Conventional trajectory-based vehicular traffic analysis approaches work well in simple environments such as a single crossing but they do not scale to more structurally complex environments such as networks of interconnected crossings (e.g. urban road networks). Local trajectory models are necessary to cope with the multi-modality of such structures, which in turn introduces new challenges. These larger and more complex environments increase the occurrences of non-consistent lack of motion and self-overlaps in observed trajectories which impose further challenges. In this paper we consider the problem of motion pattern recognition in the setting of sequential local motion pattern models. That is, classifying sub-trajectories from observed trajectories in accordance with which motion pattern that best explains it. We introduce a Gaussian process (GP) based modeling approach which outperforms the state-of-the-art GP based motion pattern approaches at this task. We investigate the impact of varying local model overlap and the length of the observed trajectory trace on the classification quality. We further show that introducing a pre-processing step filtering out stops from the training data significantly improves the classification performance. The approach is evaluated using real GPS position data from city buses driving in urban areas for extended periods of time. ; CUGS ; VR ; CADICS ; ELLIIT ; WASP
Gaussian Process Based Motion Pattern Recognition with Sequential Local Models
2018-01-01
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
DDC: | 629 |
Ship control motion forecasting method and system based on local Gaussian process regression
Europäisches Patentamt | 2023
|Time sequential nonlinear correlations for optical pattern recognition
British Library Conference Proceedings | 2001
|Gaussian process motion graph models for smooth transitions among multiple actions
British Library Online Contents | 2012
|Combining local-physical and global-statistical models for sequential deformable shape from motion
BASE | 2017
|