{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:32:00Z","timestamp":1787725920338,"version":"build-2784847793"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>For Intelligent Transportation Systems (ITS), traffic sign detection plays an essential role for autonomous vehicles to validate the condition of the roads more precisely. However, the environmental concerns, such as obstacles, lighting, and weather, may have an impact on the performance of the existing traffic sign detection systems. To overcome these problems, a model that uses a multi-scale-based learning network and image dehazing approach is developed in this work for traffic sign detection. At first, the required images are collected, and the input images undergo the pre-processing step. In this stage, the images utilize the Spatial Pyramid Pooling with Convolutional Autoencoder (SPP-CAE) for performing the image dehazing since the image is affected by unfavorable weather conditions. Finally, the pre-processed images are subjected as input to the object detection model, which employs the Multiscale Attentional Feature Fusion-based Feature Pyramid Network, incorporating Adaptive YOLOv9 (MAFF-FPN-AYv9). Here, the Multiscale Attentional Feature Fusion-based Feature Pyramid Network (MAFF-FPN) helped to extract the pertinent features and processed them under the YOLOv9 model for detecting the objects. For further improvement, the parameters present in the YOLOv9 model are optimally tuned by using the Stochastic Apiary Organizational Optimization with Population Amendment Strategy (SAOO-PAS). Lastly, the performance of the model is validated and examined by various metrics. With accuracies of 96% and 97% on the BDD100K and TT100K datasets, respectively, the results show how well this system performs, proving that the suggested model achieves superior results in detecting the traffic signs.<\/jats:p>","DOI":"10.3389\/frai.2026.1903277","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:04:05Z","timestamp":1787724245000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-scale attentional feature fusion-based traffic sign detection using image dehazing process of SPP-CAE and improved optimization of YOLOv9 model"],"prefix":"10.3389","volume":"9","author":[{"given":"Thiyagarajan","family":"V","sequence":"first","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vidhyapathi","family":"CM","sequence":"additional","affiliation":[{"name":"School of Electronics Engineering, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"ref2","doi-asserted-by":"publisher","first-page":"783","DOI":"10.22266\/ijies2024.0630.61","article-title":"Apiary organizational-based optimization algorithm: a new nature-inspired metaheuristic algorithm","volume":"17","author":"Al-Sharqi","year":"2024","journal-title":"Int. J. Intell. Eng. Syst."},{"key":"ref1","doi-asserted-by":"publisher","first-page":"128003","DOI":"10.1016\/j.eswa.2025.128003","article-title":"Saam-reflectnet: sign-aware attention-based multitasking framework for integrated traffic sign detection and retroreflectivity estimation","volume":"286","author":"Asamoah","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref9003","first-page":"1674","article-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Berman","year":"2016"},{"key":"ref9001","first-page":"1375","article-title":"Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Chen","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.32604\/cmc.2025.067286","article-title":"Toward efficient traffic-sign detection via SlimNeck and coordinate-attention fusion in YOLO-SMM","volume":"86","author":"Chen","year":"2026","journal-title":"Comput. Mater. Contin."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"124688","DOI":"10.1016\/j.eswa.2024.124688","article-title":"VisioSignNet: a dual-interactive neural network for enhanced traffic sign detection","volume":"255","author":"Chen","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"19500","DOI":"10.1109\/jiot.2024.3367899","article-title":"A semi-supervised learning framework combining CNN and multiscale transformer for traffic sign detection and recognition","volume":"11","author":"Chen","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1007\/s11227-023-05513-8","article-title":"Lotus effect optimization algorithm (LEA): a lotus nature-inspired algorithm for engineering design optimization","volume":"80","author":"Dalirinia","year":"2024","journal-title":"J. Supercomput."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s11227-025-07256-0","article-title":"A heterogeneous attention YOLO model for traffic sign detection","volume":"81","author":"Deng","year":"2025","journal-title":"J. Supercomput."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1177\/17248035251390608","article-title":"Multi-scale attention and transformer-enhanced YOLO architecture for robust traffic sign detection in complex visual environments","volume":"20","author":"Farhani","year":"2026","journal-title":"Intell. Artif."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"12950","DOI":"10.1038\/s41598-023-38778-3","article-title":"Red-tailed hawk algorithm for numerical optimization and real-world problems","volume":"13","author":"Ferahtia","year":"2023","journal-title":"Sci. Rep."