【摘要】：In this paper,we propose a saliency detection model for RGB-D images based on the contrasting features of color and depth within a Bayesian framework.The depth feature map is extracted based on superpixel contrast computation with spatial priors.We model the depth saliency map by approximating the density of depth-based contrast features using a Gaussian distribution.Similar to the depth saliency computation,the color saliency map is computed using a Gaussian distribution based on multi-scale contrasts in superpixels by exploiting low-level cues.By assuming that color-and depth-based contrast features are conditionally independent,given the classes,a discriminative mixed-membership naive Bayes(DMNB)model is used to calculate the final saliency map from the depth saliency and color saliency probabilities by applying Bayes’theorem.The Gaussian distribution parameter can be estimated in the DMNB model by using a variational inference-based expectation maximization algorithm.The experimental results on a recent eye tracking database show that the proposed model performs better than other existing models.
[Abstract]:In this paper we propose a saliency detection model for RGB-D images based on the contrasting features of color and depth within a Bayesian framework.The depth feature map is extracted based on superpixel contrast computation with spatial priors.We model the depth saliency map by approximating the density of depth-based contrast features using a Gaussian distribution. Similar to the depth saliency computation / the color saliency map is computed using a Gaussian distribution based on Multi-scale contrasts in superpixels by exploiting low-level cues.by assuming that color-and depth-based contrast features are conditionally independent given the classesa discriminative mixed-membership naive Bayes (DMNB) model is used to calculate the final saliency map from the depth saliency and color saliency probabilities by applying Bayes) the Gaussian distribution parameter can be estimated in the DMNB model by using a variational inference-based expectation maximization algorithm. The experimental results on a recent eye tracking database Show that the proposed model performs better than other existing models.
【作者單位】： Higher
【基金】：supported by the Innovation Group Plan of Beijing Academy of Science and Technology(IG201506N) the Youth Core Plan of Beijing Academy of Science and Technology(2015-16)
【分類號】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 LIU Yang;LI XueQing;WANG Lei;NIU YuZhen;;Interpolation-tuned salient region detection[J];Science China(Information Sciences);2014年01期

2 ;Learning robust principal components from L1-norm maximization[J];Journal of Zhejiang University-Science C(Computers & Electronics);2012年12期

3 ;A Software Risk Analysis Model Using Bayesian Belief Network[J];南昌工程學(xué)院學(xué)報(bào);2006年02期

4 楊欣斌,孫京誥,黃道;基于Bayesian網(wǎng)絡(luò)的缺損數(shù)據(jù)處理方法[J];華東理工大學(xué)學(xué)報(bào);2002年S1期

5 趙越;;Bayesian方法在建筑物檢測中的應(yīng)用研究[J];吉林建筑工程學(xué)院學(xué)報(bào);2010年05期

6 Amin Nikanjam;Adel Rahmani;;Exploiting Bivariate Dependencies to Speedup Structure Learning in Bayesian Optimization Algorithm[J];Journal of Computer Science & Technology;2012年05期

7 林士敏,王雙成,陸玉昌;Bayesian方法的計(jì)算學(xué)習(xí)機(jī)制和問題求解[J];清華大學(xué)學(xué)報(bào)(自然科學(xué)版);2000年09期

8 劉大有,王飛,盧奕南,薛萬欣,王松昕;基于遺傳算法的Bayesian網(wǎng)結(jié)構(gòu)學(xué)習(xí)研究[J];計(jì)算機(jī)研究與發(fā)展;2001年08期

9 ;Remote sensing image fusion based on Bayesian linear estimation[J];Science in China(Series F:Information Sciences);2007年02期

10 武燕;王宇平;劉小雄;;基于變異的Bayesian優(yōu)化算法[J];計(jì)算機(jī)工程;2007年16期

相關(guān)會議論文 前6條

1 ;A Recursive Method of Learning Bayesian Network for Rule Extraction Based on Information Theory[A];第一屆建立和諧人機(jī)環(huán)境聯(lián)合學(xué)術(shù)會議（HHME2005）論文集[C];2005年

2 ;A Reliability Improvement Predictive Approach to Software Testing with Bayesian Method[A];第二十九屆中國控制會議論文集[C];2010年

3 ;Bayesian Approaches to Genre Identification of Chinese Finance Text[A];第四屆全國信息檢索與內(nèi)容安全學(xué)術(shù)會議論文集（下）[C];2008年

4 Wenqiang Guo;Qinkun Xiao;Yongyan Hou;Ejuan Wang;Xiangqing Zhang;;Bayesian Network Learning Based on Relationship Prediction PSO and Its Application in Agricultural Expert System[A];第25屆中國控制與決策會議論文集[C];2013年

5 徐瑞;王睿;李怡;崔玉柱;;動態(tài)場景下基于Bayesian分類光流法的運(yùn)動目標(biāo)檢測[A];中國儀器儀表學(xué)會第十三屆青年學(xué)術(shù)會議論文集[C];2011年

6 Chen Yao;Lijuan Hong;Yunfei Cheng;;Error Concealment via Best Matching Block Selection Strategy[A];2013年中國智能自動化學(xué)術(shù)會議論文集（第二分冊）[C];2013年

相關(guān)博士學(xué)位論文 前1條

1 董旭初;Bayesian網(wǎng)的最優(yōu)樹分解研究[D];吉林大學(xué);2011年

相關(guān)碩士學(xué)位論文 前5條

1 于鵬;一種Bayesian網(wǎng)結(jié)構(gòu)學(xué)習(xí)算法的研究[D];吉林大學(xué);2005年

2 王昆;一種基于Bayesian CBR的推薦系統(tǒng)研究[D];河北師范大學(xué);2011年

3 王鵬;Bayesian網(wǎng)推理算法及在圖像分類上的應(yīng)用[D];吉林大學(xué);2006年

4 丁繼紅;基于CBR的Bayesian在ITS中的應(yīng)用研究[D];湖南師范大學(xué);2009年

5 魏文暢;小波非Bayesian濾波法比較及其閾值濾波算法研究[D];廈門大學(xué);2009年

，

本文編號：2125040