Search for: All records

Air pollution is a major global risk to human health and environment. Particle matter (PM) with diameters less than 2.5 micrometers (PM2.5) is more harmful to human health than other air pollutants because it can penetrate deeply into lungs and damage human respiratory system. A new image-based deep feature analysis method is presented in this paper for PM2.5 concentration estimation. Firstly, low level and high level features are extracted from images and their spectrums by a deep learning neural network, and then regression models are created using the extracted deep features to estimate the PM2.5 concentrations, which are future refined by the collected weather information. The proposed method was evaluated using a PM2.5 dataset with 1460 photos and the experimental results demonstrated that our method outperformed other state-of-the-art methods. 

Measuring the inclination angles of utility poles of the electric power distribution lines is critical to maintain power distribution systems and minimize power outages, because the poles are very vulnerable to natural disasters. However, traditional human-based pole inspection methods are very costly and require heavy workloads. In this paper, we propose a novel pole monitoring system to measure the inclination angle of utility poles from images captured by unmanned aerial vehicle (UAV) automatically. A state-of-the-art deep learning neural network is used to detect and segment utility poles from UAV street view images, and computer vision techniques are used to calculate the inclination angles based on the segmented poles. The proposed method was evaluated using 64 images with 84 utility poles taken in different weather conditions. The pole segmentation accuracy is 93.74% and the average inclination angle error is 0.59 degrees, which demonstrate the efficiency of the proposed utility pole monitoring system.