VideoPipe 2022 Challenge: Real-World Video Understanding for Urban Pipe Inspection

TL;DR

This paper introduces two new video benchmarks, QV-Pipe and CCTV-Pipe, for industrial anomaly detection in urban pipe systems, shifting focus from traditional action recognition to complex defect analysis.

Contribution

It presents novel datasets and competition tracks for real-world urban pipe anomaly detection, advancing video understanding in industrial and smart city applications.

Findings

Two high-quality datasets released for urban pipe defect detection

Established evaluation metrics and competition tracks for defect classification and localization

Encourages research on complex, multi-labeled industrial video anomalies

Abstract

Video understanding is an important problem in computer vision. Currently, the well-studied task in this research is human action recognition, where the clips are manually trimmed from the long videos, and a single class of human action is assumed for each clip. However, we may face more complicated scenarios in the industrial applications. For example, in the real-world urban pipe system, anomaly defects are fine-grained, multi-labeled, domain-relevant. To recognize them correctly, we need to understand the detailed video content. For this reason, we propose to advance research areas of video understanding, with a shift from traditional action recognition to industrial anomaly analysis. In particular, we introduce two high-quality video benchmarks, namely QV-Pipe and CCTV-Pipe, for anomaly inspection in the real-world urban pipe systems. Based on these new datasets, we will host two competitions including (1) Video Defect Classification on QV-Pipe and (2) Temporal Defect Localization on CCTV-Pipe. In this report, we describe the details of these benchmarks, the problem definitions of competition tracks, the evaluation metric, and the result summary. We expect that, this competition would bring new opportunities and challenges for video understanding in smart city and beyond. The details of our VideoPipe challenge can be found in https://videopipe.github.io.