Design of Binary Robust Independent Elementary Features through Compressive Sensing View
Jinhong Zhang, Xueqing Liu, Xiangwei Liu · International Journal of Applied Physics and Mathematics · 2015
Binary Robust Independent Elementary Feature (BRIEF) is designed to be a very simple and efficient feature point descriptor for image.In this paper, compressive sensing theory is used in proposing the reason why it works and guiding the parameter determination of BRIEF.It is proved in this paper BRIEF is the Binarization of Compressive Sensing Sampling.Also, with theoretical basis for BRIEF, there is guidance for us to design new descriptors.