Ensemble Tracking Based on Diverse Collaborative Framework With Multi-Cue Dynamic Fusion

doi:10.1109/TMM.2019.2958759

Ensemble Tracking Based on Diverse Collaborative Framework With Multi-Cue Dynamic Fusion

2020-10-01

6

PRE

AI

DOI：10.1109/TMM.2019.2958759

Original

Original request for help

Save

Abstract

En 中文

Tracking with deep neural networks has been verified to arrive at a new level accuracy in many challenging scenarios, but the tracking robustness has been still challenged by model singularity and self-learning loop mechanism. As a promising solution for the limitations, to ensemble diverse tracking strategies into a highly-interactive framework has shown a potential effectiveness in recent studies. In this work, a collaborative tracking framework is proposed by exploiting both discriminative correlation filters and deep classifiers into an ensembling framework. With a multi-cue dynamic fusion scheme performed on all the ensembled members' outputs, a robust long-term tracking can be achieved by calculating the optimal robustness scores based on a dynamic weighted sum of multi-cue metrics. Meanwhile, the obtained reliable and diverse training samples are also utilized to adaptively update the tracker in each branch with heuristic frequency, which is able to alleviate the training samples' contamination and model corruption. Experiments on the OTB-2015, Temple color 128, UAV123, VOT2016, and VOT2018 benchmark datasets have shown superior performance in comparison to other state-of-the-art tracking approaches.

Keywords:

Target tracking

Correlation

Robustness

Adaptation models

Training

Tracking loops

Collaboration

Ensembling structure

collaborative tracking framework

multi-cue dynamic fusion

heuristic frequency

Ensemble Tracking Based on Diverse Collaborative Framework With Multi-Cue Dynamic Fusion

Abstract

AI Summary

Journal

Organization