Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Unpaired Cross-Spectral Pedestrian Detection Via Adversarial Feature Learning
 
Loading...
Thumbnail Image
conference paper

Unpaired Cross-Spectral Pedestrian Detection Via Adversarial Feature Learning

Kim, Minsu
•
Joung, Sunghun
•
Park, Kihong
Show more
January 1, 2019
2019 Ieee International Conference On Image Processing (Icip)
26th IEEE International Conference on Image Processing (ICIP)

Even though there exist significant advances in recent studies, existing methods for pedestrian detection still have shown limited performances under challenging illumination conditions especially at nighttime. To address this, cross-spectral pedestrian detection methods have been presented using color and thermal, and shown substantial performance gains on the challenging circumstances. However, their paired cross-spectral settings have limited applicability in real-world scenarios. To overcome this, we propose a novel learning framework for cross-spectral pedestrian detection in an unpaired setting. Based on an assumption that features from color and thermal images share their characteristics in a common feature space to benefit their complement information, we design the separate feature embedding networks for color and thermal images followed by sharing detection networks. To further improve the cross-spectral feature representation, we apply an adversarial learning scheme to intermediate features of the color and thermal images. Experiments demonstrate the outstanding performance of the proposed method on the KAIST multi-spectral benchmark in comparison to the state-of-the-art methods.

  • Details
  • Metrics
Type
conference paper
DOI
10.1109/ICIP.2019.8803098
Web of Science ID

WOS:000521828601156

Author(s)
Kim, Minsu
•
Joung, Sunghun
•
Park, Kihong
•
Kim, Seungryong  
•
Sohn, Kwanghoon
Date Issued

2019-01-01

Publisher

IEEE

Publisher place

New York

Published in
2019 Ieee International Conference On Image Processing (Icip)
ISBN of the book

978-1-5386-6249-6

Series title/Series vol.

IEEE International Conference on Image Processing ICIP

Start page

1650

End page

1654

Subjects

cross-spectral pedestrian detection

•

adversarial learning

•

common feature space

Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
IVRL  
Event nameEvent placeEvent date
26th IEEE International Conference on Image Processing (ICIP)

Taipei, TAIWAN

Sep 22-25, 2019

Available on Infoscience
April 17, 2020
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/168222
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés