TY  - CONF
AU  - Fahad Shahbaz Khan
AU  - Muhammad Anwer Rao
AU  - Joost Van de Weijer
AU  - Andrew Bagdanov
AU  - Maria Vanrell
AU  - Antonio Lopez
A2  - CVPR
PY  - 2012//
TI  - Color Attributes for Object Detection
BT  - 25th IEEE Conference on Computer Vision and Pattern Recognition
SP  - 3306
EP  - 3313
PB  - IEEE Xplore
KW  - pedestrian detection
N2  - State-of-the-art object detectors typically use shape information as a low level feature representation to capture the local structure of an object. This paper shows that early fusion of shape and color, as is popular in image classification,leads to a significant drop in performance for object detection. Moreover, such approaches also yields suboptimal results for object categories with varying importance of color and shape.In this paper we propose the use of color attributes as an explicit color representation for object detection. Color attributes are compact, computationally efficient, and when combined with traditional shape features provide state-ofthe-art results for object detection. Our method is tested on the PASCAL VOC 2007 and 2009 datasets and results clearly show that our method improves over state-of-the-art techniques despite its simplicity. We also introduce a new dataset consisting of cartoon character images in which color plays a pivotal role. On this dataset, our approach yields a significant gain of 14% in mean AP over conventional state-of-the-art methods.
SN  - 1063-6919
SN  - 978-1-4673-1226-4
UR  - http://ieeexplore.ieee.org/xpl/articleDetails.jsp? arnumber=6248068
L1  - http://refbase.cvc.uab.es/files/KRW2012.pdf
UR  - http://dx.doi.org/10.1109/CVPR.2012.6248068
N1  - ADAS; CIC;
ID  - Fahad Shahbaz Khan2012
ER  -