Detail publikace

Realtime Pedestrian Recognition Using Siamese Network

RAJNOHA, M.

Originální název

Realtime Pedestrian Recognition Using Siamese Network

Anglický název

Realtime Pedestrian Recognition Using Siamese Network

Jazyk

en

Originální abstrakt

Image similarity measuring has many various applications. Pedestrian recognition is one of them and for the security purposes it is basically required to run in real-time. This paper proposes a deep Siamese neural network architecture for pedestrian recognition that achieves 70.28% accuracy on the test set containing 20 persons. Prediction of the model is fast enough for real-time processing.

Anglický abstrakt

Image similarity measuring has many various applications. Pedestrian recognition is one of them and for the security purposes it is basically required to run in real-time. This paper proposes a deep Siamese neural network architecture for pedestrian recognition that achieves 70.28% accuracy on the test set containing 20 persons. Prediction of the model is fast enough for real-time processing.

Dokumenty

BibTex


@inproceedings{BUT147104,
  author="Martin {Rajnoha}",
  title="Realtime Pedestrian Recognition Using Siamese Network",
  annote="Image similarity measuring has many various applications. Pedestrian recognition is one of them and for the security purposes it is basically required to run in real-time. This paper proposes a deep Siamese neural network architecture for pedestrian recognition that achieves 70.28% accuracy on the test set containing 20 persons. Prediction of the model is fast enough for real-time processing.",
  address="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  booktitle="Proceedings of the 24rd Conference STUDENT EEICT 2018",
  chapter="147104",
  howpublished="online",
  institution="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  year="2018",
  month="april",
  pages="441--445",
  publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií",
  type="conference paper"
}