Researchers 'count cars'—literally—to find a better way to control heavy traffic

August 9, 2017, Florida Atlantic University
A high-resolution camera is placed under a bridge in South Florida, which contains five through lanes. The cars drive through the regions of interest to be counted. All of the cameras used for this research had a downward inclination and the sides and top were covered with a large camera housing to prevent any major complications with direct sun angles. Credit: Florida Atlantic University

There's "Counting Crows," counting sheep, counting blessings and now researchers at Florida Atlantic University have their own version of "counting cars"—literally—in an attempt to improve traffic flow on South Florida's and our nation's overcrowded roads. And with more than 263 million registered passenger vehicles in the United States and more than 14 million registered vehicles in Florida alone, this is no small feat.

Ensuring that traffic moves smoothly and without a lot of manual intervention requires automated car counting techniques, which are often tedious and cumbersome to perform. They also are not foolproof. Car counting techniques include radar, infrared or inductive loop detectors as well as the use of traffic cameras. A computer vision-based system also can be a suitable alternative for car counting, however, this method is limited to weather conditions and natural light.

In a new study, researchers from FAU's College of Engineering and Computer Science (COECS) set out to find a better way to monitor and estimate 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, published in the journal Sensors, show that rain or shine, night or day, the system they developed significantly outperformed automated car counting methods currently used. Their system had an average accuracy rate of more than 96 percent, far above the accuracy rates of the old system.

The new program, which the researchers have named "OverFeat Framework," is showing great potential in the field of traffic monitoring and could provide an ideal solution for effectively "counting cars." OverFeat Framework is an effective combination of Convolution Neural Networks (CNN) and image classification and recognition techniques.

The research team, led by Hongbo Su, Ph.D., corresponding author of the study and an assistant professor in the Department of Civil, Environmental and Geomatics Engineering in the COECS, developed and implemented two algorithms for this new program: Background Subtraction Method (BSM) and OverFeat Framework using the Python language for automatic car counting. Su and first author of the study, Debojit Biswas, a Ph.D. student at the University, evaluated the accuracy of this new system by comparing it with manual 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."

While developing and testing this new system, the researchers also took into consideration other factors that might affect the such as vibrations on bridges and other similar conditions. They studied buses (1,300 images), cars (1,300 images), taxis (1,300 images), trucks (1,568 images) and fire rescue vehicles (1,300 images) using six traffic videos located at some of the busiest roads in South Florida. They collected footage from these cameras at different times during the day.

It is estimated that there are more than 1 million video cameras placed along major roads such as highways, freeways, motorways, expressways as well as arterial roads throughout the U.S. In Florida, there are thousands of cameras placed on busy roadways to help drivers with their everyday commutes.

"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," said Aleksandar Stevanovic, Ph.D., co-author of the study, associate professor of FAU's Department of Civil, Environmental and Geomatics Engineering, and director of the University's Laboratory for Adaptive Traffic Operations and Management. "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 flow."

Su and Stevanovic plan to work with local, state and federal government agencies as well as commercial enterprises to maximize the benefits of the system they developed and ultimately provide a new way of "counting cars."

Explore further: South Korea to test self-driving car in real traffic

Related Stories

Self-driving cars could be the answer to congested roads

November 24, 2014

If cars with drivers still suffer under gridlock conditions on roads, how will driverless cars fare any better? With greater computerisation and network awareness, driverless cars may be the answer to growing traffic congestion.

Automated automobile cattle avoidance

April 7, 2017

Driverless cars are hitting the headlines across the globe but for the foreseeable future we will still have drivers. The pressure then is how might some of the safety features of driverless cars be incorporated into conventional ...

Traffic monitoring to generate knowledge

June 16, 2015

Researchers at UPM have developed an application that generates traffic information for cities and roads by detecting a Bluetooth device boarded on vehicles.

Recommended for you

7 comments

Adjust slider to filter visible comments by rank

Display comments: newest first

srwpropertiesinc
not rated yet Aug 09, 2017
Motionloft already does this very well. They have a really neat system to count traffic. You should check out what they're up to.
rossim22
5 / 5 (1) Aug 09, 2017

Put a "Slower Traffic Keep Right" sign every half mile and pull people over for not passing in passing lanes. I think that would dramatically reduce traffic just by educating drivers. There is no reason a five-lane highway should ever have traffic unless a devastating accident occurred.

By the way... for anyone reading this....
I don't care if you have seven people in your car... if you're not passing people in the lane to your right.. get out of the car pool lane!
Captain Stumpy
not rated yet Aug 09, 2017
There is no reason a five-lane highway should ever have traffic unless a devastating accident occurred.

city + rush hour = stop and go traffic on a 5 lane

heck, even of the city is smaller, like 100,000, you will get stop and go traffic during rush hour with a 5 lane

check Huntsville, Mobile, Little Rock, Bakersfield, Berkeley, Burbank, Clearwater, Ft. Lauderdale, Gainesville etc
NoStrings
not rated yet Aug 10, 2017
You never been to Auckland, New Zealand, Stumpy. All the cities you list have nothing to complain about, comparing to Auckland.
Eikka
not rated yet Aug 10, 2017
heck, even of the city is smaller, like 100,000, you will get stop and go traffic during rush hour with a 5 lane


I'm at around 200,000 and there's one two-lane highway going north-south and two across, and they're never full to the point of stopping. Sounds like bad city planning to me if you get 5-lane gridlocks in a small city like that.
MR166
not rated yet Aug 10, 2017
I am a long time commuter in the NYC general area. During rush hour traffic flows OK at 65 to 75 MPH on roads that have a speed limit of 55. When speed limits are rigorously enforced the the result is serious stop and go traffic during the rush hour periods. When the number of cars entering a road exceed the number exiting dangerous stop and go traffic results. The same thing happens when there is an accident along the side of the road. Drivers slow down at that point and during high traffic periods stop and go traffic is created behind them.
MR166
not rated yet Aug 10, 2017
The problem is really easy to visualize. Lets say you have an hourglass that can pass 1000 grains of sand per hour. Everything is fine until you exceed that limit and then the grains of sand stop and go until they pass the bottleneck. If you could increase the size of the opening, i.e. more lanes or increase the speed of the sand the stop and go would stop.

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.