We present a method to model and classify trajectory data that come from surveillance videos. Observations of the locations of moving entities are used to estimate their expected velocity in the scene. Such estimation is performed by a Gaussian process regression that enables to approximate probabilistically the expected velocity of entities given some observed evidence in the scene. Subsequently, regions where estimations have high certainty are decomposed into zones by superpixel segmentation. Each zone represents a region where motions of entities can be explained by a quasilinear dynamical model. We evaluated the proposed method with two datasets and confirmed its reliability for characterizing and classifying trajectories.
|Titolo:||Modeling and classification of trajectories based on a Gaussian process decomposition into discrete components|
|Data di pubblicazione:||2017|
|Appare nelle tipologie:||04.01 - Contributo in atti di convegno|
File in questo prodotto:
|Modeling and classification of trajectories based on a Gaussian process decomposition into discrete components.pdf||Articolo principale||Documento in versione editoriale||Administrator Richiedi una copia|