Improving a real-time object detector with compact temporal information

Martin Ahrnbom, Morten Bornø Jensen, Karl Åström, Mikael Nilsson, Håkan Ardö, Thomas Moeslund

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceedingPeer review

2 Citeringar (SciVal)


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.
Titel på värdpublikationInternational Conference on Computer Vision Workshops, 2017
Undertitel på värdpublikationComputer Vision for Road Scene Understanding and Autonomous Driving Workshop
FörlagIEEE - Institute of Electrical and Electronics Engineers Inc.
Antal sidor8
StatusPublished - 2018 jan. 19
Evenemang16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 - Venice, Italien
Varaktighet: 2017 okt. 222017 okt. 29


Konferens16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017

Ämnesklassifikation (UKÄ)

  • Datorseende och robotik (autonoma system)


Utforska forskningsämnen för ”Improving a real-time object detector with compact temporal information”. Tillsammans bildar de ett unikt fingeravtryck.

Citera det här