{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T22:31:07Z","timestamp":1781821867015,"version":"3.54.5"},"reference-count":48,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T00:00:00Z","timestamp":1675382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2017YFE0135700"],"award-info":[{"award-number":["2017YFE0135700"]}]},{"name":"National Key Research and Development Program of China","award":["2022TS003"],"award-info":[{"award-number":["2022TS003"]}]},{"name":"National Key Research and Development Program of China","award":["D01-168\/28.07.2022"],"award-info":[{"award-number":["D01-168\/28.07.2022"]}]},{"name":"Tsinghua Precision Medicine Foundation","award":["2017YFE0135700"],"award-info":[{"award-number":["2017YFE0135700"]}]},{"name":"Tsinghua Precision Medicine Foundation","award":["2022TS003"],"award-info":[{"award-number":["2022TS003"]}]},{"name":"Tsinghua Precision Medicine Foundation","award":["D01-168\/28.07.2022"],"award-info":[{"award-number":["D01-168\/28.07.2022"]}]},{"name":"MES","award":["2017YFE0135700"],"award-info":[{"award-number":["2017YFE0135700"]}]},{"name":"MES","award":["2022TS003"],"award-info":[{"award-number":["2022TS003"]}]},{"name":"MES","award":["D01-168\/28.07.2022"],"award-info":[{"award-number":["D01-168\/28.07.2022"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Axioms"],"abstract":"<jats:p>Object detection and image recognition are some of the most significant and challenging branches in the field of computer vision. The prosperous development of unmanned driving technology has made the detection and recognition of traffic signs crucial. Affected by diverse factors such as light, the presence of small objects, and complicated backgrounds, the results of traditional traffic sign detection technology are not satisfactory. To solve this problem, this paper proposes two novel traffic sign detection models, called YOLOv5-DH and YOLOv5-TDHSA, based on the YOLOv5s model with the following improvements (YOLOv5-DH uses only the second improvement): (1) replacing the last layer of the \u2018Conv + Batch Normalization + SiLU\u2019 (CBS) structure in the YOLOv5s backbone with a transformer self-attention module (T in the YOLOv5-TDHSA\u2019s name), and also adding a similar module to the last layer of its neck, so that the image information can be used more comprehensively, (2) replacing the YOLOv5s coupled head with a decoupled head (DH in both models\u2019 names) so as to increase the detection accuracy and speed up the convergence, and (3) adding a small-object detection layer (S in the YOLOv5-TDHSA\u2019s name) and an adaptive anchor (A in the YOLOv5-TDHSA\u2019s name) to the YOLOv5s neck to improve the detection of small objects. Based on experiments conducted on two public datasets, it is demonstrated that both proposed models perform better than the original YOLOv5s model and three other state-of-the-art models (Faster R-CNN, YOLOv4-Tiny, and YOLOv5n) in terms of the mean accuracy (mAP) and F1 score, achieving mAP values of 77.9% and 83.4% and F1 score values of 0.767 and 0.811 on the TT100K dataset, and mAP values of 68.1% and 69.8% and F1 score values of 0.71 and 0.72 on the CCTSDB2021 dataset, respectively, for YOLOv5-DH and YOLOv5-TDHSA. This was achieved, however, at the expense of both proposed models having a bigger size, greater number of parameters, and slower processing speed than YOLOv5s, YOLOv4-Tiny and YOLOv5n, surpassing only Faster R-CNN in this regard. The results also confirmed that the incorporation of the T and SA improvements into YOLOv5s leads to further enhancement, represented by the YOLOv5-TDHSA model, which is superior to the other proposed model, YOLOv5-DH, which avails of only one YOLOv5s improvement (i.e., DH).<\/jats:p>","DOI":"10.3390\/axioms12020160","type":"journal-article","created":{"date-parts":[[2023,2,6]],"date-time":"2023-02-06T02:06:43Z","timestamp":1675649203000},"page":"160","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":53,"title":["Two Novel Models for Traffic Sign Detection Based on YOLOv5s"],"prefix":"10.3390","volume":"12","author":[{"given":"Wei","family":"Bai","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyi","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxu","family":"Dai","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computing, Xi\u2019an Jiaotong-Liverpool University, Suzhou 215000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhao","sequence":"additional","affiliation":[{"name":"Research Institute of Information Technology, Tsinghua University, Beijing 100080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3527-3773","authenticated-orcid":false,"given":"Zhanlin","family":"Ji","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, North China University of Science and Technology, Tangshan 063210, China"},{"name":"Telecommunications Research Centre (TRC), University of Limerick, V94 T9PX Limerick, Ireland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0535-7087","authenticated-orcid":false,"given":"Ivan","family":"Ganchev","sequence":"additional","affiliation":[{"name":"Telecommunications Research Centre (TRC), University of Limerick, V94 T9PX Limerick, Ireland"},{"name":"Department of Computer Systems, University of Plovdiv \u201cPaisii Hilendarski\u201d, 4000 Plovdiv, Bulgaria"},{"name":"Institute of Mathematics and Informatics\u2014Bulgarian Academy of Sciences, 1040 Sofia, Bulgaria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2023,2,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/s13735-017-0129-8","article-title":"An overview of traffic sign detection and classification methods","volume":"6","author":"Saadna","year":"2017","journal-title":"Int. J. Multimed. Inf. Retr."