ABSTRACT

In this study, high resolution (HR) images, GIS and Deep convolution neural network (DCNN) are used for assessment of traffic congestion. A DCNN architecture comprises of one convolution layer, two pooling layers and a five-layer fully connected neural network evaluated for identifying vehicles in a movable windows in HR images. A simple mathematical method is followed for changing the scale and orientation of the movable window to optimally mask and measure the area of vehicles. A formula is appraised to compute the traffic density using the estimated vehicles and road areas. A threshold is used to estimate traffic congestion from the measured traffic density. The method is validated by applying on World View-2 pan-sharpened multispectral images having spatial resolution 0.46 m. In comparison to CNN and ResNet-18, the proposed approach achieves a quite promising accuracy (99%) and needs less training and processing time for measuring traffic congestion in HR images.

摘要

在这项研究中，高分辨率 (HR) 图像、GIS 和深度卷积神经网络 (DCNN) 用于评估交通拥堵。DCNN 架构包括一个卷积层、两个池化层和一个五层全连接神经网络，用于识别 HR 图像中可移动窗口中的车辆。遵循一种简单的数学方法来改变可移动窗口的比例和方向，以最佳地掩盖和测量车辆的区域。使用估计的车辆和道路面积评估公式以计算交通密度。阈值用于根据测量的交通密度估计交通拥堵。该方法通过应用空间分辨率为 0.46 m 的 World View-2 全色锐化多光谱图像进行验证。与 CNN 和 ResNet-18 相比，