{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T23:42:40Z","timestamp":1777246960690,"version":"3.51.4"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":45,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"The Major Science and Technology Foundation of Zhongshan City","award":["2019B2006, 2019A40027, 2021A1003, 2023AJ002"],"award-info":[{"award-number":["2019B2006, 2019A40027, 2021A1003, 2023AJ002"]}]},{"name":"The First-Class Course Program of Guangdong Province","award":["YLKC202202"],"award-info":[{"award-number":["YLKC202202"]}]},{"name":"The Science and Technology Commissioner Project of Guangdong Province","award":["GDKTP2021025700"],"award-info":[{"award-number":["GDKTP2021025700"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Autonomous driving systems critically rely on the precise detection of distant, small traffic signs to ensure safe and efficient navigation. Nonetheless, existing detection algorithms are confronted with several significant challenges, including the limited efficacy in capturing the subtle visual features of small targets, the adverse effects of complex background clutter, and the imperative for real-time inference via computationally lightweight models. To address these challenges, we propose YOLO-AML, which effectively reduces computational complexity through parameter-free spatial transformations and low-channel convolution operations while preserving fine-grained features of small objects. The proposed Normalization-based Attention with sigmoid and tanh (NAST) module employs a hybrid gating mechanism to precisely regulate attention weight distribution, thereby suppressing background noise without introducing additional convolutional overhead. Furthermore, the C2PSA-LSKA (CLSKA) module integrated into the backbone network enhances the receptive field while minimizing parameter count, effectively mitigating the issue of traffic signs being obscured by background clutter. Additionally, a Normalized Wasserstein Distance (NWD) loss function is introduced to alleviate gradient vanishing commonly encountered with extremely small objects. Experimental results indicate that the optimized model reduces the total number of parameters by 17%, computational complexity by 16.8%, achieves a detection speed of 72.2 FPS, and improves detection accuracy by 2.0%. Grad-CAM heatmap visualization further confirms the model\u2019s enhanced feature discriminability and robustness against background interference. Overall, YOLO-AML demonstrates significant improvements in detection performance under complex real-world driving scenarios.<\/jats:p>","DOI":"10.1038\/s41598-026-43920-y","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T18:15:26Z","timestamp":1773425726000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An adaptive multi-scale lightweight network for long-distance small traffic sign detection"],"prefix":"10.1038","volume":"16","author":[{"given":"Ruishi","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjie","family":"Qu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaibing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"key":"43920_CR1","doi-asserted-by":"crossref","unstructured":"Zhu, Z. et al. Traffic-sign detection and classification in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2110\u20132118 (2016).","DOI":"10.1109\/CVPR.2016.232"},{"key":"43920_CR2","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, 779\u2013788 (2016).","DOI":"10.1109\/CVPR.2016.91"},{"key":"43920_CR3","doi-asserted-by":"publisher","first-page":"323","DOI":"10.3390\/wevj15070323","volume":"15","author":"S Fang","year":"2024","unstructured":"Fang, S., Chen, C., Li, Z., Zhou, M. & Wei, R. Yolo-adual: A lightweight traffic sign detection model for a mobile driving system. World Electric Veh. J. 15, 323 (2024).","journal-title":"World Electric Veh. J."},{"key":"43920_CR4","doi-asserted-by":"publisher","first-page":"875","DOI":"10.1049\/ipr2.12991","volume":"18","author":"YJ Qian","year":"2024","unstructured":"Qian, Y. J. & Wang, B. Tsdet: A new method for traffic sign detection based on yolov5-swint. IET Image Proc. 18, 875\u2013885 (2024).","journal-title":"IET Image Proc."