Fast Underwater Image Enhancement for Improved Visual Perception

作     者：Islam, Md Jahidul Xia, Youya Sattar, Junaed 

作者机构：Univ Minnesota Dept Comp Sci & Engn Interact Robot & Vis Lab Minneapolis MN 55455 USA 

出 版 物：《IEEE ROBOTICS AND AUTOMATION LETTERS》 (IEEE Robot. Autom.)

年 卷 期：2020年第5卷第2期

页      面：3227-3234页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 0811[工学-控制科学与工程] 

主　　题：Marine robotics deep learning in robotics and automation computer vision for automation 

摘      要：In this letter, we present a conditional generative adversarial network-based model for real-time underwater image enhancement. To supervise the adversarial training, we formulate an objective function that evaluates the perceptual image quality based on its global content, color, local texture, and style information. We also present EUVP, a large-scale dataset of a paired and an unpaired collection of underwater images (of poor and good quality) that are captured using seven different cameras over various visibility conditions during oceanic explorations and human-robot collaborative experiments. In addition, we perform several qualitative and quantitative evaluations which suggest that the proposed model can learn to enhance underwater image quality from both paired and unpaired training. More importantly, the enhanced images provide improved performances of standard models for underwater object detection, human pose estimation, and saliency prediction. These results validate that it is suitable for real-time preprocessing in the autonomy pipeline by visually-guided underwater robots. The model and associated training pipelines are available at https://***/xahidbuffon/funie-gan.