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"20633","DOI":"10.1007\/s00521-024-10279-y","article-title":"Traffic sign detection and recognition based on MMS data using YOLOv4-tiny algorithm","volume":"36","author":"Gezgin","year":"2024","journal-title":"Neural Comput. & Applic."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"104615","DOI":"10.1016\/j.dsp.2024.104615","article-title":"EDN-YOLO: multi-scale traffic sign detection method in complex scenes","volume":"153","author":"Han","year":"2024","journal-title":"Digit. Signal Process."},{"key":"ref9004","doi-asserted-by":"publisher","first-page":"2341","DOI":"10.1109\/TPAMI.2010.168","article-title":"Single Image Haze Removal Using Dark Channel Prior","volume":"33","author":"He","year":"2011","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"44191","DOI":"10.1038\/s41598-025-27959-x","article-title":"Dehaze-attention: enhancing image dehazing with a multi-scale, attention-based deep learning framework","volume":"15","author":"Huang","year":"2025","journal-title":"Sci. Rep."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"100167","DOI":"10.1016\/j.fraope.2024.100167","article-title":"Improved YOLOv8 for small traffic sign detection under complex environmental conditions","volume":"8","author":"Ji","year":"2024","journal-title":"Frankl. Open"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s13042-025-02845-0","article-title":"Msif-net: non-homogeneous image dehazing based on model selection and image fusion","volume":"17","author":"Jin","year":"2026","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"38355","DOI":"10.1016\/j.jvcir.2023.103855","article-title":"Single image dehazing using hybrid convolution neural network","volume":"83","author":"Juneja","year":"","journal-title":"Multimed. Tools Appl."},{"key":"ref16","doi-asserted-by":"crossref","first-page":"103855","DOI":"10.1016\/j.jvcir.2023.103855","article-title":"Aethra-net: single image and video dehazing using autoencoder","volume":"94","author":"Juneja","year":"","journal-title":"J. Vis. Commun. Image Represent."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"3723","DOI":"10.1007\/s11831-023-09918-9","article-title":"A comprehensive review of computational desmogging techniques","volume":"30","author":"Juneja","year":"","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"7179","DOI":"10.1007\/s11042-023-15893-x","article-title":"Desmogging of still images using residual regression network and morphological erosion","volume":"83","author":"Juneja","year":"2024","journal-title":"Multim. Tools Appl."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1467","DOI":"10.1109\/TITS.2019.2911727","article-title":"Automatic traffic sign detection and recognition using SegU-net and a modified Tversky loss function with L1-constraint","volume":"21","author":"Kamal","year":"2020","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref20","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/978-3-031-72111-3_4","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024","author":"Kang","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"861","DOI":"10.32604\/cmc.2023.035595","article-title":"Traffic sign detection with low complexity for intelligent vehicles based on hybrid features","volume":"76","author":"Khalid","year":"2023","journal-title":"Comput. Mater. Contin."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"445","DOI":"10.32604\/cmc.2023.042675","article-title":"Traffic sign recognition for autonomous vehicle using optimized YOLOv7 and convolutional block attention module","volume":"77","author":"Kuppusamy","year":"2023","journal-title":"Comput. Mater. Contin."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"114996","DOI":"10.1016\/j.asoc.2026.114996","article-title":"NightMamba: integrating physical degradation models in enhanced state-space networks for nighttime image dehazing","volume":"195","author":"Liang","year":"2026","journal-title":"Appl. Soft Comput."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1109\/TIV.2019.2919458","article-title":"Benchmarking deep learning frameworks and investigating FPGA deployment for traffic sign classification and detection","volume":"4","author":"Lin","year":"2019","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref26","doi-asserted-by":"publisher","first-page":"110039","DOI":"10.1109\/ACCESS.2023.3322371","article-title":"UCN-YOLOv5: traffic sign object detection algorithm based on deep learning","volume":"11","author":"Liu","year":"2023","journal-title":"IEEE Access"},{"key":"ref9002","first-page":"4780","article-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Li","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"25904","DOI":"10.1038\/s41598-024-76804-0","article-title":"Enhancing small target traffic sign detection with ML_SAP in YOLOv5s","volume":"14","author":"Lu","year":"2024","journal-title":"Sci. Rep."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1007\/s11554-023-01403-7","article-title":"A novel lightweight real-time traffic sign detection method based on an embedded device and YOLOv8","volume":"21","author":"Luo","year":"2024","journal-title":"J. Real-Time Image Proc."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"110783","DOI":"10.1016\/j.sigpro.2026.110783","article-title":"From structure to semantics: a fusion network with chrominance guidance and physics-inspired for single image dehazing","volume":"250","author":"Lyu","year":"2026","journal-title":"Signal Process."