Saliency-Based Diver Target Detection and Localization Method

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.

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.

Due to the nonlinearity of the imaging of sonar equipment and the complexity of the underwater sound field environment, the gray level of the target area of the acquired underwater sonar image is relatively small. These characteristics are the target of the subsequent sonar image. Work such as detection and location tracking has brought great challenges. It has brought great challenges to solving the work of positioning and tracking, which makes the research of sonar image target detection based on deep learning very important. This article aims at studying the use of sonar to detect image targets based on deep learning technology. This article proposes a variety of sound image denoising methods based on multiresolution tools. The purpose of this article is to divide the natural image into blocks at an appropriate rate according to the change of the sampling matrix and measure the underwater natural image. The sound image defines an information model. These methods have greatly changed the image and period of using remote and temporary information. The translation results of these methods are all valid. The sharpening separation method based on filtered image and bidirectional detection should be published through a solution algorithm and different frames, and the expected algorithm can be reused and extracted as an action to improve the similarity of the image and should be saved and separated in detail. The result is correct. This article studies the application of deep learning methods in sonar image target detection and designs corresponding algorithms for improvement and functional realization in view of the current deficiencies and needs in this field. The experimental results show that the improved scheme and applied algorithm proposed in this article can achieve good results, the verification sample set includes 184 remote-sensing aircraft targets, and the resolution of remote-sensing images is unified to 1644 × 971 size. The accuracy of the target detection algorithm has been significantly improved, reaching 74.6%, and the detection speed has also been greatly improved. Compared with the RNN algorithm, the speed has been increased by 7 times. The detection results confirmed that the improved algorithm has higher positioning accuracy and faster detection speed.

Saliency detection is an effective tool to extract regions of interest (ROIs) from remote sensing images. However, some existing saliency detection models focus on extracting ROI from a single image, which cannot accurately detect ROI against complex background interference. In this paper, a novel visual saliency analysis and ROI extraction model is proposed to effectively extract common ROIs from remote sensing images and exclude images without ROIs. Firstly, the single saliency maps are generated by frequency-tuned (FT) method. Secondly, the cluster method based on synthesized features is proposed to group regions with similar feature into a cluster for multiple images. Thirdly, computing the mean of saliency value as the cluster saliency suppresses the saliency value of non-common ROIs. Finally, a ROI extraction method based on the maximum saliency value is proposed to extract ROIs while eliminating the image without ROIs. Experimental results indicate our model outperforms other state-of-the-art saliency detection models, achieving highest ROC and maximal PRF values.

Detection and classification of underwater objects in sonar imagery are challenging problems. In this paper, a new coherent-based method for detecting potential targets in high-resolution sonar imagery is developed using canonical correlation analysis (CCA). Canonical coordinate decomposition allows us to quantify the changes between the returns from the bottom and any target activity in sonar images and at the same time extract useful features for subsequent classification without the need to perform separate detection and feature extraction. Moreover, in situations where any visual analysis or verification by human operators is required, the detected/classified objects can be reconstructed from the coherent features. In this paper, underwater target detection using the canonical correlations extracted from regions of interest within the sonar image is considered. Test results of the proposed method on underwater side-scan sonar images provided by the Naval Surface Warfare Center (NSWC) in Panama City, FL is presented. This database contains synthesized targets in real background varying in degree of difficulty and bottom clutter. Results illustrating the effectiveness of the CCA based detection method are presented in terms of probability of detection, and false alarm rates for various densities of background clutter.

Saliency detection in images attracts much research attention for its usage in numerous multimedia applications. In this paper, we propose a saliency detection method based on optimization for RGBD images. With RGBD images, our method utilizes the depth channel to enhance the identification of background and foreground regions. We firstly generate new depth image by using non-linear transformation and outstand object region. Then, we introduce saliency optimization framework to integrate the depth cue and other low-level cues to obtain the final saliency map. The experimental results demonstrate that our method performs better in saliency detection for RGBD Images.

Many image analysis, computer vision and multimedia applications involving consumer images rely on or benefit from saliency maps which represent where important areas of images are located. To date, virtually all image saliency detection techniques tend to produce highly blurry saliency maps. However, there are situations where the awareness of objects and their boundaries in images can greatly facilitate solutions to the problems. In this paper, we propose a novel, effective and efficient image saliency detection algorithm. Notably, our algorithm is capable of detecting salient regions of an image with clear boundaries, corresponding to objects in the scene. Yet, the algorithm is robust to background clutter commonly found in typical consumer images. A comparison of our algorithm with several state-of-the-art image saliency detection algorithms reveals the favorable performance of our algorithm in terms of the quality of saliency maps and the computational time.

Target detection in sonar images is a key step in the process of underwater target recognition. Due to the influence of noise and environment, the contours of targets in sonar images often have large irregularities, the image resolution is low, and the details are relatively small, making it difficult to be accurate. An underwater target is detected. The C-V algorithm based on curve evolution theory and level set method can only use an initial closed curve to detect multiple areas with similar gray values in the sonar image and can also detect target areas with internal holes, without the need for detection. Experiments have proved that through the use of threshold filtering, morphological filtering, and C-V algorithm, the target contour can be successfully extracted from the original sonar image, which is beneficial to the subsequent target recognition based on a large amount of experimental data.KeywordsTarget detectionLevel set methodC-V algorithmSonar image processing

Saliency detection in images is an important outstanding problem both in machine vision design and the understanding of human vision mechanisms. Recently, seminal work by Itti and Koch resulted in an effective saliency-detection algorithm. We reproduce the original algorithm in a software application Vision and explore its limitations. We propose extensions to the algorithm that promise to improve performance in the case of difficult-to-detect objects.

