Improving a real-time object detector with compact temporal information
Ahrnbom, Martin; Bornø Jensen, Morten; Åström, Karl; Nilsson, Mikael, et al. (2018-01-19). Improving a real-time object detector with compact temporal information International Conference on Computer Vision Workshops, 2017 : Computer Vision for Road Scene Understanding and Autonomous Driving Workshop, 190 - 197. 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017. Venice, Italy: IEEE - Institute of Electrical and Electronics Engineers Inc.
Conference Proceeding/Paper
|
Published
|
English
Authors:
Ahrnbom, Martin
;
Bornø Jensen, Morten
;
Åström, Karl
;
Nilsson, Mikael
, et al.
Department:
Mathematics (Faculty of Engineering)
Mathematical Imaging Group
eSSENCE: The e-Science Collaboration
ELLIIT: the Linköping-Lund initiative on IT and mobile communication
Project:
Semantic Mapping and Visual Navigation for Smart Robots
In-Depth understanding of accident causation for Vulnerable road users
Lund University AI Research
Research Group:
Mathematical Imaging Group
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.
Cite this