{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T09:00:30Z","timestamp":1790240430802,"version":"4.1.0"},"reference-count":44,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:00:00Z","timestamp":1790208000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science and Technology Support Program","award":["2012BAF12B13"],"award-info":[{"award-number":["2012BAF12B13"]}]},{"DOI":"10.13039\/501100009101","name":"Natural Science Foundation of Henan Province","doi-asserted-by":"publisher","award":["202300410117"],"award-info":[{"award-number":["202300410117"]}],"id":[{"id":"10.13039\/501100009101","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Key Project of Henan Province","award":["222102220080"],"award-info":[{"award-number":["222102220080"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>As autonomous driving systems shift from experimental testing environments to real-world open-road deployment, object detection in traffic scenes has emerged as a critical challenge in the perception pipeline. In complex traffic scenarios, significant variations in object scales (e.g., small vehicles and large infrastructure) and dynamic backgrounds often result in frequent missed detections and false positives under real-time constraints, which directly impairs driving safety. To tackle these issues, we propose Trans-DETR, an efficient end-to-end detector for traffic scenes based on a multi-scale attention mechanism and a lightweight backbone network. The conventional Convolutional Block Attention Module (CBAM) captures features at only a single scale, making it insufficient for handling multi-scale characteristics. To overcome this limitation, we introduce the Multi-Scale Attention Module (MSAM), which incorporates Multi-Scale Convolution Attention (MSCA) into the cross-scale fusion path of the model. This enables the effective extraction of multi-scale feature information and significantly improves detection accuracy. Furthermore, we propose the lightweight backbone network LiteSNet to reduce the parameter inflation and computational burden caused by traditional large-kernel convolutions. LiteSNet decouples large kernels into sequentially stacked horizontal and vertical separable convolutions, while employing dilated convolutions to expand the receptive field without information loss. This strategy significantly reduces both the parameter count and computational complexity while preserving the same effective receptive field as large kernels. Finally, we design a reparameterized detection head called RepHead, which deeply integrates cross-stage partial connections with reparameterization techniques. This allows for efficient fusion of low-level spatial details and high-level semantic features, thereby enhancing the model\u2019s ability to detect small-scale traffic targets. Experimental results demonstrate that the proposed method achieves a mean average precision (mAP) of 89.8% on the KITTI dataset, outperforming RT-DETR-L by 2.0%. It also reduces the model size by 57% and computational complexity by 55.7%, with a single-frame inference time of only 4.6 ms. Compared with state-of-the-art approaches, the proposed algorithm achieves superior performance in terms of accuracy, efficiency, and model compactness, providing strong technical support for the advancement of autonomous driving systems.<\/jats:p>","DOI":"10.3390\/s26196043","type":"journal-article","created":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T08:06:37Z","timestamp":1790237197000},"page":"6043","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["An Efficient Transformer Detector for Traffic Scenes via Lightweight Backbone and Multi-Scale Attention"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3407-4176","authenticated-orcid":false,"given":"Jinfeng","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbo","family":"Hui","sequence":"additional","affiliation":[{"name":"School of Mechanical and Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxuan","family":"He","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Ding","sequence":"additional","affiliation":[{"name":"Weihua Group Co., Ltd., Changyuan 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiao","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongpu","family":"Nan","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Henan University of Technology, Zhengzhou 450001, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"14053","DOI":"10.1109\/TITS.2025.3539565","article-title":"An Intelligent Blockchain-Enabled Authentication Protocol for Transportation Cyber-Physical Systems","volume":"26","author":"Chen","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1109\/TVT.2024.3375298","article-title":"PR-OppCL: Privacy-preserving reputation-based opportunistic federated learning in intelligent transportation system","volume":"74","author":"Li","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"14383","DOI":"10.1109\/TITS.2025.3533364","article-title":"A Hybrid Trust Management Strategy for Reliable Cyber-Physical System in Intelligent Transportation","volume":"26","author":"Seno","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1007\/s10489-024-06213-3","article-title":"Applications of pre-trained CNN models and data fusion techniques in Unity3D for connected vehicles","volume":"55","author":"Norouzi","year":"2025","journal-title":"Appl. Intell."