This paper describes a novel compact representation of local features called the tensor doublet. The representation generates a four dimensional feature vector which is significantly less complex than other approaches, such as Lowe's 128 dimensional feature vector. Despite its low dimensionality, we demonstrate here that the tensor doublet can be used for pose estimation, where the system is trained for an object and evaluated on images with cluttered background and occlusion. © Springer-Verlag Berlin Heidelberg 2005.
CITATION STYLE
Söderberg, R., Nordberg, K., & Granlund, G. (2005). An invariant and compact representation for unrestricted pose estimation. In Lecture Notes in Computer Science (Vol. 3522, pp. 3–10). Springer Verlag. https://doi.org/10.1007/11492429_1
Mendeley helps you to discover research relevant for your work.