Communications of the ACM
Researchers 'count Cars'--Literally--to Manage Traffic
The OverFeat Framework system uses two algorithms to monitor and estimate traffic flow by taking advantage of infrastructure and cameras already in place.
Credit: FAU News Desk
Researchers at Florida Atlantic University (FAU) conducted a study designed to find a better way to monitor and estimate traffic flow using intelligent traffic surveillance systems. The researchers developed OverFeat Framework, an automated car-counting system using infrastructure and cameras that were already in place.
The team says the system significantly outperforms automated car-counting methods currently in use, with an average accuracy rate of more than 96%.
OverFeat Framework is a combination of convolution neural networks and image classification and recognition techniques. The system is based on two algorithms: the Background Subtraction Method and OverFeat Framework using the Python language for automatic car counting.
"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," says FAU professor Aleksandar Stevanovic.
From FAU News Desk
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found