},{"key":"43920_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104615","volume":"153","author":"Y Han","year":"2024","unstructured":"Han, Y., Wang, F., Wang, W., Zhang, X. & Li, X. Edn-yolo: Multi-scale traffic sign detection method in complex scenes. Dig. Signal Process. 153, 104615 (2024).","journal-title":"Dig. Signal Process."},{"key":"43920_CR6","doi-asserted-by":"publisher","first-page":"2884","DOI":"10.1049\/ipr2.13141","volume":"18","author":"S Du","year":"2024","unstructured":"Du, S. et al. Tsd-yolo: Small traffic sign detection based on improved yolo v8. IET Image Proc. 18, 2884\u20132898 (2024).","journal-title":"IET Image Proc."},{"key":"43920_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121836","volume":"238","author":"S Saxena","year":"2024","unstructured":"Saxena, S., Dey, S., Shah, M. & Gupta, S. Traffic sign detection in unconstrained environment using improved yolov4. Expert Syst. Appl. 238, 121836 (2024).","journal-title":"Expert Syst. Appl."},{"key":"43920_CR8","unstructured":"Bochkovskiy, A., Wang, C.-Y. & Liao, H.-Y.\u00a0M. Yolov4: Optimal speed and accuracy of object detection. arXiv:2004.10934 (2020)."},{"key":"43920_CR9","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A. & Liao, H.-Y.\u00a0M. 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, 7464\u20137475 (2023).","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"43920_CR10","unstructured":"Jocher, G., Chaurasia, A. & Qiu, J. Ultralytics yolov8 (2023)."},{"key":"43920_CR11","unstructured":"Khanam, R. & Hussain, M. Yolov11: An overview of the key architectural enhancements. arXiv:2410.17725 (2024)."},{"key":"43920_CR12","doi-asserted-by":"publisher","first-page":"848","DOI":"10.1109\/41.649946","volume":"44","author":"A De La Escalera","year":"1997","unstructured":"De La Escalera, A., Moreno, L. E., Salichs, M. A. & Armingol, J. M. Road traffic sign detection and classification. IEEE Trans. Industr. Electron. 44, 848\u2013859 (1997).","journal-title":"IEEE Trans. Industr. Electron."},{"key":"43920_CR13","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1016\/j.neucom.2014.11.026","volume":"153","author":"J Lillo-Castellano","year":"2015","unstructured":"Lillo-Castellano, J., Mora-Jim\u00e9nez, I., Figuera-Pozuelo, C. & Rojo-\u00c1lvarez, J. L. Traffic sign segmentation and classification using statistical learning methods. Neurocomputing 153, 286\u2013299 (2015).","journal-title":"Neurocomputing"},{"key":"43920_CR14","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1109\/TITS.2010.2098029","volume":"12","author":"\u00c1 Gonz\u00e1lez","year":"2011","unstructured":"Gonz\u00e1lez, \u00c1. et al. Automatic traffic signs and panels inspection system using computer vision. IEEE Trans. Intell. Transp. Syst. 12, 485\u2013499 (2011).","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"43920_CR15","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1016\/j.patcog.2009.05.018","volume":"43","author":"A Ruta","year":"2010","unstructured":"Ruta, A., Li, Y. & Liu, X. Real-time traffic sign recognition from video by class-specific discriminative features. Pattern Recogn. 43, 416\u2013430 (2010).","journal-title":"Pattern Recogn."},{"key":"43920_CR16","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/s41315-022-00232-4","volume":"6","author":"R Ayachi","year":"2022","unstructured":"Ayachi, R., Afif, M., Said, Y. & Ben Abdelali, A. An edge implementation of a traffic sign detection system for advanced driver assistance systems. Int. J. Intell. Robot. Appl. 6, 207\u2013215 (2022).","journal-title":"Int. J. Intell. Robot. Appl."},{"key":"43920_CR17","doi-asserted-by":"crossref","unstructured":"Yang, Y. & Wu, F. Real-time traffic sign detection via color probability model and integral channel features. In Chinese Conference on Pattern Recognition, 545\u2013554 (Springer, 2014).","DOI":"10.1007\/978-3-662-45643-9_58"},{"key":"43920_CR18","doi-asserted-by":"crossref","unstructured":"Nguwi, Y.-Y. & Kouzani, A.\u00a0Z. Automatic road sign recognition using neural networks. In The 2006 IEEE International Joint Conference on Neural Network Proceedings, 3955\u20133962 (IEEE, 2006).","DOI":"10.1109\/IJCNN.2006.246916"},{"key":"43920_CR19","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1016\/j.patcog.2014.05.017","volume":"48","author":"S Salti","year":"2015","unstructured":"Salti, S., Petrelli, A., Tombari, F., Fioraio, N. & Di Stefano, L. Traffic sign detection via interest region extraction. Pattern Recogn. 