Region-Specific Road Object Detection in African Environments: Dataset Curation, Benchmarking, and Edge Deployment
Received: 30 December 2025 | Revised: 4 February 2026 and 16 February 2026 | Accepted: 25 February 2026 | Online: 4 April 2026
Corresponding author: Rumbidzai Muzata
Abstract
Road safety in Africa faces substantial challenges that current public and custom datasets for autonomous driving do not adequately address. Public datasets frequently underrepresent object classes crucial to road safety in the African region, which features unique obstacles such as wild and domestic animals, informal public vehicles, and infrastructure hazards. Without these classes, detection models often miss road obstacles, thereby reducing safety on African roads. This study introduces a custom dataset of 3,236 original images with annotations for 11 object classes. It includes wild animals (kudus, elephants), domestic animals (cattle, goats), informal public vehicles (boda bodas, tuk-tuks, minibus taxis), and infrastructure hazards (potholes, unmarked speed bumps). Three of the most recent You Only Look Once (YOLO) object detection models (versions 8, 9, and 10) were trained on our custom dataset and evaluated on an NVIDIA RTX 3050 GPU. Of all the models, YOLOv8 achieved the highest mean Average Precision (mAP)@0.5 of 94.2%, followed closely by YOLOv10 and YOLOv9 at 92.5% and 90.6%, respectively, demonstrating strong detection performance on challenging, geographically relevant data. To assess the models in real-world deployment, they were optimized with TensorRT and deployed on an NVIDIA Jetson Nano embedded platform. This optimization achieved a 77% reduction in inference time with a very small accuracy drop of 0.64%, proving that the models are capable of fast, accurate, real-time execution on inexpensive edge devices. This study addresses geographic bias in autonomous-driving datasets in Africa and offers deployment-ready solutions for inexpensive edge hardware.
Keywords:
edge deployment, geographic bias, road obstacle detection, YOLODownloads
References
J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You Only Look Once: Unified, Real-Time Object Detection," in 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 2016, pp. 779–788. DOI: https://doi.org/10.1109/CVPR.2016.91
M. Katari, G. Krishnamoorthy, L. Shanmugam, and A. Tadimarri, "Driving Towards Safety: The Role of ECUs and IMUs in Advanced Driver-Assistance Systems (ADAS)," IJFMR - International Journal For Multidisciplinary Research, vol. 6, no. 2, Apr. 2024, Art. no. IJFMR240217022. DOI: https://doi.org/10.36948/ijfmr.2024.v06i02.17022
S. A. Alhashmi and A. Al-azawi, "A Review of the Single-Stage vs. Two-Stage Detectors Algorithm:Comprehensive Insights into Object Detection," International Journal of Environmental Sciences, vol. 11, no. 3s, pp. 775–787, May 2025.
M. Othmani, "A vehicle detection and tracking method for traffic video based on faster R-CNN," Multimedia Tools and Applications, vol. 81, no. 20, pp. 28347–28365, Aug. 2022. DOI: https://doi.org/10.1007/s11042-022-12715-4
A. L. Dewi et al., "Two-Stage Object Detection for Autonomous Vehicles With VGG-16 Based Faster R-CNN," Jurnal Elektronika dan Telekomunikasi, vol. 24, no. 1, pp. 25–30, Aug. 2024. DOI: https://doi.org/10.55981/jet.551
W. Liu et al., "SSD: Single Shot MultiBox Detector," in 14th European Conference on Computer Vision, Amsterdam, Netherlands, 2016, pp. 21–37. DOI: https://doi.org/10.1007/978-3-319-46448-0_2
Y. Han, "Comparative Analysis of Two-Stage and One-Stage Object Detection Models," in Proceedings of the 2nd International Conference on Data Analysis and Machine Learning, Kuala Lumpur, Malaysia, 2024, pp. 289–294. DOI: https://doi.org/10.5220/0013515900004619
J. Wang et al., "Research on Improved YOLOv5 for Low-Light Environment Object Detection," Electronics, vol. 12, no. 14, July 2023, Art. no. 3089. DOI: https://doi.org/10.3390/electronics12143089
J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger," in 2017 IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017, pp. 6517–6525. DOI: https://doi.org/10.1109/CVPR.2017.690
A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "YOLOv4: Optimal Speed and Accuracy of Object Detection." arXiv, Apr. 23, 2020.
J. Redmon and A. Farhadi, "YOLOv3: An Incremental Improvement." arXiv, Apr. 08, 2018.
M. Jani, J. Fayyad, Y. Al-Younes, and H. Najjaran, "Model Compression Methods for YOLOv5: A Review." arXiv, July 21, 2023.
