Road Congestion Detection Based on Trajectory Stay-Place Clustering

Abstract

The results of road congestion detection can be used for the rational planning of travel routes and as guidance for traffic management. The trajectory data of moving objects can record their positions at each moment and reflect their moving features. Utilizing trajectory mining technology to effectively identify road congestion locations is of great importance and has practical value in the fields of traffic and urban planning. This paper addresses the issue by proposing a novel approach to detect road congestion locations based on trajectory stay-place clustering. First, this approach estimates the speed status of each time-stamped location in each trajectory. Then, it extracts the stay places of the trajectory, each of which is denoted as a seven-tuple containing information such as starting and ending time, central coordinate, average direction difference, and so on. Third, the time-stamped locations included in stay places are partitioned into different stay-place equivalence classes according to the timestamps. Finally, stay places in each equivalence class are clustered to mine the congestion locations of multiple trajectories at a certain period of time. Visual representation and experimental results on real-life cab trajectory datasets show that the proposed approach is suitable for the detection of congestion locations at different timestamps.

An Optimal Path-Finding Algorithm in Smart Cities by Considering Traffic Congestion and Air Pollution

“…The algorithm of [12] selects the optimal path based on five different factors including the average travel speed of the traffic, vehicles density, roads width, road traffic signals, and the roads' length, while the proposed algorithm considered traffic density and estimates average speed based on the traffic density. However, both algorithms have better performance than the method introduced in [9]. This figure shows for the proposed algorithm, the path may be longer when the air pollution factor is considered.…”

“…In that research, researchers used a K-means clustering algorithm for clustering traffic congestion. Similarly, authors in [9] used K-means clustering algorithms for traffic congestion. Due to fuzzy clustering's advantages, in [10], researchers used the C-means algorithm for clustering traffic congestion.…”

Public Traffic Congestion Estimation Using an Artificial Neural Network

“…Many studies have been conducted to study traffic congestion by using floating car data (FCD) from different aspects, including traffic congestion estimation, traffic congestion prediction, and traffic flow propagation [16][17][18]. For example, Yu et al [19] proposed a novel approach by estimating the speed in each trajectory to detect congestion locations of road segments based on stay-place clustering. By treating the congestion level analysis as a regression problem, Wang et al [20] proposed a locality constraint distance metric to characterize the congestion level.…”

“…The previous studies have achieved good performance in traffic congestion estimation, which provides practical applications in the fields of urban planning and PTN optimization [19]. In practice, no fixed definitions have been proposed for the level of traffic congestion, while the average travel speed for a road segment is the most commonly used indicator for traffic congestion estimation [15,24].…”

Grid‐Based Whole Trajectory Clustering in Road Networks Environment

“…The massive position and movement information of moving objects are generated continuously, forming large-scale trajectory data. It is of great academic significance and commercial value to mine the underlying distribution information and the evolvement rules, such as urban function partition (Niu et al [1]), traffic jam prediction (Yu et al [2]), and privacy protection (Wang et al [3]). In addition, some classical trajectory clustering algorithms such as DBSCAN (Ester et al [4]) are widely used in anomaly trajectory detection and anomaly event preven-tion (Belhadi et al [5], Belhadi et al [6], Djenouri et al [7]).…”