Multi-Scale Saliency using Local Gradient and Global Colour Features

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, the issue of scale is addressed in the context of salient object detection. To date, many single scale models have been proposed for detecting salient objects within a scene. Scale is a fundamental problem within image processing, and therefore, multiple scale techniques are investigated and evaluated, as well the presentation of a novel multi-scale saliency model. The proposed model is compared with two state-of-the-art multi-scale saliency algorithms and qualitatively evaluated with respect to algorithmic accuracy and efficiency on the publicly available MSRA10K salient object dataset.
LanguageEnglish
Title of host publication2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019)
Place of PublicationBeijing
Pages28-32
Number of pages5
ISBN (Electronic)9781450372299
DOIs
Publication statusPublished - 18 Aug 2019

Fingerprint

Color
Image processing
Object detection

Keywords

  • Multi-Scale Salient Object Detection
  • Hierarchical Saliency
  • Scale
  • Super-pixels
  • Salient Features
  • Multi-scale salient object detection
  • Hierarchical saliency
  • Salient features

Cite this

Cooley, C., Coleman, S., Gardiner, B., & Scotney, B. (2019). Multi-Scale Saliency using Local Gradient and Global Colour Features. In 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019) (pp. 28-32). Beijing. https://doi.org/10.1145/3357254.3357285
Cooley, Christopher ; Coleman, Sonya ; Gardiner, Bryan ; Scotney, Bryan. / Multi-Scale Saliency using Local Gradient and Global Colour Features. 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019). Beijing, 2019. pp. 28-32
@inproceedings{45dd9cb58f4f40ecb455eee152305e99,
title = "Multi-Scale Saliency using Local Gradient and Global Colour Features",
abstract = "In this paper, the issue of scale is addressed in the context of salient object detection. To date, many single scale models have been proposed for detecting salient objects within a scene. Scale is a fundamental problem within image processing, and therefore, multiple scale techniques are investigated and evaluated, as well the presentation of a novel multi-scale saliency model. The proposed model is compared with two state-of-the-art multi-scale saliency algorithms and qualitatively evaluated with respect to algorithmic accuracy and efficiency on the publicly available MSRA10K salient object dataset.",
keywords = "Multi-Scale Salient Object Detection, Hierarchical Saliency, Scale, Super-pixels, Salient Features, Multi-scale salient object detection, Hierarchical saliency, Salient features",
author = "Christopher Cooley and Sonya Coleman and Bryan Gardiner and Bryan Scotney",
year = "2019",
month = "8",
day = "18",
doi = "10.1145/3357254.3357285",
language = "English",
isbn = "978-1-4503-7229-9",
pages = "28--32",
booktitle = "2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019)",

}

Cooley, C, Coleman, S, Gardiner, B & Scotney, B 2019, Multi-Scale Saliency using Local Gradient and Global Colour Features. in 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019). Beijing, pp. 28-32. https://doi.org/10.1145/3357254.3357285

Multi-Scale Saliency using Local Gradient and Global Colour Features. / Cooley, Christopher; Coleman, Sonya; Gardiner, Bryan; Scotney, Bryan.

2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019). Beijing, 2019. p. 28-32.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Multi-Scale Saliency using Local Gradient and Global Colour Features

AU - Cooley, Christopher

AU - Coleman, Sonya

AU - Gardiner, Bryan

AU - Scotney, Bryan

PY - 2019/8/18

Y1 - 2019/8/18

N2 - In this paper, the issue of scale is addressed in the context of salient object detection. To date, many single scale models have been proposed for detecting salient objects within a scene. Scale is a fundamental problem within image processing, and therefore, multiple scale techniques are investigated and evaluated, as well the presentation of a novel multi-scale saliency model. The proposed model is compared with two state-of-the-art multi-scale saliency algorithms and qualitatively evaluated with respect to algorithmic accuracy and efficiency on the publicly available MSRA10K salient object dataset.

AB - In this paper, the issue of scale is addressed in the context of salient object detection. To date, many single scale models have been proposed for detecting salient objects within a scene. Scale is a fundamental problem within image processing, and therefore, multiple scale techniques are investigated and evaluated, as well the presentation of a novel multi-scale saliency model. The proposed model is compared with two state-of-the-art multi-scale saliency algorithms and qualitatively evaluated with respect to algorithmic accuracy and efficiency on the publicly available MSRA10K salient object dataset.

KW - Multi-Scale Salient Object Detection

KW - Hierarchical Saliency

KW - Scale

KW - Super-pixels

KW - Salient Features

KW - Multi-scale salient object detection

KW - Hierarchical saliency

KW - Salient features

UR - http://www.scopus.com/inward/record.url?scp=85076032812&partnerID=8YFLogxK

U2 - 10.1145/3357254.3357285

DO - 10.1145/3357254.3357285

M3 - Conference contribution

SN - 978-1-4503-7229-9

SP - 28

EP - 32

BT - 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019)

CY - Beijing

ER -

Cooley C, Coleman S, Gardiner B, Scotney B. Multi-Scale Saliency using Local Gradient and Global Colour Features. In 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition (AIPR 2019). Beijing. 2019. p. 28-32 https://doi.org/10.1145/3357254.3357285