Feedforward and Feedback Processing of Spatiotemporal Tubes for Efficient Object Localization

Khari Jarrett, Joachim Lohn-Jaramillo, Elijah Bowen, Laura Ray, Richard Granger

Abstract

We introduce a new set of mechanisms for tracking entities through videos, at substantially less expense than required by standard methods. The approach combines inexpensive initial processing of individual frames together with integration of information across long time spans (multiple frames), resulting in the recognition and tracking of spatially and temporally contiguous entities, rather than focusing on the individual pixels that comprise those entities.

Download


Paper Citation


in Harvard Style

Jarrett K., Lohn-Jaramillo J., Bowen E., Ray L. and Granger R. (2019). Feedforward and Feedback Processing of Spatiotemporal Tubes for Efficient Object Localization.In Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-351-3, pages 377-387. DOI: 10.5220/0007313603770387


in Bibtex Style

@conference{icpram19,
author={Khari Jarrett and Joachim Lohn-Jaramillo and Elijah Bowen and Laura Ray and Richard Granger},
title={Feedforward and Feedback Processing of Spatiotemporal Tubes for Efficient Object Localization},
booktitle={Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2019},
pages={377-387},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007313603770387},
isbn={978-989-758-351-3},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Feedforward and Feedback Processing of Spatiotemporal Tubes for Efficient Object Localization
SN - 978-989-758-351-3
AU - Jarrett K.
AU - Lohn-Jaramillo J.
AU - Bowen E.
AU - Ray L.
AU - Granger R.
PY - 2019
SP - 377
EP - 387
DO - 10.5220/0007313603770387