A Variational Model for Sea Image Enhancement

Accurate Fish Detection under Marine Background Noise Based on the Retinex Enhancement Algorithm and CNN

Underwater detection equipment with fish detection technology has broad application prospects in marine fishery resources exploration and conservation. In this paper, we establish a multi-scale retinex enhancement algorithm and a multi-scale feature-based fish detection model to improve underwater detection accuracy and ensure real-time performance. During image preprocessing, the enhancement algorithm combines the bionic structure of the fish retina and classical retinex theory to filter out underwater environmental noise. The detection model focuses on improving the detection performance on small-size targets using a deep learning method based on a convolutional neural network. We compare our method to current mainstream detection models (Faster R-CNN, RetinaNet, YOLO, SSDetc.), and the proposed model achieves better performance, with a mean Average Precision (mAP) of 78.31% and a mean Miss Rate (mMR) of 54.11% in the open fish image data set. The test results for the data from the field experiment prove the feasibility and stability of our model.

Underwater Image Restoration via DCP and Yin–Yang Pair Optimization

Underwater image restoration is a challenging problem because light is attenuated by absorption and scattering in water, which can degrade the underwater image. To restore the underwater image and improve its contrast and color saturation, a novel algorithm based on the underwater dark channel prior is proposed in this paper. First of all, in order to reconstruct the transmission maps of the underwater image, the transmission maps of the blue and green channels are optimized by the proposed first-order and second-order total variational regularization. Then, an adaptive model is proposed to improve the first-order and second-order total variation. Finally, to solve the problem of the excessive attenuation of the red channel, the transmission map of the red channel is compensated by Yin–Yang pair optimization. The simulation results show that the proposed restored algorithm outperforms other approaches in terms of the visual effects, average gradient, spatial frequency, percentage of saturated pixels, underwater color image quality evaluation and evaluation metric.

Multispectral Image Enhancement Based on the Dark Channel Prior and Bilateral Fractional Differential Model

Compared with single-band remote sensing images, multispectral images can obtain information on the same target in different bands. By combining the characteristics of each band, we can obtain clearer enhanced images; therefore, we propose a multispectral image enhancement method based on the improved dark channel prior (IDCP) and bilateral fractional differential (BFD) model to make full use of the multiband information. First, the original multispectral image is inverted to meet the prior conditions of dark channel theory. Second, according to the characteristics of multiple bands, the dark channel algorithm is improved. The RGB channels are extended to multiple channels, and the spatial domain fractional differential mask is used to optimize the transmittance estimation to make it more consistent with the dark channel hypothesis. Then, we propose a bilateral fractional differentiation algorithm that enhances the edge details of an image through the fractional differential in the spatial domain and intensity domain. Finally, we implement the inversion operation to obtain the final enhanced image. We apply the proposed IDCP_BFD method to a multispectral dataset and conduct sufficient experiments. The experimental results show the superiority of the proposed method over relative comparison methods.