Multi-spectral SIFT for scene category recognition

Authors:
M. Brown;S. Susstrunk
Affiliations:
Sch. of Comput. & Commun. Sci., Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland;Sch. of Comput. & Commun. Sci., Ecole Polytech. Fed. de Lausanne (EPFL), Lausanne, Switzerland
Venue:
CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition
Year:
2011

Citing 0
Cited 6

Multi-spectral saliency detection

Pattern Recognition Letters
A new biologically inspired color image descriptor

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part V
Semantic image segmentation using visible and near-infrared channels

ECCV'12 Proceedings of the 12th international conference on Computer Vision - Volume 2
Multi-spectral dataset and its application in saliency detection

Computer Vision and Image Understanding
Robust blind motion deblurring using near-infrared flash image

Journal of Visual Communication and Image Representation
Similarity-based clustering by left-stochastic matrix factorization

The Journal of Machine Learning Research

Quantified Score

Hi-index	0.00

Visualization

Abstract

We use a simple modification to a conventional SLR camera to capture images of several hundred scenes in colour (RGB) and near-infrared (NIR). We show that the addition of near-infrared information leads to significantly improved performance in a scene-recognition task, and that the improvements are greater still when an appropriate 4-dimensional colour representation is used. In particular we propose MSIFT - a multispectral SIFT descriptor that, when combined with a kernel based classifier, exceeds the performance of state-of-the-art scene recognition techniques (e.g., GIST) and their multispectral extensions. We extensively test our algorithms using a new dataset of several hundred RGB-NIR scene images, as well as benchmarking against Torralba's scene categorization dataset.