{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:16:19Z","timestamp":1777706179691,"version":"3.51.4"},"reference-count":30,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"the National Social Science Fund","award":["24BTJ068"],"award-info":[{"award-number":["24BTJ068"]}]},{"name":"Humanities and Social Science Fund of Hubei Provincial Department of Edu-cation","award":["22Y059"],"award-info":[{"award-number":["22Y059"]}]},{"name":"Key Humanities and Social Science Fund of Hubei Provincial Department of Education","award":["20D043"],"award-info":[{"award-number":["20D043"]}]},{"name":"Hubei Innovation Training Program","award":["S202210500136"],"award-info":[{"award-number":["S202210500136"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:p>As intelligent transportation systems increasingly rely on vehicle detection algorithms, their actual deployment faces significant challenges. The high computational complexity of deep learning models conflicts with resource-constrained edge devices and their real-time requirements. The detection system must maintain a stable frame rate under low-latency conditions in high-traffic environments to ensure timely traffic monitoring and decision-making, as well as adaptability to complex environments. Poor weather, changes in lighting, and intricate backgrounds can affect detection accuracy, leading to false or missed detections. Consequently, this study proposes a hardware-oriented lightweight vehicle detection framework that optimizes computational efficiency while ensuring detection accuracy. First, MobileNetV3 reconstructs the YOLO backbone feature extraction network to reduce the computational redundancy. Second, conventional convolutions are replaced with depthwise separable convolutions to decouple spatial and channel feature learning. Third, the original C3 module (a cross-stage partial bottleneck structure with three convolutional layers) is reconfigured using redesigned GhostBottleneck blocks (lightweight residual blocks that stack Ghost Modules\u2014where the first expands channels via depthwise separable convolution and the second compresses channels while retaining shortcut connections). In addition, the introduction of a novel dual-stream attention mechanism enhances prediction accuracy while maintaining detection performance. A paired-sample t-test was used to evaluate the effectiveness of the proposed algorithm. The results demonstrate that the P-values for all three key performance metrics \u2014precision, recall, and mAP@0.5 \u2014 are significantly lower than 0.05, confirming that MDE-YOLO achieves statistically significant improvements over YOLOv5s in these metrics. Compared with YOLOv5, the proposed method reduces the number of parameters, computational complexity, and model weight by 69.9%, 77.5%, and 67.8%, respectively, while maintaining an average recognition rate reduction of only 0.5%. The slight decrease in accuracy can be considered an acceptable trade-off, providing a methodological framework for overcoming the \u201caccuracy-resource\u201d dilemma in traffic perception systems.<\/jats:p>","DOI":"10.1177\/18758967251348957","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T03:17:21Z","timestamp":1749611841000},"page":"1452-1472","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Real-Time Vehicle Detection with a Lightweight Model"],"prefix":"10.1177","volume":"49","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4693-6064","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"first","affiliation":[{"name":"School of Science, Hubei University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-9663","authenticated-orcid":false,"given":"Youxi","family":"Luo","sequence":"additional","affiliation":[{"name":"School of Science, Hubei University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7388-5020","authenticated-orcid":false,"given":"Hanfang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Science, Hubei University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,6,11]]},"reference":[{"key":"e_1_3_3_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(99)00125-6"},{"key":"e_1_3_3_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-53181-2"},{"key":"e_1_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-022-06193-w"},{"key":"e_1_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_3_6_1","first-page":"580","volume-title":"2014 IEEE Conference on Computer Vision and Pattern Recognition","author":"Girshick R.","unstructured":"Girshick R., Donahue J., Darrell T, Malik J\u00a0(2014). Rich feature hierarchies for accurate object detection and semantic segmentation. In 2014 IEEE Conference on Computer Vision and Pattern Recognition (pp. 580\u2013587). Columbus, OH, USA: IEEE."},{"issue":"4","key":"e_1_3_3_7_1","first-page":"3","article-title":"Deep compression: Compressing deep neural networks with pruning","volume":"56","author":"Han S.","year":"2015","unstructured":"Han S., Huizi M., Dally W.J. (2015). Deep compression: Compressing deep neural networks with pruning. Trained Quantization and Huffman Coding Fiber, 56(4), 3\u20137. https:\/\/doi.org\/10.48550\/arXiv.1510.00149\u00a0","journal-title":"Trained Quantization and Huffman Coding Fiber"},{"key":"e_1_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"e_1_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_3_11_1","unstructured":"Howard A. G. Zhu M. Chen B. (2017). Mobilenets: Efficient convolutional neural networks for mobile vision applications."