A Survey of Target Detection and Recognition Methods in Underwater Turbid Areas PDF

applied sciences Review A Survey of Target Detection and Recognition Methods in Underwater Turbid Areas Xin Yuan , Linxu Guo , Citong Luo, Xiaoteng Zhou and Changli Yu * School of Ocean Engineering, Harbin Insti...

applied sciences Review A Survey of Target Detection and Recognition Methods in Underwater Turbid Areas Xin Yuan , Linxu Guo , Citong Luo, Xiaoteng Zhou and Changli Yu * School of Ocean Engineering, Harbin Institute of Technology, Weihai 264209, China; [email protected] (X.Y.); [email protected] (L.G.); [email protected] (C.L.); [email protected] (X.Z.) * Correspondence: [email protected]; Tel.: +86-138-6310-6670 Abstract: Based on analysis of state-of-the-art research investigating target detection and recognition in turbid waters, and aiming to solve the problems encountered during target detection and the unique influences of turbidity areas, in this review, the main problem is divided into two areas: image degradation caused by the unique conditions of turbid water, and target recognition. Existing target recognition methods are divided into three modules: target detection based on deep learning methods, underwater image restoration and enhancement approaches, and underwater image processing methods based on polarization imaging technology and scattering. The relevant research results are analyzed in detail, and methods regarding image processing, target detection, and recognition in turbid water, and relevant datasets are summarized. The main scenarios in which underwater target detection and recognition technology are applied are listed, and the key problems that exist in the current technology are identified. Solutions and development directions are discussed. This work provides a reference for engineering tasks in underwater turbid areas and an outlook on the development of underwater intelligent sensing technology in the future. Keywords: turbid water; underwater operation; image processing; target detection and recognition; intelligent sensing Citation: Yuan, X.; Guo, L.; Luo, C.; Zhou, X.; Yu, C. A Survey of Target Detection and Recognition Methods in Underwater Turbid Areas. Appl. 1. Introduction Sci. 2022, 12, 4898. https://doi.org/ Nowadays, underwater intelligent sensing technology is widely used in seabed re- 10.3390/app12104898 source exploration, fishery monitoring, underwater archaeology, underwater warfare, pipeline maintenance, and other fields. It also benefits the economy, military, culture, and Academic Editor: Andrea Prati other aspects. The future in this field is immeasurable, and the demand for large-scale Received: 12 April 2022 and long-term monitoring of the internal water body is increasing. Due to the unique Accepted: 10 May 2022 underwater operation environment, it has significant benefits but is also accompanied Published: 12 May 2022 by some challenges. Turbidity is often encountered in underwater development as the Publisher’s Note: MDPI stays neutral required targets always exist in complex water environments, and water contains a variety with regard to jurisdictional claims in of organic and inorganic suspended particles. Thus, the direction of light transmission published maps and institutional affil- is changed by the scattering or absorption of water and particles, which results in sig- iations. nificant interference in the reflected light received by the imaging system, resulting in a significant reduction in the clarity of underwater images. Compared with turbid water, intuitively, the quality and visibility of clear water is good. For example, in a small clean pond, the target characteristics obtained via visual sensing are easily recognized due to Copyright: © 2022 by the authors. the small amount of biological impurities and sediment in the water. Shallow water has Licensee MDPI, Basel, Switzerland. the advantage of good light transmittance. However, target detection in turbid water is This article is an open access article a significantly challenging task. Turbid water can be divided into shallow turbid water distributed under the terms and and two kinds of deep turbid water. Shallow turbid water, such as turbid fish farms, has conditions of the Creative Commons a significant impact on the transmission of light information due to the high density of Attribution (CC BY) license (https:// aquatic organisms and suspended matters, such as fishes and sediments, in the water. creativecommons.org/licenses/by/ This leads to significant image distortion, such as blurred target features, severe distortion, 4.0/). Appl. Sci. 2022, 12, 4898. https://doi.org/10.3390/app12104898 https://www.mdpi.com/journal/applsci Appl. Sci. 2022, 12, 4898 2 of 21 and color changes, which pose a significant challenge regarding visual technology and target recognition. Deep turbid water, such as some deep water areas, is challenged by the same problems as shallow turbid water and has low light conditions, resulting in the instrument receiving limited effective target light information. Due to these factors, traditional target detection and recognition methods cannot meet instruments’ technical requirements. Therefore, the investigation of object detection and recognition in turbid areas is necessary. Currently, research on underwater vision is mainly focusing on scenarios with good water conditions, such as experimental pools, lakes, inland rivers, etc. Due to the complexity of underwater environments, significant differences between various types of water exist. As large-scale engineering operations are often carried out at sea, most research methods do not contain adequate robustness to overcome the significant difficulties encountered in practical engineering applications. Focusing on the common applications scenes of turbid areas, this paper systematically collates the relevant research methods and the latest achievements, analyzes key technical problems, and summarizes future development directions. Since target detection in turbid water is more unique than that in clean water, this paper presents three perspectives: the first perspective is target feature