SALIENT OBJECT DETECTION VIA TWO-STAGE GRAPHS

Abstract

Despite recent advances made in salient object detection using graph theory, the approach still suffers from accuracy problems when the image is characterized by a complex structure, either in the foreground or background, causing erroneous saliency segmentation. This fundamental challenge is mainly attributed to the fact that most of existing graph-based methods take only the adjacently spatial consistency among graph nodes into consideration. In this paper, we tackle this issue from a coarse-to-fine perspective and propose a two-stage-graphs approach for salient object detection, in which two graphs having the same nodes but different edges are employed. Specifically, a weighted joint robust sparse representation model, rather than the commonly used manifold ranking model, helps to compute the saliency value of each node in the first-stage graph, thereby providing a saliency map at the coarse level. In the second stage graph, along with the adjacently spatial consistency, a new regionally spatial consistency among graph nodes is considered in order to refine the coarse saliency map, assuring uniform saliency assignment even in complex scenes. Particularly, the second stage is generic enough to be integrated in existing salient object detectors, enabling to improve their performance. Experimental results on benchmark datasets validate the effectiveness and superiority of the proposed scheme over related state-of-the-art methods.

Existing System

Deep Convolutional Neural Networks Based Salient Object Detection, Sparse Representation Based Salient Object Detection

Proposed System

In short, the contributions of this paper are summarized as follows: (1) Unlike existing graph-based methods that employ only a single graph, our major contribution lies in a two-stage-graphs based salient object detection method, in which two graphs having the same nodes but different edges are employed. More importantly, in the second-stage graph of our proposed method, the regionally spatial consistency and adjacently spatial consistency among graph nodes are simultaneously scenes. (2) The second contribution is a WJRSR model, which replaces the commonly used manifold ranking model to compute the saliency value of each node in the first-stage graph. (3) Especially, the second stage in our proposed method is generic enough to be integrated in existing salient object detectors to improve their performance.

Architecture

BLOCK DIAGRAM