NSF Award
2324972
The broader impact/commercial potential of this I-Corps project focuses on assessing state-of-the-art technologies in artificial intelligence and computer vision for traffic visualization and simulation. This is important since the construction demands keep increasing in the post-pandemic era. At the moment, many simulators used the mock-up data or random data. Meanwhile, consulting firms still deploy humans using manual clickers to count vehicles in a period of several days or weeks. This process is time and labor consuming. This project will explore implementation and commercialization opportunities with a traffic analysis tool to visualize and simulate the traffic from the analyzed data. <br/><br/>This I-Corps project develops a system to analyze the traffic cameras. It applies state-of-the-art computer vision algorithms from object detection to trajectory-based tracking in order to improve the performance of traffic flow estimation. The technology analyzes the camera data in the context of a graph; the traffic of one node can affect another node in the traffic graph. Significantly, the visual data taken from one city camera grid can be used for other cities where the traffic situation remains the same. The technology also includes a city traffic planning simulator using the analyzed traffic data. The simulator is used to support metropolitan transportation planning. The addition or removal of any traffic infrastructure can be observed from the simulator. Therefore, the simulator results can guide engineers and city authorities in urban development planning.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
