Saliency Detection Using Superpixel Belief Propagation, ICIP2014.

  • S.-C. Pei, W.-W. Chang and C.-T. Shen, “Saliency Detection using Superpixel Belief Propagation," in Proc. of 21th IEEE International Conference on Image Processing (ICIP), pp. 1135-1139, 2014.
  • System:flowchart
  • Abstrast: We propose a method to detect saliency from a single image using feature extraction and superpixel belief propagation. We observe that the previous works are hard to deal with the intrinsic material discontinuity and non-homogeneous color distribution within an object or a region. Motivated by this observation, we bring the belief propagation into the saliency detection. First, we separate the image into middlelevel superpixels and also extract the low-level feature within each superpixel. Then, we build up a Markov-Random-Field (MRF) on the middle-level super-pixels and adopt propagation technique to optimize the superpixel saliency. Afterward, we refine this middle-level solution to per-pixel saliency map. Experimental results demonstrate that our proposed method is promising as compared to the state-of-the-art methods in both MSRA-1000 and SED datasets.
  • Experimental Results on MSRA-1000 Dataset( Input, Superpixels, PR2014, ICCV2013, Ours)0_0_272_example0_0_735_example0_25_25064_example1_30_30895_example1_45_45397_example3_112_112493_example4_127_127386_example
  • Experimental Results on SED Dataset( Input, Superpixels, CA, RC, Ours) atlasredstone_exampleb1chesnuttame_exampleb2pods001_examplefullicewater_examplehot_air_balloons_05_example


在下方填入你的資料或按右方圖示以社群網站登入: 標誌

您的留言將使用 帳號。 登出 /  變更 )


您的留言將使用 Facebook 帳號。 登出 /  變更 )

連結到 %s