Recently, Associate Professor Huajun Song of the College of Oceanography and Space Informatics, China University of Petroleum (East China) has made recent research progress in the field of underwater image processing. The related research result "Enhancement-Registration-Homogenization (ERH): A Comprehensive Underwater Visual Reconstruction Paradigm" was accepted by the IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), which is the top international journal in the field of artificial intelligence and pattern recognition. Professor Song is the first author of the paper, and China University of Petroleum (East China) is the first completion unit.
Visual reconstruction of multiple underwater images with poor visibility
The high-quality, wide-field underwater images are of great significance for exploring the marine environment and conducting underwater works, but they are difficult to obtain. Most underwater acquisition devices have some limitations in capturing a full-view image of a wide-field scene. Coupled with the strong scattering and absorption of light by the water medium, the visibility of degraded underwater images is poor. To address these limitations, they investigated the underwater visual reconstruction in the paper, which aims to construct a new image with a wider field of view and better visibility based on multiple overlapping images.
The structure of the Enhancement-Registration-Homogenization (ERH) paradigm in this paper.
IEEE TPAMI is an international top journal in the fields of artificial intelligence, pattern recognition, and computer vision, etc. It is a CCF A journal, and a top journal in JCR Region 1. The latest impact factor in 2022 is 16.389. This is the first time that China University of Petroleum (East China) has published academic research in the journal.
Title: Enhancement-Registration-Homogenization (ERH): A Comprehensive Underwater Visual Reconstruction Paradigm.
Authors: Huajun Song; Laibin Chang; Ziwei Chen; Peng Ren.
Journal: IEEE Transactions on Pattern Analysis and Machine Intelligence
Date of Publication: 19 July 2021
Related Links：https://ieeexplore.ieee.org/document/9490352