50 FPS Object-Level Saliency Detection via Maximally Stable Region

The human visual system tends to consider saliency of an object as a whole. Some object-level saliency detection methods have been proposed by leveraging object proposals in bounding boxes, and regarding the entire bounding box as one candidate salient region. However, the bounding boxes can not pro...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing 2020-01, Vol.29, p.1384-1396
Main Authors: Huang, Xiaoming, Zheng, Yin, Huang, Junzhou, Zhang, Yu-Jin
Format: Article
Language:English
Subjects:
Boxes
Deep learning
Graphical models
Machine learning
maximally stable region
minimum barrier distance
Object detection
Pixels
Proposals
Salience
Saliency detection
salient object detection
seed selection
Visual systems
Visualization
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:The human visual system tends to consider saliency of an object as a whole. Some object-level saliency detection methods have been proposed by leveraging object proposals in bounding boxes, and regarding the entire bounding box as one candidate salient region. However, the bounding boxes can not provide exact object position and a lot of pixels in bounding boxes belong to the background. Consequently, background pixels in bounding box also show high saliency. Besides, acquiring object proposals needs high time cost. In order to compute object-level saliency, we consider region growing from some seed superpixels, to find one surrounding region which probably represents the whole object. The desired surrounding region has similar appearance inside and obvious difference with the outside, which is proposed as maximally stable region (MSR) in this paper. In addition, one effective seed superpixel selection strategy is presented to improve speed. MSR based saliency detection is more robust than pixel or superpixel level methods and object proposal based methods. The proposed method significantly outperforms the state-of-the-art unsupervised methods at 50 FPS. Compared with deep learning based methods, we show worse performance, but with about 1200-1600 times faster, which means better trade-off between performance and speed.
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2019.2941663