Automated Detection of Faults in Wastewater Pipes from CCTV Footage by Using Random Forests

Myrans, Joshua; Kapelan, Zoran; Everson, Richard

doi:10.1016/j.proeng.2016.07.416

Cited by 31 publications

(7 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Maximally stable external regions (MSER) is applied to extract text features from images [28]. The GIST feature descriptor is also applied and sometimes achieves better performance than HOG and SIFT [29,30]. Nevertheless, extracting features based on designed descriptors requires large amount of time and efforts to design descriptors, which may not be generic for other datasets.…”

Section: Conventional Computer Vison and Machine Learning Based Methodsmentioning

confidence: 99%

Automated sewer pipe defect tracking in CCTV videos based on defect detection and metric learning

Wang

Kumar

Cheng

2021

Automation in Construction

View full text Add to dashboard Cite

Section: Conventional Computer Vison and Machine Learning Based Methodsmentioning

confidence: 99%

Automated sewer pipe defect tracking in CCTV videos based on defect detection and metric learning

Wang

Kumar

Cheng

2021

Automation in Construction

View full text Add to dashboard Cite

“…Since the study used only HOG features, the variation of defects with different orientations and shapes degrades the performance. In another approach, Myron tackles the multi-scale GIST features and supplies them to a random forest classifier [27]. The approach profits from the GIST features that reduce the dimensionality of footage while preserving the original features that describe a frame's state.…”

Section: Defect Detection Robotmentioning

confidence: 99%

Multi‐sensors in‐line inspection robot for pipe flaws detection

Chen

Rajkumar

2020

IET Science, Measurement & Technology

View full text Add to dashboard Cite

“…Layers of features, which are not designed by engineers of a specific field, are used for general-purpose learning. Some studies have automatically detected defects from CCTV footage using these advantages [12][13][14], but they were limited to functional defects inside pipes such as cracks, deposits, and tree roots. These studies used software applications to investigate the types of defects that can be identified using existing CCTVs.…”

Section: Introductionmentioning

confidence: 99%

Determination of Internal Elevation Fluctuation from CCTV Footage of Sanitary Sewers Using Deep Learning

Yoo

Koo

et al. 2021

Water

View full text Add to dashboard Cite

The slope of sewer pipes is a major factor for transporting sewage at designed flow rates. However, the gradient inside the sewer pipe changes locally for various reasons after construction. This causes flow disturbances requiring investigation and appropriate maintenance. This study extracted the internal elevation fluctuation from closed-circuit television investigation footage, which is required for sanitary sewers. The principle that a change in water level in sewer pipes indirectly indicates a change in elevation was applied. The sewage area was detected using a convolutional neural network, a type of deep learning technique, and the water level was calculated using the geometric principles of circles and proportions. The training accuracy was 98%, and the water level accuracy compared to random sampling was 90.4%. Lateral connections, joints, and outliers were removed, and a smoothing method was applied to reduce data fluctuations. Because the target sewer pipes are 2.5 m concrete reinforced pipes, the joint elevation was determined every 2.5 m so that the internal slope of the sewer pipe would consist of 2.5 m linear slopes. The investigative method proposed in this study is effective with high economic feasibility and sufficient accuracy compared to the existing sensor-based methods of internal gradient investigation.

show abstract

Automated Detection of Faults in Wastewater Pipes from CCTV Footage by Using Random Forests

Cited by 31 publications

References 5 publications

Automated sewer pipe defect tracking in CCTV videos based on defect detection and metric learning

Automated sewer pipe defect tracking in CCTV videos based on defect detection and metric learning

Multi‐sensors in‐line inspection robot for pipe flaws detection

Determination of Internal Elevation Fluctuation from CCTV Footage of Sanitary Sewers Using Deep Learning

Contact Info

Product

Resources

About