Call For Paper - Upcoming Conferences
Research Article | Open Access | Download PDF
Volume 13 | Issue 4 | Year 2026 | Article Id. IJECE-V13I4P117 | DOI : https://doi.org/10.14445/23488549/IJECE-V13I4P117

Size Synergistic Optimization of Preprocessing and Data Augmentation for Accelerated Convergence in YOLO11-based Vehicle Detection

Ashish K. Sarvaiya, Mehul K. Vala, Brijesh R. Solanki, Amit C Rathod, Hitesh R. Khunt

Received Revised Accepted Published
12 Jan 2026 14 Feb 2026 17 Mar 2026 30 Apr 2026

Citation :

Ashish K. Sarvaiya, Mehul K. Vala, Brijesh R. Solanki, Amit C Rathod, Hitesh R. Khunt, "Size Synergistic Optimization of Preprocessing and Data Augmentation for Accelerated Convergence in YOLO11-based Vehicle Detection," International Journal of Electronics and Communication Engineering, vol. 13, no. 4, pp. 212-221, 2026. Crossref, https://doi.org/10.14445/23488549/IJECE-V13I4P117

Abstract

The performance and training efficiency of real-time object detectors depend not only on architectural design but also critically on the quality and diversity of the training data. While recent developments in the YOLO family emphasize architectural and optimization-level improvements, the systematic role of offline data preprocessing and augmentation for emerging architectures such as YOLO11 remains underexplored. This paper presents a data-centric investigation into the impact of multiple preprocessing and augmentation pipelines on the convergence behavior and detection accuracy of YOLO11 for urban vehicle detection. A custom-curated dataset comprising 3,757 images with 10,152 manually verified annotations across four vehicle classes (Bus, Car, Motorcycle, and Truck) is employed. Five distinct preprocessing pipelines are evaluated using a controlled experimental framework implemented via the Roboflow platform, with all online augmentations disabled to isolate offline data effects. Experimental results demonstrate that a synergistic pipeline combining Auto-Adjust Contrast, geometric Shear, and controlled Gaussian Noise achieves a peak mAP@50 of 93.8% while reducing convergence time by 21.3% compared to a baseline configuration. Detailed ablation and class-wise analyses confirm that the observed improvements are systematic rather than stochastic, underscoring the critical role of data-centric optimization in accelerating YOLO11 training and improving robustness in intelligent transportation systems.

Keywords

Object Detection, YOLO11, Data Augmentation, Preprocessing, Roboflow.

