{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T17:09:54Z","timestamp":1776532194966,"version":"3.51.2"},"reference-count":49,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T00:00:00Z","timestamp":1754611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>On-road vision-based systems rely on object detection to ensure vehicle safety and efficiency, making it an essential component of autonomous driving. Deep learning methods show high performance; however, they often require special hardware due to their large sizes and computational complexity, which makes real-time deployment on edge devices expensive. This study proposes lightweight object detection models based on the YOLOv5s architecture, known for its speed and accuracy. The models integrate advanced channel attention strategies, specifically the ECA module and SE attention blocks, to enhance feature selection while minimizing computational overhead. Four models were developed and trained on the KITTI dataset. The models were analyzed using key evaluation metrics to assess their effectiveness in real-time autonomous driving scenarios, including precision, recall, and mean average precision (mAP). BaseECAx2 emerged as the most efficient model for edge devices, achieving the lowest GFLOPs (13) and smallest model size (9.1 MB) without sacrificing performance. The BaseSE-ECA model demonstrated outstanding accuracy in vehicle detection, reaching a precision of 96.69% and an mAP of 98.4%, making it ideal for high-precision autonomous driving scenarios. We also assessed the models\u2019 robustness in more challenging environments by training and testing them on the BDD-100K dataset. While the models exhibited reduced performance in complex scenarios involving low-light conditions and motion blur, this evaluation highlights potential areas for improvement in challenging real-world driving conditions. This study bridges the gap between affordability and performance, presenting lightweight, cost-effective solutions for integration into real-time autonomous vehicle systems.<\/jats:p>","DOI":"10.3390\/jimaging11080263","type":"journal-article","created":{"date-parts":[[2025,8,8]],"date-time":"2025-08-08T09:56:42Z","timestamp":1754647002000},"page":"263","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Enhancing YOLOv5 for Autonomous Driving: Efficient Attention-Based Object Detection on Edge Devices"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0004-3082-8199","authenticated-orcid":false,"given":"Mortda A. A.","family":"Adam","sequence":"first","affiliation":[{"name":"School of Engineering, Howard College Campus, University of KwaZulu-Natal, Durban 4041, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-5915-0511","authenticated-orcid":false,"given":"Jules R.","family":"Tapamo","sequence":"additional","affiliation":[{"name":"School of Engineering, Howard College Campus, University of KwaZulu-Natal, Durban 4041, South Africa"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,8]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Sharma, S., Sharma, A., and Van Chien, T. (2025). The Intersection of 6G, AI\/Machine Learning, and Embedded Systems: Pioneering Intelligent Wireless Technologies, CRC Press. [1st ed.].","DOI":"10.1201\/9781003540212"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Meng, F., Hong, A., Tang, H., and Tong, G. (2025). FQDNet: A Fusion-Enhanced Quad-Head Network for RGB-Infrared Object Detection. Remote Sens., 17.","DOI":"10.3390\/rs17061095"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Yang, Z., Li, J., and Li, H. (2018, January 26\u201330). Real-Time Pedestrian and Vehicle Detection for Autonomous Driving. Proceedings of the 2018 IEEE Intelligent Vehicles Symposium (IV), Changshu, China.","DOI":"10.1109\/IVS.2018.8500642"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"152138","DOI":"10.1109\/ACCESS.2024.3481642","article-title":"SNCE-YOLO: An Improved Target Detection Algorithm in Complex Road Scenes","volume":"12","author":"Li","year":"2024","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"113442","DOI":"10.1109\/ACCESS.2024.3442484","article-title":"Super-Resolution GAN and Global Aware Object Detection System for Vehicle Detection in Complex Traffic Environments","volume":"12","author":"Wang","year":"2024","journal-title":"IEEE Access"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Farhat, W., Ben Rhaiem, O., Faiedh, H., and Souani, C. (2025). Optimized Deep Learning for Pedestrian Safety in Autonomous Vehicles. Int. J. Transp. Sci. Technol., in press.","DOI":"10.1016\/j.ijtst.2025.04.002"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Galvao, L.G., Abbod, M., Kalganova, T., Palade, V., and Huda, M.N. (2021). Pedestrian and Vehicle Detection in Autonomous Vehicle Perception Systems\u2014A Review. Sensors, 21.","DOI":"10.3390\/s21217267"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"11568","DOI":"10.1109\/TITS.2023.3292278","article-title":"Vehicle Detection for Autonomous Driving: A Review of Algorithms and Datasets","volume":"24","author":"Karangwa","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_9","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. Pattern Anal. