Coherent-based method for detection of underwater objects from sonar imagery

Multi-view sonar image generation via GAN trained with limited data for underwater object classification and detection

Object detection in underwater environments presents significant challenges due to the inherent limitations of sonar imaging, such as noise, low resolution, lack of texture, and color information. This paper introduces AquaYOLO, an enhanced YOLOv8 version specifically designed to improve object detection accuracy in underwater sonar images. AquaYOLO replaces traditional convolutional layers with a residual block in the backbone network to enhance feature extraction. In addition, we introduce Dynamic Selection Aggregation Module (DSAM) and Context-Aware Feature Selection (CAFS) in the neck network. These modifications allow AquaYOLO to capture intricate details better and reduce feature redundancy, leading to improved performance in underwater object detection tasks. The model is evaluated on two standard underwater sonar datasets, UATD and Marine Debris, demonstrating superior accuracy and robustness compared to baseline models.

Improved YOLOv7 model for underwater sonar image object detection

A challenging and attractive task in computer vision is underwater object detection. Although object detection techniques have achieved good performance in general datasets, problems of low visibility and color bias in the complex underwater environment have led to generally poor image quality; besides this, problems with small targets and target aggregation have led to less extractable information, which makes it difficult to achieve satisfactory results. In past research of underwater object detection based on deep learning, most studies have mainly focused on improving detection accuracy by using large networks; the problem of marine underwater lightweight object detection has rarely gotten attention, which has resulted in a large model size and slow detection speed; as such the application of object detection technologies under marine environments needs better real-time and lightweight performance. In view of this, a lightweight underwater object detection method based on the MobileNet v2, You Only Look Once (YOLO) v4 algorithm and attentional feature fusion has been proposed to address this problem, to produce a harmonious balance between accuracy and speediness for target detection in marine environments. In our work, a combination of MobileNet v2 and depth-wise separable convolution is proposed to reduce the number of model parameters and the size of the model. The Modified Attentional Feature Fusion (AFFM) module aims to better fuse semantic and scale-inconsistent features and to improve accuracy. Experiments indicate that the proposed method obtained a mean average precision (mAP) of 81.67% and 92.65% on the PASCAL VOC dataset and the brackish dataset, respectively, and reached a processing speed of 44.22 frame per second (FPS) on the brackish dataset. Moreover, the number of model parameters and the model size were compressed to 16.76% and 19.53% of YOLO v4, respectively, which achieved a good tradeoff between time and accuracy for underwater object detection.

This paper proposes a method to detect underwater objects using sonar image simulator and convolutional neural network (CNN). Instead of simulating very realistic sonar images which is computationally complex, we implemented a simple sonar simulator that calculates only semantic information. Then, we generated training images of target objects by adding randomized degradation effects to the simulated images. The CNN trained with these generated images is robust to the degradation effects inherent in sonar images and thus can detect target objects in real sonar images. We verified the proposed method using the sonar images captured at sea through field experiments. The proposed method can implement object detection more easily because it only uses simulated images instead of real sonar images which are challenging to acquire. The proposed method can also be applied to other sonar-image-based algorithms.

Side scan sonar images have great application prospects in underwater surveys, target detection, and engineering activities. However, the acquired sonar images exhibit low illumination, scattered noise, distorted outlines, and unclear edge textures due to the complicated undersea environment and intrinsic device flaws. Hence, this paper proposes a multi-scale fusion strategy for side scan sonar (SSS) image correction to improve the low contrast and noise interference. Initially, an SSS image was decomposed into low and high frequency sub-bands via the non-subsampled shearlet transform (NSST). Then, modified multi-scale retinex (MMSR) was employed to enhance the contrast of the low frequency sub-band. Next, sparse dictionary learning (SDL) was utilized to eliminate high frequency noise. Finally, the process of NSST reconstruction was completed by fusing the emerging low and high frequency sub-band images to generate a new sonar image. The experimental results demonstrate that the target features, underwater terrain, and edge contours could be clearly displayed in the image corrected by the multi-scale fusion strategy when compared to eight correction techniques: BPDHE, MSRCR, NPE, ALTM, LIME, FE, WT, and TVRLRA. Effective control was achieved over the speckle noise of the sonar image. Furthermore, the AG, STD, and E values illustrated the delicacy and contrast of the corrected images processed by the proposed strategy. The PSNR value revealed that the proposed strategy outperformed the advanced TVRLRA technology in terms of filtering performance by at least 8.8%. It can provide sonar imagery that is appropriate for various circumstances.

