The relevance of this study is determined by the fact that, in road-infrastructure monitoring platforms, errors at the stage of detection and interpretation of object conditions can propagate into normative and managerial decision errors, especially under real-world acquisition conditions (shadows, glare, wet/snow-covered pavement, contamination, and ambiguous defect boundaries), where the risk of misclassification and inaccurate localization increases. This is critical for threshold-based normative assessment, since even small inaccuracies may change the condition category and, consequently, lead either to unjustified maintenance assignments or to missing hazardous defects. Therefore, this paper investigates the use of detection uncertainty for road-surface defect monitoring within a multi-agent pipeline, where observation results are transferred between components together with the processing context via the Model Context Protocol as a unified mechanism for exchanging events, metadata, and interpretation parameters. The main approach is to build a computational pipeline that includes video-data preprocessing, defect detection, computation of the uncertainty indicator H(p) from the class-probability distribution, assignment of the status "automatic/validation/refinement" subsequent normative interpretation, and aggregation over road-network segments. To ensure reproducibility, each run is recorded as a unified "experiment context" (scene/frame identifier, model version, threshold parameters, decision status), enabling comparable mode-to-mode evaluation and auditing of discrepancy causes. Verification is based on comparing normative decisions with expert assessment and analyzing how the share of erroneous normative decisions depends on the automatic-decision threshold for H(p), while the risk-oriented logic routes high-uncertainty detections to validation and reduces the probability of errors in borderline cases. The results show that context logging via Model Context Protocol and accounting for H(p) improve experimental reproducibility and the soundness of normative interpretation, decreasing the risk of incorrect maintenance prioritization by separating ambiguous observations and preserving the decision rationale.
1. Zheng L., Xiao J., Wang Y., et al. Deep learning-based intelligent detection of pavement distress. Automation in Construction. 2024;168. https://doi.org/10.1016/j.autcon.2024.105772
2. Shang J., Zhang A.A., Dong Z., Zhang H., He A. Automated pavement detection and artificial intelligence pavement image data processing technology. Automation in Construction. 2024;168. https://doi.org/10.1016/j.autcon.2024.105797
3. Yang X., Zhang J., Liu W., Jing J., Zheng H., Xu W. Automation in road distress detection, diagnosis and treatment. Journal of Road Engineering. 2024;4(1):1–26. https://doi.org/10.1016/j.jreng.2024.01.005
4. Fani A., Golroo A., Naseri H., Mirhassani S.A., Gandomi A.H. Risk-based pavement maintenance planning considering budget and pavement deterioration uncertainty. Structure and Infrastructure Engineering. 2024;20(10):1437–1450. https://doi.org/10.1080/15732479.2022.2145317
5. Samadzadegan F., Dadrass Javan F., Ashtari Mahini F., Gholamshahi M., Nex F. Automatic Road Pavement Distress Recognition Using Deep Learning Networks from Unmanned Aerial Imagery. Drones. 2024;8(6). https://doi.org/10.3390/drones8060244
6. Hu Y., Chen N., Hou Y., Lin X., Jing B., Liu P. Lightweight deep learning for real-time road distress detection on mobile devices. Nature Communications. 2025;16. https://doi.org/10.1038/s41467-025-59516-5
7. Arya D., Maeda H., Ghosh S.K., Toshniwal D., Sekimoto Y. RDD2022: A multi-national image dataset for automatic road damage detection. Geoscience Data Journal. 2024. https://doi.org/10.1002/gdj3.260
8. He W., Jiang Zh., Xiao T., Xu Z., Li Y. A Survey on Uncertainty Quantification Methods for Deep Learning. arXiv. URL: https://arxiv.org/abs/2302.13425 [Accessed 24th December 2025].
9. Andéol L., Fel Th., de Grancey F., Mossina L. Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling. In: Conformal and Probabilistic Prediction with Applications: Proceedings of Machine Learning Research 204, 13–15 September 2023, Limassol, Cyprus. PMLR; 2023. P. 36–55.
10. Zhang Sh., Bei Zh., Ling T., Chen Q., Zhang L. Research on high-precision recognition model for multi-scene asphalt pavement distresses based on deep learning. Scientific Reports. 2024;14. https://doi.org/10.1038/s41598-024-77173-4
11. Li Y., Miao N., Ma L., Shuang F., Huang X. Transformer for object detection: review and benchmark. Engineering Applications of Artificial Intelligence. 2023;126. https://doi.org/10.1016/j.engappai.2023.107021
12. Huseljic D., Herde M., Hahn P., Müjde M., Sick B. Systematic Evaluation of Uncertainty Calibration in Pretrained Object Detectors. International Journal of Computer Vision. 2025;133:1033–1047. https://doi.org/10.1007/s11263-024-02219-z
13. Schlegel M., Sattler K.-U. Capturing end-to-end provenance for machine learning pipelines. Information Systems. 2025;132. https://doi.org/10.1016/j.is.2024.102495
14. Gireesh E.D., Gurupur V.P. Information Entropy Measures for Evaluation of Reliability of Deep Neural Network Results. Entropy. 2023;25(4). https://doi.org/10.3390/e25040573
15. Abdar M., Pourpanah F., Hussain S., et al. A review of uncertainty quantification in deep learning: techniques, applications and challenges. Information Fusion. 2021;76:243–297. https://doi.org/10.1016/j.inffus.2021.05.008
16. Hildebrand M., Brown A., Brown S., Waslander S.L. Assessing Distribution Shift in Probabilistic Object Detection Under Adverse Weather. IEEE Access. 2023;11:44989–45000. https://doi.org/10.1109/ACCESS.2023.3270447
17. Balanya S.A., Maroñas J., Ramos D. Adaptive temperature scaling for Robust calibration of deep neural networks. Neural Computing and Applications. 2024;36(14):8073–8095. https://doi.org/10.1007/s00521-024-09505-4
18. Gawlikowski J., Tassi C.R.N., Ali M., et al. A survey of uncertainty in deep neural networks. Artificial Intelligence Review. 2023;56(S1):1513–1589. https://doi.org/10.1007/s10462-023-10562-9
19. Yelleni S.H., Kumari D., Srijith P.K., Mohan C.K. Monte Carlo DropBlock for modeling uncertainty in object detection. Pattern Recognition. 2024;146. https://doi.org/10.1016/j.patcog.2023.110003
20. Sharifuzzaman S.A.S.M., Tanveer J., Chen Y., et al. Bayes R-CNN: An Uncertainty-Aware Bayesian Approach to Object Detection in Remote Sensing Imagery for Enhanced Scene Interpretation. Remote Sensing. 2024;16(13). https://doi.org/10.3390/rs16132405
21. Grafberger S., Groth P., Schelter S. Provenance Tracking for End-to-End Machine Learning Pipelines. In: WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023, 30 April – 04 May 2023, Austin, TX, USA. New York: Association for Computing Machinery; 2023. https://doi.org/10.1145/3543873.3587557
22. Ostroukh A.V., Kuftinova N.G., Borzenkov A.M., Podberezkin A.A., Ostroukh I.A. Research on Using Deep Learning for Transport Demand Prediction. In: 2024 Intelligent Technologies and Electronic Devices in Vehicle and Road Transport Complex, 13–15 November 2024, Moscow, Russian Federation. IEEE; 2024. P. 1–5. https://doi.org/10.1109/TIRVED63561.2024.10769599
