A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos

Amirhossein Aghamohammadi, Mei Choo Ang, Elankovan A Sundararajan, Ng Kok Weng, Marzieh Mogharrebi, Seyed Yashar Banihashem

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods.

Original languageEnglish
Article numbere0192246
JournalPLoS One
Volume13
Issue number2
DOIs
Publication statusPublished - 1 Feb 2018

Fingerprint

Target tracking
learning
Learning
Antennas
Image resolution
Adaptive algorithms
Parallel algorithms
Learning algorithms
Computer vision
Remote sensing
Cameras
Remote Sensing Technology
Color
methodology
computer vision
cameras
Experiments
remote sensing
sampling
color

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos. / Aghamohammadi, Amirhossein; Ang, Mei Choo; A Sundararajan, Elankovan; Weng, Ng Kok; Mogharrebi, Marzieh; Banihashem, Seyed Yashar.

In: PLoS One, Vol. 13, No. 2, e0192246, 01.02.2018.

Research output: Contribution to journalArticle

Aghamohammadi, Amirhossein ; Ang, Mei Choo ; A Sundararajan, Elankovan ; Weng, Ng Kok ; Mogharrebi, Marzieh ; Banihashem, Seyed Yashar. / A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos. In: PLoS One. 2018 ; Vol. 13, No. 2.
@article{2a2de525f91d4027962109c43f1b6dcd,
title = "A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos",
abstract = "Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods.",
author = "Amirhossein Aghamohammadi and Ang, {Mei Choo} and {A Sundararajan}, Elankovan and Weng, {Ng Kok} and Marzieh Mogharrebi and Banihashem, {Seyed Yashar}",
year = "2018",
month = "2",
day = "1",
doi = "10.1371/journal.pone.0192246",
language = "English",
volume = "13",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

TY - JOUR

T1 - A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos

AU - Aghamohammadi, Amirhossein

AU - Ang, Mei Choo

AU - A Sundararajan, Elankovan

AU - Weng, Ng Kok

AU - Mogharrebi, Marzieh

AU - Banihashem, Seyed Yashar

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods.

AB - Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85042070194&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85042070194&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0192246

DO - 10.1371/journal.pone.0192246

M3 - Article

C2 - 29438421

AN - SCOPUS:85042070194

VL - 13

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 2

M1 - e0192246

ER -