masonry Computer Vision Project

defect detection

Updated 7 days ago

0

views

0

downloads
Classes (3)
brick
broken_brick
crack

Metrics

Try This Model
Drop an image or
Description
  • Introducing "MCrack1300" dataset, a novel dataset tailored for instance segmentation, comprising 1300 images showcasing masonry cracks, each with a resolution of 640 pixels × 640 pixels. The dataset is divided into three subsets: 1000 images for training, 150 for validation, and another 150 for testing purposes.

  • There are a total of five annotated labels: bricks, broken_bricks, cracks, spalling, and plant. The quantities of the latter two categories are relatively low and were not recommended to put into training process.

  • The data sources are as follows: 251 images from Crack900 as RGB images (Huang et al., 2024), 376 images from the internet, and 673 images collected using a mobile phone from the University of Birmingham UK campus and its vicinity. The dataset contains various types of bricks with different colours, textures, and materials, along with cracks of varying sizes and shapes, including small, longitudinal, transverse, and step-like forms.

This dataset is part of the paper, and the preprint can be viewed: https://arxiv.org/abs/2401.15266.

Now the full paper has been published in Advanced Engineering Informatics, please check: https://doi.org/10.1016/j.aei.2024.102826

Use This Trained Model

Try it in your browser, or deploy via our Hosted Inference API and other deployment methods.

Supervision

Build Computer Vision Applications Faster with Supervision

Visualize and process your model results with our reusable computer vision tools.

Cite This Project

LICENSE
CC BY 4.0

If you use this dataset in a research paper, please cite it using the following BibTeX:

                        @misc{
                            masonry-0e1zc_dataset,
                            title = { masonry Dataset },
                            type = { Open Source Dataset },
                            author = { defect detection },
                            howpublished = { \url{ https://universe.roboflow.com/defect-detection-edbnh/masonry-0e1zc } },
                            url = { https://universe.roboflow.com/defect-detection-edbnh/masonry-0e1zc },
                            journal = { Roboflow Universe },
                            publisher = { Roboflow },
                            year = { 2024 },
                            month = { oct },
                            note = { visited on 2024-11-01 },
                            }
                        
                    

Similar Projects

See More