Survey on Deep Learning Techniques Used for Classification of Underwater Sonar Images

Automatic detection of underwater objects using side-scan sonar imagery is complicated by the variability of objects, noises, and background signatures. In recent years, as the resolution of side-scan sonar is much higher than before, the sonar imagery can be generated from sonar signal for processing. The first step of underwater object detection is to segment the underwater objects from sonar imagery. In typical sonar imagery, the object contains two parts: high-light areas (echo) and the shadow behind the object. By analyzing the features of the side- scan sonar imagery, we propose a novel segmentation algorithm for multi-object side-scan sonar imagery. First we utilize a self- adaptive window to scan the imagery and calculate the variance of the window to segment the high-light areas in sonar imagery. Then the shadows of the objects are segmented by fractal dimension. At last, the final segmentation results are achieved by combining the results from the above two steps for further analysis. This segmentation algorithm is based on analyzing the structure of objects in sonar imagery and works well in the multi- object sonar imagery.

The mosaic of sonar images is more difficult than the mosaic of traditional optical images due to their poor quality and the difficulty in extracting feature points. The existing mosaic methods of sonar images have a series of problems, such as low correct matching rate, large cumulative errors and high requirements for the quality of collected sonar images. In this paper, we proposed a high precision method to implement the mosaic of the underwater sonar video image sequence. Firstly, Accelerated Unsharp Masking (AUSM) algorithm is proposed to preprocess the original image. Then we extract KAZE feature points from preprocessed sonar images. A matching method combining multiple matching strategies with Progressive Sample Consensus (PROSAC) algorithm is followed to complete the image registration. Weighted fusion method and a region of interest (ROI) acquisition method based on the slope of right border is used to optimize the mosaicked image. Finally, we can obtain a high-quality panoramic image of underwater sonar video by a global mosaic strategy. Mosaic experiments on the sonar video image sequence collected by multi-beam sonar demonstrate that the proposed method in this paper can increase the number of feature points by about 70% and make the correct matching rate higher than 70%. The proposed method also has good robustness and the cumulative error during multi-image mosaic is less.

The authors introduce a constant false alarm rate (CFAR) detection algorithm, called K‐CFAR, for automatic detection of underwater objects in sonar imagery. The K‐CFAR adopts the K ‐distribution as a statistical model of the background. An efficient closed‐form estimator for the K ‐distribution parameters is derived by the second‐order approximation of the Polygamma function without involving a numerical iterative solution. A closed‐form expression for the CFAR detection threshold is obtained by exploiting the first‐order Laguerre approximation of the K ‐distribution. Then, to increase the probability of detection, a non‐CFAR refinement to the K‐CFAR, based on the spatial feature of the objects, is proposed. Experimental results obtained from 270 real sonar images of diverse environments demonstrate the superiority of the proposed algorithm compared to the state‐of‐the‐art in terms of receiver operating characteristic curves.

Underwater image enhancement and object detection has great potential for studying underwater environments. It has been utilized in various domains, including image-based underwater monitoring and Autonomous Underwater Vehicle (AUV)-driven applications such as underwater terrain surveying. It has been observed that, underwater images are not clear due to several factors such as: low light, the presence of small particles, different levels of refraction of light etc. Extracting high-quality features from these images to detect objects is a significant challenging task. To mitigate this challenge, MIRNet and modified version of YOLOv3 namely Underwater-YOLOv3 (U-YOLOv3) is proposed. The MIRNetisadeeplearning-based technology for enhancing underwater images. while using YOLOv3 for underwater object detection it lacks in detection of very small objects and huge size objects. To address this problem proper anchor box size, quality feature aggregation technique, and during object classification image resizing is required. The proposed U-YOLOv3 has three unique features which helps to work with above specified issue like accurate anchor box determination using the K-means++ clustering algorithm, introduced Spatial Pyramid Pooling (SPP) layer during feature extraction which helps in feature aggregation and added downsampling and upsampling to improve detection rate of very large and very small size objects. The size of the anchor box is crucial in detecting objects of different sizes, SPP helps in aggregation of features, while down and upsampling changes sizes of objects during object detection. The experiment on the Brackish and Trash-ICRA19 datasets shows that our proposed method enhances the mean average precision for both datasets by 10% and 9%, respectively, compared to the original YOLOv3 and other existing work. This enhancement demonstrates that our proposed model is more appropriate for identifying submerged items and is also capable of recognizing closely clustered, small, very large objects on the ocean floor.

