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

Predicting human trajectories is a challenging task due to the complexity ofpedestrian behavior, which is influenced by external factors such as thescene's topology and interactions with other pedestrians. A special challengearises from the dependence of the behaviour on the density of the scene. In theliterature, deep learning algorithms show the best performance in predictingpedestrian trajectories, but so far just for situations with low densities. Inthis study, we aim to investigate the suitability of these algorithms forhigh-density scenarios by evaluating them on different error metrics andcomparing their accuracy to that of knowledge-based models that have been usedsince long time in the literature. The findings indicate that deep learningalgorithms provide improved trajectory prediction accuracy in the distancemetrics for all tested densities. Nevertheless, we observe a significant numberof collisions in the predictions, especially in high-density scenarios. Thisissue arises partly due to the absence of a collision avoidance mechanismwithin the algorithms and partly because the distance-based collision metric isinadequate for dense situations. To address these limitations, we propose theintroduction of a novel continuous collision metric based on pedestrians'time-to-collision. Subsequently, we outline how this metric can be utilized toenhance the training of the algorithms.

Predicting pedestrian trajectories at different densities: A multi-criteria empirical analysis