YOLO-RTLite: A TensorRT-Optimized Lightweight Detector for Real-Time Road Object Detection
DOI:
https://doi.org/10.47839/ijc.25.2.4662Keywords:
YOLOv4, object detection, vehicle detection, animal detection, optimizationAbstract
This paper presents YOLO-RTLite, an optimized lightweight object detection model based on YOLOv4-Tiny. The proposed model addresses the challenges of accurate and reliable object detection in curved and blind road conditions, where visibility is limited and timely detection is critical. YOLO-RTLite is specifically engineered for real-time identification of critical road obstacles, focusing on vehicles and animals, to reduce road accidents and improving transportation safety. The YOLO-RTLite architecture incorporates an additional convolutional layer (with Mish activation function) and three novel skip connections to reinforce multi-scale feature propagation and feature reuse. Model performance is further improved through selective tuning of filter sizes and anchor boxes which enable better adaptation to diverse object dimensions. For real-time deployment, TensorRT-based acceleration is utilized to significantly increase inference speed. Performance results demonstrate that YOLO-RTLite achieves high precision (~95%), accuracy (~99%), robust recall (~98%), and efficient inference time (0.165 s) which is a significant improvement over its baseline model (YOLOv4 tiny). These performance stats support its suitability for safety-critical intelligent transportation systems.
References
I. J. Daisy, A. Arun, J. Emmanual J. Antony & K. B. Muhilan, “Smart vehicle assistance and accident prevention system,” International Research Journal on Advanced Engineering Hub, vol. 3, no. 3, pp. 412-419, 2025. https://doi.org/10.47392/IRJAEH.2025.0056.
J. Negrini de Araujo, V. Palade, T. Sedighi & A. Daneshkhah, “Improving the pedestrian detection performance in the absence of rich training datasets: A UK case study,” Advances in Artificial Intelligence and Machine Learning, vol. 2, no. 1, pp. 315-337, 2022. https://doi.org/10.54364/AAIML.2022.1121.
G. Öztürk, O. Eldoğan & R. Köker, “Computer vision-based lane detection and detection of vehicle, traffic sign, pedestrian using YOLOv5,” Sakarya University Journal of Science, vol. 28, no. 2, pp. 418-430, 2024. https://doi.org/10.16984/saufenbilder.1393307.
M. Zaman, S. Saha, N. Zohrabi & S. Abdelwahed, “Deep learning approaches for vehicle and pedestrian detection in adverse weather,” Proceedings of the 2023 IEEE Transportation Electrification Conference and Expo (ITEC 2023), Detroit, USA, 21-23 June 2023, pp. 1-6. https://doi.org/10.1109/ITEC55900.2023.10187020.
D. R. Niranjan, B. C. Vinaykarthik & Mohana, “Performance analysis of SSD and Faster RCNN multi-class object detection model for autonomous driving vehicle research using CARLA simulator,” Proc. IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT) 2021, 2021, pp. 497. https://doi.org/10.1109/ICECCT52121.2021.9616712.
R. Prabha, M. Sanjana, S. Harshavarthanan, A. Premika, and S. S. Sarveshwaar, “Collision avoidance system in autonomous vehicles using YOLOv4,” Proceedings of the IEEE International Conference on Communication and Information & Robotics Technology (ICCIRT), pp. 107–111, 2024. https://doi.org/10.1109/ICCIRT59484.2024.10921869.
S. Arshad, M. Sualeh, D.-H. Kim, N. Dinh, and G.-W. Kim, “Clothoid: An integrated hierarchical framework for autonomous driving in a dynamic urban environment,” Sensors, vol. 20, issue 18, article 5053, 2020. https://doi.org/10.3390/s20185053.
W. Rassameepaiboon and W. Assawinchaichote, “Vehicle avoidance reaction by two-step motion flow cluster,” Proceedings of the International Computer Science and Engineering Conference (ICSEC), pp. 1–5, 2018. https://doi.org/10.1109/ICSEC.2018.8712678.
D. Sudharson, J. Srinithi, S. Akshara, K. Abhirami, P. Sriharshitha, and K. Priyanka, “Proactive headcount and suspicious activity detection using YOLOv8,” Procedia Computer Science, vol. 230, pp. 61-69, 2023. https://doi.org/10.1016/j.procs.2023.12.061.
S. A. Dhinakar Raj, A. Singh, M. Muthanna, K. Sivasankaran, and T. S. Shekhawat, “Collision avoidance system using YOLO-based object detection and distance estimation,” Proceedings of the 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things (IDCIoT), pp. 178–184, 2025. https://doi.org/10.1109/IDCIOT64235.2025.10915167.
A. N. M. Nusari, I. Y. Ozbek and E. A. Oral, “Automatic vehicle accident detection and classification from images: A comparison of YOLOv9 and YOLO-NAS algorithms,” Proceedings of the 2024 32nd Signal Processing and Communications Applications Conference (SIU), pp. 1–4, 2024. https://doi.org/10.1109/SIU61531.2024.10600761.
