A visual attention model based on hierarchical spiking neural networks

A visual attention model based on hierarchical spiking neural networks
复制标题

基于分层尖峰神经网络的视觉注意模型

DOI:
10.1016/j.neucom.2012.01.046
复制
发表时间:
2013-09
期刊:
影响因子:
6
通讯作者:
Chen, Meigui
Chen, Meigui
中科院分区:
计算机科学2区
文献类型:
--
作者:
McGinnity, T. M.;Maguire, Liam;Cai, Rongtai;Chen, Meigui

文献摘要

参考文献

被引文献

相似文献

基于脉冲神经元的信息处理功能,提出了一种模拟视觉注意的分层脉冲神经网络。利用受视觉系统启发的脉冲神经网络,将一幅图像分解为多个视觉图像组件。基于特定的视觉图像成分和图像特征,提出了一种视觉注意系统,根据自上而下的意志控制信号提取注意区域。利用基于电导的神经元模型和一组不同层次的特定感受野,构建了分层脉冲神经网络。本文详细介绍了该网络的仿真算法和特性。仿真结果表明,该注意系统能够根据特定的图像成分或特征对物体进行视觉注意,并演示了该注意系统如何检测视觉图像中的房屋。使用提出的显著性指数,可以从多个视觉通路(如开/关颜色通路)的尖峰率图中提取感兴趣的注意区域。根据这种视觉注意原理,视觉图像处理系统可以快速地将注意力集中在特定区域,而忽略其他区域。
Based on the information processing functionalities of spiking neurons, hierarchical spiking neural networks are proposed to simulate visual attention. Using spiking neural networks inspired by the visual system, an image can be decomposed into multiple visual image components. Based on specific visual image components and image features, a visual attention system is proposed to extract attention areas according to top–down volition-controlled signals. The hierarchical spiking neural networks are constructed with a conductance-based integrate-and-fire neuron model and a set of specific receptive fields in different levels. The simulation algorithm and properties of the networks are detailed in this paper. Simulation results show that the attention system is able to perform visual attention of objects based on specific image components or features, and a demonstration shows how the attention system can detect a house in a visual image. Using the proposed saliency index, attention areas of interest can be extracted from spike rate maps of multiple visual pathways, such as ON/OFF colour pathways. According to this visual attention principle, the visual image processing system can quickly focus on specific areas while ignoring other areas.
DOI: 10.1007/11539087_54
发表时间: 2005-08
期刊: --
影响因子: --
作者:
Qingxiang Wu;T. McGinnity;L. Maguire;A. Belatreche;B. Glackin
通讯作者: Qingxiang Wu;T. McGinnity;L. Maguire;A. Belatreche;B. Glackin
DOI: 10.1007/978-3-642-14922-1_7
发表时间: 2010-08
期刊: --
影响因子: --
作者:
Qingxiang Wu;T. McGinnity;L. Maguire;German D. Valderrama-Gonzalez;P. Dempster
通讯作者: Qingxiang Wu;T. McGinnity;L. Maguire;German D. Valderrama-Gonzalez;P. Dempster
DOI: 10.1007/s12559-009-9028-5
发表时间: 2009-11
影响因子: 5.4
作者:
Yang Mu;D. Tao;Xuelong Li;F. Murtagh
通讯作者: Yang Mu;D. Tao;Xuelong Li;F. Murtagh
DOI: 10.1109/3477.678658
发表时间: 1998-06
期刊: IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society
影响因子: --
作者:
De-shuang Huang
通讯作者: De-shuang Huang
DOI: 10.1109/cvpr.2009.5206636
发表时间: 2009-06
期刊: 2009 IEEE Conference on Computer Vision and Pattern Recognition
影响因子: --
作者:
D. Damen;David C. Hogg
通讯作者: D. Damen;David C. Hogg