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"19475","DOI":"10.1038\/s41598-025-05136-4","article-title":"Explainable artificial intelligence with temporal convolutional networks for adverse weather condition detection in driverless vehicles","volume":"15","author":"Alzanin","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"5053","DOI":"10.1109\/TVT.2024.3501364","article-title":"Deep Reinforcement Learning-Based Mobile-Aware Edge Cooperative Caching Scheme in the Internet of Vehicles","volume":"74","author":"Tian","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"105905","DOI":"10.1016\/j.infrared.2025.105905","article-title":"NOC-YOLO: An exploration to enhance small-target vehicle detection accuracy in aerial infrared images","volume":"149","author":"Zhang","year":"2025","journal-title":"Infrared Phys. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., and Kweon, I.S. (2018, January 8\u201314). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"850","DOI":"10.1007\/s11760-025-04490-0","article-title":"CTS-YOLO: Real-Time Object Detection Algorithm Based on Improved YOLO11 in Complex Traffic Scenarios","volume":"19","author":"Gao","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1007\/s11227-024-06766-7","article-title":"Vehicle detection algorithm based on improved RT-DETR","volume":"81","author":"Wang","year":"2025","journal-title":"J. Supercomput."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ma, X., Dai, X., Bai, Y., Wang, Y., and Fu, Y. (2024, January 16\u201322). Rewrite the stars. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, T., Teng, Q., Sun, S., Song, W., Zhang, J., and Li, Y. (2026). CW-DETR: An Efficient Detection Transformer for Traffic Signs in Complex Weather. Sensors, 26.","DOI":"10.3390\/s26010325"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"9713","DOI":"10.1109\/TITS.2026.3676624","article-title":"BANet: Bidirectional Feature Aggregation and Adaptive Multi-Scene Perception-Based Lane Detection for Autonomous Driving","volume":"27","author":"Zhang","year":"2026","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Jung, S., Song, A., Lee, K., and Lee, W.H. (2025). Advanced Building Detection with Faster R-CNN Using Elliptical Bounding Boxes for Displacement Handling. Remote Sens., 17.","DOI":"10.3390\/rs17071247"},{"key":"ref_15","first-page":"5019114","article-title":"Multi-Scale Graph Channel Attention Detectors for Sonar Images in Smart Ocean","volume":"74","author":"Li","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/TETCI.2025.3543833","article-title":"YOLO-ITC: A New YOLO Method for Instance Segmentation of Individual Tree Crowns","volume":"10","author":"Sun","year":"2025","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"ref_17","first-page":"52","article-title":"PAB-Mamba-YOLO: VSSM assists in YOLO for aggressive behavior detection among weaned piglets","volume":"15","author":"Xia","year":"2025","journal-title":"Artif. Intell. Agric."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2527913","DOI":"10.1109\/TIM.2025.3566807","article-title":"Prior Distribution and Perception Radius are Important: Learning 3D Object Detector for Autonomous Driving","volume":"74","author":"Tao","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2094","DOI":"10.1109\/TIV.2023.3307157","article-title":"Radar-camera fusion for object detection and semantic segmentation in autonomous driving: A comprehensive review","volume":"9","author":"Yao","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_20","doi-asserted-by":"crossref","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":"ref_21","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1007\/s11760-025-03998-9","article-title":"Lightweight traffic sign detection algorithm based on improved YOLOv5 in snowy environments","volume":"19","author":"Wang","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yu, C., Jiang, X., Wu, F., Fu, Y., Pei, J., Zhang, Y., Li, X., and Fu, T. (2024). A multi-scale feature fusion based lightweight vehicle target detection network on aerial optical images. Remote Sens., 16.","DOI":"10.3390\/rs16193637"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"127477","DOI":"10.1016\/j.neucom.2024.127477","article-title":"Domain adaptation of anchor-free