Explainable Deep Anomaly Detection with Sequential Hypothesis Testing for Robotic Sewer Inspection

2025-07-30

AI Summary

To address the low efficiency and high false-alarm rate of manual CCTV-based inspection for sewer pipe leaks and blockages, this paper proposes an automated anomaly detection method integrating interpretable deep learning with Sequential Probability Ratio Testing (SPRT). The method first employs a spatially interpretable anomaly detection model to localize and attribute defects at the single-frame level; subsequently, SPRT dynamically accumulates temporal evidence across multiple frames to make robust sequential decisions, balancing fine-grained localization with noise resilience. Its key innovation lies in embedding model interpretability directly into the detection pipeline and tightly coupling spatial discrimination with temporal reasoning, thereby significantly enhancing detection accuracy and stability under complex field conditions. Experiments on real-world sewer inspection tasks demonstrate that the system achieves superior accuracy and F1-score compared to state-of-the-art baseline methods, confirming its practical viability for engineering deployment.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Interpretability, Explainability, and Transparency
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Sewer pipe faults, such as leaks and blockages, can lead to severe consequences including groundwater contamination, property damage, and service disruption. Traditional inspection methods rely heavily on the manual review of CCTV footage collected by mobile robots, which is inefficient and susceptible to human error. To automate this process, we propose a novel system incorporating explainable deep learning anomaly detection combined with sequential probability ratio testing (SPRT). The anomaly detector processes single image frames, providing interpretable spatial localisation of anomalies, whilst the SPRT introduces temporal evidence aggregation, enhancing robustness against noise over sequences of image frames. Experimental results demonstrate improved anomaly detection performance, highlighting the benefits of the combined spatiotemporal analysis system for reliable and robust sewer inspection.

Problem

• Automate sewer pipe fault detection using deep learning
• Improve anomaly detection robustness with temporal analysis
• Provide interpretable spatial localization of sewer anomalies

Innovation

• Explainable deep learning for anomaly detection
• Sequential probability ratio testing (SPRT)
• Spatiotemporal analysis for robust inspection