An enhancement method for underwater polymetallic nodule images
Fengtian Lv, Huixi Xu, Xiaohui Wang · International Conference on Mechanisms and Robotics (ICMAR 2022) · 2022
Due to the absorption and scattering of light in the water environment, the polymetallic nodule images were of low quality, such as color deviation, uneven illumination and blur, which was negative for the extraction and abundance calculation of polymetallic nodules. An improved image color correction method based on the dual transmission underwater imaging model is proposed. Its key lies in the estimation of direct component transmission (DCT) and backscattering component transmission (BCT) in the model. BCT is estimated in red, green and blue color channels, which are no longer considered equal. The DCT is estimated based on the mean pixel value and BCT of the background light region. In addition, the retinex algorithm is used to eliminate the illumination image and solve the imbalance of illumination and shadows caused by photoshooting with supplementary lighting. The image contrast is enhanced by using the contrast limited adaptive histogram equalization (CLAHE) algorithm. The polymetallic nodule images are used to evaluate the proposed method qualitatively and quantitatively. The results demonstrate that the proposed method has high performance in image visibility enhancement and color restoration. It is beneficial to the extraction and distribution analysis of polymetallic nodules.