• English
  • Deutsch
  • Log In
    or
  • Research Outputs
  • Projects
  • Researchers
  • Institutes
  • Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Konferenzschrift
  4. MissFormer: (In-)Attention-Based Handling of Missing Observations for Trajectory Filtering and Prediction
 
  • Details
  • Full
Options
2021
Conference Paper
Titel

MissFormer: (In-)Attention-Based Handling of Missing Observations for Trajectory Filtering and Prediction

Abstract
In applications such as object tracking, time-series data inevitably carry missing observations. Following the success of deep learning-based models for various sequence learning tasks, these models increasingly replace classic approaches in object tracking applications for inferring the objects' motion states. While traditional tracking approaches can deal with missing observations, most of their deep counterparts are, by default, not suited for this. Towards this end, this paper introduces a transformer-based approach for handling missing observations in variable input length trajectory data. The model is formed indirectly by successively increasing the complexity of the demanded inference tasks. Starting from reproducing noise-free trajectories, the model then learns to infer trajectories from noisy inputs. By providing missing tokens, binary-encoded missing events, the model learns to in-attend to missing data and infers a complete trajectory conditioned on the remaining inputs. In the case of a sequence of successive missing events, the model then acts as a pure prediction model. The abilities of the approach are demonstrated on synthetic data and real-world data reflecting prototypical object tracking scenarios.
Author(s)
Becker, Stefan
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Hug, Ronny
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Hübner, Wolfgang
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Arens, Michael
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Morris, Brendan Tran
Hauptwerk
Advances in Visual Computing. 16th International Symposium, ISVC 2021. Proceedings. Pt.I
Konferenz
International Symposium on Visual Computing (ISVC) 2021
DOI
10.1007/978-3-030-90439-5_41
File(s)
N-644004.pdf (1.3 MB)
Language
English
google-scholar
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB
Tags
  • transformer

  • Trajectory Data

  • fzml

  • Missing Input Data

  • Missing Observations

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Send Feedback
© 2022