J. Terven, D.-M. Córdova-Esparza, and 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, Nov. 2023. DOI: https://doi.org/10.3390/make5040083
C.-Y. Wang, I.-H. Yeh, and H.-Y. Mark Liao, "YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information," in 18th European Conference on Computer Vision, Milan, Italy, 2024, pp. 1–21. DOI: https://doi.org/10.1007/978-3-031-72751-1_1
A. Wang et al., "YOLOv10: real-time end-to-end object detection," in Proceedings of the 38th International Conference on Neural Information Processing Systems, Vancouver, Canada, 2024, pp. 107984–108011. DOI: https://doi.org/10.52202/079017-3429
S. Rahman, J. H. Rony, J. Uddin, and M. A. Samad, "Real-Time Obstacle Detection with YOLOv8 in a WSN Using UAV Aerial Photography," Journal of Imaging, vol. 9, no. 10, Oct. 2023, Art. no. 216. DOI: https://doi.org/10.3390/jimaging9100216
K. Gajjar, T. van Niekerk, T. Wilm, and P. Mercorelli, "Vision-Based Deep Learning Algorithm for Detecting Potholes," Journal of Physics: Conference Series, vol. 2162, no. 1, Jan. 2022, Art. no. 012019. DOI: https://doi.org/10.1088/1742-6596/2162/1/012019
V. Breive and T. Sledevic, "Person Detection in Thermal Images: A Comparative Analysis of YOLOv8 and YOLOv9 Models," in 2024 IEEE Open Conference of Electrical, Electronic and Information Sciences (eStream), Vilnius, Lithuania, 2024, pp. 1–4. DOI: https://doi.org/10.1109/eStream61684.2024.10542600
P. Mutabarura, N. Muchuka, and D. Segera, "Comparative Evaluation of YOLO Models on an African Road Obstacles Dataset for Real-Time Obstacle Detection," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19045–19051, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9135
K. Jadaan, E. Al-Braizat, S. Al-Rafayah, H. Gammoh, and Y. Abukahlil, "Traffic Safety in Developed and Developing Countries: A Comparative Analysis," Journal of Traffic and Logistics Engineering, vol. 6, no. 1, pp. 1–5, June 2018. DOI: https://doi.org/10.18178/jtle.6.1.1-5
B. Wilson, J. Hoffman, and J. Morgenstern, "Predictive Inequity in Object Detection." arXiv, Feb. 21, 2019.
T.-Y. Lin et al., "Microsoft COCO: Common Objects in Context," in 13th European Conference on Computer Vision, Zurich, Switzerland, 2014, pp. 740–755. DOI: https://doi.org/10.1007/978-3-319-10602-1_48
A. Geiger, P. Lenz, and R. Urtasun, "Are we ready for autonomous driving? The KITTI vision benchmark suite," in 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, 2012, pp. 3354–3361. DOI: https://doi.org/10.1109/CVPR.2012.6248074
Y. Jiang et al., "EnlightenGAN: Deep Light Enhancement Without Paired Supervision," IEEE Transactions on Image Processing, vol. 30, pp. 2340–2349, 2021. DOI: https://doi.org/10.1109/TIP.2021.3051462
M. Everingham, S. M. A. Eslami, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman, "The Pascal Visual Object Classes Challenge: A Retrospective," International Journal of Computer Vision, vol. 111, no. 1, pp. 98–136, Jan. 2015. DOI: https://doi.org/10.1007/s11263-014-0733-5
A. Song and Y. Kim, "Semantic Segmentation of Remote-Sensing Imagery Using Heterogeneous Big Data: International Society for Photogrammetry and Remote Sensing Potsdam and Cityscape Datasets," ISPRS International Journal of Geo-Information, vol. 9, no. 10, Oct. 2020, Art. no. 601. DOI: https://doi.org/10.3390/ijgi9100601
S. Randhawa, E. Aygün, G. Randhawa, B. Herfort, S. Lautenbach, and A. Zipf, "Paved or unpaved? A deep learning derived road surface global dataset from mapillary street-view imagery," ISPRS Journal of Photogrammetry and Remote Sensing, vol. 223, pp. 362–374, May 2025. DOI: https://doi.org/10.1016/j.isprsjprs.2025.02.020
A. Ziryawulawo, N. Mduma, M. Lyimo, A. Mbarebaki, R. Madanda, and A. Sam, "An Integrated Deep Learning-based Lane Departure Warning and Blind Spot Detection System: A Case Study for the Kayoola Buses," in 2023 First International Conference on the Advancements of Artificial Intelligence in African Context, Arusha, Tanzania, 2023, pp. 1–8. DOI: https://doi.org/10.1109/AAIAC60008.2023.10465276
A. Musa, M. Hamada, and M. Hassan, "A Theoretical Framework Towards Building a Lightweight Model for Pothole Detection using Knowledge Distillation Approach," SHS Web of Conferences, vol. 139, May 2022, Art. no. 03002. DOI: https://doi.org/10.1051/shsconf/202213903002
N. Jegham, C. Y. Koh, M. Abdelatti, and A. Hendawi, "YOLO Evolution: A Comprehensive Benchmark and Architectural Review of YOLOv12, YOLO11, and Their Previous Versions." arXiv, Mar. 17, 2025. DOI: https://doi.org/10.2139/ssrn.5175639
R. Kumar, D. S. Reddy, and P. Rajalakshmi, "DriveIndia: An Object Detection Dataset for Diverse Indian Traffic Scenes." arXiv, Aug. 26, 2025. DOI: https://doi.org/10.1109/ITSC60802.2025.11423478
M. N. Baig, R. Hajong, M. M. Patwary, M. S. Rahman, and H. A. Chowdhury, "BadODD: Bangladeshi Autonomous Driving Object Detection Dataset." arXiv, Jan. 19, 2024.
