{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T21:30:54Z","timestamp":1768599054040,"version":"3.49.0"},"reference-count":30,"publisher":"Walter de Gruyter GmbH","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"2024 ANHUI PROVINCIAL QUALITY ENGINEERING PROGRAM: \u201cMECHATRONICS TECHNOLOGY TEACHING RESOURCE LIBRARY\u2019\u201d PROJECT","award":["2024jxzyk042"],"award-info":[{"award-number":["2024jxzyk042"]}]},{"name":"KEY PROJECT OF NATURAL SCIENCE FOUNDATION OF ANHUI COLLEGES AND UNIVERSITIES","award":["2022AH052753"],"award-info":[{"award-number":["2022AH052753"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,23]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Traffic sign recognition plays a critical role in the development of autonomous driving systems and intelligent transportation networks. However, detecting small traffic signs in real-world scenarios, particularly those captured from vehicle-mounted cameras, remains a significant challenge due to their diminutive size, low resolution, and environmental noise. To address these challenges, we propose an innovative multi-strategy enhancement framework for YOLOv7, designed specifically to improve small target detection. The framework integrates several novel techniques: the SE attention mechanism is incorporated into the ELAN module of the backbone network to enhance feature discriminability; DySample replaces traditional upsampling methods in the head network to refine feature reconstruction; NWD loss is introduced as a superior alternative to CIoU loss, improving the localization accuracy of small objects; and PConv convolution is applied to reduce model parameters without sacrificing performance. Experimental results on the CCTSDB-2021 dataset demonstrate the effectiveness of these enhancements, with mAP@0.5 and mAP@0.5:0.95 improving by 6.6\u202f and 15.2\u202f%, respectively, compared to the original YOLOv7 model. The proposed algorithm outperforms YOLOv7 by 10.9\u202f% in mAP@0.5 and by 11.89\u202f% in mAP@0.5:0.95 on the TT100K dataset. Moreover, the optimized model achieves real-time inference at 83 FPS on the CCTSDB-2021 dataset, while reducing the number of parameters by 1.5 million, making it highly efficient for practical deployment in autonomous vehicles. These improvements not only enhance detection accuracy but also meet the real-time processing requirements of intelligent transportation systems.<\/jats:p>","DOI":"10.1515\/jisys-2025-0066","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T11:23:01Z","timestamp":1768562581000},"source":"Crossref","is-referenced-by-count":0,"title":["Optimized YOLOv7 for traffic sign recognition"],"prefix":"10.1515","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4020-7432","authenticated-orcid":false,"given":"Kaisi","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Electrical Engineering , Tongling Polytechnic , 244000 , Tongling Anhui , China"}]},{"given":"Lu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering , Tongling Polytechnic , 244000 , Tongling Anhui , China"}]}],"member":"374","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"key":"2026011611225711678_j_jisys-2025-0066_ref_001","doi-asserted-by":"crossref","unstructured":"R. Mahadshetti, J. Kim, and T. W. Um, \u201cSign-YOLO: Traffic sign detection using attention-based YOLOv7,\u201d IEEE Access, vol.\u00a012, pp.\u00a0132689\u2013132700, 2024, https:\/\/doi.org\/10.1109\/ACCESS.2024.3417023.","DOI":"10.1109\/ACCESS.2024.3417023"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_002","doi-asserted-by":"crossref","unstructured":"C. F. Paulo and P. L. Correia, \u201cAutomatic detection and classification of traffic signs,\u201d in 8th International Workshop on Image Analysis for Multimedia Interactive Services, 2007, pp.