An enhancement method for underwater polymetallic nodule images

Fengtian Lv; Huixi Xu; Xiaohui Wang

doi:10.1117/12.2652238

10 November 2022 An enhancement method for underwater polymetallic nodule images

Fengtian Lv, Huixi Xu, Xiaohui Wang

Proceedings Volume 12331, International Conference on Mechanisms and Robotics (ICMAR 2022); 123313L (2022) https://doi.org/10.1117/12.2652238
Event: International Conference on Mechanisms and Robotics (ICMAR 2022), 2022, Zhuhai, China

Abstract

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.

Citation Download Citation

Fengtian Lv, Huixi Xu, and Xiaohui Wang "An enhancement method for underwater polymetallic nodule images", Proc. SPIE 12331, International Conference on Mechanisms and Robotics (ICMAR 2022), 123313L (10 November 2022); https://doi.org/10.1117/12.2652238

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available