Přístupnostní navigace
E-application
Search Search Close
Publication detail
RAJNOHA, M.
Original Title
Realtime Pedestrian Recognition Using Siamese Network
Type
conference paper
Language
English
Original Abstract
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.
Keywords
surveillance, pedestrian, recognition, Siamese, deep learning
Authors
Released
26. 4. 2018
Publisher
Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií
Location
Brno
ISBN
978-80-214-5614-3
Book
Proceedings of the 24rd Conference STUDENT EEICT 2018
Edition number
první
Pages from
441
Pages to
445
Pages count
5
BibTex
@inproceedings{BUT147104, author="Martin {Rajnoha}", title="Realtime Pedestrian Recognition Using Siamese Network", booktitle="Proceedings of the 24rd Conference STUDENT EEICT 2018", year="2018", number="první", pages="441--445", publisher="Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií", address="Brno", isbn="978-80-214-5614-3" }