Using Street View Images to Identify Road Noise Barriers with Ensemble Classification Model and Geospatial Analysis

Road noise barriers (RNBs) are important urban infrastructures to relieve the harm of traffic noise pollution for citizens. Therefore, obtaining the spatial distribution characteristics of RNBs, such as precise positions and mileage, can be of great help for obtaining more accurate urban noise maps and assessing the quality of the urban living environment for sustainable urban development. However, an effective and efficient method for identifying RNBs and acquiring their attributes in large areas is scarce. This study constructs an ensemble classification model (ECM) to automatically identify RNBs at the city level based on Baidu Street View (BSV). Firstly, the bootstrap sampling method is proposed to build a street view image-based train set, where the effect of imbalanced categories of samples was reduced by adding confusing negative samples. Secondly, two state-of-theart deep learning models, ResNet and DenseNet, are ensembled to construct an ECM based on the bagging framework. Finally, a post-processing method has been proposed based on geospatial analysis to eliminate street view images (SVIs) that are misclassified as RNBs. This study takes Suzhou, China as the study area to validate the proposed method. The model achieved an accuracy and F1-score of 0.98 and 0.90, respectively. The total mileage of the RNBs in Suzhou was 178,919 m. The results demonstrated the performance of the proposed RNBs identification framework. The significance of obtaining RNBs attributes for accelerating sustainable urban development has been demonstrated through the case of photovoltaic noise barriers (PVNBs).