Blurriness Guided Underwater Salient Object Detection
Yan‐Tsung Peng, Yu‐Cheng Lin, Wen‐Yi Peng · OCEANS 2021: San Diego – Porto · 2021
There is little work done for underwater saliency objection detection (SOD), but it is vital to artificial intelligence-driven underwater analysis. Recent research has shown that depth information would increase SOD accuracy, but it may not be accessible to most RGB datasets. Since image blurriness could be an estimate of underwater scene depth [1], we propose to use a self-derived blurriness cue and fuse it into the RGB stream to boost SOD accuracy. Experimental results demonstrate the effectiveness of the proposed method. Our work would also contribute a public underwater SOD dataset to the field of underwater SOD.