The pavement crack datasets used in paper, crack detection results on each datasets, trained model, and crack annotation tool are stored in Google Drive, One Drive, and Daidu Yunpan extract code: jviq.

This repository contains the code for crack detection on concrete surfaces. It is a PyTorch implementation of Deep Learning-Based Crack Damage Detection Using Convolutional Neural Networks with DeepCrack. DeepCrack: A Deep Hierarchical Feature Learning Architecture for Crack Segmentation

In practice, many cracks, e.g., pavement cracks, show poor continuity and low contrast, which bring great challenges to image-based crack detection by using low-level features. In this paper, we propose DeepCrack-an end-to-end trainable deep convolutional neural network for automatic crack detection by learning high-level features for crack ...

Comprehensive and versatile infrastructural crack types are supported in the dataset, including the pavements, bridges, and buildings cracks. The dataset for crack segmentation contains 11,298 crack images annotated with fine-grained pixel-level labels.

Therefore, to evaluate the robustness of the crack model, I tried to come up with several cases that could happen in practice. These images could be found in the folder ./test_imgs in the same repository. pure crack: these are ideal cases where only crack objects occur in the images.

Here we tried with around twenty images of both crack and non-crack to test. Without some cases, the cracks become very visible accurately in our output image. So we can say that 80-90% accuracy can be possible if the images are very clear or transparent.

You can detect crack paths and crack tips fully automatically using our crack detection module. This module provides two independent methodologies for crack detection - our line intercept method together with an iterative crack tip correction algorithm based on the Williams expansion [15] and our trained convolutional neural networks [4, 9].

The aim of this study is to examine deep learning techniques for crack detection on images from masonry walls. A dataset with photos from masonry structures is produced containing complex backgrounds and various crack types and sizes.

I analyzed confusion matrix results of the CNN models, then determined accuracy, precision, recall, and F1 score metrics. Next, I plotted prediction probabilities for each type of classification. Prediction probabiities are important in crack detection.

This is the crack data set used in the article "Automated Bridge Crack Detection Using Convolutional Neural Networks". If you want to use this data set, we recommend that you quote our paper[1]. The bridge crack data set in [2] is artificially …