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"100442","DOI":"10.1016\/j.prime.2024.100442","article-title":"Traffic sign detection and recognition using deep learning-based approach with haze removal for autonomous vehicle navigation","volume":"7","author":"Rani","year":"2024","journal-title":"E-Prime Adv. Electr. Eng. Electron. Energy"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1425","DOI":"10.32604\/cmc.2024.052667","article-title":"A hybrid feature fusion traffic sign detection algorithm based on YOLOv7","volume":"80","author":"Ren","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"48","DOI":"10.3390\/vision8030048","article-title":"Diabetic retinopathy features segmentation without coding experience with computer vision models YOLOv8 and YOLOv9","volume":"8","author":"Rizzieri","year":"2024","journal-title":"Vision"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"88387","DOI":"10.1007\/s11042-023-17146-3","article-title":"A lightweight method for small scale traffic sign detection based on YOLOv4-tiny","volume":"83","author":"Shen","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"25005","DOI":"10.1007\/s11042-023-16451-1","article-title":"A performance comparison of YOLOv8 models for traffic sign detection in the Robotaxi-full scale autonomous vehicle competition","volume":"83","author":"Soylu","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"4466","DOI":"10.1109\/TITS.2018.2886283","article-title":"Traffic sign detection using a multi-scale recurrent attention network","volume":"20","author":"Tian","year":"2019","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"102674","DOI":"10.1016\/j.aei.2024.102674","article-title":"A universal traffic sign detection system using a novel self-training neural network modelling approach","volume":"62","author":"Trappey","year":"2024","journal-title":"Adv. Eng. Inform."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"91","DOI":"10.3390\/biomimetics9020091","article-title":"The pine cone optimization algorithm (PCOA)","volume":"9","author":"Valikhan Anaraki","year":"2024","journal-title":"Biomimetics"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TITS.2023.3309644","article-title":"Vehicle-mounted adaptive traffic sign detector for small-sized signs in multiple working conditions","volume":"25","author":"Wang","year":"","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"18509","DOI":"10.1109\/access.2026.3659918","article-title":"RFAM-YOLO: reinforced feature aggregation and multi-attention YOLOv8s for high-precision traffic sign detection","volume":"14","author":"Wang","year":"2026","journal-title":"IEEE Access"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"148880","DOI":"10.1109\/ACCESS.2024.3476371","article-title":"MMW-YOLOv5: a multi-scale enhanced traffic sign detection algorithm","volume":"12","author":"Wang","year":"2024","journal-title":"IEEE Access"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"3360","DOI":"10.1007\/s11227-023-05594-5","article-title":"A lightweight vehicle mounted multi-scale traffic sign detector using attention fusion pyramid","volume":"80","author":"Wang","year":"","journal-title":"J. Supercomput."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"592","DOI":"10.34028\/iajit\/20\/4\/5","article-title":"Spatial pyramid pooling and adaptively feature fusion based YOLOv3 for traffic sign detection","volume":"20","author":"Xiong","year":"2023","journal-title":"Int. Arab J. Inf. Technol."},{"key":"ref42","first-page":"486","author":"Yagis","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.1109\/TITS.2016.2614548","article-title":"An incremental framework for video-based traffic sign detection, tracking, and recognition","volume":"18","author":"Yuan","year":"2017","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref44","doi-asserted-by":"publisher","first-page":"880","DOI":"10.3390\/electronics13050880","article-title":"Efficient vision transformer YOLOv5 for accurate and fast traffic sign detection","volume":"13","author":"Zeng","year":"2024","journal-title":"Electronics"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"7558","DOI":"10.1038\/s41598-025-88184-0","article-title":"YOLO-BS: a traffic sign detection algorithm based on YOLOv8","volume":"15","author":"Zhang","year":"2025","journal-title":"Sci. Rep."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"109536","DOI":"10.1016\/j.engappai.2024.109536","article-title":"TSD-DETR: a lightweight real-time detection transformer of traffic sign detection for long-range perception of autonomous driving","volume":"139","author":"Zhang","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"109619","DOI":"10.1016\/j.sigpro.2024.109619","article-title":"Enhancing autonomous driving safety: a robust traffic sign detection and recognition model TSD-YOLO","volume":"225","author":"Zhao","year":"2024","journal-title":"Signal Process."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1903277\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T06:04:06Z","timestamp":1787724246000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1903277\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":51,"alternative-id":["10.3389\/frai.2026.1903277"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1903277","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"article-number":"1903277"}}