Underwater salient object detection based on red channel correction

Under the environment of ocean development, underwater object detection technology has been widely used. Underwater salient object detection technology plays an important role in this process. The characteristics of light transmission under water determine the attenuation of color information in underwater images. In this paper, a method of underwater salient object detection based on red channel correction is designed based on the characteristics of the fastest attenuation of red channel in underwater images. First, the red channel component of the underwater image is weighted and corrected, and then the corrected three RGB components are used to construct the quaternion. The salient target detection calculation is carried out by PQFT method, and finally the salient object image is obtained. Experimental results show that, compared with the traditional SR and PQFT methods, the proposed method has higher accuracy and lower error rate in detecting the boundary of visually significant underwater object.