extraction and detection based on deep learning methods, the second perspective is underwater image restoration and enhancement, and the last perspective is image processing based on the po- larization imaging approach. The contents of this paper are summarized as follows: (1) the application of ConvNet and a typical network, such as Faster RCNN and YOLOv3 , and a comparison of the Canny edge detection algorithm and a track prediction algo- rithm combined with practical engineering are introduced, and the disadvantages of deep learning methods and their corresponding solutions are analyzed. (2) Some methods, in- cluding the migrating defogging algorithm and addition of the haze reduction module, for restoring and enhancing underwater images are summarized. (3) The polarization-based imaging technology and scattering-based image processing methods are summarized and compared. (4) Some minor research methods (such as the use of an electric field) are introduced. (5) The commonly used visual research datasets in visual research carried out in turbid underwater environments are summarized to provide a reference for future study. 2. Research Field Analysis In recent years, the emergence of deep learning has provided a new direction for target detection and recognition in turbid waters. The combination of this field with image processing, polarization imaging technology, and other areas has also obtained excellent experimental results as presented in the latest papers. However, little scientific research has been conducted on this aspect at present. In this field, scholars engaged in underwater vision have presented some research attempting to improve the scattering and enhancement of image contrast. In the exploration of new methods, researchers who were inspired by biology, such as marine organisms , have used electronic communication and sonar to broaden their understanding of solutions and promote the development of target detection and recognition in turbid waters. Based on the Web of Science database and the keyword turbid zone target recogni- tion, the fields involved in research results presented over the last five years were identified. It was found that the application fields of these studies are very comprehensive, with strong generality and crossover. According to the identified applications of target detection and recognition in turbid waters, it can be concluded that this research field covers a wide range of disciplines. Moreover, it can be applied in, but not limited to, engineering, optics, instruments instrumentation, communication, computer science, oceanography, telecommunications, physics, chemistry and environmental ecology, chemical analysis, and biomedical engineering, such as the detection of targets in turbid solution samples. Figure 1 shows the general statistical results of the application of this study in various areas.  Appl. Sci. 2022, 12, x FOR PEER REVIEW 3 of 22 Appl. Sci. 2022, 12, x FOR PEER REVIEW 3 of 22 samples. Figure 1 shows the general statistical results of the application of this study in Appl. Sci. 2022, 12, 4898 various areas. samples. Figure 1 shows the general statistical results of the application of this study3 of in21 various areas. Figure 1. Percentages of different application areas. Figure Figure1.1.Percentages Percentagesofofdifferent differentapplication applicationareas. areas. Due to the unique environmental impacts of turbid waters, research on target detec- tion in Dueclear waters hasenvironmental progressed more significantly than target detection in turbid wa- Due totothe the unique unique impacts environmental impacts of of turbid turbid waters, waters,research researchon ontarget targetdetection detec- ters. At in clear present, waters most hashas advanced progressed target more detection significantly and recognition than target approaches detection inin in water turbid use waters. tion in clear waters progressed more significantly than target detection turbid wa- deep learning, At present, most polarization advanced imaging, target and detection other andand techniques, recognition and researchers approaches in water have used use use deep ters. At present, most advanced target detection recognition approaches in water these methods learning, in turbidimaging, polarization water to and develop othernew improvedand techniques, methods, whichhave researchers is significant used for these deep learning, polarization imaging, and other techniques, and researchers have used promoting methods in the development turbid water to of underwater develop new target improved detection technology. methods, which is significant for these methods in turbid water to develop new improved methods, which is significant for promoting the development of underwater target promoting the development of underwater target detection technology. detection technology. 3. Problems in Turbid Areas 3. Problems in Turbid Areas turbidity areas include aquaculture farms, shallow coastal In engineering, 3. Problems in Turbidcommon Areas areas,Indeep engineering, sea areas, common turbidity etc. Aquatic areas include aquaculture farmsaquaculture often resultfarms, in severeshallow coastal blurring of In engineering, common turbidity areas include aquaculture farms, shallow coastal areas, bodies water deep sea dueareas, to theetc. Aquatic density aquaculture of aquatic organismsfarms andoften result inlight insufficient severe blurring of transmittance areas, water deep seadue areas, etc. Aquatic aquaculture farmsand often result in severe blurring ofin in the bodies water body. to Most the density shallow of aquatic organisms water receives abundant insufficient light, butlight the transmittance turbidity of the water bodies the water due body. to the Mostdue density shallow of aquatic water sediment,organisms receives abundant and insufficient light transmittance water body is high to coastal aquatic light, but theand organisms, turbidity human of activities. the water inbody the water is high body. due Most to shallow coastal sediment,water receives aquatic abundant organisms, andlight, but activities. human the turbidity Deepofsea theis Deep sea is characterized by weak light but clear water quality. Underwater images of water body is high characterized duelight to coastal sediment, aquaticUnderwater organisms, images and human activities. specific turbidby weak waters but clear are demonstrated water quality. in Figure 2. of specific turbid Deep watersseaareis demonstrated characterized by weak light in Figure 2. but clear water quality. Underwater images of specific turbid waters are demonstrated in Figure 2. (a) (b) (c) Figure Figure 2. 