Direct visual servoing in the frequency domain - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles IEEE Robotics and Automation Letters Year : 2020

Direct visual servoing in the frequency domain

Eric Marchand


In this paper, we propose an original approach to extend direct visual servoing to the frequency domain. Whereas most of visual servoing approaches relied on the geometric features, recent works have highlighted the importance of taking into account the photometric information of the entire images. This leads to direct visual servoing (DVS) approaches. In this paper we propose no longer to consider the image itself in the spatial domain but its transformation in the frequency domain. The idea is to consider the Discrete Cosine Transform (DCT) which allows to represent the image in the frequency domain in terms of a sum of cosine functions that oscillate at various frequencies. This leads to a new set of coordinates in a new precomputed orthogonal basis, the coefficients of the DCT. We propose to use these coefficients as the visual features that are then consider in a visual servoing control law. We then exhibit the analytical formulation of the interaction matrix related to these coefficients. Experimental results validate our approach.
Fichier principal
Vignette du fichier
dct-final.pdf (2.45 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-02290424 , version 1 (17-09-2019)
hal-02290424 , version 2 (03-01-2020)



Eric Marchand. Direct visual servoing in the frequency domain. IEEE Robotics and Automation Letters, 2020, 5 (2), pp.620-627. ⟨10.1109/LRA.2020.2965027⟩. ⟨hal-02290424v2⟩
139 View
487 Download



Gmail Mastodon Facebook X LinkedIn More