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

In recent years, road safety has attracted significant attention fromresearchers and practitioners in the intelligent transport systems domain. Asone of the most common and vulnerable groups of road users, pedestrians causegreat concerns due to their unpredictable behavior and movement, as subtlemisunderstandings in vehicle-pedestrian interaction can easily lead to riskysituations or collisions. Existing methods use either predefinedcollision-based models or human-labeling approaches to estimate thepedestrians' risks. These approaches are usually limited by their poorgeneralization ability and lack of consideration of interactions between theego vehicle and a pedestrian. This work tackles the listed problems byproposing a Pedestrian Risk Level Prediction system. The system consists ofthree modules. Firstly, vehicle-perspective pedestrian data are collected.Since the data contains information regarding the movement of both the egovehicle and pedestrian, it can simplify the prediction of spatiotemporalfeatures in an interaction-aware fashion. Using the long short-term memorymodel, the pedestrian trajectory prediction module predicts theirspatiotemporal features in the subsequent five frames. As the predictedtrajectory follows certain interaction and risk patterns, a hybrid clusteringand classification method is adopted to explore the risk patterns in thespatiotemporal features and train a risk level classifier using the learnedpatterns. Upon predicting the spatiotemporal features of pedestrians andidentifying the corresponding risk level, the risk patterns between the egovehicle and pedestrians are determined. Experimental results verified thecapability of the PRLP system to predict the risk level of pedestrians, thussupporting the collision risk assessment of intelligent vehicles and providingsafety warnings to both vehicles and pedestrians.

Prediction of Pedestrian Spatiotemporal Risk Levels for Intelligent Vehicles: A Data-driven Approach