A Knowledge Graph Framework for Detecting Traic Events Using Stationary Cameras

With the rapid increase in urban development, it is critical to utilize dynamic sensor streams for trac understanding, especially in larger cities where route planning or infrastructure planning is more critical. Œis creates a strong need to understand trac paŠerns using ubiquitous sensors to allow city ocials to be better informed when planning urban construction and to provide an understanding of the trac dynamics in the city. In this study, we propose our framework ITSKG (Imagery-based Trac Sensing Knowledge Graph) which utilizes the stationary trac camera information as sensors to understand the trac paŠerns. Œe proposed system extracts image-based features from trac camera images, adds a semantic layer to the sensor data for trac information, and then labels trac 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 beŠer understanding of our system. Œis framework adds a new dimension to existing trac 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 trac event detection system.