Home⇛SMN Digest⇛vol. 10 no. 2 (2024)

Autoassess AI: Vision-Based Car Damage Assessment Using Deep Learning

Maria Carmelle Pedrosa | Brenda A. Quismorio | Elmer Peramo

Discipline: Artificial Intelligence

 

Abstract:

This study addresses the need for an automated car damage assessment system to reduce processing time and increase throughput at the XYZ1 repair center, a facility currently reliant on manual, time-intensive evaluations. To meet this need, the researcher developed a modular AI-based solution leveraging computer vision and deep learning, specifically targeting damage location, type, and severity classification. The solution utilized EfficientNetV2B0 and MobileNetV2 models for location and severity classification, and YOLOv8 (You Only Look Once) for damage type detection. These models were trained and evaluated on a curated dataset of car damage images, meeting technical success criteria for accuracy, F1 score, and mean Average Precision (mAP). EfficientNetV2B0 achieved a 92% F1 score for location classification, while YOLOv8s achieved a 74.3% mAP in damage type detection. YOLOv8s performed well with visually distinct damages but faced challenges with subtle damage types, such as cracks. This AI-driven solution shows potential for improving operational efficiency, aligning with XYZ’s goal of streamlining damage assessments, enhancing customer experience, and setting a new standard in automotive repair services.



References:

  1. Aggarwal, A., Kumar, V., & Gupta, R. (2023). Object Detection Based Approaches in Image Classification: A Brief Overview. 2023 IEEE Guwahati Subsection Conference (GCON), pp. 1-6. IEEE. 10.1109/GCON58516.2023.10183609
  2. Aziz, L., Haji Salam, S. B., Sheikh, U. U., & Ayub, S. (2020, September). Exploring Deep Learning-Based Architecture, Strategies, Applications and Current Trends in Generic Object Detection: A Comprehensive Review. IEEE Access, vol. 8, pp. 170461-170495. IEEE. 10.1109/ACCESS.2020.3021508
  3. Barrow, H. G., & Tenenbaum, J. M. (1981, May). Computational vision. Proceedings of the IEEE, 69(5), pp. 572-595. IEEE. 10.1109/PROC.1981.12026
  4. Bhumbla, S., Gupta, D. K., & Nisha. (2023). A Review: Object Detection Algorithms. 2023 Third International Conference on Secure Cyber Computing and Communication (ICSCCC), pp. 827-832. IEEE. 10.1109/ICSCCC58608.2023.10176865
  5. Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei Fei, L. (2009). ImageNet: A large-scale hierarchical image database. 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248-255. 10.1109/CVPR.2009.5206848
  6. Freenergi, A. (2019, July 12). Convolutional Neural Network for Object Recognition and Detection. Medium. Retrieved March 27, 2024, from https://medium.com/@ringlayer/convolutional-neural-network-for-object-recognition-and-detection-126a22af8975
  7. Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. 2014 IEEE Conference on Computer Vision and Pattern Recognition, 580-587. IEEE. https://doi.org/10.1109/CVPR.2014.81
  8. Gomede, E. (2023, November 9). Understanding R-CNN: A Revolution in Object Detection Medium. Retrieved March 27, 2024, from https://medium.com/@evertongomede/understanding-r-cnn-a-revolution-in-object-detection-a02c2754218c
  9. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press. http://www.deeplearningbook.org
  10. Malik, H. S., Dwivedi, M., Omakar, S. N., Samal, S. R., Rathi, A., Monis, E. B., Khanna, B., & Tiwari, A. (2020). Deep Learning Based Car Damage Classification and Detection. EasyChair Preprint.
  11. Qaddour, J., & Siddiqa, S. A. (2023). Automatic damaged vehicle estimator using enhanced deep learning algorithm. Intelligent Systems with Applications, vol. 18 https://doi.org/10.1016/j.iswa.2023.200192
  12. Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You Only Look Once: Unified, Real-Time Object Detection. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 779-788. IEEE. https://doi.org/10.1109/CVPR.2016.91
  13. Rosenfeld, A. (1988, August). Computer vision: basic principles. Proceedings of the IEEE, 76(8), pp. 863-868. IEEE. 10.1109/5.5961
  14. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4510-4520. 10.1109/CVPR.2018.00474
  15. Shorten, C., & Khoshgoftaar, T. M. (2019, July). A survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6. https://doi.org/10.1186/s40537-019-0197-0
  16. Tan, M., & Le, Q. V. (2021). EfficientNetV2: Smaller Models and Faster Training. International Conference on Machine Learning, pp. 10096-10106. https://doi.org/10.48550/arXiv.2104.00298
  17. Van Ruitenbeek, R. E., & Bhulai, S. (2022). Convolutional Neural Networks for vehicle damage detection. Machine Learning with Applications. https://doi.org/10.1016/j.mlwa.2022.100332
  18. Wang, X., Li, W., & Wu, Z. (2023). CarDD: A New Dataset for Vision-Based Car Damage Detection. IEEE Transactions on Intelligent Transportation Systems, 24(7), pp. 7202-7214. 10.1109/TITS.2023.3258480
  19. Weights & Biases. (2024). Weights & Biases Docs. Weights & Biases Documentation: W&B Docs. Retrieved June 16, 2024, from https://docs.wandb.ai/.
  20. Zhu, Q., Liu, Y., Shen, Y., & Zhao, Z. (2021). Research on Intelligent Damage Assessment System for Time-sharing Rental Vehicles Based on Image Recognition. Journal of Physics. 10.1088/1742-6596/1880/1/012012

Tools


Copyright © 2025  KITE Digital Educational Solutions |  Exclusively distributed by CE-Logic