Image and Video Understanding Lab
Home
People
Current
Alumni
Collaboration
Visiting
Research
Publications
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2008
2007
2005
Datasets
Join Us
Media
Albums
Image Gallery
Large Scale Asset Extraction for Urban Images
Home
>
Publications
>
Large Scale Asset Extraction for Urban Images
Large Scale Asset Extraction for Urban Images
Bibliography:
Lama Affara, Liangliang Nan, Bernard Ghanem, Peter Wonka
"Large Scale Asset Extraction for Urban Images"
European Conference on Computer Vision (ECCV 2016)
Publication Extra Information:
[supplementary material]
[video]
[code]
Authors:
Lama Affara, Liangliang Nan, Bernard Ghanem, Peter Wonka
Keywords:
urban assets, object proposals, image rectification
Year:
2016
Abstract:
Abstract
Object proposals are currently used for increasing the computational efficiency of object detection. We propose a novel adaptive pipeline for interleaving object proposals with object classification and use it as a formulation for asset detection. We first preprocess the images using a novel and efficient rectification technique. We then employ a particle filter approach to keep track of three priors, which guide proposed samples and get updated using classifier output. Tests performed on over 1000 urban images demonstrate that our rectification method is faster than existing methods without loss in quality, and that our interleaved proposal method outperforms current state-of-the-art. We further demonstrate that other methods can be improved by incorporating our interleaved proposals.
Website
Download Document
No
©
2019
King Abdullah University of Science and Technology. All rights reserved.
|
Team Site
Image and Video Understanding Lab
http://
http://
http://
The beginning and end dates for each internship will be agreed upon between the Faculty and the Intern. Visa processing time will be a determining factor in actual start date. Minimum period is three months. Maximum period is six months.
5