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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We present the first event-based learning approach for motion segmentation inindoor scenes and the first event-based dataset - EV-IMO - which includesaccurate pixel-wise motion masks, egomotion and ground truth depth. Ourapproach is based on an efficient implementation of the SfM learning pipelineusing a low parameter neural network architecture on event data. In addition tocamera egomotion and a dense depth map, the network estimates pixel-wiseindependently moving object segmentation and computes per-object 3Dtranslational velocities for moving objects. We also train a shallow networkwith just 40k parameters, which is able to compute depth and egomotion.  Our EV-IMO dataset features 32 minutes of indoor recording with up to 3 fastmoving objects simultaneously in the camera field of view. The objects and thecamera are tracked by the VICON motion capture system. By 3D scanning the roomand the objects, accurate depth map ground truth and pixel-wise object masksare obtained, which are reliable even in poor lighting conditions and duringfast motion. We then train and evaluate our learning pipeline on EV-IMO anddemonstrate that our approach far surpasses its rivals and is well suited forscene constrained robotics applications.

EV-IMO: Motion Segmentation Dataset and Learning Pipeline for Event Cameras