Skip to main content
Other
Salient Object Detection via Objectness Proposals
29th AAAI Conference on Artificial Intelligence
  • Tam Nguyen, University of Dayton
Document Type
Conference Paper
Publication Date
1-1-2015
Abstract

Salient object detection has gradually become a popular topic in robotics and computer vision research. This paper presents a real-time system that detects salient objects by integrating objectness, foreground, and compactness measures. Our algorithm consists of four basic steps. First, our method generates the objectness map via object proposals. Based on the objectness map, we estimate the background margin and compute the corresponding foreground map which prefers the foreground objects. From the objectness map and the foreground map, the compactness map is formed to favor the compact objects. We then integrate those cues to form a pixel-accurate saliency map which covers the salient objects and consistently separates foreground and background.

Inclusive pages
4286-4287
Document Version
Published Version
Comments

This document is provided for download in compliance with the publisher's policy on self-archiving. Permission documentation is on file.

Publisher
Association for the Advancement of Artificial Intelligence
Place of Publication
Austin, TX
Citation Information
Tam Nguyen. "Salient Object Detection via Objectness Proposals" 29th AAAI Conference on Artificial Intelligence (2015)
Available at: http://works.bepress.com/tam-nguyen/20/