P. Tan, Z. Wang, and X. Chang, "Road Obstacle Detection Method Based on Improved YOLOv5," Algorithms, vol. 18, no. 6, May 2025, Art. no. 300. DOI: https://doi.org/10.3390/a18060300
M. E. Irhebhude, M. T. Ahmed, I. A. Ibrahim, and I. Shuaibu, "Real-Time YOLOv5-Based Object Detection for Autonomous Vehicles on Nigerian Roads," International Journal of Recent Advances in Multidisciplinary Topics, vol. 6, no. 12, pp. 19–25, Dec. 2025. DOI: https://doi.org/10.65138/ijramt.2025.v6i12.3168
"Photo by Bobby Randu on Pexels." Pexels. https://www.pexels.com/photo/man-riding-bicycle-on-street-20818748/.
"Photo by Henning Borgersen on Unsplash." Unsplash. https://unsplash.com/photos/brown-deer-crossing-on-pathway-dP5tzqn2Jjg.
"Open Images Dataset V6." Googleapis, [Online]. Available: https://storage.googleapis.com/openimages/web/factsfigures.html.
E. C. Nnadozie, P. Casaseca-de-la-Higuera, O. Iloanusi, O. Ani, and C. Alberola-López, "Simplifying YOLOv5 for deployment in a real crop monitoring setting," Multimedia Tools and Applications, vol. 83, no. 17, pp. 50197–50223, May 2024. DOI: https://doi.org/10.1007/s11042-023-17435-x
P. Gupta, N. Vadgaonkar, J. Nirmal, and N. Mehendale, "A hybrid CNN–ViT framework for skin disease classification via feature extraction and selection," Neural Computing and Applications, vol. 37, no. 32, pp. 27151–27177, Nov. 2025. DOI: https://doi.org/10.1007/s00521-025-11664-x
S. Sultana, B. Ahmed, M. Paul, M. R. Islam, and S. Ahmad, "Vision-Based Robust Lane Detection and Tracking in Challenging Conditions," IEEE Access, vol. 11, pp. 67938–67955, 2023. DOI: https://doi.org/10.1109/ACCESS.2023.3292128
N. Aboudeshish, D. Ignatov, and R. Timofte, "AugmentGest: Can Random Data Cropping Augmentation Boost Gesture Recognition Performance?" arXiv, June 08, 2025.
A. S. Geetha, M. A. R. Alif, M. Hussain, and P. Allen, "Comparative Analysis of YOLOv8 and YOLOv10 in Vehicle Detection: Performance Metrics and Model Efficacy," Vehicles, vol. 6, no. 3, pp. 1364–1382, Aug. 2024. DOI: https://doi.org/10.3390/vehicles6030065
G. Jocher, J. Qiu, and A. Chaurasia. "Ultralytics YOLO." GitHub. https://github.com/ultralytics/ultralytics.
Z. Chen, Y. Fang, J. Yin, S. Lv, F. Sheikh Muhammad, and L. Liu, "A novel lightweight YOLOv8-PSS model for obstacle detection on the path of unmanned agricultural vehicles," Frontiers in Plant Science, vol. 15, Dec. 2024, Art. no. 1509746. DOI: https://doi.org/10.3389/fpls.2024.1509746
I. Katsamenis et al., "DORIE: Dataset of Road Infrastructure Elements—A Benchmark of YOLO Architectures for Real-Time Patrol Vehicle Monitoring," Sensors, vol. 25, no. 21, Oct. 2025, Art. no. 6653. DOI: https://doi.org/10.3390/s25216653
S. A. Dhinakar Raj, A. Singh, T. S. Shekhawat, M. M. M, and K. Sivasankaran, "Collision Avoidance System using YOLO-based Object Detection and Distance Estimation," in 2025 3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, Bengaluru, India, 2025, pp. 178–184. DOI: https://doi.org/10.1109/IDCIOT64235.2025.10915167
I. J. Ratul, Y. Zhou, and K. Yang, "Accelerating Deep Learning Inference: A Comparative Analysis of Modern Acceleration Frameworks," Electronics, vol. 14, no. 15, July 2025, Art. no. 2977. DOI: https://doi.org/10.3390/electronics14152977
N. M. Alahdal, F. Abukhodair, L. H. Meftah, and A. Cherif, "Real-time Object Detection in Autonomous Vehicles with YOLO," Procedia Computer Science, vol. 246, pp. 2792–2801, Jan. 2024. DOI: https://doi.org/10.1016/j.procs.2024.09.392
Downloads
How to Cite
License
Copyright (c) 2026 Rumbidzai Muzata, Celestin Nkundineza, James Kuria Kimotho
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
