Real-Time Out of Distribution Detection in 2D Object Detection for Autonomous Cars

Year 2025, Volume: 5 Issue: 1st Future of Vehicles Conf., 28 - 36, 28.12.2025

Lorant Szabo , Zoltán Weltsch , Andrea Major

https://doi.org/10.64808/engineeringperspective.1814718

Abstract

The development of autonomous transportation systems represents a critical step toward achieving intelligent and reliable mobility. Ensuring accurate, real-time environmental perception and the robust detection of unexpected or rare events remains a major challenge for autonomous vehicles operating in complex and dynamic environments. To address this, we propose a novel processing pipeline that constructs Bird’s Eye View (BEV) representations from raw 3D LiDAR point clouds using both intensity and height map channels, thereby retaining essential geometric and reflective features. On top of these BEV representations, an optimized YOLOv11-based deep learning model is applied for high-precision object detection. A key contribution of our work is the integration of a real-time Out-of-Distribution (OOD) detection module, which employs lightweight statistical techniques in conjunction with learned feature representations to ensure minimal computational overhead while maintaining operational robustness. The proposed architecture enables the reliable identification of standard traffic objects as well as the detection of atypical or previously unseen events, such as overturned vehicles or unknown obstacles. Experimental evaluation on representative driving scenarios demonstrates that our method achieves approximately 95% detection accuracy, outperforming conventional baselines in both speed and reliability. Overall, the results highlight the potential of combining state-of-the-art deep neural detection frameworks with efficient, statistically grounded OOD analysis for enhancing the safety and trustworthiness of autonomous vehicle perception systems.

Keywords

Autonomous Driving , Object Detection , LiDAR , Bird’s-Eye View (BEV) , Out-of-Distribution (OOD) Detection , YOLO , Real-Time Systems