Traditional sonar image target detection analysis has problems such as long detection time, low detection accuracy and slow detection speed. To solve these problems, this paper will use the multi-feature fusion sonar image target detection algorithm based on the particle swarm optimization algorithm to analyze the sonar image. This algorithm uses the particle swarm algorithm to optimize the combination of multiple feature vectors and realizes the adaptive selection and combination of features, thus improving the accuracy and efficiency of sonar image target detection. The results show that: when other conditions are the same, under the particle group optimization algorithm, the sonar image multiple feature detection algorithm for three sonar image detection time between 4s-9.9s, and the sonar image single feature detection algorithm of three sonar image detection time between 12s-20.9s, shows that the PSO in multiple feature fusion sonar image target detection with better performance and practicability, can be effectively applied to the sonar image target detection field.

Sonar image object detection plays a crucial role in obstacle detection, target recognition, and environmental perception in autonomous underwater vehicles (AUVs). However, the complex underwater acoustic environment introduces various interferences, such as noise, scattering, and echo, which hinder the effectiveness of existing object detection methods in achieving satisfactory accuracy and robustness. To address these challenges in forward-looking sonar (FLS) images, we propose a novel multi-level feature aggregation network (MLFANet). Specifically, to mitigate the impact of seabed reverberation noise, we designed a low-level feature aggregation module (LFAM), which enhances key low-level image features, such as texture, edges, and contours in the object regions. Given the common presence of shadow interference in sonar images, we introduce the discriminative feature extraction module (DFEM) to suppress redundant features in the shadow regions and emphasize the object region features. To tackle the issue of object scale variation, we designed a multi-scale feature refinement module (MFRM) to improve both classification accuracy and positional precision by refining the feature representations of objects at different scales. Additionally, the CIoU-DFL loss optimization function was constructed to address the class imbalance in sonar data and reduce model computational complexity. Extensive experimental results demonstrate that our method outperforms state-of-the-art detectors on the Underwater Acoustic Target Detection (UATD) dataset. Specifically, our approach achieves a mean average precision (mAP) of 81.86%, an improvement of 7.85% compared to the best-performing existing model. These results highlight the superior performance of our method in marine environments.

A local discrimination basis is selected among the possible wavelet packet bases in order to create a two-class classifier for high dimensional signals. We use the classifier for target detection in images and signals. The position of the target is also determined. A method invariant to the localization of the target in the analyzed image is developed in order to reduce the time complexity of the algorithm. We apply the method on mine detection in sonar images.

Due to complex lighting circumstances and other factors, visual saliency recognition of underwater images is not as good as visual saliency detection models that function well on land when applied to underwater environments. The dearth of large-scale annotated underwater picture datasets has further hindered the development of visual saliency detection in underwater images. we propose an attention-based approach for underwater image saliency detection to address this issue. The backbone network is pre-trained using both land and underwater image datasets, which effectively solves the problem of fewer datasets. After that, a residual refinement module incorporating a channel-space attention mechanism is merged, the model as a whole is trained end-to-end using underwater image datasets, and the model accuracy is experimentally tested. The experimental results in three underwater image datasets show that our method is better than several other methods in the mainstream evaluation indicators of the saliency detection.

Saliency and co-saliency detection aim to distinguish conspicuous foreground objects from single and multiple images, thus are essential in many multimedia and vision applications. To achieve balanced efficiency and accuracy, most recent successful saliency detectors are based on superpixels. However, saliency detection with single-scale superpixel segmentation may fail in capturing intrinsic salient objects of complex natural scenes with small-scale high-contrast backgrounds. To tackle this problem, we present a simple strategy using multiscale superpixels to jointly detect salient object via low-rank optimisation. Specifically, we first build a multiscale superpixel pyramid and derive the corresponding saliency map by multimodal saliency features and priors at each single scale. Then, we use joint low-rank analysis of multiscale saliency maps to obtain a more reliable and adaptively-fused saliency map, which properly takes all scales saliency into account. We further propose a GMM generative co-saliency prior to enable the above approach to detect co-salient objects from multiple images. Extensive experiments on benchmark datasets validate the effectiveness and superiority of the proposed saliency and co-saliency detector over state-of-the-arts.

Underwater object recognition in sonar images, such as mine detection and wreckage detection of a submerged airplane, is a very challenging task. The main difficulties include but are not limited to object rotation, confusion from false targets and complex backgrounds, and extensibility of recognition ability on diverse types of objects. In this paper, we propose an underwater object detection and recognition method using a transformable template matching approach based on prior knowledge. Specifically, we first extract features and construct a template from sonar video sequences based on the analysis of acoustic shadows and highlight regions. Then, we identify the target region in the objective image by fast saliency detection techniques based on FFT, which can significantly improve efficiency by avoiding an exhaustive global search. After affine transformation of the template according to the orientation of the target, we extract normalized gradient features and calculate the similarity between the template and the target region, which can solve various difficulties mentioned above using only one template. Experimental results demonstrate that the proposed method can well recognize different underwater objects, such as mine‐like objects and triangle‐like objects and can satisfy the demands of real‐time application.