2. Underwater (a) Underwater images imagesofofturbid turbidwater. (b)(a)(a) water. AnAnunderwater underwaterphoto of (c) photo aoffish farm. a fish (b) An farm. (b) un- An derwater underwater image imageof shallow of water. shallow (c) water. An (c) underwater An underwaterimage of image deep of sea. deep sea. Figure 2. Underwater images of turbid water. (a) An underwater photo of a fish farm. (b) An un- derwater image of shallow water. (c) An underwater image of deep sea. In general, general, turbid turbidwater watercannot cannotbebepurified, purified,soso thethe density density of suspended of suspended particles particles in in tur- bid water turbid results water in low results contrast, in low with contrast, no no with inherent inherentcharacteristics, blurring, characteristics, andand blurring, distortion. distor- In general, turbid water cannot be purified, so the density of suspended particles in The most tion. difficult The most problem difficult encountered problem during encountered the use during theofuse some detection of some approaches detection is the approaches turbid water results in low contrast, with no inherent characteristics, blurring, and distor- scattering is effect of the scattering water effect on the on of water light thewave. light Therefore, strong strong wave. Therefore, backscattered light, which backscattered light, tion. The most difficult problem encountered during the use of some detection approaches carries impurity information, obscures the target data, and reduces the image contrast. is the scattering effect of water on the light wave. Therefore, strong backscattered light, Although typical optical image methods, such as the use of underwater cameras, offer an inherently high resolution capability, the unknown imaging conditions, including the optical water type, scene location, illumination , and absorption and scattering character- istics of the marine medium, severely limit the image performance. For example, the visible range in the Singapore coastline area is only 2–3 m. Due to the attenuation of reflected  which carries impurity information, obscures the target data, and reduces the image con- trast. Although typical optical image methods, such as the use of underwater cameras, offer an inherently high resolution capability, the unknown imaging conditions, including the optical water type, scene location, illumination , and absorption and scattering char- Appl. Sci. 2022, 12, 4898 acteristics of the marine medium, severely limit the image performance. For example,4 of 21 the visible range in the Singapore coastline area is only 2–3 m. Due to the attenuation of reflected light, blurring caused by tiny impurities, and abnormal changes in color, the ac- curacy of targetcaused light, blurring recognition is reduced. by tiny impurities, and abnormal changes in color, the accuracy of Considering target recognitionthe objective limitations of optical sensors in underwater scenes, most is reduced. common detectionthe Considering methods in turbid objective areasof limitations areoptical based sensors on computer vision theory in underwater andmost scenes, uti- common lize detection non-optical methods sensors, such inas turbid areas etc. lidar, sonar, are However, based on computer as a result vision theory and of the complexity utilize and non-optical significant sensors, such interference as lidar, in turbid sonar, waters, etc. methods these However,cannot as a result of the provide complexity satisfying re- and significant interference in turbid waters, these methods cannot provide sults. Thus, the investigation of new approaches based on these methodologies is difficult. satisfying results. This work Thus, the investigation focuses of new methods on target detection approaches based based onon these deep methodologies learning, is difficult. some underwater This work image focuses on restoration target detection enhancement methods methods, andbased on deepimage underwater learning, some underwater processing methods image on based restoration enhancement polarization imaging,methods, which haveanddemonstrated underwater image processing the most advancedmethods based target de- on polarization tection imaging, performances and which meet the have demonstrated requirements the most advanced of underwater target intelligent detection sensing tech- performances nology. and meet the The underwater requirements image processing ofeffect underwater intelligent is depicted sensing in Figure 3. technology. The underwater image processing effect is depicted in Figure 3. (a) (b) Figure Figure 3. 3. Comparison Comparison of images before before and andafter afterunderwater underwaterimage imageprocessing. processing.(a)(a)Before Before analysis analysis of of the image. (b) After analysis of the image. the image. (b) After analysis of the image. 