{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T13:30:39Z","timestamp":1789479039078,"version":"build-2803163510"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:00:00Z","timestamp":1765497600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:00:00Z","timestamp":1765497600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Key Scientific Research Project of Higher Education of Henan Province","award":["No. 24A520025"],"award-info":[{"award-number":["No. 24A520025"]}]},{"DOI":"10.13039\/501100017700","name":"Henan Provincial Science and Technology Research Project","doi-asserted-by":"publisher","award":["No. 252102320286"],"award-info":[{"award-number":["No. 252102320286"]}],"id":[{"id":"10.13039\/501100017700","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-025-27441-8","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T10:58:08Z","timestamp":1765537088000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Pedestrian detection in aerial image based on convolutional neural network with attention mechanism and multi-scale prediction"],"prefix":"10.1038","volume":"15","author":[{"given":"Jiaxi","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaquan","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shitong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,12]]},"reference":[{"key":"27441_CR1","doi-asserted-by":"publisher","first-page":"1696","DOI":"10.1109\/TIFS.2020.3040881","volume":"16","author":"SA Kumar","year":"2020","unstructured":"Kumar, S. A., Yaghoubi, E., Das, A., Harish, B. & Proenca, H. The p-destre: A fully annotated dataset for pedestrian detection, tracking, and short\/long-term re-identification from aerial devices. IEEE Trans. Inf. Forensics Secur. 16, 1696\u20131708 (2020).","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"27441_CR2","first-page":"157","volume":"29","author":"A Nguyen","year":"2021","unstructured":"Nguyen, A. & Lee, B. Enhancing traffic safety through pedestrian detection: A deep learning approach. J. Transport. Saf. 29, 157\u2013174 (2021).","journal-title":"J. Transport. Saf."},{"key":"27441_CR3","doi-asserted-by":"publisher","first-page":"37905","DOI":"10.1109\/ACCESS.2021.3063681","volume":"9","author":"S Sambolek","year":"2021","unstructured":"Sambolek, S. & Ivasic-Kos, M. Automatic person detection in search and rescue operations using deep cnn detectors. IEEE Access 9, 37905\u201337922 (2021).","journal-title":"IEEE Access"},{"key":"27441_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3132332","volume":"71","author":"J Shen","year":"2022","unstructured":"Shen, J. et al. Finger vein recognition algorithm based on lightweight deep convolutional neural network. IEEE Trans. Instrum. Meas. 71, 1\u201313. https:\/\/doi.org\/10.1109\/TIM.2021.3132332 (2022).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"27441_CR5","doi-asserted-by":"crossref","unstructured":"Gomaa, A., Abdelwahab, M.\u00a0M. & Abo-Zahhad, M. Real-time algorithm for simultaneous vehicle detection and tracking in aerial view videos. In 2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS). 222\u2013225 (IEEE, 2018).","DOI":"10.1109\/MWSCAS.2018.8624022"},{"key":"27441_CR6","doi-asserted-by":"publisher","first-page":"255","DOI":"10.3390\/wevj15060255","volume":"15","author":"A Gomaa","year":"2024","unstructured":"Gomaa, A. & Abdalrazik, A. Novel deep learning domain adaptation approach for object detection using semi-self building dataset and modified yolov4. World Electr. Veh. J. 15, 255 (2024).","journal-title":"World Electr. Veh. J."},{"key":"27441_CR7","doi-asserted-by":"crossref","unstructured":"Gomaa, A. Advanced domain adaptation technique for object detection leveraging semi-automated dataset construction and enhanced yolov8. In 2024 6th Novel Intelligent and Leading Emerging Sciences Conference (NILES). 211\u2013214 (IEEE, 2024).","DOI":"10.1109\/NILES63360.2024.10753164"},{"key":"27441_CR8","doi-asserted-by":"crossref","unstructured":"Liu, W. et al. SSD: Single shot multibox detector. In Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part I. Vol. 14. 