References

• 1. Ali, M. L., & Zhang, Z. (2024). The YOLO framework: A compre-hensive review of evolution, applications, and benchmarks in object detection. Computers, 13(12), 336. https://doi.org/10.3390/computers13120336
• 2. Jin, X., Yang, H., He, X., Liu, G., Yan, Z., & Wang, Q. (2023). Ro-bust LiDAR-based vehicle detection for on-road autonomous driving. Remote Sensing, 15(12), 3160. https://doi.org/10.3390/rs15123160
• 3. Li, H., Sima, C., Dai, J., Wang, W., Lu, L., Wang, H., ... & Qiao, Y. (2023). Delving into the devils of bird’s-eye-view perception: A re-view, evaluation and recipe. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(4), 2151-2170. https://doi.org/10.1109/TPAMI.2023.3333838
• 4. Shen, J., Fang, Z., & Huang, J. (2025). Point-Level Fusion and Channel Attention for 3D Object Detection in Autonomous Driving. Sensors, 25(4), 1097. https://doi.org/10.3390/s25041097
• 5. Shao, Y., Tan, A., Sun, Z., Zheng, E., Yan, T., & Liao, P. (2023). PV-SSD: A Multi-Modal Point Cloud Feature Fusion Method for Projection Features and Variable Receptive Field Voxel Features. arXiv preprint arXiv:2308.06791. https://doi.org/10.48550/arXiv.2308.0679
• 6. Wang, J., Zhu, M., Sun, D., Wang, B., Gao, W., & Wei, H. (2019). MCF3D: Multi-stage complementary fusion for multi-sensor 3D ob-ject detection. IEEE Access, 7, 90801-90814. https://doi.org/10.1109/ACCESS.2019.2927012
• 7. Khanam, R., & Hussain, M. (2024). Yolov11: An overview of the key architectural enhancements. arXiv preprint arXiv:2410.17725. https://doi.org/10.48550/arXiv.2410.17725
• 8. Wang, C. Y., Yeh, I. H., & Mark Liao, H. Y. (2024, September). Yolov9: Learning what you want to learn using programmable gradi-ent information. In European conference on computer vision (pp. 1-21). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72751-1_1
• 9. Wang, C. Y., & Liao, H. Y. M. (2024). YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systems. APSIPA Transactions on Signal and Information Processing, 13(1). https://doi.org/10.1561/116.20240058
• 10. Huang, Z., Zhao, Y., Xiao, H., Wu, C., & Ge, L. (2025). Du-oSpaceNet: Leveraging Both Bird's-Eye-View and Perspective View Representations for 3D Object Detection. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 2560-2570). https://doi.org/10.48550/arXiv.2405.10577
• 11. Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019, Ju-ly). Optuna: A next-generation hyperparameter optimization frame-work. In Proceedings of the 25th ACM SIGKDD international con-ference on knowledge discovery & data mining (pp. 2623-2631). https://doi.org/10.1145/3292500.3330701
• 12. Chen, A., Chow, A., Davidson, A., Ghodsi, A., Hong, S. A., Kon-winski, A., Murching, S., Nykodym, T., Ogilvie, P., Parkhe, M., Xie, F., & Zumar, C. (2020). Developments in mlflow: A system to accel-erate the machine learning lifecycle. In Proceedings of the fourth in-ternational workshop on data management for end-to-end machine learning (pp. 1-4). https://doi.org/10.1145/3399579.3399867
• 13. Lin, T. Y., Maire, M., Belongie, S., Hays, J., & Zitnick, C. L. Mi-crosoft coco: Common objects in context, European Conf. Computer Vision (Springer, Cham, 2014), 740-755. https://doi.org/10.1007/978-3-319-10602-1_48
• 14. Zhang, H., Cisse, M., Dauphin, Y. N., & Lopez-Paz, D. (2017). mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412. https://doi.org/10.48550/arXiv.1710.09412
• 15. Kingma, D. P., & Ba, J. (2017). Adam: A method for stochastic op-timization. https://doi.org/10.48550/arXiv.1412.6980
• 16. Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regular-ization. https://doi.org/10.48550/arXiv.1711.05101
• 17. Hosang, J., Benenson, R., & Schiele, B. (2017). Learning non-maximum suppression. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4507-4515). https://doi.org/10.48550/arXiv.1705.02950
• 18. Miyai, A., Yang, J., Zhang, J., Ming, Y., Lin, Y., Yu, Q., ... & Ai-zawa, K. (2024). Generalized out-of-distribution detection and be-yond in vision language model era: A survey. arXiv preprint arXiv:2407.21794. https://doi.org/10.48550/arXiv.2407.21794
• 19. Veeramacheneni, L., & Valdenegro-Toro, M. (2022). A Benchmark for Out of Distribution Detection in Point Cloud 3D Semantic Seg-mentation. arXiv preprint arXiv:2211.06241. https://doi.org/10.48550/arXiv.2211.06241
• 20. Hodge, V., & Austin, J. (2004). A survey of outlier detection meth-odologies. Artificial intelligence review, 22(2), 85-126. https://doi.org/10.1023/B:AIRE.0000045502.10941.a9
• 21. Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM computing surveys (CSUR), 41(3), 1-58. https://doi.org/10.1145/1541880.1541882
• 22. Muhr, D., Affenzeller, M., & Küng, J. (2023). A probabilistic trans-formation of distance-based outliers. Machine Learning and Knowledge Extraction, 5(3). https://doi.org/10.3390/make5030042
• 23. Binzat, U., & Yıldıztepe, E. (2023). The adjusted histogram-based outlier score-AHBOS. Mugla Journal of Science and Technology, 9(1), 92-100. https://doi.org/10.22531/muglajsci.1252876
• 24. Aggarwal, C. C. (2017). Outlier analysis. Springer. https://doi.org/10.1007/978-3-319-47578-3
• 25. Lu, S., Wang, Y., Sheng, L., He, L., Zheng, A., & Liang, J. (2025). Out-of-distribution detection: A task-oriented survey of recent ad-vances. ACM Computing Surveys, 58(2), 1-39. https://doi.org/10.48550/arXiv.2409.11884
• 26. Kösel, M., Schreiber, M., Ulrich, M., Gläser, C., & Dietmayer, K. (2024, June). Revisiting out-of-distribution detection in lidar-based 3d object detection. In 2024 IEEE Intelligent Vehicles Symposium (IV) (pp. 2806-2813). IEEE. https://doi.org/10.1109/IV55156.2024.10588849
• 27. Yuhas, M., & Easwaran, A. (2022). Demo abstract: Real-time out-of-distribution detection on a mobile robot. arXiv preprint arXiv:2211.11520. https://doi.org/10.48550/arXiv.2211.11520