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Leibe, B., Matas, J., Sebe, N., and Welling, M. (2016, January 11\u201314). SSD: Single Shot MultiBox Detector. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46466-4"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"42816","DOI":"10.1109\/ACCESS.2024.3378568","article-title":"YOLOv1 to v8: Unveiling Each Variant\u2013A Comprehensive Review of YOLO","volume":"12","author":"Hussain","year":"2024","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, B., Zhu, P., Li, P., Zuo, W., and Hu, Q. (2019). ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. arXiv.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., and Sun, G. (2017). Squeeze-and-Excitation Networks. arXiv.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sarda, A., Dixit, S., and Bhan, A. (2021, January 4\u20136). Object Detection for Autonomous Driving Using YOLO (You Only Look Once) Algorithm. Proceedings of the 2021 Third International Conference on Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), Tirunelveli, India.","DOI":"10.1109\/ICICV50876.2021.9388577"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wen, S., Wang, D., Meng, J., Mu, J., and Irampaye, R. (2022). MobileYOLO: Real-Time Object Detection Algorithm in Autonomous Driving Scenarios. Sensors, 22.","DOI":"10.3390\/s22093349"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"178566","DOI":"10.1109\/ACCESS.2024.3507713","article-title":"MXT-YOLOv7t: An Efficient Real-Time Object Detection for Autonomous Driving in Mixed Traffic Environments","volume":"12","author":"Afdhal","year":"2024","journal-title":"IEEE Access"},{"key":"ref_17","first-page":"1","article-title":"YOLOv4-5D: An Effective and Efficient Object Detector for Autonomous Driving","volume":"70","author":"Cai","year":"2021","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"22342","DOI":"10.1109\/ACCESS.2023.3252021","article-title":"MCS-YOLO: A Multiscale Object Detection Method for Autonomous Driving Road Environment Recognition","volume":"11","author":"Cao","year":"2023","journal-title":"IEEE Access"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"25345","DOI":"10.1109\/TITS.2022.3158253","article-title":"Edge YOLO: Real-Time Intelligent Object Detection System Based on Edge-Cloud Cooperation in Autonomous Vehicles","volume":"23","author":"Liang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"He, Q., Xu, A., Ye, Z., Zhou, W., and Cai, T. (2023). Object Detection Based on Lightweight YOLOX for Autonomous Driving. Sensors, 23.","DOI":"10.21203\/rs.3.rs-3053457\/v1"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"111704","DOI":"10.1016\/j.asoc.2024.111704","article-title":"SwinYOLOv7: Robust Ship Detection in Complex Synthetic Aperture Radar Images","volume":"160","author":"Yasir","year":"2024","journal-title":"Appl. Soft Comput."},{"key":"ref_22","first-page":"1","article-title":"YOLOv8-Lite: A Lightweight Object Detection Model for Real-Time Autonomous Driving Systems","volume":"1","author":"Yang","year":"2024","journal-title":"ICCK Trans. Emerg. Top. Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wei, F., and Wang, W. (2025). SCCA-YOLO: A Spatial and Channel Collaborative Attention Enhanced YOLO Network for Highway Autonomous Driving Perception System. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-90743-4"},{"key":"ref_24","unstructured":"Khanam, R., and Hussain, M. (2024). Yolov11: An overview of the key architectural enhancements. arXiv."},{"key":"ref_25","unstructured":"Tian, Y., Ye, Q., and Doermann, D. (2025). YOLOv12: Attention-Centric Real-Time Object Detectors. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lv, W., Xu, S., Wei, J., Wang, G., Dang, Q., Liu, Y., and Chen, J. (2024). DETRs Beat YOLOs on Real-Time Object Detection. arXiv.","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"ref_27","unstructured":"Kadiyapu, D.C.M., Mangali, V.S., Thummuru, J.R., Sattula, S., Annapureddy, S.R., and Arunkumar, M.S. (2025, January 6\u20137). Improving the Autonomous Vehicle Vision with Synthetic Data Using Gen AI. Proceedings of the 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), Tiruchirappalli, India."},{"key":"ref_28","unstructured":"Ghosh, A., Kumar, G.P., Prasad, P., Kumar, D., Jain, S., and Chopra, J. (2023). Synergizing Generative Intelligence: Advancements in Artificial Intelligence for Intelligent Vehicle Systems and Vehicular Networks. Iconic Res. Eng. J., 7, Available online: https:\/\/2.zoppoz.workers.dev:443\/https\/www.researchgate.net\/publication\/376406497_Synergizing_Generative_Intelligence_Advancements_in_Artificial_Intelligence_for_Intelligent_Vehicle_Systems_and_Vehicular_Networks."