Multiple People Tracking and Gait Recognition for Video Surveillance

Beschreibung

This thesis tackles the problems of multiple people tracking and gait recognition with a focus on occlusion handling in video surveillance. For the tracking, the proposed method adopts a hierarchical way of tracking along with a robust re-identification module, which produces affinity measures for data association. For gait recognition, two issues are addressed: 1) incomplete gait cycles, by presenting a fully convolutional network to restore complete gait cycles and 2) view variation, by proposing a variant of the non-negative matrix factorization algorithm.

Autor*in

Maryam Babaee

Themen in »Multiple People Tracking and Gait Recognition for Video Surveillance«

Multiple People Tracking Gait Recognition Deep Learning

Stimmen zu »Multiple People Tracking and Gait Recognition for Video Surveillance«

Details

Link teilen