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Y\u0131ld\u0131z, G., and Dizdaro\u011flu, B. (2019, January 6\u20137). Traffic Sign Detection via Color and Shape-Based Approach. Proceedings of 2019 1st International Informatics and Software Engineering Conference (UBMYK), Ankara, Turkey.","DOI":"10.1109\/UBMYK48245.2019.8965590"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Shen, X., Liu, J., Zhao, H., Liu, X., and Zhang, B. (2021, January 8\u201311). Research on Multi-Target Recognition Algorithm of Pipeline Magnetic Flux Leakage Signal Based on Improved Cascade RCNN. Proceedings of 2021 3rd International Conference on Industrial Artificial Intelligence (IAI), Shenyang, China.","DOI":"10.1109\/IAI53119.2021.9619400"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"110227","DOI":"10.1109\/ACCESS.2020.3001279","article-title":"Data-driven based tiny-YOLOv3 method for front vehicle detection inducing SPP-net","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"42183","DOI":"10.1007\/s11042-021-11446-2","article-title":"Object detection and recognition using contour based edge detection and fast R-CNN","volume":"81","author":"Rani","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","article-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","volume":"39","author":"Ren","year":"2017","journal-title":"IEEE Trans. Pat. Analys. Mach. Intell."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Fan, J., Huo, T., and Li, X. (2020, January 18\u201320). A Review of One-Stage Detection Algorithms in Autonomous Driving. Proceedings of 2020 4th CAA International Conference on Vehicular Control and Intelligence (CVCI), Hangzhou, China.","DOI":"10.1109\/CVCI51460.2020.9338663"},{"key":"ref_8","unstructured":"Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (1997, January 17\u201319). You Only Look Once: Unified, Real-Time Object Detection. Proceedings of Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Juan, PR, USA."},{"key":"ref_9","unstructured":"Redmon, J., and Farhadi, A. (1997, January 17\u201319). YOLO9000: Better, Faster, Stronger. Proceedings of Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Juan, PR, USA."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Lv, N., Xiao, J., and Qiao, Y. (2022). Object Detection Algorithm for Surface Defects Based on a Novel YOLOv3 Model. Processes, 10.","DOI":"10.3390\/pr10040701"},{"key":"ref_11","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). Yolov4: Optimal speed and accuracy of object detection. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"108213","DOI":"10.1016\/j.knosys.2022.108213","article-title":"Joint-attention feature fusion network and dual-adaptive NMS for object detection","volume":"241","author":"Ma","year":"2022","journal-title":"Knowl. Based Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","article-title":"A review on the attention mechanism of deep learning","volume":"452","author":"Niu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_14","unstructured":"Hu, J., Shen, L., and Sun, G. (1997, January 17\u201319). Squeeze-And-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Juan, PR, USA."},{"key":"ref_15","unstructured":"Woo, S., Park, J., Lee, J.-Y., and Kweon, I.S. (2020, January 23\u201328). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Liang, H., Zhou, H., Zhang, Q., and Wu, T. (2022). Object Detection Algorithm Based on Context Information and Self-Attention Mechanism. Symmetry, 14.","DOI":"10.3390\/sym14050904"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Lou, Y., Ye, X., Li, M., Li, H., Chen, X., Yang, X., and Liu, X. (2022, January 3\u20135). Object Detection Model of Cucumber Leaf Disease Based on Improved FPN. Proceedings of 2022 IEEE 6th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Beijing, China.","DOI":"10.1109\/IAEAC54830.2022.9929873"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., and Girshick, R. (2017, January 22\u201329). Mask R-Cnn. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., and Jia, J. (2018). Path Aggregation Network for Instance Segmentation. arXiv.","DOI":"10.1109\/CVPR.2018.00913"},{"key":"ref_20","first-page":"12993","article-title":"Distance-IoU loss: Faster and better learning for bounding box regression","volume":"34","author":"Zheng","year":"2020","journal-title":"Proc. Proc. AAAI Conf. Artif. Intell."},{"key":"ref_21","unstructured":"Zou, Z., Shi, Z., Guo, Y., and Ye, J. (2019). Object detection in 20 years: A survey. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"23729","DOI":"10.1007\/s11042-020-08976-6","article-title":"A review of object detection based on deep learning","volume":"79","author":"Xiao","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1007\/s11042-022-13300-5","article-title":"Automatic logo detection from document image using HOG features","volume":"82","author":"Dixit","year":"2022","journal-title":"Multimed. Tools Appl."},{"key":"ref_24","first-page":"8146","article-title":"DPM: A novel training method for physics-informed neural networks in extrapolation","volume":"35","author":"Kim","year":"2021","journal-title":"Proc. Proc. AAAI Conf. Artif. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"253","DOI":"10.31577\/cai_2022_1_253","article-title":"Brain Tumor Detection Using Selective Search and Pulse-Coupled Neural Network Feature Extraction","volume":"41","author":"Niepceron","year":"2022","journal-title":"Comput. Inform."