{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,19]],"date-time":"2026-11-19T00:27:35Z","timestamp":1795048055235,"version":"4.10.2"},"reference-count":22,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2021,12,28]],"date-time":"2021-12-28T00:00:00Z","timestamp":1640649600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>For facing of the problems caused by the YOLOv4 algorithm\u2019s insensitivity to small objects and low detection precision in traffic light detection and recognition, the Improved YOLOv4 algorithm is investigated in the paper using the shallow feature enhancement mechanism and the bounding box uncertainty prediction mechanism. The shallow feature enhancement mechanism is used to extract features from the network and improve the network\u2019s ability to locate small objects and color resolution by merging two shallow features at different stages with the high-level semantic features obtained after two rounds of upsampling. Uncertainty is introduced in the bounding box prediction mechanism to improve the reliability of the prediction of the bounding box by modeling the output coordinates of the prediction bounding box and adding the Gaussian model to calculate the uncertainty of the coordinate information. The LISA traffic light data set is used to perform detection and recognition experiments separately. The Improved YOLOv4 algorithm is shown to have a high effectiveness in enhancing the detection and recognition precision of traffic lights. In the detection experiment, the area under the PR curve value of the Improved YOLOv4 algorithm is found to be 97.58%, which represents an increase of 7.09% in comparison to the 90.49% score gained in the Vision for Intelligent Vehicles and Applications Challenge Competition. In the recognition experiment, the mean average precision of the Improved YOLOv4 algorithm is 82.15%, which is 2.86% higher than that of the original YOLOv4 algorithm. The Improved YOLOv4 algorithm shows remarkable advantages as a robust and practical method for use in the real-time detection and recognition of traffic signal lights.<\/jats:p>","DOI":"10.3390\/s22010200","type":"journal-article","created":{"date-parts":[[2021,12,29]],"date-time":"2021-12-29T02:31:27Z","timestamp":1640745087000},"page":"200","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":66,"title":["Traffic Lights Detection and Recognition Method Based on the Improved YOLOv4 Algorithm"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8565-8690","authenticated-orcid":false,"given":"Qingyan","family":"Wang","sequence":"first","affiliation":[{"name":"School of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xintao","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujing","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changyue","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Measurement-Control and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vladimir Ivanovich","family":"Mikulovich","sequence":"additional","affiliation":[{"name":"School of Radio Physics and Electronics, Belarusian State University, 220030 Minsk, Belarus"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,12,28]]},"reference":[{"key":"ref_1","first-page":"996","article-title":"Pedestrian tracking and detection combined algorithm based on multi-granularity features","volume":"57","author":"Wang","year":"2020","journal-title":"Comput. Res. Dev."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Xiang, N., Cao, Z., Wang, Y., and Jia, Q. (2021, January 7\u201310). A Real-Time Vehicle Traffic Light Detection Algorithm Based on Modified YOLOv3. Proceedings of the 2021 IEEE 4th International Conference on Electronics Technology, Chengdu, China.","DOI":"10.1109\/ICET51757.2021.9451081"},{"key":"ref_3","first-page":"143","article-title":"Traffic Light Detection Based on YOLOv3 Optimization Algorithm","volume":"40","author":"Sun","year":"2020","journal-title":"Acta Opt. Sin."},{"key":"ref_4","first-page":"163","article-title":"Accurate Recognition and State Estimation of Traffic Lights in Urban Environment","volume":"29","author":"Cai","year":"2014","journal-title":"Control. Decis."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Philipsen, M.P., Jensen, M.B., M\u00f8gelmose, A., Moeslund, T.B., and Trivedi, M.M. (2015, January 15\u201318). Traffic Light Detection: A Learning Algorithm and Evaluations on Challenging Dataset. Proceedings of the 2015 IEEE 18th International Conference on Intelligent Transportation Systems, Gran Canaria, Spain.","DOI":"10.1109\/ITSC.2015.378"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Du, X.-P., Li, Y., Guo, Y., and Xiong, H. (2017, January 21\u201323). Vision-Based Traffic Light Detection for Intelligent Vehicles. Proceedings of the 2017 4th International Conference on Information Science and Control Engineering, Changsha, China.","DOI":"10.1109\/ICISCE.2017.275"},{"key":"ref_7","first-page":"314","article-title":"Real-time Detection and Recognition of Traffic Signal Lights Based on Time-space Relationship Model","volume":"45","author":"Li","year":"2018","journal-title":"Comput. Sci."