Eng. Appl. Artif. Intell."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37938-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37938-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37938-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T00:03:58Z","timestamp":1771459438000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-37938-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":56,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["37938"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-37938-5","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,31]]},"assertion":[{"value":"20 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2026","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":"Competing interests"}},{"value":"Not applicable. This study involves technical research on computer vision algorithms and UAV systems without human subjects participation. All aerial imagery used in experiments was collected in compliance with local aviation regulations and privacy laws. No identifiable personal information was included in the datasets.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All authors have reviewed and approved the final manuscript for publication. The authors consent to the publication of this work in its current form.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"6814"}}