Improving a real-time object detector with compact temporal information

Ahrnbom, Martin (author): Lund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Lund University Research Groups,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH

Åström, Karl (author): Lund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Lund University Research Groups,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH

Nilsson, Mikael (author): Lund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Lund University Research Groups,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH

Ardö, Håkan (author): Lund University,Lunds universitet,Mathematical Imaging Group,Forskargrupper vid Lunds universitet,Matematik LTH,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Lund University Research Groups,Mathematics (Faculty of Engineering),Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH

(creator_code:org_t)

2018
2018
English 8 s.
In: International Conference on Computer Vision Workshops, 2017 : Computer Vision for Road Scene Understanding and Autonomous Driving Workshop - Computer Vision for Road Scene Understanding and Autonomous Driving Workshop. ; , s. 190-197

Related links:: http://openaccess.th... (free); show more...; http://dx.doi.org/10...; https://lup.lub.lu.s...; https://doi.org/10.1...; show less...

Abstract Subject headings

Neural networks designed for real-time object detectionhave 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 foregrounddetection algorithm can be used to obtain compact temporaldata, which can be fed into a neural network alongside RGBimages. We propose an approach for doing this, based onan existing object detector, that re-uses pretrained weightsfor the processing of RGB images. The neural network wastested 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%), witha roughly 40% increase in computational time.

By the author/editor: Ahrnbom, Martin; Bornø Jensen, Mo ...; Åström, Karl; Nilsson, Mikael; Ardö, Håkan; Moeslund, Thomas

About the subject

NATURAL SCIENCES: NATURAL SCIENCES; and Computer and Inf ...; and Computer Vision ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.