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

We present a self-supervised approach to ignoring "distractors" in cameraimages for the purposes of robustly estimating vehicle motion in clutteredurban environments. We leverage offline multi-session mapping approaches toautomatically generate a per-pixel ephemerality mask and depth map for eachinput image, which we use to train a deep convolutional network. At run-time weuse the predicted ephemerality and depth as an input to a monocular visualodometry (VO) pipeline, using either sparse features or dense photometricmatching. Our approach yields metric-scale VO using only a single camera andcan recover the correct egomotion even when 90% of the image is obscured bydynamic, independently moving objects. We evaluate our robust VO methods onmore than 400km of driving from the Oxford RobotCar Dataset and demonstratereduced odometry drift and significantly improved egomotion estimation in thepresence of large moving vehicles in urban traffic.

Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environments