Smartphone-Based Air Pollution Image Dataset (SAPID)

This dataset is comprised of 456 images divided into five Air Quality Index categories designated by the United States Environmental Protection Agency, with 135 in the Good class, 188 in the Moderate class, 29 in the Unhealthy for Sensitive Groups class, 78 in the Unhealthy class, and 26 in the Very Unhealthy class. This dataset will allow researchers to build more robust and accessible computer vision related algorithms with everyday applications in environment and healthcare fields.