Visual Saliency Detection With Free Energy Theory

被引：72

作者：

Gu, Ke ^{[1
]}

Zhai, Guangtao ^{[1
]}

Lin, Weisi ^{[2
]}

Yang, Xiaokang ^{[1
]}

Zhang, Wenjun ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, Inst Image Commun & Informat Proc, Shanghai Key Lab Digital Media Proc & Transmiss, Shanghai 200240, Peoples R China

[2] Nanyang Technol Univ, Sch Comp Engn, Singapore 639798, Singapore

来源：

IEEE SIGNAL PROCESSING LETTERS | 2015年 / 22卷 / 10期

基金：

美国国家科学基金会;

关键词：

Bi-lateral filtering; free energy; linear autoregressive (AR) model; saliency detection; semi-parametric model; ATTENTION; PRINCIPLE; MODEL;

D O I：

10.1109/LSP.2015.2413944

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

Visual saliency can be thought of as the product of human brain activity. Most existing models were built upon local features or global features or both. Lately, a so-called free energy principle unifies several brain theories within one framework, and tells where easily surprise human viewers in a visual stimulus through a psychological measure. We believe that this "surprise" should be highly related to visual saliency, and thereby introduce a novel computational Free Energy inspired Saliency detection technique (FES). Our method computes the local entropy of the gap between an input image signal and its predicted counterpart that is reconstructed from the input one with a semi-parametric model. Experimental results prove that our algorithm predicts human fixation points accurately and is superior to classical/state-of-the-art competitors.

引用

页码：1552 / 1555

页数：4

共 29 条

[1]

[Anonymous], 2007, 2007 IEEE C COMPUTER, DOI [DOI 10.1109/CVPR.2007.383267, 10.1109/CVPR.2007.383267]

[2]

Attias H, 2000, ADV NEUR IN, V12, P209

[3] State-of-the-Art in Visual Attention Modeling [J].

Borji, Ali ;

Itti, Laurent .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2013, 35 (01) :185-207

[4]

Borji A, 2012, PROC CVPR IEEE, P478, DOI 10.1109/CVPR.2012.6247711

[5] Saliency, attention, and visual search: An information theoretic approach [J].

Bruce, Neil D. B. ;

Tsotsos, John K. .

JOURNAL OF VISION, 2009, 9 (03)

[6]

Cerf M., 2008, P ADV NEUR INF PROC, V20

[7]

Dong L., 2014, J VIS COMMUN IMAGE R, V24, P27

[8] Bottom-Up Saliency Detection Model Based on Human Visual Sensitivity and Amplitude Spectrum [J].

Fang, Yuming ;

Lin, Weisi ;

Lee, Bu-Sung ;

Lau, Chiew-Tong ;

Chen, Zhenzhong ;

Lin, Chia-Wen .

IEEE TRANSACTIONS ON MULTIMEDIA, 2012, 14 (01) :187-198

[9] The free-energy principle: a unified brain theory? [J].

Friston, Karl J. .

NATURE REVIEWS NEUROSCIENCE, 2010, 11 (02) :127-138

[10] Saliency from hierarchical adaptation through decorrelation and variance normalization [J].

Garcia-Diaz, Anton ;

Fdez-Vidal, Xose R. ;

Pardo, Xose M. ;

Dosil, Raquel .

IMAGE AND VISION COMPUTING, 2012, 30 (01) :51-64

← 1 2 3 →