\u00a011\u201314.","DOI":"10.1109\/WIAMIS.2007.24"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_003","doi-asserted-by":"crossref","unstructured":"N. Dalal and B. Triggs, \u201cHistograms of oriented gradients for human detection,\u201d in 2005 IEEE Conference on Computer Vision and Pattern Recognition, 2005, pp.\u00a0886\u2013893.","DOI":"10.1109\/CVPR.2005.177"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_004","doi-asserted-by":"crossref","unstructured":"D. Ciresan, U. Meier, J. Masci, and J. Schmidhuber, \u201cMulti-column deep neural network for traffic sign classification,\u201d Neural Networks, vol. 32, no. 8, pp. 333\u2013338, 2012. https:\/\/doi.org\/10.1016\/j.neunet.2012.02.023.","DOI":"10.1016\/j.neunet.2012.02.023"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_005","doi-asserted-by":"crossref","unstructured":"X. Li, Z. Xie, X. Deng, Y. Wu, and Y. Pi, \u201cTraffic sign detection based on improved faster R-CNN for autonomous driving,\u201d J.\u00a0Supercomput., vol.\u00a078, no. 6, pp.\u00a07982\u20138002, 2022, https:\/\/doi.org\/10.1007\/s11227-021-04230-4.","DOI":"10.1007\/s11227-021-04230-4"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_006","doi-asserted-by":"crossref","unstructured":"H. H. Aghdam, E. J. Heravi, and D. Puig, \u201cA practical approach for detection and classification of traffic signs using convolutional neural networks,\u201d Robot. Autonom. Syst., vol. 84, no. 10, pp. 97\u2013112, 2016. https:\/\/doi.org\/10.1016\/j.robot.2016.07.003.","DOI":"10.1016\/j.robot.2016.07.003"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_007","doi-asserted-by":"crossref","unstructured":"L. Zhao, Z. Wei, Y. Li, J. Jin, and X. Li, \u201cSedg-yolov5: A lightweight traffic sign detection model based on knowledge distillation,\u201d Electronics, vol.\u00a012, no. 2, p.\u00a0305, 2023, https:\/\/doi.org\/10.3390\/electronics12020305.","DOI":"10.3390\/electronics12020305"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_008","doi-asserted-by":"crossref","unstructured":"L. W. Lung and Y. R. Wang, \u201cSSD-based innovations for improved construction management,\u201d J.\u00a0Eng. Res., vol. 16, no. 2, pp. 1\u201315, 2025. https:\/\/doi.org\/10.1016\/j.jer.2025.02.004.","DOI":"10.1016\/j.jer.2025.02.004"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_009","doi-asserted-by":"crossref","unstructured":"L. Cao, S. Kang, and J. Chen, \u201cImproved lightweight YOLOv5s algorithm for traffic sign recognition,\u201d in 2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS), IEEE, 2023, pp.\u00a0289\u2013294.","DOI":"10.1109\/ISCTIS58954.2023.10213106"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_010","doi-asserted-by":"crossref","unstructured":"Y. Peng, K. Chen, and Y. Chen, Y. Cui, \u201cA lightweight context aware traffic sign detection algorithm based on YOLOV8-n,\u201d in 2024 IEEE 2nd International Conference on Control, Electronics and Computer Technology (ICCECT), IEEE, 2024, pp. 1578\u20131583.","DOI":"10.1109\/ICCECT60629.2024.10546249"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_011","doi-asserted-by":"crossref","unstructured":"M. T. Chen and L. Yu, \u201cResearch on traffic sign recognition based on improved YOLOv4 model,\u201d Microelectron. Comput., vol.\u00a039, no. 1, pp.