A Multi-Year Urban Streetlight Imagery Dataset for Visual Monitoring and Spatio-Temporal Drift Detection

TL;DR

This paper introduces a comprehensive multi-year urban streetlight image dataset with rich metadata, enabling research on visual drift, anomaly detection, and model stability in smart city applications.

Contribution

It provides a large-scale, real-world dataset with a self-supervised framework for drift detection, supporting long-term vision system evaluation in urban environments.

Findings

Dataset contains over 526,000 images from 22 cameras.

Two drift metrics are defined: centroid drift and reconstruction error.

Models trained separately for day/night images and each camera.

Abstract

We present a large-scale, longitudinal visual dataset of urban streetlights captured by 22 fixed-angle cameras deployed across Bristol, U.K., from 2021 to 2025. The dataset contains over 526,000 images, collected hourly under diverse lighting, weather, and seasonal conditions. Each image is accompanied by rich metadata, including timestamps, GPS coordinates, and device identifiers. This unique real-world dataset enables detailed investigation of visual drift, anomaly detection, and MLOps strategies in smart city deployments. To promtoe seconardary analysis, we additionally provide a self-supervised framework based on convolutional variational autoencoders (CNN-VAEs). Models are trained separately for each camera node and for day/night image sets. We define two per-sample drift metrics: relative centroid drift, capturing latent space deviation from a baseline quarter, and relative reconstruction error, measuring normalized image-domain degradation. This dataset provides a realistic, fine-grained benchmark for evaluating long-term model stability, drift-aware learning, and deployment-ready vision systems. The images and structured metadata are publicly released in JPEG and CSV formats, supporting reproducibility and downstream applications such as streetlight monitoring, weather inference, and urban scene understanding. The dataset can be found at https://doi.org/10.5281/zenodo.17781192 and https://doi.org/10.5281/zenodo.17859120.