Semi-Supervised Pipe Video Temporal Defect Interval Localization
This addresses the need for accurate defect localization in sewer pipe inspections, reducing annotation costs and adapting to domain-specific challenges, though it is incremental as it builds on existing semi-supervised and weakly supervised techniques.
The study tackled the problem of temporal defect localization in sewer pipe CCTV inspection by introducing a semi-supervised method that leverages unlabeled data and visual odometry, achieving a 41.89% average precision and an 8.14% improvement over state-of-the-art methods.
In sewer pipe Closed-Circuit Television (CCTV) inspection, accurate temporal defect localization is essential for effective defect classification, detection, segmentation and quantification. Industry standards typically do not require time-interval annotations, even though they are more informative than time-point annotations for defect localization, resulting in additional annotation costs when fully supervised methods are used. Additionally, differences in scene types and camera motion patterns between pipe inspections and Temporal Action Localization (TAL) hinder the effective transfer of point-supervised TAL methods. Therefore, this study introduces a Semi-supervised multi-Prototype-based method incorporating visual Odometry for enhanced attention guidance (PipeSPO). PipeSPO fully leverages unlabeled data through unsupervised pretext tasks and utilizes time-point annotated data with a weakly supervised multi-prototype-based method, relying on visual odometry features to capture camera pose information. Experiments on real-world datasets demonstrate that PipeSPO achieves 41.89% average precision across Intersection over Union (IoU) thresholds of 0.1-0.7, improving by 8.14% over current state-of-the-art methods.