Low data image based urban noise estimation
Year: 2026
Type: preprint
Abstract: Urban noise pollution represents a critical environmental challenge with significant public health implications. Traditional noise monitoring requires expensive sensor networks, limiting scalability. We introduce a machine learning framework predicting background noise from casual smartphone imagery with only 400 samples. Our pipeline combines transformer-based semantic segmentation (SegFormer) with interpretable hand-crafted features (natural/manmade proportions, movable- object metrics, visual complexity) fed into Support Vector Regression. Critically, we introduce perceptually-grounded evaluation based on the ±3 dB just-noticeable difference threshold established in psychoacoustic research. Our framework requires dramatically fewer resources than large-scale deep learning approaches, enabling scalable citizen-science driven urban acoustic monitoring.
Source: Research Square
Authors: Priyanshu Sarma-Sarkar, Rajkumar Saini
Language: English
Topic: Noise Effects and Management
Subfield: Acoustics and Ultrasonics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7204564876