Object Detection

Deteccão_fixacoes_trilhos Computer Vision Project

Drop an image or


8431 images
Explore Dataset

Here are a few use cases for this project:

  1. Railway Track Maintenance: This model can be used by railway departments to inspect railway tracks, detect any irregularities such as broken fasteners, missing nuts, rail cracks, spalling etc. This automated inspection can help in proactive maintenance, ensuring safety and operational efficiency of the railway system.

  2. Infrastructure Assessment Tools Development: Companies developing infrastructure assessment tools can incorporate this model to analyze the condition of railway tracks. This will provide their customers with detailed reports regarding the integrity of the track system, the presence of any defects, and when maintenance or repairs may be required.

  3. Development of Autonomous Trains: This model could be used in the development of autonomous trains, aiding the on-board AI systems in identifying potential issues with the tracks in real-time. This could serve as a critical part of the safety system, stopping the train before reaching a faulty part of track if a problem is detected.

  4. Training AI Models for Other Transport Infrastructure: For research and development teams working on AI models to detect infrastructure problems in other transport modes, this model could serve as a valuable learning tool about what to look for, how to interpret what's being seen, and how to classify various issues.

  5. Educational Purpose: Curriculum designers or educators teaching about railway system maintenance could use this tool to demonstrate real-world practices relating to system inspection, defect identification, and troubleshooting. Given the variety of defects it can detect, this model could serve as a comprehensive educational resource.

Trained Model API

This project has a trained model available that you can try in your browser and use to get predictions via our Hosted Inference API and other deployment methods.

Cite this Project

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

@misc{ deteccao_fixacoes_trilhos_dataset,
    title = { Deteccão_fixacoes_trilhos Dataset },
    type = { Open Source Dataset },
    author = { TrilhosObjectDetection },
    howpublished = { \url{ } },
    url = { },
    journal = { Roboflow Universe },
    publisher = { Roboflow },
    year = { 2023 },
    month = { sep },
    note = { visited on 2023-12-08 },

Find utilities and guides to help you start using the Deteccão_fixacoes_trilhos project in your project.

Last Updated

3 months ago

Project Type

Object Detection




0, 1, 13, 14, 15, 2, 3, 5, 6, 8, 9, Baseplaterotation, Braids, CES, Corrugation, Defectives fastener, Falta_Grampo, Falta_Parafuso, Fisplates, Grampo, Jump, Marquage, Missing Nuts, Placa, Placa_Contratrilho, Placa_Deslizante, Placa_Gêmea, Placa_Gêmea_sem_grampo, Seal, Soudure, Spalling, Squat, Surface Defect, Tirefon, Tirefond_Faltante, Wheel Burn, braid, clip, defective_fastener, eclip_break, fastener, fastener_broken, fishplate, gr, marquage, missing, missing_nut, rail_crack, rail_screw_break, seal, soudure, spike, splice_bar, splice_bar_x, trackbed_stuff

Views: 328

Views in previous 30 days: 83

Downloads: 14

Downloads in previous 30 days: 1


CC BY 4.0