Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2023 Jul 4;17:1219363. doi: 10.3389/fnins.2023.1219363

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

Copyright © 2023 Yu, Zheng, Chen, Zhang and Huang.

This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

PMC Copyright notice

Architecture of the proposed approach. The end-to-end framework contains three modules: (1) Feature extraction from input images, (2) Image features are projected to BEV features, and (3) BEV semantic representation prediction. A Transformer-based network encodes global-local spatial features powered by multi-head attention. The image-plane features can be transformed to BEV-plane features with the smallest possible loss of feature information. A generative network further processes BEV global-local spatial features and predicts the final classification probabilities.