Trajectories for novel and detailed traffic information

Abstract

Trajectories based on GPS tracks have been studied for a number of years but only to a limited degree been used for analyzing and monitoring traffic. This paper shows how novel and important information about traffic can be computed from trajectories. Concretely the paper proposes to compute the central metric free-flow speed from trajectories, instead of using point-based measurements such as inductionloops. This free-flow speed is widely used to compute and monitor the congestion level. The paper argues that the actual travel-time is a more accurate metric. The paper suggests a novel approach to analyzing individual intersections that enables traffic analysts to compute queue lengths and estimated time to pass an intersection. Finally, the paper uses associative rule mining for evaluating green waves on road stretches. Such information can be used to verify that signalized intersections are correctly coordinated, and navigational device manufacturers to advice drivers in real-time on expected behavior of signalized intersections. The main conclusion is that trajectories can provide novel insight into the actual traffic situation that is not possible using existing approaches. Further, extracting this information requires no expensive changes to the road-network infrastructure, which is a problem with the technologies currently used.

Visual Traffic Jam Analysis Based on Trajectory Data

“…Krogh et al [25] have studied green waves on road stretches with signalized intersections. However, this differs from traffic jam propagation, and their scenario is much simpler than our city network.…”

“…Unfortunately we do not have it in our data. Krogh et al [25] estimate free-flow speed from non-peak hour speed records. However, in Beijing different dWays may have different nonpeak hours.…”

“…As far as we know, there is no previous work in visual analytics that deeply studies these traffic jam aspects. Traditional traffic jam detection methods are based on road side sensors, like induction loops or radar [31] and monitor only a few critical points [25]. A GPS based method, however, can theoretically monitor a complete road network.…”

User‐centered road network traffic analysis with MobilityDB

“…There is an extensive literature about the use of car data to compute road performance indicators . In Krogh et al (2012), GPS trajectories are used to estimate the free flow speed over road segments, to compute flow indicators at intersections, and to assess the coordination between the different traffic signals that affect traffic flow on a road. A microscopic analysis is performed for two selected roads using a set of GPS trajectories.…”

Hierarchical and Networked Vehicle Surveillance in ITS: A Survey

“…Traditional traffic jam detection methods are based on road side sensors, such as induction loops or radar and monitor only a few critical points [229]. A GPS-based method, however, can theoretically monitor a complete road network.…”