AQPDBJUT Dataset: Picture-Based PM Monitoring in the Campus of BJUT

TL;DR

This paper introduces the AQPDBJUT dataset with 1,500 campus photos to evaluate photobased particulate matter monitoring methods, revealing current approaches are insufficient for effective campus PM control.

Contribution

The paper presents a new campus-specific dataset for PM monitoring and assesses existing photobased methods, highlighting their limitations in campus environments.

Findings

Existing methods are inadequate for campus PM monitoring

The dataset enables better evaluation of PM detection techniques

Photobased approaches need improvement for practical use

Abstract

Ensuring the students in good physical levels is imperative for their future health. In recent years, the continually growing concentration of Particulate Matter (PM) has done increasingly serious harm to student health. Hence, it is highly required to prevent and control PM concentrations in the campus. As the source of PM prevention and control, developing a good model for PM monitoring is extremely urgent and has posed a big challenge. It has been found in prior works that photobased methods are available for PM monitoring. To verify the effectiveness of existing PM monitoring methods in the campus, we establish a new dataset which includes 1,500 photos collected in the Beijing University of Technology. Experiments show that stated-of-the-art methods are far from ideal for PM monitoring in the campus.