An annotated water-filled, and dry potholes dataset for deep learning applications

Journal article

Dib, J., Sirlantzis, K. and Howells, G. 2023. An annotated water-filled, and dry potholes dataset for deep learning applications. Data in Brief. 48, p. 109206. https://doi.org/10.1016/j.dib.2023.109206
AuthorsDib, J., Sirlantzis, K. and Howells, G.
AbstractPotholes have long posed a challenging risk to automated systems due to their random and stochastic shapes and the reflectiveness of their surface when filled with water, whether it is "muddy" water or clear water. This has formed a significant limitation to autonomous assistive technologies such as Electric-Powered Wheelchairs (EPWs), mobility scooters, etc. due to the risk potholes pose on the user's well-being as it could cause severe falls and injuries as well as neck and back problems. Current research proved that Deep Leaning technologies are one of the most relevant solutions used to detect potholes due to the high accuracy of the detection. One of the main limitations to the datasets currently made available is the lack of photos describing water-filled, rabble-filled, and random coloured potholes. The purpose of our dataset is to provide the answer to this problem as it contains 713 high-quality photos representing 1152 manuall-annotated potholes in different shapes, locations, colours, and conditions, all of which were manually-collected via a mobile phone and within different areas in the United Kingdom along with two additional benchmarking videos recorded via a dashcam.
KeywordsWater-filled potholes; Transfer learning; Images dataset; Artificial neural networks; Dry potholes; Potholes; Deep learning
Year2023
JournalData in Brief
Journal citation48, p. 109206
PublisherElsevier
ISSN2352-3409
Digital Object Identifier (DOI)https://doi.org/10.1016/j.dib.2023.109206
https://doi.org/S2352-3409(23)00325-6
Official URLhttps://www.sciencedirect.com/science/article/pii/S2352340923003256
Publication dates
Online06 May 2023
Publication process dates
Accepted02 May 2023
Deposited07 Jun 2023
Publisher's version
License
Output statusPublished
Permalink -

https://repository.canterbury.ac.uk/item/94w4x/an-annotated-water-filled-and-dry-potholes-dataset-for-deep-learning-applications

Download files

Publisher's version
1-s2.0-S2352340923003256-main.pdf
License: CC BY 4.0

  • 44
    total views
  • 19
    total downloads
  • 0
    views this month
  • 4
    downloads this month

Export as

Related outputs

Cancer: Investigating the impact of the implementation platform on machine learning models
Olowolayemo, A. S., Souag, A. and Sirlantzis, K. 2024. Cancer: Investigating the impact of the implementation platform on machine learning models. in: Mengoni, M. and Souag, A. (ed.) AIHealth 2024, The First International Conference on AI-Health ThinkMind.
Effect of Gait Speed on Trajectory Prediction Using Deep Learning Models for Exoskeleton Applications
Kolaghassi, R., Marcelli, G. and Sirlantzis, K. 2023. Effect of Gait Speed on Trajectory Prediction Using Deep Learning Models for Exoskeleton Applications. Sensors. 23 (12), p. 5687. https://doi.org/10.3390/s23125687
Depth estimation and validation of plenoptic light field camera
Khan, Ali, Hossain, Md. Moinul, Sirlantzis, Konstantinos, Covaci, Alexandra and Chowdhury, Wasif Shafaet 2023. Depth estimation and validation of plenoptic light field camera. in: 2023 IEEE International Conference on Imaging Systems and Techniques (IST) IEEE.
Train vs. play: Evaluating the effects of gamified and non-gamified wheelchair skills training using virtual reality
Zorzi, C., Tabbaa, Luma, Covaci, Alexandra, Sirlantzis, Konstantinos and Marcelli, Gianluca 2023. Train vs. play: Evaluating the effects of gamified and non-gamified wheelchair skills training using virtual reality. Bioengineering. 10 (11), p. 1269. https://doi.org/10.3390/bioengineering10111269
Community areas of sustainable care and dementia excellence in Europe (CASCADE) - Final report: A process and technology evaluation of the CASCADE programme in the United Kingdom implementation sites
Martin, A., Hatzidimitriadou, E., Sangeorzan, I., Smith, R., Wright, T., Price, N., Sirlantzis, K. and Rajapakse, S. 2023. Community areas of sustainable care and dementia excellence in Europe (CASCADE) - Final report: A process and technology evaluation of the CASCADE programme in the United Kingdom implementation sites. Canterbury Canterbury Christ Church University.
Augmented reality (AR) for surgical robotic and autonomous systems: State of the art, challenges, and solutions
Seetohul, J,, Shafiee, M. and Sirlantzis, K. 2023. Augmented reality (AR) for surgical robotic and autonomous systems: State of the art, challenges, and solutions. Sensors. 23 (13), p. 6202. https://doi.org/10.3390/s23136202
Design and control of a single-leg exoskeleton with gravity compensation for children with unilateral cerebral palsy
Sarajchi, M. and Sirlantzis, K. 2023. Design and control of a single-leg exoskeleton with gravity compensation for children with unilateral cerebral palsy. Sensors. 23 (13), p. 6103. https://doi.org/1424-8220/23/13/6103
Virtual and augmented reality in healthcare education (VARE) project report
Hatzidimitriadou, E., Taylor, J., Clark, N., Field, S., Reader, J., Buttery, A., Singh, B., Arealis, G. and Sirlantzis, K. 2022. Virtual and augmented reality in healthcare education (VARE) project report. Canterbury Canterbury Christ Church University.