Traffic flow estimation with data from a video surveillance camera

• Published in: Journal of big data Vol. 6; no. 1; pp. 1 - 15
• Main Authors: Fedorov, Aleksandr, Nikolskaia, Kseniia, Ivanov, Sergey, Shepelev, Vladimir, Minbaleev, Alexey
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 07.08.2019; Springer Nature B.V; SpringerOpen
• Subjects: Algorithms; Anchors; Big Data; Cameras; Classification; Communications Engineering; Computational Science and Engineering; Computer Science; Convolutional neural network; Counting; Data Mining and Knowledge Discovery; Database Management; Driving; Heuristic methods; Information Storage and Retrieval; Mathematical Applications in Computer Science; Methodology; Networks; Optimization; Surveillance; Surveillance data; Traffic analysis; Traffic flow; Traffic flow estimation; Traffic surveillance; Vehicle detection; Vehicles; Video data; Vehicle detection; Traffic analysis; Traffic flow estimation; Convolutional neural network; Surveillance data
• ISSN: 2196-1115; 2196-1115
• DOI: 10.1186/s40537-019-0234-z

This study addresses the problem of traffic flow estimation based on the data from a video surveillance camera. Target problem here is formulated as counting and classifying vehicles by their driving direction. This subject area is in early development, and the focus of this work is only one of the busiest crossroads in city Chelyabinsk, Russia. To solve the posed problem, we employed the state-of-the-art Faster R-CNN two-stage detector together with SORT tracker. A simple regions-based heuristic algorithm was used to classify vehicles movement direction. The baseline performance of the Faster R-CNN was enhanced by several modifications: focal loss, adaptive feature pooling, additional mask branch, and anchors optimization. To train and evaluate detector, we gathered 982 video frames with more than 60,000 objects presented in various conditions. The experimental results show that the proposed system can count vehicles and classify their driving direction during weekday rush hours with mean absolute percentage error that is less than 10%. The dataset presented here might be further used by other researches as a challenging test or additional training data.