Předpovídání trajektorie vozidel a chodců pro asistenční systémy řízení

This bachelor thesis deals with representation of a traffic scene by processing monocular video sequence. I try to predict a trajectory of detected vehicles in a short time horizon, based on created representation. Current approaches use multiple expensive sensors to gather instant information of environment. In the thesis I introduce technique, which is able to extract data from an environment by image processing techniques without the need of expensive sensors.  The result of this work is a system creating opportunity to reduce the sensor costs of a system for scene representation and  trajectory prediction of vehicles in the scene. In addition, comparison of models trained on differently processed data is provided, as well as data about how my system approximates the most reliable prediction models.

trajectory prediction, autonomous systems, path estimation, object detecion, image processing, raster representation, 3D detection, object tracking, localization, semantic segmentation, monocular video