Light Field Distortion Feature for Transparent Object Recognition

Kazuki Maeno, Hajime Nagahara, Atsushi Shimada, Rin-Ichiro Taniguchi; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 2786-2793

Abstract


Current object-recognition algorithms use local features, such as scale-invariant feature transform (SIFT) and speeded-up robust features (SURF), for visually learning to recognize objects. These approaches though cannot apply to transparent objects made of glass or plastic, as such objects take on the visual features of background objects, and the appearance of such objects dramatically varies with changes in scene background. Indeed, in transmitting light, transparent objects have the unique characteristic of distorting the background by refraction. In this paper, we use a single-shot light Aeld image as an input and model the distortion of the light Aeld caused by the refractive property of a transparent object. We propose a new feature, called the light Aeld distortion (LFD) feature, for identifying a transparent object. The proposal incorporates this LFD feature into the bag-of-features approach for recognizing transparent objects. We evaluated its performance in laboratory and real settings.

Related Material


[pdf]
[bibtex]
@InProceedings{Maeno_2013_CVPR,
author = {Maeno, Kazuki and Nagahara, Hajime and Shimada, Atsushi and Taniguchi, Rin-Ichiro},
title = {Light Field Distortion Feature for Transparent Object Recognition},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}