Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

A TWO-STREAM SIAMESE NEURAL NETWORK FOR VEHICLE RE-IDENTIFICATION BY USING NON-OVERLAPPING CAMERAS

Abstract: 

We describe in this paper a Two-Stream Siamese Neural Network for vehicle re-identification. The proposed network is fed simultaneously with small coarse patches of the vehicle shape’s, with 96 × 96 pixels, in one stream, and fine features extracted from license plate patches, easily readable by humans, with 96 × 48 pixels, in the other one. Then, we combined the strengths of both streams by merging the Siamese distance descriptors with a sequence of fully connected layers, as an attempt to tackle a major problem in the field, false alarms caused by a huge number of car design and models with nearly the same appearance or by similar license plate strings. In our experiments, with 2 hours of videos containing 2982 vehicles, extracted from two low-cost cameras in the same roadway, 546 ft away, we achieved a F-measure and accuracy of 92.6% and 98.7%, respectively. We show that our network, available at https://github.com/icarofua/siamese-two-stream, outperforms other One-Stream architectures, even if they use higher resolution image features.

up
0 users have voted:

Paper Details

Authors:
Icaro Oliveira, Keiko Fonseca, Rodrigo Minetto
Submitted On:
19 September 2019 - 6:09am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Icaro Oliveira de Oliveira
Paper Code:
2372
Document Year:
2019
Cite

Document Files

ICIP 2019.pdf

(82)

Keywords

Subscribe

[1] Icaro Oliveira, Keiko Fonseca, Rodrigo Minetto, "A TWO-STREAM SIAMESE NEURAL NETWORK FOR VEHICLE RE-IDENTIFICATION BY USING NON-OVERLAPPING CAMERAS", IEEE SigPort, 2019. [Online]. Available: http://sigport.org/4719. Accessed: Nov. 29, 2020.
@article{4719-19,
url = {http://sigport.org/4719},
author = {Icaro Oliveira; Keiko Fonseca; Rodrigo Minetto },
publisher = {IEEE SigPort},
title = {A TWO-STREAM SIAMESE NEURAL NETWORK FOR VEHICLE RE-IDENTIFICATION BY USING NON-OVERLAPPING CAMERAS},
year = {2019} }
TY - EJOUR
T1 - A TWO-STREAM SIAMESE NEURAL NETWORK FOR VEHICLE RE-IDENTIFICATION BY USING NON-OVERLAPPING CAMERAS
AU - Icaro Oliveira; Keiko Fonseca; Rodrigo Minetto
PY - 2019
PB - IEEE SigPort
UR - http://sigport.org/4719
ER -
Icaro Oliveira, Keiko Fonseca, Rodrigo Minetto. (2019). A TWO-STREAM SIAMESE NEURAL NETWORK FOR VEHICLE RE-IDENTIFICATION BY USING NON-OVERLAPPING CAMERAS. IEEE SigPort. http://sigport.org/4719
Icaro Oliveira, Keiko Fonseca, Rodrigo Minetto, 2019. A TWO-STREAM SIAMESE NEURAL NETWORK FOR VEHICLE RE-IDENTIFICATION BY USING NON-OVERLAPPING CAMERAS. Available at: http://sigport.org/4719.
Icaro Oliveira, Keiko Fonseca, Rodrigo Minetto. (2019). "A TWO-STREAM SIAMESE NEURAL NETWORK FOR VEHICLE RE-IDENTIFICATION BY USING NON-OVERLAPPING CAMERAS." Web.
1. Icaro Oliveira, Keiko Fonseca, Rodrigo Minetto. A TWO-STREAM SIAMESE NEURAL NETWORK FOR VEHICLE RE-IDENTIFICATION BY USING NON-OVERLAPPING CAMERAS [Internet]. IEEE SigPort; 2019. Available from : http://sigport.org/4719