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

Generating a detailed near-field perceptual model of the environment is animportant and challenging problem in both self-driving vehicles and autonomousmobile robotics. A Bird Eye View (BEV) map, providing a panopticrepresentation, is a commonly used approach that provides a simplified 2Drepresentation of the vehicle surroundings with accurate semantic levelsegmentation for many downstream tasks. Current state-of-the art approaches togenerate BEV-maps employ a Convolutional Neural Network (CNN) backbone tocreate feature-maps which are passed through a spatial transformer to projectthe derived features onto the BEV coordinate frame. In this paper, we evaluatethe use of vision transformers (ViT) as a backbone architecture to generate BEVmaps. Our network architecture, ViT-BEVSeg, employs standard visiontransformers to generate a multi-scale representation of the input image. Theresulting representation is then provided as an input to a spatial transformerdecoder module which outputs segmentation maps in the BEV grid. We evaluate ourapproach on the nuScenes dataset demonstrating a considerable improvement inthe performance relative to state-of-the-art approaches.

ViT-BEVSeg: A Hierarchical Transformer Network for Monocular Birds-Eye-View Segmentation