},{"key":"e_1_3_3_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/s24082394"},{"key":"e_1_3_3_14_1","article-title":"Squeezenet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size","volume":"1602","author":"Iandola F. N.","year":"2016","unstructured":"Iandola F. N., Han S., Moskewicz M. W., Ashraf K., Dally W.J., Keutzer K. (2016). Squeezenet: AlexNet-level accuracy with 50x fewer parameters and <1MB model size. ArXiv, abs\/1602.07360. https:\/\/doi.org\/10.48550\/arXiv.1602.07360","journal-title":"ArXiv"},{"key":"e_1_3_3_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2022.01.135"},{"key":"e_1_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3410231"},{"key":"e_1_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13169316"},{"key":"e_1_3_3_18_1","first-page":"136","article-title":"Filter elastic deep neural network channel pruning compression method","volume":"32","author":"Li R. Q.","year":"2022","unstructured":"Li R. Q., Zhu L., Liu Y. Y. (2022). Filter elastic deep neural network channel pruning compression method. Computer Engineering and Applications, 32, 136\u2013141.","journal-title":"Computer Engineering and Applications"},{"key":"e_1_3_3_19_1","doi-asserted-by":"crossref","unstructured":"Liu W. Anguelov D. Erhan D. Szegedy C. Reed S. Fu C.-Y. Berg A. C. (2016). SSD: Single Shot MultiBox Detector. In B. Leibe J. Matas N. Sebe & M. Welling (Eds.) Computer Vision \u2013 ECCV 2016 (pp. 21\u201337). Springer International Publishing. https:\/\/doi.org\/10.1007\/978-3-319-46448-0_2","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_3_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3368848"},{"key":"e_1_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_3_3_22_1","first-page":"10242","volume-title":"Advances in Neural Information Processing Systems 32","author":"Snyder C.","year":"2019","unstructured":"Snyder C., Do M. N. (2019). Advances in Neural Information Processing Systems 32 (NeurIPS Vol. 32, pp. 10242\u201310253). Curran Associates."},{"key":"e_1_3_3_23_1","first-page":"1","volume-title":"YOLOv8: A novel object detection algorithm with enhanced performance and robustness2024 Int Conf Adv Data Eng Intell Comput Syst (ADICS)","author":"Varghese R.","year":"2024","unstructured":"Varghese R., Sambath M. (2024). YOLOv8: A novel object detection algorithm with enhanced performance and robustness. 2024 Int Conf Adv Data Eng Intell Comput Syst (ADICS) (pp. 1\u20136), Chennai, India."},{"issue":"1","key":"e_1_3_3_24_1","first-page":"2590","article-title":"Lightweight object detection in low light: Pixel-wise depth refinement and TensorRT optimization","volume":"23","author":"Vinoth K.","year":"2024","unstructured":"Vinoth K., Sasikumar P. (2024). Lightweight object detection in low light: Pixel-wise depth refinement and TensorRT optimization. Results in Engineering, 23(1), 2590\u20131230. https:\/\/doi.org\/10.1016\/j.rineng.2024.102510","journal-title":"Results in Engineering"},{"key":"e_1_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/s24041182"},{"key":"e_1_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102907"},{"key":"e_1_3_3_27_1","doi-asserted-by":"crossref","unstructured":"Woo S. Park J. Lee J-Y. Kweon I. (2018). CBAM: Convolutional block attention module. arXiv:1807.06521.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_3_3_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21030880"},{"issue":"5","key":"e_1_3_3_29_1","first-page":"801","article-title":"Layer pruning via fusible residual convolutional block for deep neural networks","volume":"58","author":"Xu P. T.","year":"2022","unstructured":"Xu P. T., Cao J., Fanhua S., Wenyu S., Pu L. (2022). Layer pruning via fusible residual convolutional block for deep neural networks . Journal of Peking University (Natural Science Edition), 58(5), 801\u2013807. https:\/\/doi.org\/10.48550\/arXiv.2011.14356","journal-title":"Journal of Peking University (Natural Science Edition)"},{"issue":"12","key":"e_1_3_3_30_1","first-page":"136","article-title":"Neural network pruning algorithm based on filter distribution fitting","volume":"32","author":"Zhang J. Y.","year":"2022","unstructured":"Zhang J. Y., Kou J. Q., Liu N. Z. (2022). Neural network pruning algorithm based on filter distribution fitting. Computer Technology Development, 32(12), 136\u2013141. \u00a0https:\/\/doi.org\/10.3969\/j.issn.1673-629X.2022.12.021","journal-title":"Computer Technology Development"},{"key":"e_1_3_3_31_1","doi-asserted-by":"publisher","DOI":"10.3390\/s24237684"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems: Applications in Engineering and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18758967251348957","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/18758967251348957","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/18758967251348957","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:46:12Z","timestamp":1777455972000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/18758967251348957"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,11]]},"references-count":30,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["10.1177\/18758967251348957"],"URL":"https:\/\/doi.org\/10.1177\/18758967251348957","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,11]]}}}