Adaptive Local Contrast Normalization for Robust Object Detection and Pose Estimation

Mahdi Rad, Vincent Lepetit and Peter Roth

Abstract

To be robust to illumination changes when detecting objects in images, the current trend is to train a Deep Network with training images captured under many different lighting conditions. Unfortunately, creating such a training set is very cumbersome, or sometimes even impossible, for some applications such as 3D pose estimation of speciļ¬c objects, which is the application we focus on in this paper. We therefore propose a novel illumination normalization method that lets us learn to detect objects and estimate their 3D pose under challenging illumination conditions from very few training samples. Our key insight is that normalization parameters should adapt to the input image. In particular, we realized this via a Convolutional Neural Network trained to predict the parameters of a generalization of the Difference-of-Gaussians method.

Session

Posters

Files

PDF iconPaper (PDF)
PDF iconSupplementary (PDF)

DOI

10.5244/C.31.35
https://dx.doi.org/10.5244/C.31.35

Citation

Mahdi Rad, Vincent Lepetit and Peter Roth. Adaptive Local Contrast Normalization for Robust Object Detection and Pose Estimation. In T.K. Kim, S. Zafeiriou, G. Brostow and K. Mikolajczyk, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 35.1-35.12. BMVA Press, September 2017.

Bibtex

            @inproceedings{BMVC2017_35,
                title={Adaptive Local Contrast Normalization for Robust Object Detection and Pose Estimation},
                author={Mahdi Rad, Vincent Lepetit and Peter Roth},
                year={2017},
                month={September},
                pages={35.1-35.12},
                articleno={35},
                numpages={12},
                booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
                publisher={BMVA Press},
                editor={Tae-Kyun Kim, Stefanos Zafeiriou, Gabriel Brostow and Krystian Mikolajczyk},
                doi={10.5244/C.31.35},
                isbn={1-901725-60-X},
                url={https://dx.doi.org/10.5244/C.31.35}
            }