University of Reading Research Data Archive

Trash screen blockage detection using cameras and deep learning: code and dataset

How to cite this Dataset


This dataset provides access to the images and network weights produced during our research on trash screen detection, along with minimum working examples allowing to use the network weights on new trash screen camera images. The images come from 54 different cameras with open access feeds provided by the Environment Agency (, and were collected from January 2022 to January 2023. The images were manually annotated with a "clear" (if the trash screen looks clear), "blocked" (if the trash screen looks blocked) or "other" (if unsure) label. The network weights and minimum working examples allow to estimate labels of new trash screen images using three different methods: a classifier, a siamese network and an anomaly detection method.

Resource Type: Dataset
Creators: Vandaele, Remy
Contributors: Dance, Sarah ORCID logoORCID: and Ojha, Varun
Rights-holders: University of Reading, Crown
Data Publisher: University of Reading
Publication Year: 2023
Data last accessed: 12 July 2024
Metadata Record URL:
Organisational units: Science > School of Mathematical, Computational and Physical Sciences > National Centre for Earth Observation (NCEO)
Science > School of Mathematical, Computational and Physical Sciences > Department of Meteorology
Participating Organisations: University of Reading, Newcastle University
Keywords: trash screen, deep learning, camera images
Data Availability: OPEN


Download all (.zip)





Actions (Log-in required)

View item View item