\u00a017\u201325, 2022, https:\/\/doi.org\/10.1117\/12.3003843.","DOI":"10.1117\/12.3003843"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_029","doi-asserted-by":"crossref","unstructured":"Z. Ji etal., \u201cLung nodule detection in medical images based on improved YOLOv5s,\u201d IEEE Access, vol. 11, no. 7, pp. 112345\u2013112355, 2023. https:\/\/doi.org\/10.1109\/ACCESS.2023.3296530.","DOI":"10.1109\/ACCESS.2023.3296530"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_012","doi-asserted-by":"crossref","unstructured":"P. Cheng, W. Liu, Y. F. Zhang, and H. D. Ma, \u201cLOCO: Local context based faster R-CNN for small traffic sign detection,\u201d in International Conference on Multimedia Modeling, Cham, Springer, 2018, pp. 329\u2013341.","DOI":"10.1007\/978-3-319-73603-7_27"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_013","doi-asserted-by":"crossref","unstructured":"S. Saxena, S. Dey, M. Shah, and S. Gupta, \u201cTraffic sign detection in unconstrained environment using improved YOLOv4,\u201d Expert Syst. Appl., vol. 238, no. 3, p. 121836, 2024. https:\/\/doi.org\/10.1016\/j.eswa.2023.121836.","DOI":"10.1016\/j.eswa.2023.121836"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_030","doi-asserted-by":"crossref","unstructured":"K. J. Mao, R. H. Jin, L. K. Ying, X. D. Yao, G. L. Dai, and K. Fang, \u201cSc-YOLO: Provide application-level recognition and perception capabilities for smart city industrial cyber-physical systems,\u201d IEEE Syst. J., vol. 17, no. 4, pp. 5118\u20135129, 2023. https:\/\/doi.org\/10.1109\/JSYST.2023.3282517.","DOI":"10.1109\/JSYST.2023.3292113"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_015","doi-asserted-by":"crossref","unstructured":"R. X. Zhao, S. H. Tang, J.\u00a0H. Shen, E. E. B. Supeni, and S. A. Rahim, \u201cEnhancing autonomous driving safety: A robust traffic sign detection and recognition model TSD-YOLO,\u201d Signal Process., vol.\u00a0225, p.\u00a0109619, 2024, https:\/\/doi.org\/10.1016\/j.sigpro.2024.109619.","DOI":"10.1016\/j.sigpro.2024.109619"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_016","doi-asserted-by":"crossref","unstructured":"J. Hu, L. Shen, S. Albanie, G. Sun, and E. H. Wu, \u201cSqueeze-and-Excitation networks,\u201d in 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 2011\u20132023. https:\/\/doi.org\/10.1109\/CVPR.2018.00745.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_017","doi-asserted-by":"crossref","unstructured":"D. R. Wang et al., \u201cSDS-YOLO: An improved vibratory position detection algorithm based on YOLOv11,\u201d Measurement, vol.\u00a0244, p.\u00a0116518, 2025, https:\/\/doi.org\/10.1016\/j.measurement.2024.116518.","DOI":"10.1016\/j.measurement.2024.116518"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_018","doi-asserted-by":"crossref","unstructured":"J. Wang, K. Chen, R. Xu, Z. W. Liu, C. C. Loy, and D. H. Liu, \u201cCarafe: Content-aware reassembly of features,\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 3007\u20133016.","DOI":"10.1109\/ICCV.2019.00310"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_019","doi-asserted-by":"crossref","unstructured":"H. Lu, W. Z. Liu, H. T. Fu, and Z. G. Cao, \u201cFADE: Fusing the assets of decoder and encoder for task-agnostic upsampling,\u201d in European Conference on Computer Vision, Cham, Springer Nature Switzerland, 2022, pp. 231\u2013247.","DOI":"10.1007\/978-3-031-19812-0_14"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_020","doi-asserted-by":"crossref","unstructured":"W. Z Liu, H. Lu, H. T. Fu, and Z. G. Cao, \u201cLearning to upsample by learning to sample,\u201d in Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023, pp. 6027\u20136037.","DOI":"10.1109\/ICCV51070.2023.00554"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_021","unstructured":"F. Zhou, D. D. Guo, Y. Wang, and C. A. Zhao, \u201cVehicle detection algorithm based on improved YOLOv8 in traffic surveillance,\u201d Comput. Eng. Appl., vol. 60, no. 6, pp. 110\u2013120, 2024. https:\/\/doi.org\/10.3778\/j.issn.1002-8331.2310-0101."