Saliency Guided Hierarchical Robust Visual Tracking

12/21/2018
by   Fangwen Tu, et al.
6

A saliency guided hierarchical visual tracking (SHT) algorithm containing global and local search phases is proposed in this paper. In global search, a top-down saliency model is novelly developed to handle abrupt motion and appearance variation problems. Nineteen feature maps are extracted first and combined with online learnt weights to produce the final saliency map and estimated target locations. After the evaluation of integration mechanism, the optimum candidate patch is passed to the local search. In local search, a superpixel based HSV histogram matching is performed jointly with an L2-RLS tracker to take both color distribution and holistic appearance feature of the object into consideration. Furthermore, a linear refinement search process with fast iterative solver is implemented to attenuate the possible negative influence of dominant particles. Both qualitative and quantitative experiments are conducted on a series of challenging image sequences. The superior performance of the proposed method over other state-of-the-art algorithms is demonstrated by comparative study.

READ FULL TEXT

page 3

page 4

page 7

page 9

research
12/19/2018

Shallow Cue Guided Deep Visual Tracking via Mixed Models

In this paper, a robust visual tracking approach via mixed model based c...
research
02/24/2015

Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network

We propose an online visual tracking algorithm by learning discriminativ...
research
11/23/2020

SCGAN: Saliency Map-guided Colorization with Generative Adversarial Network

Given a grayscale photograph, the colorization system estimates a visual...
research
07/04/2020

Jointly Modeling Motion and Appearance Cues for Robust RGB-T Tracking

In this study, we propose a novel RGB-T tracking framework by jointly mo...
research
10/25/2021

TAPL: Dynamic Part-based Visual Tracking via Attention-guided Part Localization

Holistic object representation-based trackers suffer from performance dr...
research
11/16/2018

HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Images

Co-saliency detection aims to discover common and salient objects in an ...
research
02/02/2017

Learning a time-dependent master saliency map from eye-tracking data in videos

To predict the most salient regions of complex natural scenes, saliency ...

Please sign up or login with your details

Forgot password? Click here to reset