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Behrendt, K., Novak, L., and Botros, R. (June, January 29). A Deep Learning Approach to Traffic Lights: Detection, Tracking, and Classification. Proceedings of the 2017 IEEE International Conference on Robotics and Automation, Singapore.","DOI":"10.1109\/ICRA.2017.7989163"},{"key":"ref_9","first-page":"147","article-title":"Detection and Recognition of Traffic Lights Based on Faster R-CNN","volume":"38","author":"Pan","year":"2019","journal-title":"Transducer Microsyst. Technol."},{"key":"ref_10","unstructured":"Morten, B.J., Kamal, N., and Thomas, B. (2017, January 21\u201326). Evaluating State-of-the-art Object Detector on Challenging Traffic Light Data. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Muller, J., and Dietmayer, K. (2018, January 4\u20137). Detecting Traffic Lights by Single Shot Detection. Proceedings of the 21st IEEE International Conference on Intelligent Transportation Systems, Maui, HI, USA.","DOI":"10.1109\/ITSC.2018.8569683"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Possatti, L.C., Guidolini, R., Cardoso, V.B., Berriel, R.F., Paix\u00e3o, T.M., Badue, C., de Souza, A.F., and Oliveira-Santos, T. (2019, January 14\u201319). Traffic Light Recognition Using Deep Learning and Prior Maps for Autonomous Cars. Proceedings of the 2019 International Joint Conference on Neural Networks, Budapest, Hungary.","DOI":"10.1109\/IJCNN.2019.8851927"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Du, L., Chen, W., Fu, S., Kong, H., Li, C., and Pei, Z. (2019, January 14\u201317). Real-time Detection of Vehicle and Traffic Light for Intelligent and Connected Vehicles Based on YOLOv3 Network. Proceedings of the 2019 5th International Conference on Transportation Information and Safety, Liverpool, UK.","DOI":"10.1109\/ICTIS.2019.8883761"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"124963","DOI":"10.1109\/ACCESS.2021.3109798","article-title":"An Improved Light-Weight Traffic Sign Recognition Algorithm Based on YOLOv4-Tiny","volume":"9","author":"Wang","year":"2021","journal-title":"IEEE Access"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Peng, J., Xu, M., and Yan, Y. (2021, January 27\u201329). Automatic Recognition of Pointer Meter Reading Based on Yolov4 and Improved U-net Algorithm. Proceedings of the 2021 IEEE International Conference on Electronic Technology, Communication and Information (ICETCI), Changchun, China.","DOI":"10.1109\/ICETCI53161.2021.9563496"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"15501477211018374","DOI":"10.1177\/15501477211018374","article-title":"An improved traffic lights recognition algorithm for autonomous driving in complex scenarios","volume":"17","author":"Li","year":"2021","journal-title":"Int. J. Distrib. Sens. Netw."},{"key":"ref_17","first-page":"373","article-title":"Improved SSD Algorithm and Analysis of Small Target Detection Performance in Remote Sensing Images","volume":"39","author":"Wang","year":"2019","journal-title":"Acta Opt. Sin."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Liao, M.H.-Y., Yeh, I.H., Wu, Y.-H., Chen, P.-Y., and Hsieh, J.-W. (2020, January 14\u201319). CSPNet: A New Backbone that can Enhance Learning Capability of CNN. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, Washington State Convention Center, Seattle, WA, USA.","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"He, Y., Zhu, C., Wang, J., Savvides, M., and Zhang, X. (2019, January 15\u201320). Bounding Box Regression with Uncertainty for Accurate Object Detection. Proceedings of the 2019 IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00300"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Akshayaa, S., and Nithin, S. (2021, January 4\u20136). Comparative study of pedestrian detection techniques for driver assistance system. Proceedings of the 2021 Second International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India.","DOI":"10.1109\/ICESC51422.2021.9532716"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1800","DOI":"10.1109\/TITS.2015.2509509","article-title":"Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives","volume":"17","author":"Morten","year":"2016","journal-title":"Trans. Intell. Transp. Syst."},{"key":"ref_22","unstructured":"Loshchilov, I., and Hutter, F. (2016). SGDR: Stochastic Gradient Descent with Warm Restarts. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/1\/200\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T07:55:03Z","timestamp":1760169303000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/1\/200"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,28]]},"references-count":22,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,1]]}},"alternative-id":["s22010200"],"URL":"https:\/\/doi.org\/10.3390\/s22010200","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,28]]}}}