Traffic flow estimation with data from a video surveillance camera

Abstract

Urbanization and increased building density of cities are essential features of modern society. Not only does such a way of life bring economic benefits, but it also poses a new set of problems for city authorities. One of these problems is efficient traffic management and analysis. High population density leads to the tremendous number of personal cars, an increased number of freight vehicles for transportation of commodities and goods, tight pedestrian traffic. Transportation tasks can no longer be addressed by sub-optimal heuristics, based on the small amount of the manually gathered statistics. To make efficient decisions, forecast and assess their consequences, authorities require an automated system for analyzing traffic flow throughout the city. Nowadays, many cities have low-cost video surveillance systems, also known as closed-circuit television (CCTV). They exhibit rapid growth nowadays and usually include heterogeneous cameras with various resolution, mounting points, and frame rates [43]. CCTV works 24 h a day, 7 days a week and generates a massive amount of information, called Big Data. Among other applications, this data can serve as a foundation for the automated traffic surveillance system.

A Systematic Analysis of Big Image Data Methodologies in Various Applications

“…Fedorov, et al [17] proposed a region based heuristic method for vehicles movement classification. Several modification has been applied on the Faster R-CNN such as focal loss, anchors optimization, adaptive feature pooling and additional mask branch.…”

The Capacity of the Road Network: Data Collection and Statistical Analysis of Traffic Characteristics

“…These methods solve the problem of combining on a frame-by-frame basis, but their combinatorial complexity exponentially depends on the number of objects being tracked, which makes them unsuitable for real-time tracking. The developed technology allows you to calculate and classify vehicles in the directions of movement with an average percentage error of less than 10% [5]. Our solution allows to increase the capacity and safety of intersection c given the nature and parameters cross the roadway in groups of pedestrians and drivers behavior to ensure minimal inconvenience to pedestrians.…”

A New Model for Locating Plate Recognition Devices to Minimize the Impact of the Uncertain Knowledge of the Routes on Traffic Estimation Results

“…As is well known, estimating the origin-destination trip matrix, route flows, and link flows is essential to achieving efficient traffic management. Many authors have dealt with this problem, trying to estimate these traffic flows using either information from traditional sources such as traffic counts (see, among others, Castillo et al [1,2] and Perrakis et al [3]) or information from more innovative sources such as mobile phones and GPS data (Huang et al [4], Ibarra-Espinosa et al [5], and Moreira-Matias et al [6]), Big Data (Toole et al [7] and Zin et al [8]), or automatic vehicle identification (AVI) data (Castillo et al [9], Fu et al [10], and Fedorov et al [11], among others).…”