Search research articles

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Robot-Based Procedure for 3D Reconstruction of Abdominal Organs Using the Iterative Closest Point and Pose Graph Algorithms.

Journal of imaging·2025

Same author

Reducing Training Data Using Pre-Trained Foundation Models: A Case Study on Traffic Sign Segmentation Using the Segment Anything Model.

Journal of imaging·2024

Same author

Image-Based 3D Reconstruction in Laparoscopy: A Review Focusing on the Quantitative Evaluation by Applying the Reconstruction Error.

Journal of imaging·2024

Same author

Fused Projection-Based Point Cloud Segmentation.

Sensors (Basel, Switzerland)·2022

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Improving Sewer Damage Inspection: Development of a Deep Learning Integration Concept for a Multi-Sensor System.

Jan Thomas Jung^1,2, Alexander Reiterer^1,2

¹Department of Sustainable Systems Engineering, University of Freiburg, Georges-Köhler-Allee 10, 79110 Freiburg im Breisgau, Germany.

Sensors (Basel, Switzerland)

|December 17, 2024

Summary

This study introduces a new multi-sensor robot and deep learning approach for automated sewer pipe inspection. The system enhances data quality and accuracy in detecting pipe damage, improving urban infrastructure maintenance.

Keywords:

3D vision LiDAR artificial intelligence automated inspection computer vision damage detection point cloud robotic inspection sewer pipes urban infrastructure

More Related Videos

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Related Experiment Videos

Last Updated: Jun 4, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Area of Science:

Robotics and Automation
Artificial Intelligence
Civil Engineering

Background:

Sewer pipe maintenance is crucial for urban infrastructure but relies on manual, error-prone methods.
Current AI-powered sewer inspection robots lack sufficient data quality for reliable deep learning (DL) model training.
Existing vision-based systems struggle with comprehensive data capture and accurate damage assessment.

Purpose of the Study:

To develop a novel multi-sensor robotic system integrated with a deep learning (DL) concept for automated sewer inspection.
To overcome the data quality limitations of current vision-based inspection robots.
To improve the reliability and accuracy of sewer pipe damage detection and quantification.

Main Methods:

A comprehensive review of 2D (image) and 3D (point cloud) sewage pipe inspection techniques was conducted.
A novel multi-sensor robotic system was designed, integrating a camera array, front camera, and LiDAR sensor.
Tailored deep learning (DL) models were proposed for each sensor type to optimize damage detection and processing.

Main Results:

The proposed system enhances surface data capture and overall data quality for sewer inspections.
Assigning specific damage types to the most suitable sensor improves detection and quantification accuracy.
The multi-sensor approach with tailored DL models achieved higher accuracy for individual damage types compared to single-sensor systems.

Conclusions:

The developed multi-sensor robotic system offers a significant advancement in automated sewer inspection technology.
Integrating tailored deep learning models with multi-sensor data fusion improves the accuracy and reliability of damage detection.
This approach provides a more robust and efficient solution for maintaining critical urban underground infrastructure.