Home » Saliency Detection for Videos

Saliency Detection for Videos


In this work, we explore using 3D FFT local spectra for saliency detection in videos. We develop a spectral location based decomposition scheme to divide a 3D FFT cube into two components, one related to temporal changes and the other related to spatial changes. Temporal saliency and spatial saliency are detected separately using features derived from each spectral component within the classic framework based on the center-surround model. The two detection results are then combined to yield a saliency map. We apply the same detection algorithm to different color channels (YIQ) and incorporate the results into the final saliency determination. The proposed technique is tested with the public CRCNS database. Both visual and numerical evaluations verify the promising performance of our technique.

[Related Publication]

  1. Z. Long and G. AlRegib, “Saliency Detection for Videos Using 3D FFT Local Spectra” Human Vision and Electronic Imaging XX, SPIE Electronic Imaging , San Francisco, CA, Feb. 8-12, 2015. [PDF] [Poster/Lec] [Bib] [Code]
%d bloggers like this: