Toggle Main Menu Toggle Search

Open Access padlockePrints

Enhanced GM-PHD Filter Using CNN-Based Weight Penalization for Multi-Target Tracking

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


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


© 2017 IEEE. In this paper, an enhanced Gaussian mixture probability hypothesis density filter (GM-PHD) using convolutional neural network (CNN) based weight penalization is proposed to track multiple targets in video. Existing GM-PHD filter based tracking methods are not always able to accurately track the targets when they are in close proximity, especially with noisy detection responses or in a crowded environments. To address this issue, a measurement classification step which combines a confidence score with a gating technique is presented to discard the false measurements and initialise new-born targets. High level human features extracted from a pre-trained CNN are utilized to penalize the ambiguous weights in the weight matrix. In addition, we integrate an improved track management scheme with occlusion handling to form the tracks of confirmed targets and maintain the track continuity. Experimental results on two publicly available benchmark video sequences validate the efficacy of our proposed method in video-based multi-target tracking.

Publication metadata

Author(s): Fu Z, Naqvi SM, Chambers JA

Publication type: Conference Proceedings (inc. Abstract)

Publication status: Published

Conference Name: Sensor Signal Processing for Defence Conference (SSPD 2017)

Year of Conference: 2017

Online publication date: 21/12/2017

Acceptance date: 23/09/2017

Publisher: IEEE


DOI: 10.1109/SSPD.2017.8233230

Library holdings: Search Newcastle University Library for this item

ISBN: 9781538616635