Adaptive Multi-Level Region Merging for Salient Object Detection
Paper in proceedings, 2014

Most existing salient object detection algorithms face the problem of either under or over-segmenting an image. More recent methods address the problem via multi-level segmentation. However, the number of segmentation levels is manually predetermined and only works well on specific class of images. In this paper, a new salient object detection scheme is presented based on adaptive multi-level region merging. A graph based merging scheme is developed to reassemble regions based on their shared contour strength. This merging process is adaptive to complete contours of salient objects that can then be used for global perceptual analysis, e.g., foreground/ground separation. Such contour completion is enhanced by graph-based spectral decomposition. We show that even though simple region saliency measurements are adopted for each region, encouraging performance can be obtained after across-level integration. Experiments by comparing with 13 existing methods on three benchmark datasets including MSRA-1000, SOD and SED show the proposed method results in uniform object enhancement and achieves state-of-the-art performance.

saliency measures

Salient object detection

multi-level segmentation

Author

Keren Fu

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Signal Processing

Chen Gong

Yixiao Yun

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Signal Processing

Yijun Li

Irene Yu-Hua Gu

Chalmers, Signals and Systems, Signalbehandling och medicinsk teknik, Signal Processing

Jie Yang

Jingyi Yu

British Machine Vision Conference (BMVC) 2014

11 -

Areas of Advance

Transport

Subject Categories

Information Science

Signal Processing

Computer Vision and Robotics (Autonomous Systems)

More information

Created

10/6/2017