The theory of compressive sampling (CS) was reintroduced by Candes, Romberg and Tao, and D. Donoho in 2006. Using a priori knowledge that a signal is sparse, it has been mathematically proven that CS can defY Nyquist sampling theorem. Theoretically, reconstruction of a CS image relies on the minimization and optimization techniques to solve this complex almost NP-complete problem. There are many paths to consider when compressing and reconstructing an image but these methods have remained untested and unclear on natural images, such as underwater sonar images. The goal of this research is to perfectly reconstruct the original sonar image from a sparse signal while maintaining pertinent information, such as mine-like object, in Side-scan sonar (SSS) images. Goldstein and Osher have shown how to use an iterative method to reconstruct the original image through a method called Split Bregman's iteration. This method decouples the energies using portions of the energy from both the !1 and !2 norm. Once the energies are split, Bregman iteration is used to solve the unconstrained optimization problem by recursively solving the problems simultaneously. The faster these two steps or energies can be solved then the faster the overall method becomes. While the majority of CS research is still focused on the medical field, this paper will demonstrate the effectiveness of the Split Bregman's methods on sonar images.

The most popular and crucial piece of equipment for underwater target detection right now is side-scan sonar, which primarily plays a crucial role in underwater operations. Unfortunately, in general, side-scan sonar images have low resolution and suffer from significant noise interference, making target recognition with these images highly challenging. In this paper, we employ deep learning techniques to recognize underwater targets using side scan sonar imagery. This paper begins by outlining the current state of underwater target detection research as well as briefly describing its importance and historical context. The imaging process of side-scan sonar pictures is studied in greater depth, and it is determined that noise on sonar images is caused principally by the combined effect of external and internal noise. This causes extra noise in sonar pictures, lowering image quality and affecting target identification performance. Proper sonar image pre-processing findings can provide more consistent target detection help. After then, the YOLOv5 target detection algorithm is investigated and improved. By performing several sets of comparison trials, the updated technique improves the accuracy and speed of side-scan sonar image target recognition and finally overcomes the issues of missed detection, false detection, and low accuracy of overlapping tiny object recognition.

In the computer vision field, underwater object detection has been a challenging task. Due to the attenuation of light in a medium and the scattering of light by suspended particles in water, underwater optical images often face the problems of color distortion and target feature blurring, which greatly affect the detection accuracy of underwater object detection. Although deep learning-based algorithms have achieved state-of-the-art results in the field of object detection, most of them cannot be applied to practice because of the limited computing capacity of a low-power processor embedded in unmanned underwater vehicles. This paper proposes a lightweight underwater object detection network based on the YOLOX model called LUO-YOLOX. A novel weighted ghost-CSPDarknet and simplified PANet were used in LUO-YOLOX to reduce the parameters of the whole model. Moreover, aiming to solve the problems of color distortion and unclear features of targets in underwater images, this paper proposes an efficient self-supervised pre-training joint framework based on underwater auto-encoder transformation (UAET). After the end-to-end pre-training process with the self-supervised pre-training joint framework, the backbone of the object detection network can extract more essential and robust features from degradation images when retrained on underwater datasets. Numerous experiments on the URPC2021 and detecting underwater objects (DUO) datasets verify the performance of our proposed method. Our work can assist unmanned underwater vehicles to perform underwater object detection tasks more accurately.

Sonar image object detection is essential in underwater rescue and resource exploration. Although many convolution neural network (CNN)-based object detection algorithms have achieved great success in natural images. However, for underwater sonar images, problems, such as seabed reverberation noise interference, low proportion of foreground object region pixels, and poor imaging resolution, present considerable challenges to achieving accurate underwater object detection. To address these problems, we propose a novel sonar image object detector called the multilevel feature fusion network (MLFFNet). The detector consists of multiscale convolution module (MS-Conv), multilevel feature extraction module (ML-FEM), multilevel feature fusion module (ML-FFM), neighborhood channel attention mechanism (N-CAM), multiscale feature pyramid module (MS-FPN), and feature association module (FA). First, we use the MS-Conv to extract different scale feature information in the object region. Second, the ML-FEM and ML-FFM are used to obtain the local detail and global context features. Third, the N-CAM and MS-FPN are used to obtain the foreground objects’ semantic feature and position feature, and suppress the background region noise interference. Finally, we use the FA module to enhance the category and feature correlation of different objects. Extensive experiments are conducted on the real scene sonar image dataset. The experimental results demonstrate that MLFFNet performs better than other state-of-the-art object detection methods. Code and dataset are publicly at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/darkseid-arch/SonarMLFFNet</uri> .