DocumentCode :
2401498
Title :
Spatio-temporal Saliency detection using phase spectrum of quaternion fourier transform
Author :
Guo, Chenlei ; Ma, Qi ; Zhang, Liming
Author_Institution :
Dept. of Electron. Eng., Fudan Univ., Shanghai
fYear :
2008
fDate :
23-28 June 2008
Firstpage :
1
Lastpage :
8
Abstract :
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.
Keywords :
Fourier transforms; computer vision; natural scenes; object detection; spatiotemporal phenomena; spectral analysis; amplitude spectrum; computer vision; natural scenes; object detection; phase spectrum; quaternion Fourier transform; saliency map; spatio-temporal saliency detection; spectral residual approach; Computational modeling; Computer vision; Eyes; Fourier transforms; Humans; Layout; Object detection; Phase detection; Quaternions; Strontium;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
Conference_Location :
Anchorage, AK
ISSN :
1063-6919
Print_ISBN :
978-1-4244-2242-5
Electronic_ISBN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2008.4587715
Filename :
4587715
Link To Document :
بازگشت