Evaluating salient object detection in natural images with multiple objects having multi-level saliency

Salient object detection is evaluated using binary ground truth (GT) with the labels being salient object class and background. In this study, the authors corroborate based on three subjective experiments on a novel image dataset that objects in natural images are inherently perceived to have varyin...

Full description

Saved in:
Bibliographic Details
Published in:IET image processing 2020-08, Vol.14 (10), p.2249-2262
Main Authors: Yildirim, Gökhan, Sen, Debashis, Kankanhalli, Mohan, Süsstrunk, Sabine
Format: Article
Language:English
Subjects:
dataset images
image dataset
image segmentation
multilevel maps
multilevel saliency GT dataset
multilevel salient objects
multiobject image
multiobject natural images
object detection
object saliency
Research Article
salient object class detection capability
statistical analysis
visual perception
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Salient object detection is evaluated using binary ground truth (GT) with the labels being salient object class and background. In this study, the authors corroborate based on three subjective experiments on a novel image dataset that objects in natural images are inherently perceived to have varying levels of importance. The authors' dataset, named SalMoN (saliency in multi-object natural images), has 588 images containing multiple objects. The subjective experiments performed record spontaneous attention and perception through eye fixation duration, point clicking and rectangle drawing. As object saliency in a multi-object image is inherently multi-level, they propose that salient object detection must be evaluated for the capability to detect all multi-level salient objects apart from the salient object class detection capability. For this purpose, they generate multi-level maps as GT corresponding to all the dataset images using the results of the subjective experiments, with the labels being multi-level salient objects and background. They then propose the use of mean absolute error, Kendall's rank correlation and average area under precision–recall curve to evaluate existing salient object detection methods on their multi-level saliency GT dataset. Approaches that represent saliency detection on images as local-global hierarchical processing of a graph perform well in their dataset.
ISSN:1751-9659
1751-9667
DOI:10.1049/iet-ipr.2019.0787