Abstract
Automatic traffic flow classification is useful to reveal road congestions and accidents. Nowadays, roads and highways are equipped with a huge amount of surveillance cameras, which can be used for real-time vehicle identification, and thus providing traffic flow estimation. This research provides a comparative analysis of state-of-the-art object detectors, visual features, and classification models useful to implement traffic state estimations. More specifically, three different object detectors are compared to identify vehicles. Four machine learning techniques are successively employed to explore five visual features for classification aims. These classic machine learning approaches are compared with the deep learning techniques. This research demonstrates that, when methods and resources are properly implemented and tested, results are very encouraging for both methods, but the deep learning method is the most accurately performing one reaching an accuracy of 99.9% for binary traffic state classification and 98.6% for multiclass classification.
Highlights
Urban roads and highways have, nowadays, plenty of surveillance cameras initially installed for various security reasons
Two approaches are compared in this research: The first one relies on visual features evaluated from traffic videos through computer vision algorithms using state-of-the-art object detectors and classifiers, the latter considers deep learning models able to automatically extract features from videos needed for the final classification
Metrics boxes provided by the object detector can be compared to the real vehicle annotation the most accurately performing one
Summary
Urban roads and highways have, nowadays, plenty of surveillance cameras initially installed for various security reasons. Traffic videos coming from these cameras can be used to estimate the traffic state, to automatically identify congestions, accidents, and infractions, and helping the transport management to face critical aspects of the mobility. This information can be used to plan the mid and long-term roads mobility strategy. This is a clear example of a smart city application having a strong impact on citizens’ security [1]. Studies dealing with traffic state estimation by videos adopt a common processing pipeline, which includes the following: . It is difficult to identify and select the best algorithms to be adopted because, often, systems reported in many studies are different at many stages, as well as adopt different datasets and testing conditions. This research provides a brief review of the most used techniques and reports an extended and systematic experimental comparison under common set-up conditions, highlighting strengths
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