21\u201337 (Springer, 2016).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"27441_CR9","unstructured":"Khanam, R. & Hussain, M. Yolov11: An overview of the key architectural enhancements (2024). arXiv:2410.17725."},{"key":"27441_CR10","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. 2980\u20132988 (2017).","DOI":"10.1109\/ICCV.2017.324"},{"key":"27441_CR11","first-page":"789","volume":"34","author":"C Zhang","year":"2022","unstructured":"Zhang, C. & Kim, D. Comparative analysis of one-stage and two-stage deep learning architectures for pedestrian detection. J. Comput. Vis. 34, 789\u2013805 (2022).","journal-title":"J. Comput. Vis."},{"key":"27441_CR12","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28 (2015)."},{"key":"27441_CR13","doi-asserted-by":"crossref","unstructured":"Girshick, R., Donahue, J., Darrell, T. & Malik, J. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 580\u2013587 (2014).","DOI":"10.1109\/CVPR.2014.81"},{"key":"27441_CR14","doi-asserted-by":"publisher","first-page":"3551","DOI":"10.3390\/electronics11213551","volume":"11","author":"S Iftikhar","year":"2022","unstructured":"Iftikhar, S. et al. Deep learning-based pedestrian detection in autonomous vehicles: Substantial issues and challenges. Electronics 11, 3551 (2022).","journal-title":"Electronics"},{"key":"27441_CR15","doi-asserted-by":"publisher","first-page":"26023","DOI":"10.1007\/s11042-020-09242-5","volume":"79","author":"A Gomaa","year":"2020","unstructured":"Gomaa, A., Abdelwahab, M. M. & Abo-Zahhad, M. Efficient vehicle detection and tracking strategy in aerial videos by employing morphological operations and feature points motion analysis. Multimed. Tools Appl. 79, 26023\u201326043. https:\/\/doi.org\/10.1007\/s11042-020-09242-5 (2020).","journal-title":"Multimed. Tools Appl."},{"key":"27441_CR16","doi-asserted-by":"crossref","unstructured":"Shen, J. et al. An algorithm based on lightweight semantic features for ancient mural element object detection. npj Heritage Sci. 13, 70 (2025).","DOI":"10.1038\/s40494-025-01565-6"},{"key":"27441_CR17","unstructured":"Xu, S. et al. Pp-yoloe: An evolved version of yolo (2022). arXiv:2203.16250."},{"key":"27441_CR18","doi-asserted-by":"publisher","first-page":"17493","DOI":"10.1038\/s41598-025-02111-x","volume":"15","author":"OF Hassan","year":"2025","unstructured":"Hassan, O. F., Ibrahim, A. F., Gomaa, A., Makhlouf, M. & Hafiz, B. Real-time driver drowsiness detection using transformer architectures: A novel deep learning approach. Sci. Rep. 15, 17493 (2025).","journal-title":"Sci. Rep."},{"key":"27441_CR19","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1109\/TRS.2025.3537604","volume":"3","author":"L Cheng","year":"2025","unstructured":"Cheng, L. & Cao, S. Transrad: Retentive vision transformer for enhanced radar object detection. IEEE Trans. Radar Syst. 3, 303\u2013317. https:\/\/doi.org\/10.1109\/TRS.2025.3537604 (2025).","journal-title":"IEEE Trans. Radar Syst."},{"key":"27441_CR20","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1109\/THMS.2022.3145097","volume":"52","author":"L Dai","year":"2022","unstructured":"Dai, L., Liu, J. & Ju, Z. Binocular feature fusion and spatial attention mechanism based gaze tracking. IEEE Trans. Hum.-Mach. Syst. 52, 302\u2013311 (2022).","journal-title":"IEEE Trans. Hum.-Mach. Syst."},{"key":"27441_CR21","doi-asserted-by":"publisher","first-page":"2880","DOI":"10.1109\/TII.2020.3022912","volume":"17","author":"H Hu","year":"2020","unstructured":"Hu, H., Li, Q., Zhao, Y. & Zhang, Y. Parallel deep learning algorithms with hybrid attention mechanism for image segmentation of lung tumors. IEEE Trans. Indus. Inform. 17, 2880\u20132889 (2020).","journal-title":"IEEE Trans. Indus. Inform."},{"key":"27441_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2023.3346488","volume":"73","author":"J Shen","year":"2024","unstructured":"Shen, J., Liu, N., Sun, H., Li, D. & Zhang, Y. An instrument indication acquisition algorithm based on lightweight deep convolutional neural network and hybrid attention fine-grained features. IEEE Trans. Instrum. Meas. 73, 1\u201316. https:\/\/doi.org\/10.1109\/TIM.2023.3346488 (2024).