N. Choudhary, R. Sharma, D. Upadhyay, A. Verma and V. Jain, “Enhanced traffic sign recognition using advanced YOLOv8 model,” Proceedings of the 2024 4th International Conference on Intelligent Technologies (CONIT), Bangalore, India, 2024, pp. 1-4. https://doi.org/10.1109/CONIT61985.2024.10626450.
A. Albouchi, M. A. Hajjaji and A. Mtibaa, “Deep learning-based object detection approach for autonomous vehicles,” Proceedings of the 2022 IEEE International Conference on Secure Trust and Data Management Applications (STA), Sousse, Tunisia, 2022, pp. 89-94. https://doi.org/10.1109/STA56120.2022.10018993.
M. Jakubec, E. Lieskovská, B. Bučko and K. Zábovská, “Comparison of CNN-based models for pothole detection in real-world adverse conditions: Overview and evaluation,” Applied Sciences, vol. 13, no. 9, article 5810, 2023. https://doi.org/10.3390/app13095810.
M. Shirpour, N. Khairdoost, M. A. Bauer and S. S. Beauchemin, “Traffic object detection and recognition based on the attentional visual field of drivers,” IEEE Transactions on Intelligent Vehicles, vol. 8, no. 1, pp. 594–604, 2023. https://doi.org/10.1109/TIV.2021.3133849.
P. Goswami & A. B. M. A. Hossain, “Street object detection from synthesized and processed semantic image: A deep learning-based study,” Human-Centric Intelligent Systems, vol. 3, pp. 487–507, 2023. https://doi.org/10.1007/s44230-023-00043-1.
H. Wang, W. Niu, Y. Liu, Y. Tan & C. Xiu, “Low-speed collision prevention warning for intelligent vehicles based on digital twin and deep learning,” Proceedings of the 2024 IEEE International Conference on Digital Systems and Intelligent Systems (ICDSIS), Hassan, India, 2024, pp. 1-7. https://doi.org/10.1109/ICDSIS61070.2024.10594607.
Y. P. Yong, S. J. Lee, Y. H. Chang, K. H. Lee, S. W. Kwon, C. S. Cho & S. W. Chung, “Object detection and distance measurement algorithm for collision avoidance of precast concrete installation during crane lifting process,” Buildings, vol. 13, no. 10, article 2551, 2023. https://doi.org/10.3390/buildings13102551.
N. Devulapalli, V. Matus, E. Eso, Z. Ghassemlooy & R. Pérez-Jiménez, “Lane-cross detection using optical camera-based road-to-vehicle communications,” in Proceedings of the 2021 17th International Symposium on Wireless Communication Systems (ISWCS), pp. 240–244, 2021. https://doi.org/10.1109/ISWCS49558.2021.9562196.
P. V., S. Dhanya, “3DYOLO: Real-time 3D object detection in 3D point clouds for autonomous driving,” Proceedings of the International Geoscience and Remote Sensing Symposium (IGARSS), Ahmedabad, India, 2021, pp. 41-44. https://doi.org/10.1109/InGARSS51564.2021.9791912.
Y. Liu, Y. Shi, “VRU-YOLO: A small object detection algorithm for vulnerable road users in complex scenes,” IEEE Access, vol. 13, pp. 19996-20015, 2025. https://doi.org/10.1109/ACCESS.2025.3534321.
A.R. Pathak, A.C. Elster, “Applying transfer learning to traffic surveillance videos for accident detection,” Proceedings of the International Conference on Applied Artificial Intelligence (ICAPAI), Halden, Norway, 2022, pp. 1-7. https://doi.org/10.1109/ICAPAI55158.2022.9801568.
J. Nine, R. Mathavan, “Traffic light and back-light recognition using deep learning and image processing with Raspberry Pi,” Engineering Science and Synthetic, vol. 8, no. 2, 2021. https://doi.org/10.14464/ess.v8i2.490.
K. Sarvajcz, L. Ari, J. Menyhrt, “AI on the road: NVIDIA Jetson Nano-powered computer vision-based system for real-time pedestrian and priority sign detection,” Applied Sciences, vol. 14, 1440, 2024. https://doi.org/10.3390/app14041440.
T. Winkle, C. Erbsmehl, K. Bengler, “Area-wide real-world test scenarios of poor visibility for safe development of automated vehicles,” European Transport Research Review, vol. 10, p. 55, 2018. https://doi.org/10.1186/s12544-018-0304-x.
N.K. Ragesh, R. Rajesh, “Pedestrian detection in automotive safety: Understanding state-of-the-art,” IEEE Access, 2019. https://doi.org/10.1109/ACCESS.2019.2909992.
A. Paiboonrattanakorn, S. Phimoltares, “Neural computing-based pedestrian detection from image sequence,” Int. Jt. Conf. Comput. Sci. Softw. Eng., vol. 7, pp. 47864-47890, 2019. https://doi.org/10.1109/JCSSE.2012.6261921.