4. Research 4. Research on on Target Target Detection and Recognition in Turbid Turbid Waters Waters 4.1. Target Detection Based on Deep Learning Methods 4.1. Target Detection Based on Deep Learning Methods In recent In recent years, years, deep deep learning learning technology technology hashas been been widely widely used used inin underwater underwater image image defogging and target identification. Methods based on deep learning defogging and target identification. Methods based on deep learning investigate image investigate image sets by sets by training training the the neural neural network network andand seek seek to to establish establish aa logical logical relationship relationship to to improve improve the image clarity or extract target features for intelligent recognition. In turbid waters, the image clarity or extract target features for intelligent recognition. In turbid waters, such as typical fish farms, monitoring of fish in real-time is required. Therefore, accurate such as typical fish farms, monitoring of fish in real-time is required. Therefore, accurate identification of targets and prediction of motion trajectories in turbid waters is important. identification of targets and prediction of motion trajectories in turbid waters is important. Due to the typical problems, such as low contrast, a lack of inherent features, blurring, Due to the typical problems, such as low contrast, a lack of inherent features, blurring, and distortion, caused by the turbidity of water or the presence of suspended particles in and distortion, caused by the turbidity of water or the presence of suspended particles in water in aquaculture farms, target detection of fish is difficult. This section discusses the water in aquaculture farms, target detection of fish is difficult. This section discusses the applicability of deep learning networks for target recognition in turbid waters and methods applicability of deep learning networks for target recognition in turbid waters and meth- to improve the deep learning defects. ods to improve the deep learning defects. Traditional target detection methods manually extract the features of target areas, Traditional target detection methods manually extract the features of target areas, which is time consuming and has poor robustness. With the appearance of the deep learning which is time consuming and has poor robustness. With the appearance of the deep learn- convolution neural network, the target detection algorithm entered a new stage. Existing ing convolution target detection neural network, algorithms the target are mainly detection divided algorithmalgorithms into two-stage entered a new and stage. Ex- one-stage isting target detection algorithms are mainly divided into two-stage algorithms. Two-stage algorithms mainly include the RCNN series algorithms (RCNN , algorithms and one- stage algorithms. Fast RCNN Two-stage , Faster RCNN algorithms mainly include ). These algorithms the RCNN first generate series regional algorithms proposals, and (RCNN , Fast RCNN , Faster RCNN ). These algorithms first generate then perform classification and regression tasks on the regional proposals. Thus, detection regional proposals, is improved, andbut thentheperform processingclassification and regression time is increased tasks on accordingly. Suchthealgorithms regional proposals. are more Thus, suitable for the detection of static underwater objects, such as seafloor rocks,Such detection is improved, but the processing time is increased accordingly. algo- corals, etc. rithms are more suitable for the detection of static underwater objects, Single-stage algorithms mainly include the SSD algorithm and YOLO series algorithms such as seafloor (YOLO , YOLOv2 , YOLOv3 ). These algorithms improve the detection speed and maintain the detection effect as much as possible and use the direct regression method to forecast the category and location of targets. Therefore, such an algorithm is suitable for when the target detection required is frequent due to frequent aquatic activities, such as those of fish. Effective target feature detectors and classifiers provide deep learning methods with an advantage in turbid water environments, which is why it is important for computers Appl. Sci. 2022, 12, 4898 5 of 21 to adapt the fuzzy characteristic of turbid water and precisely identify target features. Lakshmi and Santhanam proposed two types of classifiers: one is a two-classification convolution neural network for distinguishing between the target and background while the other is a multi-classification convolution neural network for predicting the background or one type of target, such as shoes and ropes. They trained a convolution neural network (CNN) to classify 64 × 64 inputs. The images were classified, and the classifier was used as the target feature detector. The accuracy rate of the 2-class convolution neural network was 93.9%, and the target detection accuracy rate of the multi-class convolution neural network was 90.1%, which is higher than existing multi-class detectors (88%). Phooi et al. focused on the selection and improvement of the basic network architecture in Faster RCNN. They preprocessed the acquired images and tested the basic network performance under different network architectures in Faster RCNN to select the best basic network for image training in turbid media. The experimental results showed that the accuracy of MobileNetV2 on the basic network was 87.52%, which is better than other architectures. A comparison of the experimental results is shown in Table 1. Table 1. Comparison of the experimental results of different basic networks. The networks were pretrained by the ImageNet. Number of Number of Trainable Training Model Type Accuracy (%) Parameters Parameters Storage ResNet50 34,386,842 34,356,164 137.8 MB 78.28% MobileNet 8,280,256 8,255,236 33.3 MB 82.19% MobileNetV2 6,743,096 6,701,188 27.2 MB 84.57% DenseNet 42,726,388 42,672,772 171.4 MB 83.98% To extract features from turbid areas with significant interference, Wei et al. focused on a one-stage algorithm and proposed a target detection algorithm YOLOv3- brackish based on an improved scale and attention mechanism. In this algorithm, the extrusion excitation module is added behind the deep convolution layer, which enhances the feature extraction ability of the YOLOv3 model. To solve the problem of multiple small targets, the identification of which is difficult, shallow features with greater location information were combined with deep features to improve the detection performance of the small target model. The experimental results showed that the improved YOLOv3- Appl. Sci. 2022, 12, x FOR PEER REVIEW brackish model performed better than SSD, Faster CNN, and YOLOv3, and the effect 6 of 22 is demonstrated in Figure 4. Figure 4. Comparison Figure 4. Comparison of target detection of target detection results. results. (a) Original picture. (a) Original picture. (b) (b) Correct