Salient Object Detection Based on Background Feature Clustering

Kan Huang,Bo Lv,Yong Zhang,Yongbiao Shi

doi:10.1155/2017/4183986

Abstract

Automatic estimation of salient object without any prior knowledge tends to greatly enhance many computer vision tasks. This paper proposes a novel bottom-up based framework for salient object detection by first modeling background and then separating salient objects from background. We model the background distribution based on feature clustering algorithm, which allows for fully exploiting statistical and structural information of the background. Then a coarse saliency map is generated according to the background distribution. To be more discriminative, the coarse saliency map is enhanced by a two-step refinement which is composed of edge-preserving element-level filtering and upsampling based on geodesic distance. We provide an extensive evaluation and show that our proposed method performs favorably against other outstanding methods on two most commonly used datasets. Most importantly, the proposed approach is demonstrated to be more effective in highlighting the salient object uniformly and robust to background noise.

Highlights

As an important preprocessing technique in computer vision to reduce computational complexity, saliency has attracted much attention in recent years
We suggest that clustering features within the pseudobackground region would give a suitable representation of the background distribution
Statistical and structural information of background can be fully exploited to construct background distribution, which would allow for a subsequently more accurate saliency measurement, and (2) we propose a new refinement framework, which is composed of edgepreserving element-level filtering and upsampling based on geodesic distance

Summary

Introduction

As an important preprocessing technique in computer vision to reduce computational complexity, saliency has attracted much attention in recent years. Algorithms based on these cues usually work well in situations where foreground object appears to be distinctive in terms of contrast or rarity They may fail in dealing with images containing various background patterns. There are two main contributions underlying our proposed approach: (1) we propose a novel way to construct background distribution of an image based on clustering method. In this way, statistical and structural information of background can be fully exploited to construct background distribution, which would allow for a subsequently more accurate saliency measurement, and (2) we propose a new refinement framework, which is composed of edgepreserving element-level filtering and upsampling based on geodesic distance. The new refinement framework has an excellent ability to uniformly highlight the salient object and removing background noise

Proposed Approach

Experiment

Findings

Conclusion