M.A.A. Hammoudeh, M. Alsaykhan, R. Alsalameh, N. Althwaibi, “Computer vision: A review of detecting objects in videos challenges and techniques,” Int. J. Online Eng., vol. 18, issue 1, 2022. https://doi.org/10.3991/ijoe.v18i01.27577.
N. Yadav, U. Thakur, A. Poonia, R. Chandel, “Post-crash detection and traffic analysis,” Int. Conf. Signal Process. Integr. Netw. (SPIN), Noida, India, 2021, pp. 1092-1097. https://doi.org/10.1109/SPIN52536.2021.9565964.
M.I.B. Ahmed, R. Zaghdoud, M.S. Ahmed, R. Sendi, S. Alsharif, J. Alabdulkarim, B.A.A. Saad, R. Alsabt, A. Rahman, G. Krishnasamy, “A real-time computer vision based approach to detection and classification of traffic incidents,” Big Data Cogn. Comput., vol. 7, issue 1, 22, 2023. https://doi.org/10.3390/bdcc7010022.
A. Pravallika, M.F. Hashmi, A. Gupta, “Deep learning frontiers in 3D object detection: A comprehensive review for autonomous driving,” IEEE Access, vol. 12, pp. 173936-173980, 2024. https://doi.org/10.1109/ACCESS.2024.3456893.
N. Murali, D. Beulah David, “Advanced VANET technology for emergency vehicle safety in time-critical scenario,” Proceedings of the International Conference on Smart Technologies in Electrical Vehicles, Communication & Computing Control (ICONSTEM), Chennai, India, 2023, pp. 1-8. https://doi.org/10.1109/ICONSTEM56934.2023.10142332.
R. Sapkota, Z. Meng, M. Churuvija, X. Du, Z. Ma, M. Karkee, “Comprehensive performance evaluation of YOLOv12, YOLO11, YOLOv10, YOLOv9 and YOLOv8 on detecting and counting fruitlet in complex orchard environments,” 2024. https://doi.org/10.36227/techrxiv.172954111.18265256/v2.
Z. E. Kaymakcı, M. Akarsu, C. Öztürk, “Multiple small-scale object detection in aerial vehicle images using standard or optimized YOLO detectors,” Proceedings of the International Symposium on Innovations in Intelligent Systems and Applications (INISTA), 2023, pp. 1-5. https://doi.org/10.1109/INISTA59065.2023.10310562.
A. Bulut, F. Ozdemir, Y. S. Bostanci, M. Soyturk, “Performance evaluation of recent object detection models for traffic safety applications on edge,” Proceedings of the IPMV Conference, 2023, pp. 1-6. https://doi.org/10.1145/3582177.3582178.
D.-S. Bacea, F. Oniga, “Single stage architecture for improved accuracy real-time object detection on mobile devices,” Image and Vision Computing, vol. 130, p. 104613, 2023. https://doi.org/10.1016/j.imavis.2022.104613.
M. Li, C. Li, S. Wang, W. Xie, “Efficient WFFA-SSD with weighted-feature fusion block and lightweight design for small object detection,” Scientific Reports, vol. 13, no. 1, 9883, 2023. https://doi.org/10.1038/s41598-023-36972-x.
Q. Zhong, Y. Liu, L. Ma, Y. Ma, “Anchor box optimization for object detection,” Proceedings of the IEEE Winter Conference on Applications of Computer Vision (WACV), 2020, pp. 1325-1333. https://doi.org/10.1109/WACV45572.2020.9093351.
M. Tan, R. Pang, Q. V. Le, “EfficientDet: Scalable and efficient object detection,” arXiv preprint arXiv:1911.09070, 2019. https://arxiv.org/abs/1911.09070.
NVIDIA Corporation, TensorRT Developer Guide, NVIDIA Developer, 2019. [Online]. Available at: https://docs.nvidia.com/deeplearning/tensorrt/developer-guide.
J. Terven, D.-M. Córdova-Esparza, J.-A. Romero-González, “A comprehensive review of YOLO architectures in computer vision: From YOLOv1 to YOLOv8 and YOLO-NAS,” Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp. 1680-1716, 2023. https://doi.org/10.3390/make5040083.
Z.E. Kaymakcı, M. Akarsu, C. Öztürk, “Multiple small-scale object detection in aerial vehicle images using standard or optimized YOLO detectors,” Proceedings of the International Symposium on Innovations in Intelligent Systems and Applications (INISTA), Hammamet, Tunisia, 2023, pp. 1-5. https://doi.org/10.1109/INISTA59065.2023.10310562.
A. Bulut, F. Ozdemir, Y.S. Bostanci, M. Soyturk, “Performance evaluation of recent object detection models for traffic safety applications on edge,” Proceedings of the International Conference on Image Processing and Machine Vision (IPMV), 2023, pp. 1-6. https://doi.org/10.1145/3582177.3582178.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
