Characterization of the impact of visual odometry drift on the control of an autonomous vehicle

Bazeille, Stéphane; Josso-Laurain, Thomas; Ledy, Jonathan; Rebert, Martin; Assaad, Mohamad Al; Orjuela, Rodolfo

doi:10.1109/iv47402.2020.9304687

Cited by 4 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 Today, we are interested in enhancing the number of the detected key-points in the raw LF images using a method based on the interaction between the available types of micro-lenses. We are mainly interested in light cameras in autonomous navigation in order to perform accurate scale visual odometry in order to replace some of the methods that are developed in this field 2 , 3 . This paper dives deeper into PFIs, which produce visually consistent images that can be used with any standard key-points detectors.…”

Section: Introductionmentioning

confidence: 99%

Enhanced key-point detection for plenoptic imaging

Assaad

Bazeille

Josso-Laurain

et al. 2023

Sixteenth International Conference on Quality Control by Artificial Vision

View full text Add to dashboard Cite

Standard imaging techniques do not get as much information from a scene as light-field imaging. Light-field (LF) cameras can measure the light intensity reflected by an object and, most importantly, the direction of its light rays. This information can be used in different applications, such as depth estimation, in-plane focusing, creating full-focused images, etc. However, standard key-point detectors often employed in computer vision applications cannot be applied directly to plenoptic images due to the nature of raw LF images. This work presents an approach for key-point detection dedicated to plenoptic images. Our method allows using of conventional key-point detector methods. It forces the detection of this key-point in a set of micro-images of the raw LF image. Obtaining this important number of key-points is essential for applications that require finding additional correspondences in the raw space, such as disparity estimation, indirect visual odometry techniques, and others. The approach is set to the test by modifying the Harris key-point detector.

show abstract

Section: Introductionmentioning

confidence: 99%