FASA: Fast, Accurate, and Size-Aware Salient Object Detection

Fast and accurate salient-object detectors are important for various image processing and computer vision applications, such as adaptive compression and object segmentation. It is also desirable to have a detector that is aware of the position and the size of the salient objects. In this paper, we propose a salient-object detection method that is fast, accurate, and size-aware. For efficient computation, we quantize the image colors and estimate the spatial positions and sizes of the quantized colors. We then feed these values into a statistical model to obtain a probability of saliency. In order to estimate the final saliency, this probability is combined with a global color contrast measure. We test our method on two public datasets and show that our method significantly outperforms the fast state-of-the-art methods. In addition, it has comparable performance and is an order of magnitude faster than the accurate state-of-the-art methods. We exhibit the potential of our algorithm by processing a high-definition video in real time.


Editor(s):
Cremers, D
Reid, I
Saito, H
Yang, Mh
Published in:
Computer Vision - ACCV 2014, 9005, 514-528
Presented at:
12th Asian Conference on Computer Vision (ACCV), Singapore, Nov 1-5, 2014
Year:
2015
Publisher:
Berlin, Springer-Verlag Berlin
ISSN:
0302-9743
ISBN:
978-3-319-16811-1
978-3-319-16810-4
Laboratories:




 Record created 2015-12-02, last modified 2018-05-09

n/a:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)