Toggle Main Menu Toggle Search

Open Access padlockePrints

Particle PHD Filter Based Multiple Human Tracking using Online Group-Structured Dictionary Learning

Lookup NU author(s): Zeyu Fu, Pengming Feng, Federico Angelini, Professor Jonathon Chambers, Dr Mohsen Naqvi

Downloads


Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


Abstract

An enhanced Sequential Monte Carlo probability hypothesis density (SMC-PHD) filter based multiple human tracking system is presented. The proposed system mainly exploits two concepts: a novel adaptive gating technique and an online group-structured dictionary learning strategy. Conven-tional PHD filtering methods preset the target birth intensity and the gating threshold for selecting real observations for the PHD update. This often yields inefficiency in false positives and missed detections in a cluttered environment. To address this issue, a measurement-driven mechanism based on a novel adaptive gating method is proposed to adaptively update the gating sizes. This yields an accurate approach to discriminate between survival and residual measurements by reducing the clutter inferences. In addition, online group-structured dictionary learning with a maximum voting method is used to robustly estimate the target birth intensity. It enables the new-born targets to be automati-cally detected from noisy sensor measurements. To improve the adaptability of our group-structured dictionary to appearance and illumination changes, we employ the Simultaneous Codeword Optimization (SimCO) algorithm for the dictionary update stage. Experimental results demonstrate our proposed method achieves the best performance amongst state-of-the-art Random Finite Set (RFS) based methods, and the second best online tracker ranked on the leaderboard of latest MOT17 Challenge.


Publication metadata

Author(s): Fu Z, Feng P, Angelini F, Chambers JC, Naqvi SM

Publication type: Article

Publication status: Published

Journal: IEEE Access

Year: 2018

Volume: 6

Pages: 14764-14778

Online publication date: 16/03/2018

Acceptance date: 03/03/2018

Date deposited: 14/03/2018

ISSN (electronic): 2169-3536

Publisher: IEEE

URL: https://doi.org/10.1109/ACCESS.2018.2816805

DOI: 10.1109/ACCESS.2018.2816805


Altmetrics

Altmetrics provided by Altmetric


Actions

Find at Newcastle University icon    Link to this publication


Share