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"150651","DOI":"10.1109\/ACCESS.2024.3476177","article-title":"GenCoder: A Generative AI-Based Adaptive Intra-Vehicle Intrusion Detection System","volume":"12","author":"Smolin","year":"2024","journal-title":"IEEE Access"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Lu, J., Yang, W., Xiong, Z., Xing, C., Tafazolli, R., Quek, T.Q.S., and Debbah, M. (2024). Generative AI-Enhanced Multi-Modal Semantic Communication in Internet of Vehicles: System Design and Methodologies. arXiv.","DOI":"10.1109\/MVT.2025.3545399"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhang, J., Liu, Z., Wei, H., Zhang, S., Cheng, W., and Yin, H. (2023, January 24\u201326). CAE-YOLOv5: A Vehicle Target Detection Algorithm Based on Attention Mechanism. Proceedings of the 2023 China Automation Congress (CAC), Wuhan, China.","DOI":"10.1109\/CAC59555.2023.10451120"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Wang, J., Dong, Y., Zhao, S., and Zhang, Z. (2023). A High-Precision Vehicle Detection and Tracking Method Based on the Attention Mechanism. Sensors, 23.","DOI":"10.3390\/s23020724"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wang, Z., Men, S., Bai, Y., Yuan, Y., Wang, J., Wang, K., and Zhang, L. (2024). Improved Small Object Detection Algorithm CRL-YOLOv5. Sensors, 24.","DOI":"10.20944\/preprints202408.1218.v1"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Jia, X., Tong, Y., Qiao, H., Li, M., Tong, J., and Liang, B. (2023). Fast and Accurate Object Detector for Autonomous Driving Based on Improved YOLOv5. Sci. Rep., 13.","DOI":"10.1038\/s41598-023-36868-w"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Liu, T., Dongye, C., and Jia, X. (2023, January 6\u20138). The Research on Traffic Sign Recognition Algorithm Based on Improved YOLOv5 Model. Proceedings of the 2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE), Guangzhou, China.","DOI":"10.1109\/ICCECE58074.2023.10135475"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2070","DOI":"10.1007\/s10489-021-02491-3","article-title":"YOLOv3-MT: A YOLOv3 Using Multi-Target Tracking for Vehicle Visual Detection","volume":"52","author":"Wang","year":"2022","journal-title":"Appl. Intell."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"61546","DOI":"10.1109\/ACCESS.2023.3262601","article-title":"R-YOLOv5: A Lightweight Rotational Object Detection Algorithm for Real-Time Detection of Vehicles in Dense Scenes","volume":"11","author":"Li","year":"2023","journal-title":"IEEE Access"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"88075","DOI":"10.1109\/ACCESS.2024.3417267","article-title":"A Novel Framework for Vehicle Detection and Tracking in Night Ware Surveillance Systems","volume":"12","author":"Almujally","year":"2024","journal-title":"IEEE Access"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"3825","DOI":"10.1007\/s10115-025-02375-9","article-title":"Comprehensive Review of Deep Learning-Based Tiny Object Detection: Challenges, Strategies, and Future Directions","volume":"67","author":"Muzammul","year":"2025","journal-title":"Knowl. Inf. Syst."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"46024","DOI":"10.1109\/ACCESS.2024.3382245","article-title":"SatDetX-YOLO: A More Accurate Method for Vehicle Target Detection in Satellite Remote Sensing Imagery","volume":"12","author":"Zhao","year":"2024","journal-title":"IEEE Access"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Adam, M.A.A., and Tapamo, J.R. (2025). Survey on Image-Based Vehicle Detection Methods. World Electr. Veh. J., 16.","DOI":"10.3390\/wevj16060303"},{"key":"ref_42","unstructured":"Jocher, G. (2025, May 10). Ultralytics YOLOv5, Version 7.0; 2020. Available online: https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/ultralytics\/yolov5."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., and Doll\u00e1r, P. (2015). Microsoft COCO: Common Objects in Context. arXiv.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_44","unstructured":"Bochkovskiy, A., Wang, C.-Y., and Liao, H.-Y.M. (2020). YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv."},{"key":"ref_45","unstructured":"Redmon, J., and Farhadi, A. (2018). YOLOv3: An Incremental Improvement. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1177\/0278364913491297","article-title":"Vision Meets Robotics: The KITTI Dataset","volume":"32","author":"Geiger","year":"2013","journal-title":"Int. J. Robot. Res."},{"key":"ref_47","unstructured":"Yu, F., Xian, W., Chen, Y., Liu, F., Liao, M., Madhavan, V., and Darrell, T. (2018). BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"40701","DOI":"10.1109\/ACCESS.2022.3166923","article-title":"ALODAD: An Anchor-Free Lightweight Object Detector for Autonomous Driving","volume":"10","author":"Liang","year":"2022","journal-title":"IEEE Access"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1109\/TIV.2022.3165353","article-title":"Cross-Domain Object Detection for Autonomous Driving: A Stepwise Domain Adaptative YOLO Approach","volume":"7","author":"Li","year":"2022","journal-title":"IEEE Trans. Intell. Veh."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.mdpi.com\/2313-433X\/11\/8\/263\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:26:11Z","timestamp":1760034371000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.mdpi.com\/2313-433X\/11\/8\/263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,8]]},"references-count":49,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,8]]}},"alternative-id":["jimaging11080263"],"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.3390\/jimaging11080263","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,8]]}}}