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

Cooperatively utilizing both ego-vehicle and infrastructure sensor data cansignificantly enhance autonomous driving perception abilities. However,temporal asynchrony and limited wireless communication in traffic environmentscan lead to fusion misalignment and impact detection performance. This paperproposes Feature Flow Net (FFNet), a novel cooperative detection framework thatuses a feature flow prediction module to address these issues invehicle-infrastructure cooperative 3D object detection. Rather thantransmitting feature maps extracted from still-images, FFNet transmits featureflow, which leverages the temporal coherence of sequential infrastructureframes to predict future features and compensate for asynchrony. Additionally,we introduce a self-supervised approach to enable FFNet to generate featureflow with feature prediction ability. Experimental results demonstrate that ourproposed method outperforms existing cooperative detection methods whilerequiring no more than 1/10 transmission cost of raw data on the DAIR-V2Xdataset when temporal asynchrony exceeds 200$ms$. The code is available at\href{https://github.com/haibao-yu/FFNet-VIC3D}{https://github.com/haibao-yu/FFNet-VIC3D}.

Vehicle-Infrastructure Cooperative 3D Object Detection via Feature Flow Prediction