Underwater image recovery based on water type estimation and adaptive color correction.

In underwater environments, light propagation is affected by scattering and absorption, leading to color distortion and quality degradation of underwater images. In addition, the presence of a color cast in the image and variations in the attenuation coefficients across various water bodies bring great challenges for underwater image restoration. In this paper, an underwater image restoration method based on water body type estimation and adaptive color correction is proposed. Initially, the underwater images are categorized into color casts and non-color casts according to their hue, and a water body type estimation method based on image color and blurriness is introduced for improving the accuracy of transmission map estimation. Following this, we performed adaptive color correction on the image using a nonlinear transformation, which effectively eliminates color cast. Then the background light position is corrected using the degree of color cast of the image to restore the hue and brightness of the image more naturally. Ultimately, the acquired background light and transmission map are utilized to generate clear underwater images using the image formation model (IFM). Experiments on the widely used UIEB benchmark and SUID datasets show that our method effectively solves the problems of image color distortion and quality degradation, generating satisfactory visual effects.

Short-Term Prediction of Multi-Energy Loads Based on Copula Correlation Analysis and Model Fusions.

To improve the accuracy of short-term multi-energy load prediction models for integrated energy systems, the historical development law of the multi-energy loads must be considered. Moreover, understanding the complex coupling correlation of the different loads in the multi-energy systems, and accounting for other load-influencing factors such as weather, may further improve the forecasting performance of such models. In this study, a two-stage fuzzy optimization method is proposed for the feature selection and identification of the multi-energy loads. To enrich the information content of the prediction input feature, we introduced a copula correlation feature analysis in the proposed framework, which extracts the complex dynamic coupling correlation of multi-energy loads and applies Akaike information criterion (AIC) to evaluate the adaptability of the different copula models presented. Furthermore, we combined a NARX neural network with Bayesian optimization and an extreme learning machine model optimized using a genetic algorithm (GA) to effectively improve the feature fusion performances of the proposed multi-energy load prediction model. The effectiveness of the proposed short-term prediction model was confirmed by the experimental results obtained using the multi-energy load time-series data of an actual integrated energy system.