Geometric-visual descriptor for improved image based localization - Archive ouverte HAL Access content directly
Conference Papers Year :

Geometric-visual descriptor for improved image based localization

(1) , (1) , (1) , (1)
Achref Ouni
Eric Royer
Michel Dhome


This paper addresses the problem of image based localization. The goal is to find quickly and accurately the relative pose from a query taken from a stereo camera and a map obtained using visual SLAM which contains poses and 3D points associated to descriptors. In this paper we introduce a new method that leverages the stereo vision by adding geometric information to visual descriptors. This method can be used when the vertical direction of the camera is known (for example on a wheeled robot). This new geometric visual descriptor can be used with several image based localization algorithms based on visual words. We test the approach with different datasets (indoor, outdoor) and we show experimentally that the new geometric-visual descriptor improves standard image based localization approaches.
Fichier principal
Vignette du fichier
Geometric_visual_descriptor_for_improved_image_based_localization_of_a_wheeled_robot.pdf (912.18 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03024935 , version 1 (26-11-2020)


Attribution - CC BY 4.0


  • HAL Id : hal-03024935 , version 1


Achref Ouni, Eric Royer, Marc Chevaldonné, Michel Dhome. Geometric-visual descriptor for improved image based localization. VCIP, Dec 2020, MACAO, China. ⟨hal-03024935⟩
50 View
168 Download


Gmail Facebook Twitter LinkedIn More