Correct annotation. annotation. The The target detection result of (c) SSD, (d) Faster RCNN, (e) YOLOv3, and (f) YOLOv3-brackish. target detection result of (c) SSD, (d) Faster RCNN, (e) YOLOv3, and (f) YOLOv3-brackish. Liu et al. combined image processing with deep learning to realize species iden- tification and density calculation of marine organisms to monitor the invasion of marine organisms in real-time. An underwater camera was used to capture image data in real- time within the monitoring range and deep learning was used to achieve end-to-end Appl. Sci. 2022, 12, 4898 6 of 21 Liu et al. combined image processing with deep learning to realize species iden- tification and density calculation of marine organisms to monitor the invasion of marine organisms in real-time. An underwater camera was used to capture image data in real-time within the monitoring range and deep learning was used to achieve end-to-end recognition of jellyfish. First, the convolution neural network was designed and improved, and a convolution neural network composed of two convolution layers, two pooling layers, and a full connection layer was obtained. After training, the convolution neural network was predicted using test sample images. Under the non-uniform light field, the characteristics of the biological images taken in turbid water were investigated using image sharpening, edge detection, edge closure, hole filling, etc. A binary image separate from the target and background was obtained, demonstrating real-time estimation of the marine biological density. The results showed that this method can be effectively applied to calculate the marine biological density and detect marine biological species. This study provides a reference for the early warning of biological invasion in offshore waters. Ahmed et al. focused on the comparison of various existing edge detection methods, including Laplace, SobelX, SobelY, Combined Sobel, and the Canny detector. The results of these methods were obtained and analyzed, as shown in Table 2. Table 2. Results of edge detection algorithms. Type Accuracy Accuracy Evaluation Laplacian 68.9% Normal Sobel X 79.26% High Sobel Y 79% High Combined Sobel 88.9% Very high Canny 89.13% Very high When the Laplace method was used, the accuracy was 68%. The accuracy of SobelX was similar to that of SobelY. Canny showed higher accuracy than the other methods and has been widely used in edge detection. Therefore, the Canny edge detection method is the best algorithm for detecting the edge of the target contour in a turbid area. In practical engineering applications, an algorithm that can identify the underwater bios trajectory of fisheries to enable easier localization and capture has also been inves- tigated. As an optimization tool, the genetic algorithm has been widely used in various fields, but it has not been fully studied in terms of the trajectory prediction of moving targets. However, in a recent study, the concept of the dynamic traveler problem based on the genetic algorithm and Newton equation of motion was used to obtain excellent results in predicting the minimum distance traveled by a moving fishing boat in the future. Since use of the genetic algorithm (GA) in this field has not been fully realized, Palconit et al. further discussed its application potential in fish tracking based on GA. On the other hand, the deep learning algorithms recurrent neural network (RNN) and long short-term memory (LSTM) have been used in several visual track prediction methods to predict targets, including pedestrians, vehicles, mobile robots, fish, etc. The results from these methods were shown to be better than most tracking methods, and thereby underwater video fish tracking research has been carried out based on RNN-LSTM. The results showed that trajectory prediction using LSTM is more accurate than the use of a genetic algorithm, but both showed an acceptable accuracy and the average absolute percentage errors of GA and LSTM were 2.8~30.5% and 3.33~17.74%, respectively. LSTM has been widely used in trajectory prediction in many fields while the genetic algorithm has seldom been used as a trajectory prediction method. The results of GA can be improved through the use of addi- tional variables or fitness functions, such as Newton’s equation of motion and quadratic regression. Three-dimensional coordinates have been shown to provide more accurate prediction results for GA and LSTM, so it can be further extended for two-dimensional and three-dimensional path prediction in the future, such as the use of GA and LSTM in fish tracking and marking or investigation of its combination with other tracking algorithms. Appl. Sci. 2022, 12, 4898 7 of 21 Intelligent target recognition and positioning using deep learning methods is powerful. However, the accuracy of underwater target recognition is affected by the image clarity, and deep learning methods are only applicable in waters that are similar to the training set image, so this method has some limitations. Therefore, the combination of good image restoration methods and deep learning methods can make target detection and recognition in turbid waters more effective. 4.2. Underwater Image Restoration and Enhancement Methods Deep learning has been widely used in underwater image restoration and enhance- ment to improve the quality of underwater images to a certain extent. Methods based on deep learning can be used to study the relationship between the features of an image set by training the neural network, and reduce the error caused by prior invalidity. Some characteristics of turbid water are similar to those of foggy weather, including problems regarding the attenuation of reflected light, blur caused by tiny impurities, and abnormal changes in color. These factors result in severe color distortion and low visibility in the captured image, so suitable light models and algorithms need to be developed to eliminate any negative impacts. Because underwater image processing and defogging have certain similarities, various defogging algorithms have been gradually improved for application to the enhancement of underwater images. Thomas et al. developed a fully connected convolution neural network for un- derwater image defogging. The integration of low-level and high-level features through the depth frame of the encoder-decoder helped to restore blurred images, showing better results than existing methods, such as the structural similarity index (SSIM) , peak signal to noise ratio (PSNR), and mean square error (MSE). It was also able to retain details during the removal of fog. Dudhane et al. proposed an end-to-end trainable image defogging network called LIGHT-Net, which includes a color constancy module and a haze reduction module. The color constancy module was used to remove color differences in the image caused by the weather conditions, and the haze reduction module used an initial residual module to reduce the haze effect. Feature sharing was also proposed in this module, which means the features learned at the initial level are effectively shared through the network. The experimental results of this method are promising. Yin and Ma proposed a migration learning method for several types of naturally degraded image enhancement, including underwater image enhancement. They used transfer learning for each specific natural degradation. By repeatedly applying the general enhancement model, they overcame existing problems regarding the shortage of training datasets for in-depth learning methods and the computational burden of the training process. The enhanced model was finetuned, and its performance surpassed several of the most advanced methods designed for specific tasks, such as uwcnn and funie-gan. Martin et al. proposed a combination of image enhancement, image recovery, and the convolution neural network, resulting in a method for target detection of recovered images. Due to the maximum number of green pixels in underwater images, under dark channel prior method (UDCP)-based energy transmission restoration (UD-ETR) was proposed to process green channel images and obtain the recovered images. The image processing results are displayed in Table 3. On this basis, a method for fish detection in restored images using CNN was proposed, and a PC-based automatic target detection recognition visual system was developed. The training results of CNN were also shown to be significantly better than that of the traditional model, which solves the problem of inaccurate target detection caused by blurred images. Appl. Sci. 2022, 12, 4898 8 of 21 Table 3. Comparison of the parameters from transmission map estimation and UD-ETR. Existing Approach (Transmission Proposed Approach Parameters Map Estimation) (UD-ETR-Based Restoration) Contract luminance 39 89 UCIQE 12 26 Saturation 0.1 0.5 Chroma 2.5 5.5 PSNR 5 14 RMSE 140 50 MSE 1.7 0.3 Cecilia et al. proposed an effective edge perception restoration and enhancement model for severely blurred shallow coastal images with low contrast. Restoration methods, which are based on the dark channel and rolling guidance filter, were used to restore and denoise such images, resulting in clearer edge perception. This method introduced a rolling guidance filter in dark channel prior (DCP) restoration, which effectively restored images and decreased the noise in the images. This experiment showed that the rolling filter based on the recovery model has better denoising effects. Regarding the enhancement of the quality of underwater images taken in different water body types, the image forming model used in earlier methods is imprecise and its restoration effect is poor. Zhou et al. developed a defogging method using a modified model. They first designed an underwater image depth estimation method to create depth maps and estimate backscattering based on the depth values of each pixel, and then removed backscattering based on a more accurate underwater imaging model. To address the color distortion characteristics of the turbid area, they proposed a color correction method to automatically adjust the global color distribution of an image. This method used a single underwater image as the input, eliminating the effects of light wave absorption and scattering. Experiments have demonstrated that this approach has better applicability compared with previous research methods. Considering that scattering attenuation and color correction of high-turbidity underwa- ter images affects the classification results of target recognition based on machine learning (ML), Li et al. proposed a contrast-enhanced method to remove scattering. This enhance- ment method considers the illumination and camera spectral characteristics, eliminates scattering, and correctly restores the scene color. They also used different ML approaches for classification in their research to confirm that this method can be applied to classification and recognition architecture preprocessing based on deep learning, which showed a better image classification effect. However, for practical applications, use of the scattering removal algorithm does not provide the accuracy required by practical engineering. Yang proposed an underwater polarized imaging target enhancement technique based on non-polarized illumination to overcome the disadvantages of the current un- derwater polarized scattering algorithm, such as its low accuracy and limited application range. The use of unpolarized light ensures that any polarization difference between the target reflected light and stray light can be detected. At the same time, the characteristic parameter of the polarization angle ensures accurate estimation of the stray light inten- sity. Compared with current underwater polarized imaging technology based on linear polarized light illumination, it has a wider application range and higher image restoration accuracy. The results showed that the visibility of underwater restored images is improved effectively, and the contrast is improved by at least 100%. Meanwhile, this technique can be applied to water environments with various material targets, imaging distances, diverse impurities, and turbidity levels, and has potential application value in many underwater imaging fields. Drews-Jr et al. proposed a new underwater restoration method based