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

Understanding the behaviors and intentions of humans are one of the mainchallenges autonomous ground vehicles still faced with. More specifically, whenit comes to complex environments such as urban traffic scenes, inferring theintentions and actions of vulnerable road users such as pedestrians become evenharder. In this paper, we address the problem of intent action prediction ofpedestrians in urban traffic environments using only image sequences from amonocular RGB camera. We propose a real-time framework that can accuratelydetect, track and predict the intended actions of pedestrians based on atracking-by-detection technique in conjunction with a novel spatio-temporalDenseNet model. We trained and evaluated our framework based on real datacollected from urban traffic environments. Our framework has shown resilientand competitive results in comparison to other baseline approaches. Overall, weachieved an average precision score of 84.76% with a real-time performance at20 FPS.

Real-time Intent Prediction of Pedestrians for Autonomous Ground Vehicles via Spatio-Temporal DenseNet