Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform
Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform
复制标题
DOI：
10.1109/cvpr.2008.4587715
复制
发表时间：
2008-06
期刊：
影响因子：
--
通讯作者：
Chenlei Guo;Qi Ma;Liming Zhang
中科院分区：
文献类型：
--
作者：
Chenlei Guo;Qi Ma;Liming Zhang
自然场景中的显著区域通常被认为是人眼注意焦点的候选区域，是目标检测的关键阶段。在计算机视觉中，已经提出了许多模型来模拟眼睛的行为，如显着性工具箱（STB），神经形态视觉工具箱（NVT）等，但它们需要很高的计算成本，并且它们的显著结果主要依赖于参数的选择。最近提出了一种简单快速的基于傅立叶变换的显著图提取方法--谱残差法。结果是好的，但原因值得怀疑。
Salient areas in natural scenes are generally regarded as the candidates of attention focus in human eyes, which is the key stage in object detection. In computer vision, many models have been proposed to simulate the behavior of eyes such as SaliencyToolBox (STB), neuromorphic vision toolkit (NVT) and etc., but they demand high computational cost and their remarkable results mostly rely on the choice of parameters. Recently a simple and fast approach based on Fourier transform called spectral residual (SR) was proposed, which used SR of the amplitude spectrum to obtain the saliency map. The results are good, but the reason is questionable.