A New Model of Visual Attention Selection Based on Amplitude Modulation Fourier Transform

摘要：

In this paper, a new approach for visual attention selection called Amplitude Modulation Fourier Transform is proposed, which is based on two up-to-date works: Spectral Residual model (SR) and Phase Fourier Transform (PFT). We try to explore the nature of AMFT by analyzing its intrinsic mechanism and summarizing its merits and disadvantages. We also propose a new attention selection method called Multi-Channel and Multi-Scale Amplitude Modulation (MCMSAM). For proving the advantage of MCMSAM, we design several simulations to compare our model with Spectral Residual Model, Phase Fourier Transform and traditional Saliency ToolBox.

关键词： Attention Selection Saliency Map Fourier Transform Spectral Residual Phase Fourier Transform Saliency ToolBoz

作者: Dongyue Chen Chengdong Wu

作者单位: School of Information Science and Engineering, Northeastern University, Shenyang 110004

会议类型: 国际会议

会议名称: 2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)

会议地点: 广西桂林

会议语种:英文

页码: 4617-4622

在线出版日期: 2009-06-17（万方平台首次上网日期，不代表论文的发表时间）