CAMHighways Dataset
Please allow social and marketing cookies to show embedded content.
The Digital Roads team is proud to present the CAMHighways dataset, built from mobile mapping data that surveyed over 40km of UK Highways.
The dataset consists of textured meshes for road assets (including the pavement, traffic signs and road furniture), segmented and classified point clouds, orthomosaics generated from pavement images, defect label annotations and shapefiles, and ground penetrating radar point clouds. All modalities are georeferenced and can be integrated into game engines and/or GIS software.
The CAMHighways datatset was created to facilitate and automate the building of a Digital Twin (DT), a digital representation of the highway, to streamline inspection and maintenance through virtual reality, robotics simulation, and DT- and AI-driven data analysis. It also serves as a valuable source for other applications, such as training semantic scene understanding and defect detection algorithms.
A paper has been written to introduce the dataset and outline the data preparation process, including novel automation methods developed for this purpose, as well as integration guidelines and possible applications. The paper is available from Advanced Engineering Informatics, Volume 64, March 2025, The paper is available free of charge for a limited time: CAMHighways: The Cambridge Highways dataset
The Digital Roads dataset has been made publicly available to help further investigation into the management of our national infrastructure.
Publicly Accessible dataset
The hosting of the Digital Roads dataset is provided by our spin-out company, didimi. To access the dataset, please follow the instructions below.
Work Instructions:
1. Go to the Didimi website: https://www.didimi.com/
2. Click on login in the top right
3. Create an account via the Auth0 popup,
4. This will send you an email with a link to validate your account,
5. Please allow a few minutes for the authorisation to replicate across systems. Once validated the user should go to the following website link: https://375440353596.signin.aws.amazon.com/console
6. Log in using the email address used to create the Didimi account and the temporary password: DigitalRoadsOfTheFuture2024!
Note: Please do not edit the Account ID number
7. The user will be taken to a page to update the password, this needs to be compliant with AWS password policy.
8. Once this is completed the user will have access to the S3 storage hosting the CAMHighways dataset.
a. If it is not shown on the home screen search for ‘S3’
9. There will be a large list of objects, the only element that will be accessible will be the ‘camhighways-sample’ which holds the sample dataset.
CAMHighways Dataset by Alix Marie d’Avigneau, Lilia Potseluyko, Nzebo Richard Anvo, Hussameldin M. Taha, Varun Kumar Reja , Diana Davletshina , Percy Lam , Lavindra de Silva , Abir Al-Tabbaa and Ioannis Brilakis is licensed under CC BY 4.0 
Please note: For access to the larger dataset a request will need to be sent to drf-initiative@eng.cam.ac.uk with details of your use case to be assessed by the Digital Roads team. You will be contacted by Didimi once access to the full dataset has been added to your profile.