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

One crucial information for a pedestrian crowd simulation is the number ofagents moving from an origin to a certain target. While this setup has a largeimpact on the simulation, it is in most setups challenging to find the numberof agents that should be spawned at a source in the simulation. Often, numberare chosen based on surveys and experience of modelers and event organizers.These approaches are important and useful but reach their limits when we wantto perform real-time predictions. In this case, a static information about theinflow is not sufficient. Instead, we need a dynamic information that can beretrieved each time the prediction is started. Nowadays, sensor data such asvideo footage or GPS tracks of a crowd are often available. If we can estimatethe number of pedestrians who stem from a certain origin from this sensor data,we can dynamically initialize the simulation. In this study, we use densityheatmaps that can be derived from sensor data as input for a random forestregressor to predict the origin distributions. We study three differentdatasets: A simulated dataset, experimental data, and a hybrid approach withboth experimental and simulated data. In the hybrid setup, the model is trainedwith simulated data and then tested on experimental data. The resultsdemonstrate that the random forest model is able to predict the origindistribution based on a single density heatmap for all three configurations.This is especially promising for applying the approach on real data since thereis often only a limited amount of data available.

Can we learn where people come from? Retracing of origins in merging situations