48, 1039\u20131049. https:\/\/doi.org\/10.1016\/j.patcog.2014.05.017 (2015).","journal-title":"Pattern Recogn."},{"key":"43920_CR20","doi-asserted-by":"publisher","unstructured":"Wang, G., Ren, G., Wu, Z., Zhao, Y. & Jiang, L. A robust, coarse-to-fine traffic sign detection method. In The 2013 International Joint Conference on Neural Networks, IJCNN 2013, Dallas, TX, USA, August 4-9, 2013, 1\u20135, https:\/\/doi.org\/10.1109\/IJCNN.2013.6706812 (IEEE, 2013).","DOI":"10.1109\/IJCNN.2013.6706812"},{"key":"43920_CR21","doi-asserted-by":"publisher","unstructured":"Xiao, Z., Yang, Z., Geng, L. & Zhang, F. Traffic sign detection based on histograms of oriented gradients and boolean convolutional neural networks. In 2017 International Conference on Machine Vision and Information Technology (CMVIT), 111\u2013115, https:\/\/doi.org\/10.1109\/CMVIT.2017.26 (2017).","DOI":"10.1109\/CMVIT.2017.26"},{"key":"43920_CR22","doi-asserted-by":"publisher","unstructured":"Houben, S., Stallkamp, J., Salmen, J., Schlipsing, M. & Igel, C. Detection of traffic signs in real-world images: The german traffic sign detection benchmark. In The 2013 International Joint Conference on Neural Networks (IJCNN), 1\u20138, https:\/\/doi.org\/10.1109\/IJCNN.2013.6706807 (2013).","DOI":"10.1109\/IJCNN.2013.6706807"},{"key":"43920_CR23","doi-asserted-by":"crossref","unstructured":"Liu, W. et al. Ssd: Single shot multibox detector. In European conference on computer vision, 21\u201337 (Springer, 2016).","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"43920_CR24","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":"43920_CR25","doi-asserted-by":"publisher","unstructured":"Girshick, R. Fast r-cnn. In 2015 IEEE International Conference on Computer Vision (ICCV), 1440\u20131448, https:\/\/doi.org\/10.1109\/ICCV.2015.169 (2015).","DOI":"10.1109\/ICCV.2015.169"},{"key":"43920_CR26","doi-asserted-by":"publisher","unstructured":"Ren, S., He, K., Girshick, R. & Sun, J. Faster r-cnn: Towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence39, 1137\u20131149, https:\/\/doi.org\/10.1109\/TPAMI.2016.2577031 (2017).","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"43920_CR27","doi-asserted-by":"publisher","unstructured":"Huang, Z., Huang, L., Gong, Y., Huang, C. & Wang, X. Mask scoring r-cnn. In 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 6402\u20136411, https:\/\/doi.org\/10.1109\/CVPR.2019.00657 (2019).","DOI":"10.1109\/CVPR.2019.00657"},{"key":"43920_CR28","doi-asserted-by":"publisher","first-page":"1396","DOI":"10.1049\/iet-its.2018.5171","volume":"12","author":"S Natarajan","year":"2018","unstructured":"Natarajan, S., Annamraju, A. K. & Baradkar, C. S. Traffic sign recognition using weighted multi-convolutional neural network. IET Intel. Transport Syst. 12, 1396\u20131405 (2018).","journal-title":"IET Intel. Transport Syst."},{"key":"43920_CR29","doi-asserted-by":"publisher","first-page":"1483","DOI":"10.1109\/TPAMI.2019.2956516","volume":"43","author":"Z Cai","year":"2019","unstructured":"Cai, Z. & Vasconcelos, N. Cascade r-cnn: High quality object detection and instance segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 43, 1483\u20131498 (2019).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"43920_CR30","doi-asserted-by":"publisher","first-page":"7558","DOI":"10.1038\/s41598-025-88184-0","volume":"15","author":"H Zhang","year":"2025","unstructured":"Zhang, H., Liang, M. & Wang, Y. Yolo-bs: a traffic sign detection algorithm based on yolov8. Sci. Rep. 15, 7558 (2025).","journal-title":"Sci. Rep."},{"key":"43920_CR31","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ad9517","volume":"36","author":"X Zheng","year":"2024","unstructured":"Zheng, X., Guan, Z., Chen, Q., Wen, G. & Lu, X. A lightweight road traffic sign detection algorithm based on adaptive sparse channel pruning. Meas. Sci. Technol. 36, 016176 (2024).","journal-title":"Meas. Sci. Technol."