Estimating Annual Average Daily Traffic from Satellite Imagery and Air Photos: Empirical Results

Abstract

Vehicles can be identified in high-resolution satellite imagery that recently has become available to the civilian community. The vehicle information contained in this imagery, and in air-based imagery, could be used in annual average daily traffic (AADT) estimation, a task conducted by many transportation agencies around the world. However, because the imagery provides information equivalent to traffic counts of very short duration, it is possible that the information is too noisy to be of use. Empirical differences between AADT estimated from 14 satellite images and air photos of Interstate segments in Ohio and the corresponding AADT estimated from traditional, ground-based estimates are presented. The distribution in differences appears relatively unbiased, implying that averaging the estimates of several images of the same segment can decrease estimate errors. The empirical errors are small enough to indicate that AADT estimation errors and ground-based sampling efforts could both be reduced by combining satellite-based data with traditional ground-based data. The differences between the image-based and the ground-based estimates are smaller in the few cases in which ground-based estimates inspired greater confidence, implying that the image-based estimates may be better than what is indicated in the distribution of differences. Evidence also suggests that the differences tend to decrease when the image leads to longer equivalent traffic count duration, indicating the potential to condition the use of the image-based data on this readily available parameter.

Fundamental diagram estimation by using trajectories of probe vehicles

“…Alternatively, remote sensing (e.g., image recognition) from satellites is used to measure the jam density directly. Although remote sensing does not provide us time-continuous traffic state variables, such as flow and speed (because the time interval between two measurements is extremely long, few hours to few days at least), it measures space-continuous density accurately (McCord et al, 2003). Thus, the jam density could be inferred as an upper limit of such measured density.…”

A novel approach to model traffic on road segments of large-scale urban road networks

“…Other methods utilize to estimate traffic volume are; image-based data such as high-resolution satellite images and aerial photographs [21], machine learning algorithms such as Artificial Neural Network (ANN) and location-based social network data such as social media, GPS, Bluetooth data. Nevertheless application of those methods are also limited due to cost constraints on purchasing and processing image data [22,12]; the requirement of an extensive baseline data and more complex statistical procedures that demand high technical competence for the calibration of machine learning algorithms [12,23]; and lack of big data and limited online users that makes the sample size too small for application of location-based social network data [21,24,25].…”

Roadway traffic monitoring from an unmanned aerial vehicle

“…AADT is estimated following the methodology of [7], using either estimate of hourly volume discussed above, (in this case Equations 2 and 3 or Equation 5A),…”