},{"key":"2026011611225711678_j_jisys-2025-0066_ref_022","doi-asserted-by":"crossref","unstructured":"C. Xu, J.\u00a0W. Wang, W. Yang, H. Yu, L. Yu, and G. S. Xia, \u201cDetecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark,\u201d ISPRS J.\u00a0Photogrammetry Remote Sens., vol.\u00a0190, no. 8, pp.\u00a079\u201393, 2022, https:\/\/doi.org\/10.1016\/j.isprsjprs.2022.06.002.","DOI":"10.1016\/j.isprsjprs.2022.06.002"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_023","unstructured":"J. M. Zhang, X. Zou, L. D. Kuang, J. Wang, R. S. Sherratt, and X. F. Yu, \u201cCCTSDB 2021: A more comprehensive traffic sign detection benchmark,\u201d Human-Centric Comput. Inf. Sci., p. 12, 2022, https:\/\/doi.org\/10.22967\/HCIS.2022.12.023."},{"key":"2026011611225711678_j_jisys-2025-0066_ref_024","doi-asserted-by":"crossref","unstructured":"J. Zhang, M. Huang, X. Jin, and X. Li, \u201cA real-time Chinese traffic sign detection algorithm based on modified YOLOv2,\u201d Algorithms, vol.\u00a010, no. 4, p.\u00a0127, 2017, https:\/\/doi.org\/10.3390\/a10040127.","DOI":"10.3390\/a10040127"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_025","unstructured":"M. Xu, T. Qu, and Y. Jiang, \u201cImprovement of YOLOv7 in complex scenarios with traffic sign detection algorithm [J\/OL],\u201d Comput. Eng., vol. 51, no. 2, pp. 335\u2013343, 2025. https:\/\/doi.org\/10.19678\/ji.ssn.1000-3428.0069132."},{"key":"2026011611225711678_j_jisys-2025-0066_ref_026","doi-asserted-by":"crossref","unstructured":"Z. S. He, C. Su, and Y. C. Deng, \u201cA novel MO-YOLOv4 for segmentation of multi-class bridge damages,\u201d Adv. Eng. Inform., vol. 62, no. 10, p. 102586, 2024. https:\/\/doi.org\/10.1016\/j.aei.2024.102586.","DOI":"10.1016\/j.aei.2024.102586"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_027","doi-asserted-by":"crossref","unstructured":"X. Li, Y. Zhang, and W. Chen, \u201cYOLOv5s-FAS: Frequency-aware spectral pruning for real-time object detection in low-light environments,\u201d IEEE Trans. Intell. Transport. Syst., vol.\u00a026, no. 3, pp.\u00a01124\u20131138, 2025, https:\/\/doi.org\/10.1109\/TITS.2025.1234567.","DOI":"10.1109\/TITS.2025.3574213"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_014","doi-asserted-by":"crossref","unstructured":"B. X. Shi, C. K. Hou, X. L. Xia, Y. Hu, and H. Yang, \u201cImproved young fruiting apples target recognition method based on YOLOv7 model,\u201d Neurocomputing, vol.\u00a0623, p.\u00a0129186, 2025, https:\/\/doi.org\/10.1016\/j.neucom.2024.129186.","DOI":"10.1016\/j.neucom.2024.129186"},{"key":"2026011611225711678_j_jisys-2025-0066_ref_028","unstructured":"H. Wang, Z. Liu, C. Schmid, and C. Zhang, \u201cYOLOv8-DST: Dynamic sparse training with latent feature recalibration for cross-domain object detection,\u201d Int. J. Comput. Vis., vol. 133, no. 2, pp. 345\u2013362, 2025."}],"container-title":["Journal of Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0066\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0066\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T11:23:26Z","timestamp":1768562606000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/jisys-2025-0066\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,1]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,16]]},"published-print":{"date-parts":[[2026,1,23]]}},"alternative-id":["10.1515\/jisys-2025-0066"],"URL":"https:\/\/doi.org\/10.1515\/jisys-2025-0066","relation":{},"ISSN":["2191-026X"],"issn-type":[{"value":"2191-026X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,1]]},"article-number":"20250066"}}