Researchers at Florida Atlantic University (FAU) have developed a new method for counting vehicles that uses sophisticated algorithms combined with data taken from existing traffic cameras.
Conventional automated vehicle counting techniques include radar, infrared or inductive loop detectors, as well as the use of traffic cameras. A computer vision-based system can also be a suitable alternative, however, this method is limited to weather conditions and natural light.
The team from FAU’s College of Engineering and Computer Science (COECS) set out to find a better way to monitor and estimate traffic flow using intelligent traffic surveillance systems. They wanted to develop an automated car counting system using infrastructure and cameras already in place that could perform well both day and night, and in sunny and cloudy weather conditions. Results of their study show that under all conditions, the system they developed significantly outperformed automated car counting methods currently used, with an average accuracy rate of more than 96%, far above those of old methodologies.
While developing and testing the new system, the team also took into consideration other factors that might affect the video cameras, such as vibrations on bridges and other similar conditions. Their new ‘OverFeat Framework’ program is an effective combination of convolutional neural networks (CNN) and image classification and recognition techniques. The research team, led by COECS assistant professor Hongbo Su, developed and implemented two algorithms for this new program: Background Subtraction Method (BSM) and OverFeat Framework using the Python language for automatic car counting.
“Understanding the physical traffic load is critical for managing traffic, as well as for renovating roads or building new roads,” said Su. “Counting cars is necessary in order to understand the density of cars on our roads, which ultimately helps engineers and decision makers in their planning and budgeting processes.”
Associate professor and director of the FAU’s Laboratory for Adaptive Traffic Operations and Management (LATOM), Aleksandar Stevanovic, commented, “The best part of this new system is that you don’t need any extra infrastructure, because the cameras are already placed at strategic locations on our roads and highways.
“We are utilizing videos from these cameras to accurately count cars to give us better knowledge about congestion on our roads. Then, we will share this information with traffic management specialists so that they can figure out how best to address the issues to optimize driving, provide new routes and ultimately improve traffic flow.”