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

Modeling crowd behavior relies on accurate data of pedestrian movements at ahigh level of detail. Imaging sensors such as cameras provide a good basis forcapturing such detailed pedestrian motion data. However, currently availablecomputer vision technologies, when applied to conventional video footage, stillcannot automatically unveil accurate motions of groups of people or crowds fromthe image sequences. We present a novel data collection approach for studyingcrowd behavior which uses the increasingly popular low-cost sensor MicrosoftKinect. The Kinect captures both standard camera data and a three-dimensionaldepth map. Our human detection and tracking algorithm is based on agglomerativeclustering of depth data captured from an elevated view - in contrast to thelateral view used for gesture recognition in Kinect gaming applications. Ourapproach transforms local Kinect 3D data to a common world coordinate system inorder to stitch together human trajectories from multiple Kinects, which allowsfor a scalable and flexible capturing area. At a testbed with real-worldpedestrian traffic we demonstrate that our approach can provide accuratetrajectories from three Kinects with a Pedestrian Detection Rate of up to 94%and a Multiple Object Tracking Precision of 4 cm. Using a comprehensive datasetof 2240 captured human trajectories we calibrate three variations of the SocialForce model. The results of our model validations indicate their particularability to reproduce the observed crowd behavior in microscopic simulations.

Kinects and Human Kinetics: A New Approach for Studying Crowd Behavior