References

  1. Zhong-Qiu Zhao et al., “Object Detection with Deep Learning: A Review,” IEEE Transactions on Neural Networks and Learning Systems, vol. 30, no. 11, pp. 3212-3232, 2019.
    [    CrossRef] [Google Scholar] [Publisher Link]
  2. Joseph Redmon et al., “You Only Look Once: Unified, Real-Time Object Detection,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 779-788, 2016.
    [    CrossRef] [Google Scholar] [Publisher Link]
  3. Alexey Bochkovskiy, Chien-Yao Wang, and Hong-Yuan Mark Liao, “YOLOv4: Optimal Speed and Accuracy of Object Detection,” arXiv preprint, pp. 1-17, 2020.
    [    CrossRef] [Google Scholar] [Publisher Link]
  4. YOLOv8: A New State-of-the-Art Computer Vision Model, Roboflow, 2023. [Online]. Available: https://yolov8.com/
  5. Ao Wang et al., “YOLOv10: Real-Time End-to-End Object Detection,” arXiv preprint, pp. 1-21, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  6. S. Nikhileswara Rao, YOLOv11 Architecture Explained: Next-Level Object Detection with Enhanced Speed and Accuracy, Medium, 2024. [Online]. Available: https://medium.com/@nikhil-rao-20/yolov11-explained-next-level-object-detection-with-enhanced-speed-and-accuracy-2dbe2d376f71
  7. Connor Shorten, and Taghi M. Khoshgoftaar, “A Survey on Image Data Augmentation for Deep Learning,” Journal of Big Data, vol. 6, pp. 1-48, 2019.
    [    CrossRef] [Google Scholar] [Publisher Link]
  8. Shaoqing Ren et al., “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, no. 6, pp. 1137-1149, 2017.
    [    CrossRef] [Google Scholar] [Publisher Link]
  9. Glenn Jocher et al., “ultralytics/yolov5: v6.2 - YOLOv5 Classification Models, Apple M1, Reproducibility, ClearML and Deci.ai integrations,” Zenodo, 2022.
    [    CrossRef] [Google Scholar] [Publisher Link]
  10. Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao, “YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors,” 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada, pp. 7464-7475, 2023. [CrossRef] [Google Scholar] [Publisher Link]
  11. Explore Ultralytics YOLOv8, Ultralytics, 2023. [Online]. Available: https://docs.ultralytics.com/models/yolov8/
  12. Gang Liu et al., “RFCS-YOLO: Target Detection Algorithm in Adverse Weather Conditions via Receptive Field Enhancement and Cross-Scale Fusion,” Sensors, vol. 25, no. 3, pp. 1-20, 2025.
    [    CrossRef] [Google Scholar] [Publisher Link]
  13. Yingkun Song et al., “MEB-YOLO: An Efficient Vehicle Detection Method in Complex Traffic Road Scenes,” Computers, Materials & Continua, vol. 75, no. 3, pp. 5761-5784, 2023.
    [    CrossRef] [Google Scholar] [Publisher Link]
  14. Barret Zoph et al., “Learning Data Augmentation Strategies for Object Detection,” 16th European Conference, Computer Vision – ECCV 2020, Glasgow, UK, vol. 12372, pp. 566-583, 2020.
    [    CrossRef] [Google Scholar] [Publisher Link]
  15. Ekin D. Cubuk et al., “RandAugment: Practical Automated Data Augmentation with a Reduced Search Space,” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 702-703, 2020.
    [    Google Scholar] [Publisher Link]
  16. Haoran Gao, “Vehicle Detection and Tracking Based on YOLO11,” Proceedings of the 2nd International Conference on Data Science and Engineering (ICDSE 2025), pp. 481-486, 2025.
    [    Google Scholar] [Publisher Link]
  17. Chris M. Bishop, “Training with Noise is Equivalent to Tikhonov Regularization,” Neural Computation, vol. 7, no. 1, pp. 108-116, 1995.
    [    CrossRef] [Google Scholar] [Publisher Link]
  18. Jiacheng Li et al., “Road Object Detection of YOLO Algorithm with Attention Mechanism,” Frontiers in Signal Processing, vol. 5, no. 1, pp. 9-16, 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  19. Jinpeng He et al., “Enhancing YOLO for Occluded Vehicle Detection with Grouped Orthogonal Attention and Dense Object Repulsion,” Scientific Reports, vol. 14, pp. 1-15, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  20. Zheng Ge et al., “YOLOX: Exceeding YOLO Series in 2021,” arXiv preprint, pp. 1-7, 2021.
    [    CrossRef] [Google Scholar] [Publisher Link]
  21. Mujadded Al Rabbani Alif, “YOLOv11 for Vehicle Detection: Advancements, Performance, and Applications in Intelligent Transportation Systems,” arXiv preprint, pp. 1-16, 2024.
    [    CrossRef] [Google Scholar] [Publisher Link]
  22. Mark Everingham et al., “The Pascal Visual Object Classes (VOC) Challenge,” International Journal of Computer Vision, vol. 88, pp. 303-338, 2010.
    [    CrossRef] [Google Scholar] [Publisher Link]
  23. Tsung-Yi Lin et al., “Microsoft COCO: Common Objects in Context,” Proceedings of the European Conference on Computer Vision (ECCV), Zurich, Switzerland, pp. 740-755, 2014.
    [    CrossRef] [Google Scholar] [Publisher Link]
  24. Sanghyun Woo et al., “CBAM: Convolutional Block Attention Module,” Proceedings of the European Conference on Computer Vision (ECCV), pp. 3-19, 2018.
    [    Google Scholar] [Publisher Link]
  25. Ramprasaath R. Selvaraju et al., “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization,” Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 618-626, 2017.
    [    Google Scholar] [Publisher Link]