Original title:
Realtime Pedestrian Recognition Using Siamese
Network
Authors:
Rajnoha, Martin Document type: Papers
Language:
eng Publisher:
Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií 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:
deep learning; pedestrian; recognition; Siamese; surveillance Host item entry: Proceedings of the 24th Conference STUDENT EEICT 2018, ISBN 978-80-214-5614-3
Institution: Brno University of Technology
(web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library. Original record: http://hdl.handle.net/11012/138273