Category-Independent Object-Level Saliency Detection
Authors:
- Yangqing JiaYJYangqing Jia
- Mei HanMHMei Han
- 1 December 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1761-1768
Abstract
It is known that purely low-level saliency cues such as frequency does not lead to a good salient object detection result, requiring high-level knowledge to be adopted for successful discovery of task-independent salient objects. In this paper, we propose an efficient way to combine such high-level saliency priors and low-level appearance models. We obtain the high-level saliency prior with the objectness algorithm to find potential object candidates without the need of category information, and then enforce the consistency among the salient regions using a Gaussian MRF with the weights scaled by diverse density that emphasizes the influence of potential foreground pixels. Our model obtains saliency maps that assign high scores for the whole salient object, and achieves state-of-the-art performance on benchmark datasets covering various foreground statistics.Keywords
This publication has 21 references indexed in Scilit:
- Salient Object Detection: A Discriminative Regional Feature Integration Approach2013
- Saliency filters: Contrast based filtering for salient region detection2012
- Center-surround divergence of feature statistics for salient object detection2011
- Image Signature: Highlighting Sparse Salient RegionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2011
- Learning to predict where humans look2009
- TurboPixels: Fast Superpixels Using Geometric FlowsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Learning to Detect A Salient Object2007
- An Integrated Model of Top-Down and Bottom-Up Attention for Optimizing Detection Speed2006
- Contrast-based image attention analysis by using fuzzy growing2003
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998