},{"key":"43920_CR32","unstructured":"Tan, M. & Le, Q. Efficientnetv2: Smaller models and faster training. In International conference on machine learning, 10096\u201310106 (PMLR, 2021)."},{"key":"43920_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121352","volume":"236","author":"KW Lau","year":"2024","unstructured":"Lau, K. W., Po, L.-M. & Rehman, Y. A. U. Large separable kernel attention: Rethinking the large kernel attention design in cnn. Expert Syst. Appl. 236, 121352 (2024).","journal-title":"Expert Syst. Appl."},{"key":"43920_CR34","doi-asserted-by":"crossref","unstructured":"Sunkara, R. & Luo, T. No more strided convolutions or pooling: A new cnn building block for low-resolution images and small objects. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 443\u2013459 (Springer, 2022).","DOI":"10.1007\/978-3-031-26409-2_27"},{"key":"43920_CR35","doi-asserted-by":"publisher","unstructured":"Zhou, X., Yang, G., Chen, Y., Li, L. & Chen, B.\u00a0M. Vdtnet: A high-performance visual network for detecting and tracking of intruding drones. IEEE Transactions on Intelligent Transportation Systems25, 9828\u20139839, https:\/\/doi.org\/10.1109\/TITS.2024.3350920 (2024).","DOI":"10.1109\/TITS.2024.3350920"},{"key":"43920_CR36","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1007\/s11760-025-04276-4","volume":"19","author":"M Yang","year":"2025","unstructured":"Yang, M. & Han, S. Ets-yolo: An efficient yolo-based model for real-time traffic sign recognition. SIViP 19, 650 (2025).","journal-title":"SIViP"},{"key":"43920_CR37","unstructured":"Wang, J., Xu, C., Yang, W. & Yu, L. A normalized gaussian wasserstein distance for tiny object detection. arXiv:2110.13389 (2021)."},{"key":"43920_CR38","unstructured":"Liu, Y., Shao, Z., Teng, Y. & Hoffmann, N. Nam: Normalization-based attention module. arXiv:2111.12419 (2021)."},{"key":"43920_CR39","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2025.103891","volume":"69","author":"X Zhou","year":"2026","unstructured":"Zhou, X., Chen, X., Chen, J. & Chen, B. M. An accurate and resource-efficient network for surface anomaly detection via enhanced downsampling and activation representation. Adv. Eng. Inform. 69, 103891. https:\/\/doi.org\/10.1016\/j.aei.2025.103891 (2026).","journal-title":"Adv. Eng. Inform."},{"key":"43920_CR40","first-page":"1","volume":"19","author":"C Wang","year":"2025","unstructured":"Wang, C., Song, X., Wang, J. & Yan, X. An improved yolov11 algorithm for small object detection in uav images. SIViP 19, 1\u201312 (2025).","journal-title":"SIViP"},{"key":"43920_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3548216","volume":"74","author":"X Zhou","year":"2025","unstructured":"Zhou, X., Han, B., Li, L., Chen, J. & Chen, B. M. Drnet: A miniature and resource- efficient mav detector. IEEE Trans. Instrum. Meas. 74, 1\u201314. https:\/\/doi.org\/10.1109\/TIM.2025.3548216 (2025).","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"43920_CR42","first-page":"733","volume":"9","author":"M-H Guo","year":"2023","unstructured":"Guo, M.-H., Lu, C.-Z., Liu, Z.-N., Cheng, M.-M. & Hu, S.-M. Computational visual media. Vis. Attent. Netw. 9, 733\u2013752 (2023).","journal-title":"Vis. Attent. Netw."},{"key":"43920_CR43","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y. & Kweon, I.\u00a0S. Cbam: Convolutional block attention module. In Proceedings of the European Conference on Computer Vision (ECCV), 3\u201319 (2018).","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"43920_CR44","unstructured":"Ioffe, S. & Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning, 448\u2013456 (pmlr, 2015)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-43920-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-43920-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-43920-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T23:14:07Z","timestamp":1777245247000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-43920-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["43920"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-43920-y","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]},"assertion":[{"value":"30 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 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"}}],"article-number":"13459"}}