VideoPipe Challenge @ ICPR2022

Challenge on Real-World Video Understanding for Urban Pipe Inspection
Sunday 21th August 2022

Task 1: Video Defect Classification Task 2: Temporal Defect Localization

NEWS

  • 2022-05-19
    • The leader board is released. Thanks for participation in our challenge.
    • We list the top results on the Results Page , and technical reports of top solutions in two tracks can now be downloaded .
  • 2022-03-01
    • We have published competitions for Track 1: Video Defect Classification, Track 2: Temporal Defect Localization. Competitions start at March 5, 2022, midnight UTC and finish at May 5, 2022, 11:59 p.m. UTC.
    • Data for training and validation is now available on the competition pages above. Registration for the competition begins on March 1, 2022.
  • 2022-2-28
    • The QV-Pipe dataset and CCTV-Pipe dataset can be downloaded from competition page. [QV-Pipe] [CCTV-Pipe]

Challenge abstract

Video understanding is an important problem in computer vision. Currently, the well-studied task in this problem 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 to bring new opportunities and challenges for video understanding in smart city and beyond.

Video Defect Classification: Predicting the categories of pipe defects in a short QV video.

Temporal Defect Localization: Finding the temporal locations of pipe detects and recognizing their corresponding categories in a long CCTV video.

The challenge has set up cash prize for winner teams.

Track 1: Video Defect Classification The 1st place winner will receive $1,500 + Certificate ;
The 2nd place prize of $500 + Certificate ;
The 3rd place prize of $250 + Certificate .
Track 2: Temporal Defect Localization The 1st place winner will receive $1,500 + Certificate ;
The 2nd place prize of $500 + Certificate ;
The 3rd place prize of $250 + Certificate .

Attending the Workshop

ICPR 2022 will primarily be held in person in Montreal, QC, but remote presentations and attendance will be accommodated.The workshop will be held on Sunday 21th August 2022 as a half-day event. Please refer to this page for more information.