DairyPPENet: A dataset for detection of hygiene-related personal protective equipment in dairy processing plants

Read full text Summarise with VIRAT
Authors: Mirko Gueregat
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This work introduces DairyPPENet, a dataset designed for detecting hygiene-related personal protective equipment (PPE) used in dairy processing environments. The dataset was collected from CCTV cameras installed in a dairy processing plant located in Valdivia, Chile. Images were extracted from RTSP video streams and manually annotated using the CVAT annotation platform. DairyPPENet contains 751 RGB images and 6,692 annotated PPE instances belonging to three classes relevant for food safety: mask, hairnet, and glove. The dataset reflects real industrial conditions including partial occlusions, worker posture variability, multi-person scenes, and small object detection challenges. The dataset is intended to support research on automated compliance monitoring systems in food processing environments and benchmarking of object detection models in industrial scenarios.

Fields of Study & Subjects

Advanced Neural Network Applications Industrial Vision Systems and Defect Detection Smart Agriculture and AI

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
31 March 2026
Language
EN
Document type
Preprint