Accurate pedestrian localization in overhead depth images via Height-Augmented HOG

Werner Kroneman (Corresponding author), Alessandro Corbetta (Corresponding author), Federico Toschi (Corresponding author)

Onderzoeksoutput: Bijdrage aan tijdschriftTijdschriftartikelAcademicpeer review

Samenvatting

We tackle the challenge of reliably and automatically localizing pedestrians in real-life conditions through overhead depth imaging at unprecedented high-density conditions. Leveraging upon a combination of Histogram of Oriented Gradients-like feature descriptors, neural networks, data augmentation and custom data annotation strategies, this work contributes a robust and scalable machine learning-based localization algorithm, which delivers near-human localization performance in real-time, even with local pedestrian density of about 3 ped/m2, a case in which most stateof- the art algorithms degrade significantly in performance.
Originele taal-2Engels
Pagina's (van-tot)33-40
Aantal pagina's8
TijdschriftCollective Dynamics
Volume5
DOI's
StatusGepubliceerd - 2020
Evenement9th international conference on Pedestrian and Evacuation Dynamics - Lund, Zweden
Duur: 21 aug 201824 aug 2018

Vingerafdruk Duik in de onderzoeksthema's van 'Accurate pedestrian localization in overhead depth images via Height-Augmented HOG'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit