Detecting convoys in networks of short-range sensors
Le résumé fourni par la source
Detecting groups of vehicles traveling together as a convoy is an important problem in military and law enforcement applications. License plate recognition sensors are an emerging technology which can be used to solve this problem. The sensors are deployed throughout road networks across the world and meta-data about the vehicles passing in front of each sensor is collected. These provide discrete, irregularly sampled, time series information about where vehicles are traveling. This thesis proposes a method to solve the problem of detecting convoys utilizing irregularly sampled time series information about objects moving between sensors. The system presented in this thesis is a hypothesis test to determine if a pair of objects is traveling in a convoy or independently. The models for the hypothesis test are based on a semi-Markov process model for an object traveling between sensor locations which are the states in the Markov process. The system is analyzed utilizing a real dataset which shows that it does in fact detect pairs of objects which appear to be traveling together in a convoy. It is then analyzed utilizing a simulated dataset containing an equal number of pairs traveling in convoys as well as independently and the performance on the number of accurate detections as well as false detections is summarized. The system described solves the problem of detecting convoys utilizing limited-range sensors, such as license plate recognition sensors. The system presented is represented as a general system determining if "objects" are moving together in a path that appears tied together versus independently. This allows the system to have future applications to other fields that is not just license plate recognition information of vehicular movements. It can be generalized to other problems of determining similar paths in Markov chain environments.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.