object detection for urban traffic","volume":"582","author":"Yu","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_24","first-page":"5035213","article-title":"MF-YOLO: A lightweight method for real-time dangerous driving behavior detection","volume":"73","author":"Wang","year":"2024","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Liu, Z., Yan, J., and Zhang, J. (2024). Research on a Recognition Algorithm for Traffic Signs in Foggy Environments Based on Image Defogging and Transformer. Sensors, 24.","DOI":"10.3390\/s24134370"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"115391","DOI":"10.1016\/j.asoc.2026.115391","article-title":"Multi-scale feature reconstruction and gated dual-attention network for driver attention prediction","volume":"199","author":"Zhang","year":"2026","journal-title":"Appl. Soft Comput."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1016\/j.patrec.2025.01.027","article-title":"TS-DETR: Multi-scale DETR for traffic sign detection and recognition","volume":"190","author":"Cui","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Shi, Y., Li, J., Jia, Y., and Hong, Q. (2026). LDA-DETR: A lightweight dynamic attention-enhanced DETR for small object detection. PLoS ONE, 21.","DOI":"10.1371\/journal.pone.0340977"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"105930","DOI":"10.1016\/j.rineng.2025.105930","article-title":"WDFS-DETR: A Transformer-based framework with multi-scale attention for small object detection in UAV engineering tasks","volume":"27","author":"Liu","year":"2025","journal-title":"Results Eng."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024, January 16\u201322). Detrs beat yolos on real-time object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"129904","DOI":"10.1016\/j.neucom.2025.129904","article-title":"YOLO-ELWNet: A lightweight object detection network","volume":"636","author":"Song","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_32","unstructured":"Duan, K., Bai, S., Xie, L., Qi, H., Huang, Q., and Tian, Q. (November, January 27). Centernet: Keypoint triplets for object detection. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea."},{"key":"ref_33","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). Yolox: Exceeding yolo series in 2021. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1007\/s11227-025-06944-1","article-title":"Traffic target detection based on context enhancement and feature purification","volume":"81","author":"Liu","year":"2025","journal-title":"J. Supercomput."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3983","DOI":"10.1007\/s11760-024-03003-9","article-title":"SES-YOLOv8n: Automatic driving object detection algorithm based on improved YOLOv8","volume":"18","author":"Sun","year":"2024","journal-title":"Signal Image Video Process."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1007\/s11760-025-04157-w","article-title":"An improved YOLOv11 algorithm for small object detection in UAV images","volume":"19","author":"Wang","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast r-cnn. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020, January 13\u201319). Efficientdet: Scalable and efficient object detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"38157","DOI":"10.1109\/ACCESS.2023.3268106","article-title":"YOLOX++ for transmission line abnormal target detection","volume":"11","author":"Bi","year":"2023","journal-title":"IEEE Access"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"100651","DOI":"10.1016\/j.ijnaoe.2025.100651","article-title":"YOLO-ESFM: A multi-scale YOLO algorithm for sea surface object detection","volume":"17","author":"Wei","year":"2025","journal-title":"Int. J. Nav. Archit. Ocean. Eng."},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Wang, C.Y., Bochkovskiy, A., and Liao, H.Y.M. (2023, January 17\u201324). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00721"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"4052","DOI":"10.1109\/TIP.2025.3581729","article-title":"WS-SAM: Generalizing SAM to Weakly Supervised Object Detection with Category Label","volume":"34","author":"Wang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Wiseman, Y. (2017). Real-time monitoring of traffic congestions. Proceedings of the 2017 IEEE International Conference on Electro Information Technology (EIT), IEEE.","DOI":"10.1109\/EIT.2017.8053413"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6043\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T08:09:58Z","timestamp":1790237398000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6043"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,24]]},"references-count":44,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196043"],"URL":"https:\/\/doi.org\/10.3390\/s26196043","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,24]]}}}