Improving a real-time object detector with compact temporal information

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

Abstract

Neural networks designed for real-time object detection
have recently improved significantly, but in practice, look-
ing at only a single RGB image at the time may not be ideal.
For example, when detecting objects in videos, a foreground
detection algorithm can be used to obtain compact temporal
data, which can be fed into a neural network alongside RGB
images. We propose an approach for doing this, based on
an existing object detector, that re-uses pretrained weights
for the processing of RGB images. The neural network was
tested on the VIRAT dataset with annotations for object de-
tection, a problem this approach is well suited for. The ac-
curacy was found to improve significantly (up to 66%), with
a roughly 40% increase in computational time.

Detaljer

Författare
Enheter & grupper
Externa organisationer
  • Aalborg University
Forskningsområden

Ämnesklassifikation (UKÄ) – OBLIGATORISK

  • Datorseende och robotik (autonoma system)
Originalspråkengelska
Titel på värdpublikationInternational Conference on Computer Vision Workshops, 2017
Undertitel på gästpublikationComputer Vision for Road Scene Understanding and Autonomous Driving Workshop
FörlagIEEE--Institute of Electrical and Electronics Engineers Inc.
Sidor190-197
Antal sidor8
StatusPublished - 2018 jan 19
PublikationskategoriForskning
Peer review utfördJa
Evenemang16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italien
Varaktighet: 2017 okt 222017 okt 29

Konferens

Konferens16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017
LandItalien
OrtVenice
Period2017/10/222017/10/29

Related projects

Visa alla (3)