Bottom-up attention: pulsed PCA transform and pulsed cosine transform
Bottom-up attention: pulsed PCA transform and pulsed cosine transform
复制标题
自下而上的注意力：脉冲PCA变换和脉冲余弦变换
DOI：
10.1007/s11571-011-9155-z
复制
发表时间：
2011-11-01
影响因子：
3.7
通讯作者：
Zhang, Liming
中科院分区：
文献类型：
--
作者：
Yu, Ying;Wang, Bin;Zhang, Liming
在本文中，我们提出了一个基于脉冲主成分分析（PCA）变换的自下而上视觉注意计算模型，该模型简单地利用PCA系数的符号来产生空间和运动显著性。我们进一步将脉冲PCA变换扩展为脉冲余弦变换，该变换不仅与数据无关，而且计算速度非常快。提出的模型具有以下生物学合理性。首先，利用神经网络中的Hebbian规则获得模型中的PCA投影向量；其次，脉冲PCA变换的输出本质上是二值的，模拟了人脑中的神经元脉冲。第三，与许多基于傅里叶变换的方法一样，我们的模型也实现了频域皮质中心环绕抑制。心理物理模式和自然图像的实验结果表明，该模型在显著性检测和人眼注视预测方面比现有的注意模型更有效。
In this paper we propose a computational model of bottom-up visual attention based on a pulsed principal component analysis (PCA) transform, which simply exploits the signs of the PCA coefficients to generate spatial and motional saliency. We further extend the pulsed PCA transform to a pulsed cosine transform that is not only data-independent but also very fast in computation. The proposed model has the following biological plausibilities. First, the PCA projection vectors in the model can be obtained by using the Hebbian rule in neural networks. Second, the outputs of the pulsed PCA transform, which are inherently binary, simulate the neuronal pulses in the human brain. Third, like many Fourier transform-based approaches, our model also accomplishes the cortical center-surround suppression in frequency domain. Experimental results on psychophysical patterns and natural images show that the proposed model is more effective in saliency detection and predict human eye fixations better than the state-of-the-art attention models.