Bachelor Thesis Maneuver Identification in Highway Traffic Using Elastic Template Matching

Background Early identification and interpretation of traffic maneuvers will become key elements of modern driver assistance systems. Currently, only simple traffic situations can be detected by using a decision tree (DT) procedure in most cases. Even though this approach is straightforward, it still requires an expert to build a different DT for every maneuver. Moreover, for complex driving behaviors such simple logic identification does not work. In a background work, a template (or pattern) matching (TM) algorithm for maneuver recognition in highway traffic with a particular focus on a cut-in maneuver has been developed. Goal The goal of this work will be to apply the developed TM algorithm to other (simple) driving maneuvers, such as following, pull-in and pull-out, overtaking etc. The idea is using the real data collected from sensors to do the following: 1. Extract the maneuvers under study from the data; 2. Build a maneuver template; 3. Adjust the algorithm parameters; 4. Evaluate the developed identifications for each of the maneuvers. Optional An on-line algorithm for a full description of the surrounding highway traffic.