A Multi-Year Urban Streetlight Imagery Dataset for Visual Monitoring and Drift Detection
Abstract
"A longitudinal visual dataset of urban streetlight scenes captured daily over several years including 2025, accompanied by structured metadata for smart city monitoring, drift detection, and anomaly analysis. Includes over 526,000 images with timestamps and GPS metadata, enabling vision-based model training in urban environments."
Description
Overview
This large visual dataset supports urban monitoring, anomaly detection and spatio-temporal drift detection using imagery from streetlight cameras deployed across ® Bristol, UK.
Dataset Contents
- Data modality: Images + CSV metadata
- Scale: 526,000+ images
- File formats: JPEG, CSV
- Metadata: Timestamps, GPS
Collection Methodology- Environment: Urban deployment
- Duration: Multi-year coverage
- Devices/Sensors: Fixed cameras
- Sampling rate: Hourly
Labels and Targets- Labeling: Not labeled (vision analytics)
- Ground truth: Timestamped images
Recommended Use Cases- Vision model training
- Anomaly and drift detection
- Urban monitoring research
Limitations and Considerations- Large storage and compute requirements
Access and Licensing
- Labeling: Not labeled (vision analytics)
- Ground truth: Timestamped images
Recommended Use Cases- Vision model training
- Anomaly and drift detection
- Urban monitoring research
Limitations and Considerations- Large storage and compute requirements
Access and Licensing
- Large storage and compute requirements
Access and Licensing
This dataset is available at official repository page. Licensed under CC BY 4.0.
📊 View Data Structure
To explore column names, data types, and sample rows, visit the official dataset page on Zenodo.
Preview on Zenodo
Cite This Dataset
Li, P., Mavromatis, I., Sahadevan, A., Farnham, T., & Aijaz, A. (2025). A Multi-Year Urban Streetlight Imagery Dataset for Visual Monitoring and Drift Detection. [Dataset]. Zenodo. https://doi.org/10.5281/zenodo.17781192
Select your preferred citation style above. The citation will automatically update and you can copy it to your clipboard.
Original source: Zenodo (2025). Visit official page for more details.
Indexed by IoTDataset.com on Feb 07, 2026
Ready to Start Your Research?
Download this dataset directly from the official repository and start building your next breakthrough project.