on monocu- lar image sequences, which utilizes the time relationship and geometric and environmental information to improve the quality of visual features in underwater images. It can also Appl. Sci. 2022, 12, 4898 9 of 21 robustly estimate the depth map and attenuation coefficient. The attenuation coefficient is used to evaluate the loss of light in the medium, so the accuracy of its estimation affects image restoration. Depth estimation is realized using adaptive optical flow and struc- ture motion technology, and the attenuation coefficient is estimated by introducing an underwater optical attenuation model into the RANSAC frame. Meanwhile, a depth map is estimated from the combination of motion structure technology and model-based restoration. The simulation and real image test results showed that the method restores the image, thus improving the ability of target recognition and feature matching. Cheng et al. proposed a method for image fusion based on the Mueller matrix to enhance the quality of underwater degradation images. Each Mueller matrix element image is given a weight and fused to generate a new image. The optimal weights are obtained by searching for values that maximize the image quality. The validity of this method was proved by comparison with the Mueller matrix image and the latest method using objective and subjective analysis. Moreover, the image was enhanced using analog weights. Due to the nature of the Mueller matrix, this method improves the underwater observation distance and image quality, and provides the enhanced images with information that is unavailable when conventional methods are used. Due to the absorption and scattering of light in water, color projection and poor contrast are often present in underwater images. Zhou et al. proposed an underwater image restoration method based on a priori underwater features. They first established a powerful model to estimate the background light based on the characteristics of flatness, hue, and brightness, thus effectively mitigating color distortion. The red channel of the color-corrected image was then compensated to correct its transmission map. The rough transmission diagram was refined by combining it with a structure-guided filter. 4.3. Underwater Image Processing Based on Polarization Imaging and Scattering The most difficult problem encountered during optical detection in turbid areas is the scattering effect of water on the light wave, which mainly results in low image contrast, a reduction in resolution, and image blurring. Scattering includes forward and backward scattering processes. When forward scattering occurs, light deviates from the original trans- mission path, resulting in a reduced image resolution and blurred image. Backscattered light, which carries suspended particulate information, produces a ‘curtain effect’ on the target image and reduces the image contrast. Therefore, it is necessary to overcome the scattering and reflection problems in underwater imaging to improve the imaging distance and quality. Polarized imaging technology has obvious advantages in removing background scat- tered light and achieving clear underwater images by deeply mining the uniqueness and differences in polarization information in a scattered light field. Currently, accurate es- timation of the polarization characteristics and relationship between target information light and background scattered light, inverting the intensity distribution of target informa- tion light and background scattered light, are key research areas of underwater imaging technology. Research has shown that the polarization characteristics of incident polarized light can be used to separate these two kinds of light in a scene, effectively restoring a clear scene, improving the contrast and clarity of imaging results, and aiding underwater target detection and recognition. Because underwater search and rescue operations often face target detection problems in high-turbidity water, exploration of polarization imaging technology that is suitable for turbid water is necessary. An overview of this method is depicted in Figure 5. With a long research history and significant basic experience, polarization imaging technology is suitable for more in-depth research in this direction. Currently, polarization imaging methods are being developed for the unique environment of turbid waters.  ing technology. Research has shown that the polarization characteristics of incident po- larized light can be used to separate these two kinds of light in a scene, effectively restor- ing a clear scene, improving the contrast and clarity of imaging results, and aiding under- water target detection and recognition. Because underwater search and rescue operations often face target detection problems in high-turbidity water, exploration of polarization Appl. Sci. 2022, 12, 4898 10 of 21 imaging technology that is suitable for turbid water is necessary. An overview of this method is depicted in Figure 5. Figure 5. An overview of underwater data processing methods based on polarization imaging. Figure 5. An overview of underwater data processing methods based on polarization imaging. With a long research Underwater models for history and significant studying turbidity and basic experience,have illumination polarization imaging been established, technology which is suitable is helpful for more for optical in-depth research research of target in this and detection direction. Currently, recognition polarization in turbid waters. imaging Bailey et methods are beinga developed al. proposed model based foron thethe unique spatial environment variation inofunderwater turbid waters. environ- ments and coherent Underwater light and models used it forturbidity for studying low-contrastand target detection illumination havein turbid water. This been established, model which is was used for helpful to theoretically optical research studyof the effects target of turbidity, detection projection in and recognition space-frequency turbid waters. variation, Bailey et al. and three-dimensional proposed a model target shapes based on theonspatial unstructured scattered