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

Estimating the distance to objects is crucial for autonomous vehicles whenusing depth sensors is not possible. In this case, the distance has to beestimated from on-board mounted RGB cameras, which is a complex task especiallyin environments such as natural outdoor landscapes. In this paper, we present anew method named M4Depth for depth estimation. First, we establish a bijectiverelationship between depth and the visual disparity of two consecutive framesand show how to exploit it to perform motion-invariant pixel-wise depthestimation. Then, we detail M4Depth which is based on a pyramidal convolutionalneural network architecture where each level refines an input disparity mapestimate by using two customized cost volumes. We use these cost volumes toleverage the visual spatio-temporal constraints imposed by motion and to makethe network robust for varied scenes. We benchmarked our approach both in testand generalization modes on public datasets featuring synthetic cameratrajectories recorded in a wide variety of outdoor scenes. Results show thatour network outperforms the state of the art on these datasets, while alsoperforming well on a standard depth estimation benchmark. The code of ourmethod is publicly available at https://github.com/michael-fonder/M4Depth.

M4Depth: Monocular depth estimation for autonomous vehicles in unseen environments