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"27441_CR23","doi-asserted-by":"publisher","first-page":"15644","DOI":"10.1109\/TITS.2022.3144359","volume":"23","author":"Y Luo","year":"2022","unstructured":"Luo, Y., Zhang, C., Lin, W., Yang, X. & Sun, J. Sequential attention-based distinct part modeling for balanced pedestrian detection. IEEE Trans. Intell. Transport. Syst. 23, 15644\u201315654 (2022).","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"27441_CR24","doi-asserted-by":"publisher","first-page":"8678","DOI":"10.1109\/TMM.2024.3381377","volume":"26","author":"X Li","year":"2024","unstructured":"Li, X., Chen, S., Tian, C., Zhou, H. & Zhang, Z. M2fnet: Mask-guided multi-level fusion for rgb-t pedestrian detection. IEEE Trans. Multimed. 26, 8678\u20138690. https:\/\/doi.org\/10.1109\/TMM.2024.3381377 (2024).","journal-title":"IEEE Trans. Multimed."},{"key":"27441_CR25","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1109\/TITS.2024.3483892","volume":"26","author":"S Hao","year":"2025","unstructured":"Hao, S. et al. Mdfoanet: A novel multi-modal pedestrian detection network based on multi-scale image dynamic feature optimization and attention mapping. IEEE Trans. Intell. Transport. Syst. 26, 268\u2013282. https:\/\/doi.org\/10.1109\/TITS.2024.3483892 (2025).","journal-title":"IEEE Trans. Intell. Transport. Syst."},{"key":"27441_CR26","doi-asserted-by":"publisher","first-page":"13276","DOI":"10.1109\/TNNLS.2024.3443455","volume":"36","author":"X Zhang","year":"2025","unstructured":"Zhang, X. et al. Tfdet: Target-aware fusion for rgb-t pedestrian detection. IEEE Trans. Neural Netw. Learn. Syst. 36, 13276\u201313290. https:\/\/doi.org\/10.1109\/TNNLS.2024.3443455 (2025).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"27441_CR27","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y. et al. 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. 390\u2013391 (2020).","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"27441_CR28","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y. et al. Feature pyramid networks for object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2117\u20132125 (2017).","DOI":"10.1109\/CVPR.2017.106"},{"key":"27441_CR29","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J. & Jia, J. Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8759\u20138768 (2018).","DOI":"10.1109\/CVPR.2018.00913"},{"key":"27441_CR30","doi-asserted-by":"publisher","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","volume":"52","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z. et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52, 8574\u20138586 (2021).","journal-title":"IEEE Trans. Cybern."},{"key":"27441_CR31","unstructured":"Shao, S. et al. Crowdhuman: A benchmark for detecting human in a crowd. arXiv:1805.00123 (2018)."},{"key":"27441_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, S., Benenson, R. & Schiele, B. Citypersons: A diverse dataset for pedestrian detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 3213\u20133221 (2017).","DOI":"10.1109\/CVPR.2017.474"},{"key":"27441_CR33","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P. & Girshick, R.\u00a0B. Mask R-CNN. CoRR (2017). arXiv:1703.06870.","DOI":"10.1109\/ICCV.2017.322"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27441-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27441-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27441-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T10:58:13Z","timestamp":1765537093000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-27441-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":33,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["27441"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-27441-8","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7333218\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"9 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2025","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"}}],"article-number":"43677"}}