English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Visual Odometry (VO) is one of the fundamental tasks in computer vision forrobotics. However, its performance is deeply affected by High Dynamic Range(HDR) scenes, omnipresent outdoor. While new Automatic-Exposure (AE) approachesto mitigate this have appeared, their comparison in a reproducible manner isproblematic. This stems from the fact that the behavior of AE depends on theenvironment, and it affects the image acquisition process. Consequently, AE hastraditionally only been benchmarked in an online manner, making the experimentsnon-reproducible. To solve this, we propose a new methodology based on anemulator that can generate images at any exposure time. It leverages BorealHDR,a unique multi-exposure stereo dataset collected over 8.4 km, on 50trajectories with challenging illumination conditions. Moreover, it containspose ground truth for each image and a global 3D map, based on lidar data. Weshow that using these images acquired at different exposure times, we canemulate realistic images keeping a Root-Mean-Square Error (RMSE) below 1.78 %compared to ground truth images. To demonstrate the practicality of ourapproach for offline benchmarking, we compared three state-of-the-art AEalgorithms on key elements of Visual Simultaneous Localization And Mapping(VSLAM) pipeline, against four baselines. Consequently, reproducible evaluationof AE is now possible, speeding up the development of future approaches. Ourcode and dataset are available online at this link:https://github.com/norlab-ulaval/BorealHDR

Exposing the Unseen: Exposure Time Emulation for Offline Benchmarking of Vision Algorithms