The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLVIII-4/W3-2022
https://doi.org/10.5194/isprs-archives-XLVIII-4-W3-2022-41-2022
https://doi.org/10.5194/isprs-archives-XLVIII-4-W3-2022-41-2022
02 Dec 2022
 | 02 Dec 2022

GIS BASED SMART NOISE MAPPING TO COMPARE ORGANIZED TRAFFIC AND UNORGANIZED TRAFFIC FOR A DEVELOPING SMARTCITY

R. Dubey, S. Bharadwaj, and S. Biswas

Keywords: Anechoic chamber, Barrier attenuation, Calibration, GIS, organized traffic, semantic segmentation, smart city

Abstract. One of the most pervasive environmental dangers to humans is noise. It has detrimental effects on a person's health, including tinnitus, heart attacks, cardiovascular illness, and hearing problems. A noise prediction model, traffic noise data, and 3D geographic data are all necessary for noise mapping. Smart noise mapping uses crowdsourced mobile applications to manage noise data, free satellite data to extract 3D information, and GIS interpolation to create a noise map of a given area. Roads, buildings, and land use/land cover are all planned by the city planner. Controlled traffic is provided by the proposed smart city, but healthier living conditions are not included. This paper aims to compare the benefits of organised and disorganised traffic using the criterion of noise pollution level. Google Images and a noise app were used to create a smart noise mapping approach that adjusted noise levels for various sorts of automobiles. The method is used to create noise maps of a busy crossroads in the growing metropolis of Lucknow, Uttar Pradesh, India. Before and after the junction became structured, noise maps were produced (separate lanes were designed for traffic in different directions). For three crucial traffic hours each day, it was seen that the scheduled traffic reduced noise levels by 15–20 dB or more. This paper tries to find out the advantages of organized traffic against unorganized traffic in terms of the yardstick of noise. The semantic segmentation method is used to characterise cars, making it simple to categorise various sets of vehicles into small, medium, and heavy vehicle categories. Data from several crossings in that smart city before and after the development was used to confirm the results.