Deep Learning-Based Method for Detection of External Air Conditioner Units from Street View Images

Fei Yang,Meng Wang

doi:10.3390/rs13183691

Abstract

Heat waves may negatively impact the economy and human life under global warming. The use of air conditioners can reduce the vulnerability of humans to heat wave disasters. However, air conditioner usage has been not clear until now. Traditional registration investigation methods are cumbersome and require expensive labor and time. This study used a Labelme image tagging tool and an available street view images database to firstly establish a monographic dataset to detect external air conditioner unit features and proposed two deep learning algorithms of Mask-RCNN and YOLOv5 to automatically retrieve air conditioners. The training dataset used street view images in the 2nd Ring Road area of downtown Beijing. The model evaluation mAP of Mask-RCNN and YOLOv5 reached 0.99 and 0.9428. In comparison, the performance of YOLOv5 was superior, which is attributed to the YOLOv5 model being better at detecting smaller target entities equipped with a lighter network structure and an enhanced feature extraction network. We demonstrated the feasibility of using street view images to retrieve air conditioners and showed their great potential to detect air conditioners in the future.

Highlights

This study proposes a convenient and low-cost detection method to extract external air conditioner unit features by applying Mask-RCNN and YOLOv5 theories in target detection tasks
This study proposes the use of a manual annotation method for available and high-quality street view images to construct a monographic training dataset for air conditioner external units for the first time
The widely used and publicly available pre-trained coco weight file was used as the initial weight based on the idea of parameter migration and taken as the initial retraining weight of the pretraining model in the Mask-RCNN training process

Summary

Introduction

Heat wave disasters have become more frequent and severe with global warming [1,2]. Have destructive impacts on national economies and human health [3,4]. Temperature records of major metropolises in the eastern coastal region of China (e.g., the Beijing–Tianjin–Hebei region, the Pearl River Delta, and the Yangtze River Delta) have surged significantly compared with those of surrounding cities; the urban heat island effect caused by urbanization enhances heat wave impacts [5,6]. Extreme heat waves are associated with increased mortality and the incidence of various underlying diseases [7,8], such as cardiovascular disease, acute kidney failure, dehydration, and acute respiratory disease [9,10]

Methods

Results

Discussion

Conclusion