Engineering Commons^™

Modeling Pedestrian Behavior In Video, Paul Scovanner

Electronic Theses and Dissertations

The purpose of this dissertation is to address the problem of predicting pedestrian movement and behavior in and among crowds. Specifically, we will focus on an agent based approach where pedestrians are treated individually and parameters for an energy model are trained by real world video data. These learned pedestrian models are useful in applications such as tracking, simulation, and artificial intelligence. The applications of this method are explored and experimental results show that our trained pedestrian motion model is beneficial for predicting unseen or lost tracks as well as guiding appearance based tracking algorithms. The method we have developed …

Estimation Of Pedestrian Safety At Intersections Using Simulation And Surrogate Safety Measures, Nithin K. Agarwal

University of Kentucky Doctoral Dissertations

With the number of vehicles increasing in the system every day, many statewide policies across the United States aim to increase the use of non- motorized transportation modes. This could have safety implications because the interaction between motorists and non-motorists could increase and potentially increasing pedestrian-vehicle crashes. Few models that predict the number of pedestrian crashes are not sensitive to site-specific conditions or intersection designs that may influence pedestrian crashes. Moreover, traditional statistical modeling techniques rely extensively on the sparsely available pedestrian crash database.

This study focused on overcoming these limitations by developing models that quantify potential interactions between pedestrians …