X3ogre: Connecting X3D to a State of the Art Rendering Engine
Proceedings Web3D 2017
International Conference on 3D Web Technology (WEB3D) <22, 2017, Brisbane, Australia>
We connect X3D to the state of the art OGRE renderer using our prototypical x3ogre implementation. At this we perform a comparison of both on a conceptual level, highlighting similarities and differences. Our implementation allows swapping X3D concepts for OGRE concepts and vice versa. We take advantage of this to analyse current shortcomings in X3D and propose X3D extensions to overcome those.
Path Prediction in Multiagent Pedestrian Scenario
Darmstadt, TU, Master Thesis, 2015
A great task humans can carry out by means of visual perception is to predict the movement of objects based on the previous behavior. This task can - to a certain extent - also be applied if no previous behavior has been seen, e.g. estimating the future position of an object by just looking at a single image. In this master thesis, the task of estimating the behavior of multiple agents in an image sequence was carried out. Based on a training set of pedestrian data, features have been extracted and via machine learning arranged into a framework, which helps to predict the future position of all the identified agents in the sequence. This prediction algorithm was applied to two data sets. To evaluate the progress over a state of the art single agent path prediction approach, which was modified to better fit the multi agent case, new metrics were introduced for rating path prediction approaches.