With the rapid increase in urban development, it is critical to utilize dynamic sensor streams for traffic understanding, especially in larger cities where route planning or infrastructure planning is more critical. This creates a strong need to understand traffic patterns using ubiquitous sensors to allow city officials to be better informed when planning urban construction and to provide an understanding of the traffic dynamics in the city. In this study, we propose our framework ITSKG (Imagery-based Traffic Sensing Knowledge Graph) which utilizes the stationary traffic camera information as sensors to understand the traffic patterns. The proposed system extracts image-based features from traffic camera images, adds a semantic layer to the sensor data for traffic information, and then labels traffic imagery with semantic labels such as congestion. We share a prototype example to highlight the novelty of our system and provide an online demo to enable users to gain a better understanding of our system. This framework adds a new dimension to existing traffic modeling systems by incorporating dynamic image-based features as well as creating a knowledge graph to add a layer of abstraction to understand and interpret concepts like congestion to the traffic event detection system.
& Sheth, A.
(2017). A Knowledge Graph Framework for Detecting Traffic Events Using Stationary Cameras. .