- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2018 25th IEEE International Conference on Image Processing (ICIP) - Athens, Greece (2018.10.7-2018.10.10)] 2018 25th IEEE International Conference on Image Processing (ICIP) - Visual-Quality-Driven Learning for Underwater Vision Enhancement
摘要： The image processing community has witnessed remarkable advances in enhancing and restoring images. Nevertheless, restoring the visual quality of underwater images remains a great challenge. End-to-end frameworks might fail to enhance the visual quality of underwater images since in several scenarios it is not feasible to provide the ground truth of the scene radiance. In this work, we propose a CNN-based approach that does not require ground truth data since it uses a set of image quality metrics to guide the restoration learning process. The experiments showed that our method improved the visual quality of underwater images preserving their edges and also performed well considering the UCIQE metric.
关键词： Image Restoration,Underwater Vision,Deep Learning,Image Quality Metrics
更新于2025-09-23 15:21:21
-
A Mathematical Model of Laser Radiation Propagation in Seawater
摘要： Based on the well-known models of optical properties of a seawater layer in the spectral range of 530–550 nm, a mathematical model of the propagation of laser radiation is proposed. The mathematical model is obtained by solving radiative transfer equation for a narrow beam using a few-parameter approximation of the scattering indicatrix of the seawater layer. The model makes it possible to determine the spatial distribution of irradiance at a given distance from the laser radiation source by the known Secchi disk depth. The results of numerical experiments for water areas with known optical properties are given.
关键词： water inherent optical properties,turbid medium,optical radiation transfer,underwater vision system
更新于2025-09-16 10:30:52
-
The Role of the Effect of Shadowing of Some Wavy Regions by Other Wavy Regions in the Formation of an Image of Snell’s Window
摘要： The shadowing of some regions of a wavy water surface by other regions can significantly influence the backscattered signal not only in the problem of remote monitoring of a water reservoir at grazing angles (e.g., in radar), but also in the problems of underwater vision. In this work, we present the results of a theoretical study of this phenomenon with respect to the model of underwater imaging of the sky (Snell’s window) near the image boundary. The numerical-simulation method is used to develop the statistically mean image of Snell’s window, which allows for the shadowing effects, and the corrected formula of the estimate of a wave parameter, namely, the water-surface slope variance, is obtained using the value of blurring of the boundary of Snell’s window.
关键词： underwater vision,wavy water surface,shadowing,numerical simulation,Snell’s window
更新于2025-09-04 15:30:14