Home
Uni-Logo
 

Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior

IEEE International Conference on Computer Vision and Pattern Recognition (CVPR): 4354-4363, 2020
Abstract: In this paper, we investigate the problem of anticipating future dynamics, particularly the future location of other vehicles and pedestrians, in the view of a moving vehicle. We approach two fundamental challenges: (1) the partial visibility due to the egocentric view with a single RGB camera and considerable field-of-view change due to the egomotion of the vehicle; (2) the multimodality of the distribution of future states. In contrast to many previous works, we do not assume structural knowledge from maps. We rather estimate a reachability prior for certain classes of objects from the semantic map of the present image and propagate it into the future using the planned egomotion. Experiments show that the reachability prior combined with multi-hypotheses learning improves multimodal prediction of the future location of tracked objects and, for the first time, the emergence of new objects. We also demonstrate promising zero-shot transfer to unseen datasets.
Paper Supplementary Poster GitHub

Images and movies

 

See also

Teaser Figure


Short Advertisement


Supplementary Results


BibTex reference

@InProceedings{MCBB20,
  author       = "O. Makansi and {\"O}. {\c{C}}i{\c{c}}ek and K. Buchicchio and T. Brox",
  title        = "Multimodal Future Localization and Emergence Prediction for Objects in Egocentric View with a Reachability Prior",
  booktitle    = "IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)",
  pages        = "4354-4363",
  month        = " ",
  year         = "2020",
  keywords     = "future prediction, multimodal distribution learning, future localization, egocentric view, context-awareness, trajectory forecasting, autonomous driving, uncertainty estimation, autonomous systems, multihypotheses learning",
  url          = "http://lmbweb.informatik.uni-freiburg.de/Publications/2020/MCBB20"
}

Other publications in the database