Autonomous concrete crack detection using deep fully convolutional neural network

Advances in Computer Vision-Based Civil Infrastructure Inspection and Monitoring

This article implements the state‐of‐the‐art deep learning technologies for a civil engineering application, namely recognition of structural damage from images. Inspired by ImageNet Chall...

Deep Transfer Learning for Image-Based Structural Damage Recognition

The spatial characteristics of cracks are significant indicators to assess and evaluate the health of existing buildings and infrastructures However, the current manual crack description 

Automatic Pixel-Level Crack Detection and Measurement Using Fully Convolutional Network

Comparison of deep convolutional neural networks and edge detectors for image-based crack detection in concrete

Computer vision-based techniques were developed to overcome the limitations of visual inspection by trained human resources and to detect structural damage in images remotely, but most methods detect only specific types of damage, such as concrete or steel cracks. To provide quasi real-time simultaneous detection of multiple types of damages, a Faster Region-based Convolutional Neural Network (Faster R-CNN)-based structural visual inspection method is proposed. To realize this, a database including 2,366 images (with 500 × 375 pixels) labeled for five types of damages—concrete crack, steel corrosion with two levels (medium and high), bolt corrosion, and steel delamination—is developed. Then, the architecture of the Faster R-CNN is modified, trained, validated, and tested using this database. Results show 90.6%, 83.4%, 82.1%, 98.1%, and 84.7% average precision (AP) ratings for the five damage types, respectively, with a mean AP of 87.8%. The robustness of the trained Faster R-CNN is evaluated and demonstrated using 11 new 6,000 × 4,000-pixel images taken of different structures. Its performance is also compared to that of the traditional CNN-based method. Considering that the proposed method provides a remarkably fast test speed (0.03 seconds per image with 500 × 375 resolution), a framework for quasi real-time damage detection on video using the trained networks is developed.

Autonomous Structural Visual Inspection Using Region-Based Deep Learning for Detecting Multiple Damage Types

Steel tendons have a vital role in prestressed concrete members and the stability of the members depends on tendons. The steel tendons corrode over time or when encased in grouts with excessive levels of chloride. The steel tendons are pre-tensioned or post-tensioned to 80 percent of their ultimate tensile strength, and significant corrosions can increase tensile stress leading to tendon breakage. For the purpose of safety and maintaining schedule, it is critical to develop a wire break monitoring methods for post-tensioning bridges. In this work, Fuzzy C-means clustering technique was employed to detect acoustic emissions released from breaking wires of post-tensioning steel tendons bounded in grout. To collect acoustic emissions of wire break and grout cracks, a constant rate tensile loads were applied to tendons embedded in grouts until a wire broke, and piezoelectric transducers attached to the tendons were used pick up the released acoustic signals. To improve the robustness of the clustering method, environmental acoustic noises were collected from a bridge and added to the database of the tensile tests. Wire break detection using acoustic emissions and Fuzzy C-mean clustering achieved 100 percent accuracy in detecting wire breaking acoustic signals while the acoustic signals of grout cracks and environmental noises were not detected as a wire break.

Sadegh Mahmoudkhani

Papers

Autonomous Structural Visual Inspection Using Region-Based Deep Learning for Detecting Multiple Damage Types

Acoustic Emissions Sensor and Fuzzy C-mean Clustering Based Break Detection in Post-Tensioning Tendons