In recent years, many countries have developed a variety of algorithms concerning automatic traffic congestion identification (ATCI). Based on the well-known Antony Downs’ Law of Peak-Hour Traffic Congestion, traffic demand has the tendency to be greater than traffic supply. Therefore, traffic congestion cannot be solved simply through increasing the construction of road infrastructure or expanding the scale of the network with the aim of satisfying the increasing traffic demand. It is necessary for us to strengthen traffic control and transform our existing road transport system by using advanced intelligent technology to greatly improve the traffic capacity and service quality of road networks.

The first step is to automatically identify traffic congestion before traffic control. Based on the detection and quantitative analysis of physical indexes related to traffic, and due to the accumulated experience of long-term research, we can develop a thorough understanding of the formation, spread, and disappearance of traffic congestion. This can then guide the establishment of road planning and traffic policy. Early ATCI algorithms, which mainly regard traffic emergencies as the research object, are usually established based on traffic data such as traffic flow, traffic share, and location speed. In terms of the data techniques employed, they are mainly composed of decision trees, statistical analysis, smoothing and filtering, and other conventional methods. The content and methods of research in ATCI have changed significantly in recent years, in particular the development of big data and computational intelligence theory and methods. Therefore, the development of ATCI is a vital part of resolving the traffic congestion problems in the future.

The purpose of this Special Issue is to promote research concerning all aspects of traffic systems, focusing on the identification and management of traffic congestion. We welcome both original research and review articles.

Potential topics include but are not limited to the following:

• Definition of under-sampled trajectory information and sampling threshold analysis methods
• Path matching methods and path reconstruction of under-sampled trajectory data
• Road network traffic flow perception
• Section travel speed perception
• Intersection delay perception
• Changing rules of intersection bottleneck expression indexes
• Intersection dynamic bottleneck expression indexes
• The expression of regional traffic state imbalances
• Regional traffic bottleneck expression index
• Formation mechanisms of intersection bottlenecks
• Formation mechanisms of regional bottlenecks
• Artificial Intelligence (AI) solutions in ATCI
• Big data solutions in ATCI