variation light components in underwater environ- and the target structured return signal. The results showed that the ments and coherent light and used it for low-contrast target detection in turbid water. This model’s accuracy is adequate model wasfor theto used modeling of noise theoretically study reduction the effects technology. of turbidity, This result indicates projection that the space-frequency received variation,three-dimensional and three-dimensional target target imageshapes can be onmodeled with backscattering unstructured scattered light and struc- compo- tured illumination, nents and the targetand noise reduction structured and target return signal. identification The results showed can thatbetheachieved model’sin the accu- model environment. Based on the image degradation model, Han racy is adequate for the modeling of noise reduction technology. This result indicates that considered image degradation the received due to the joint effects three-dimensional of forward target image can andbebackward modeled scattered light, estimated with backscattering and the structured illumination, and noise reduction and target identification can be and degradation function of forward scattered light using the edge method, further achieved in restored the model clear scene images. environment. Based Heonconstructed a turbid water the image degradation polarization model, Han imaging considered model, im- and then obtained age degradation duethetopolarization degree the joint effects of of target and forward information backward light and background scattered light, esti- scattered light using the optical correlation principle to restore mated the degradation function of forward scattered light using the edge method, and the clear scene. furtherOnrestored the premise clearofscene establishing images.an Heoptical model,aHan constructed water turbid proposed an active polarization under- imaging water polarization imaging method, which is based on the imaging model, and then obtained the polarization degree of target information light and back- noise analysis model, and groundstudied the effect scattered lightofusing noisethethatoptical is introduced during correlation the polarization principle to restoreimaging the clearprocess scene. on the final imaging quality. This method resulted in the best polarization On the premise of establishing an optical model, Han proposed an active under- azimuth image for active underwater polarization imaging, and the relationship water polarization imaging method, which is based on the imaging noise analysis model,between different polarizer images and the final imaging quality was established. This method can effectively realize and studied the effect of noise that is introduced during the polarization imaging process the imaging distance in a high-turbidity water body, improve the imaging quality and on the final imaging quality. This method resulted in the best polarization azimuth image detection effect, and providing support for underwater search and rescue work in rivers for active underwater polarization imaging, and the relationship between different polar- and offshore areas. izer images and the final imaging quality was established. This method can effectively Huang proposed a polarization image restoration algorithm and a new curve realize the imaging distance in a high-turbidity water body, improve the imaging quality fitting-based method to estimate the target signal of polarization difference images. Based and detection effect, and providing support for underwater search and rescue work in on the polarization effect of reflected light in underwater imaging, the former was used rivers and offshore areas. to restore underwater blurred images with polarization imaging, and study the imaging model of underwater active illumination imaging systems and the transmission behavior of polarization information in an underwater turbid medium. The latter considers the polarization effect of the reflected light from the object in the scene to derive the true trans- mission coefficient image and underwater restored image. Both can overcome the invalid detection problem in the area corresponding to objects with a low degree of deflection and effectively enhance the underwater imaging quality. As backscattered light occurs due to the presence of high concentrations of impurities in turbid water, the reflected light from an object is easily confused, which makes it difficult to distinguish the object from the environment. Therefore, the division of reflected light from interfering light, such as backscattered light, which reflects the characteristic of the object, is a core issue for underwater image processing using polarized imaging. At present, several methods, such as optical sensing technology, the polarization filter method, and the backscattering interference suppression method, that can separate coherent light from incoherent light exist. Cochenour et al. proposed new optical sensing technology Appl. Sci. 2022, 12, 4898 11 of 21 based on the orbital angular momentum (OAM). The target is illuminated by a Gauss beam. By setting a diffraction spiral phase plate at the receiving end, the reflected and backscattered light of the object passes through the phase plate to form vortex light, thus spatial separation of coherent and incoherent light is achieved. Experiments have shown that the echo of a ballistic target can achieve detection that is two to three orders of magnitude the level of backscattered clutter. The detection of this coherent element is realized using a complex optical heterodyne scheme. In addition, the detection of this small coherent signal is completed without the use of any complex optical heterodyne scheme, which indicates that the unique characteristics of OAM can be used to distinguish between objects and the environment. Amer et al. used a polarized imaging optical system to reduce the influence of underwater beam diffusion on image acquisition and optimized the DCP method. They used a low-pass polarization Gauss filter to calculate the illumination from the input image and enhance underwater optical imaging, which