A Promising Underwater Image Restoration Algorithm

Recently, a research group led by YANG Ping, assistant director and researcher of IOE’s AO laboratory, has proposed a new underwater image restoration algorithm to solve the problem of red component attenuation. 

Due to the special optical environment of the ocean and different propagation characteristics, the light with different wavelengths will cause the images collected by underwater sensors to appear color distortion, visual blur and contrast reduction.  

Underwater image is an important carrier of marine information and related to underwater imaging systems closely. In recent years, scientists have carried out a lot of research on underwater imaging. Compared to the high cost of improving the imaging system equipment, digital image processing is more flexible, simple and easy to implement. 

YANG and his team cooperate with the scientists from Yantai Coastal Zone Research Institute, Chinese Academy of Sciences, they analyze the typical patterns collected in the Bohai sea area. Based on the different attenuation and scattering characteristics of different wavelengths under water, they compensate the image color distortion by means of restoring the intensity information and edge information in red channel. Then, on the basis of image intensity data distribution, they stretch the dynamic range of the image to improve the contrast and visual effect of the image. 

The color of restored image is more realistic and the overall contrast is increased by more than two times. The algorithm can process the video with 1280×810 resolution in real time on the hardware platform. This achievement is expected to be widely used in underwater target detection, marine geotechnical engineering exploration, marine resources exploration and other underwater areas. If paired with an underwater robot, it will have a broader application prospect. 

The study, published in opto-electronic advances, was supported by the National Key Scientific Equipment Development Project of China, the National High-Tech R&D Program of China and the Natural Science Foundation of China, Outstanding Youth Fund of Sichuan Province. 


Figure 1, the restored underwater image. 


CAO Qiang 

Institute of Optics and Electronics 

Email: caoqiang@ioe.ac.cn 

  Copyright © The Institute of Optics And Electronics, The chinese Academy of Sciences
Address: Box 350, Shuangliu, Chengdu, Sichuan, China
Email:dangban@ioe.ac.cn Post Code: 610 209 备案号:蜀ICP备05022581号