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"012033","DOI":"10.1088\/1742-6596\/1544\/1\/012033","article-title":"Overview of Two-Stage Object Detection Algorithms","volume":"1544","author":"Du","year":"2020","journal-title":"Proc. J. Phys. Conf. Ser."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1016\/j.procs.2022.01.135","article-title":"A Review of Yolo algorithm developments","volume":"199","author":"Jiang","year":"2022","journal-title":"Procedia Comput. Sci."},{"key":"ref_29","unstructured":"Bouabid, S., and Delaitre, V. (2020). Mixup regularization for region proposal based object detectors. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, J., Dong, Z., Yang, Y., Luo, Q., and Gao, M. (2022, January 1\u20133). An Attention based YOLOv5 Network for Small Traffic Sign Recognition. Proceedings of 2022 IEEE 31st International Symposium on Industrial Electronics (ISIE), Anchorage, AK, USA.","DOI":"10.1109\/ISIE51582.2022.9831717"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Liu, X., Jiang, X., Hu, H., Ding, R., Li, H., and Da, C. (2021, January 14\u201317). Traffic Sign Recognition Algorithm Based on Improved YOLOv5s. Proceedings of 2021 International Conference on Control, Automation and Information Sciences (ICCAIS), Xi\u2019an, China.","DOI":"10.1109\/ICCAIS52680.2021.9624657"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, X. (2022, January 12\u201314). Traffic Lights Detection Method Based on the Improved YOLOv5 Network. Proceedings of 2022 IEEE 4th International Conference on Civil Aviation Safety and Information Technology (ICCASIT), Dali, China.","DOI":"10.1109\/ICCASIT55263.2022.9986726"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"111655","DOI":"10.1016\/j.measurement.2022.111655","article-title":"Fast vehicle detection algorithm in traffic scene based on improved SSD","volume":"201","author":"Chen","year":"2022","journal-title":"Measurement"},{"key":"ref_34","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA."},{"key":"ref_35","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1007\/BF02553326","article-title":"Review of sigmoid volvulus","volume":"25","author":"Ballantyne","year":"1982","journal-title":"Dis. Colon Rectum"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, Y., Gao, M., and Dong, Z. (2021). Improved YOLOv5 network for real-time multi-scale traffic sign detection. arXiv.","DOI":"10.1007\/s00521-022-08077-5"},{"key":"ref_38","unstructured":"Zhu, Z., Liang, D., Zhang, S., Huang, X., Li, B., and Hu, S. (1997, January 17\u201319). Traffic-Sign Detection and Classification in the Wild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Juan, PR, USA."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"2233","DOI":"10.1007\/s00521-021-06526-1","article-title":"A real-time and high-precision method for small traffic-signs recognition","volume":"34","author":"Chen","year":"2022","journal-title":"Neural Comput. Appl."},{"key":"ref_40","first-page":"23","article-title":"CCTSDB 2021: A more comprehensive traffic sign detection benchmark","volume":"12","author":"Zhang","year":"2022","journal-title":"Hum. Cent. Comput. Inf. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, M., Jin, X., and Li, X. (2017). A real-time Chinese traffic sign detection algorithm based on modified YOLOv2. Algorithms, 10.","DOI":"10.3390\/a10040127"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"15095","DOI":"10.1007\/s11042-018-6562-8","article-title":"Spatial and semantic convolutional features for robust visual object tracking","volume":"79","author":"Zhang","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1080\/01621459.1937.10503522","article-title":"The use of ranks to avoid the assumption of normality implicit in the analysis of variance","volume":"32","author":"Friedman","year":"1937","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1214\/aoms\/1177731944","article-title":"A comparison of alternative tests of significance for the problem of m rankings","volume":"11","author":"Friedman","year":"1940","journal-title":"Ann. Math. Stat."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1080\/01621459.1961.10482090","article-title":"Multiple Comparisons among Means","volume":"56","author":"Dunn","year":"1961","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1491","DOI":"10.1109\/TFUZZ.2017.2735947","article-title":"Streaming feature selection for multilabel learning based on fuzzy mutual information","volume":"25","author":"Lin","year":"2017","journal-title":"IEEE Trans. Fuzzy Syst."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1080\/03610928008827904","article-title":"Approximations of the critical region of the fbietkan statistic","volume":"9","author":"Iman","year":"1980","journal-title":"Commun. Stat. Theory Methods"},{"key":"ref_48","first-page":"1","article-title":"Statistical Comparisons of Classifiers over Multiple Data Sets","volume":"7","year":"2006","journal-title":"J. Mach. Learn. Res."}],"container-title":["Axioms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1680\/12\/2\/160\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T18:23:42Z","timestamp":1760120622000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1680\/12\/2\/160"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,3]]},"references-count":48,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["axioms12020160"],"URL":"https:\/\/doi.org\/10.3390\/axioms12020160","relation":{},"ISSN":["2075-1680"],"issn-type":[{"value":"2075-1680","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,3]]}}}