87 results about "Sonar imagery" patented technology

The invention discloses a complex underwater side-scan sonar exploration detection method and device based on a multi-dimensional attention collaborative lightweight anti-noise detection framework, and the device comprises an underwater side-scan sonar imaging device which is used for obtaining a sonar image of a detected target; the computer is connected with the underwater side-scan sonar imaging equipment and comprises a backbone feature extraction network module which is used for processing an input sonar image through a multi-scale edge refining module and outputting a three-scale feature map; the check feature fusion network module is used for realizing cross-channel and cross-space information fusion through the focusing space adaptive local attention module, performing adaptive modulation and deep information aggregation on multi-scale features through a channel frequency aggregation and attention mechanism, and outputting three enhanced feature maps; and the YOLOhead detection head module is used for generating a target detection frame according to the enhanced feature map, and outputting a detection result after non-maximum suppression processing.

The invention discloses an imaging method, system and device for correcting range migration based on frequency domain phase multiplication, and the method comprises the following steps: carrying out the range pulse compression of echo data of each receiving array element in a range frequency domain; performing data preprocessing according to a phase center approximation method to obtain equivalent transmit-receive combined synthetic aperture sonar data; deriving a secondary distance compression item at the reference distance in the two-dimensional frequency domain, and performing secondary distance compression processing; deriving a space-variant migration phase term of range migration correction corresponding to each target with different distances; carrying out filtering processing on the two-dimensional frequency domain sonar data; a filtered result is converted to a range-direction time domain and an azimuth-direction Doppler domain, data of targets at corresponding distances are extracted, and the data extracted each time are combined in sequence; and for the data after range migration correction, azimuth pulse compression is carried out in a range time domain and an azimuth Doppler domain, and the data is converted to a two-dimensional time domain to obtain a sonar image.

The invention relates to the technical field of underwater target detection, in particular to a target recognition method and system based on a sonar image assisting an optical image. The method comprises the following steps: acquiring an underwater optical image and a sonar image, inputting the underwater optical image and the sonar image into a double-flow multi-scale feature extraction backbone network, and generating an optical multi-scale feature map and a sonar multi-scale feature map; processing the multi-scale feature map through an optical-sonar adaptive feature fusion module to generate enhanced multi-modal fusion features; inputting the multi-modal fusion features into a detection head, and outputting an underwater target detection result; according to the method, the problems of optical-sonar image modal isomerism and space mismatch are effectively solved, and the precision and robustness of underwater target detection are remarkably improved.

The invention discloses a sonar image underwater detection method and system based on hierarchical attention feature fusion, and the method comprises the steps: collecting the foresight sonar data of an underwater typical target, and making a detection training and testing data set of a sonar image; constructing a local and global attention processing module, a re-parameterization processing module and a hierarchical feature fusion network; constructing a target detection algorithm model based on YOLOv10, taking the feature fusion network as a neck network of the YOLOv10, and removing a deep feature map detection branch of the YOLOv10; and training a target detection algorithm model by using the manufactured data set, and inputting a foresight sonar image into the trained model for reasoning to obtain a detection result of the underwater typical target. According to the invention, the accuracy and robustness of an underwater target detection algorithm are improved.

The invention provides a sonar intelligent interpretation method and system, and the method comprises the steps: integrating end-side equipment (disposed on a ship-borne platform) and side-side equipment (disposed in a shore-based machine room) to form a sonar intelligent interpretation system; through the intelligent sonar interpretation system, full-process automatic processing of sonar interpretation from data acquisition of sonar images to interpretation is realized, the interpretation efficiency of the sonar images is effectively improved, and in addition, the intelligent sonar interpretation system also can be used for realizing automatic interpretation of the sonar images on the basis of mass sonar image data (namely sonar images stored in a data warehouse) obtained through actual measurement. Model training of the sonar interpretation model and training examination of interpretation personnel are synchronously achieved, a sustainable closed-loop optimization system is formed, and the problems that in traditional sonar interpretation, the interpretation accuracy is low, the data reuse rate is poor, and personnel training examination is difficult are solved.

The invention belongs to the technical field of underwater target detection, and discloses an underwater complex target detection method and system based on generation and detection collaborative optimization, and the method comprises the steps: generating a side-scan sonar simulation sample through employing a CycleGAN, and screening out a high-quality sample through employing a pre-trained YOLO model, so as to construct an enhanced data set; an improved target detection model with YOLOv8 as a baseline is constructed, the model integrates a lightweight backbone network formed by deep separable convolution and an inverted bottleneck structure, a feature fusion neck network adopting element multiplication and residual connection, and an EMA attention module introduced in front of a detection head, and the model is trained by using the enhanced training data set; and performing target detection on an input underwater side-scan sonar image by using the improved YOLOv8 model after training is completed. According to the method, the problems of scarcity of underwater samples and multi-scale detection of targets are effectively solved, and the model lightweight is realized while the detection precision is improved.

The invention relates to foresight sonar image enhancement, in particular to a foresight sonar image enhancement method based on feature space conversion and multi-frame fusion, and the method comprises the steps: mapping an original foresight sonar image from a low-quality pixel space to a feature space which is more stable to noise and is more consistent with a heterogeneous image through a feature space conversion module; the forward-looking sonar data self-supervising method comprises the following steps: constructing a self-supervising model to reduce a field gap between a sonar image and a heterogeneous image, so that the self-supervising model more effectively adapts to forward-looking sonar data, the modeling capability of the self-supervising model for unknown degradation factors is enhanced, and consistent input is provided for a multi-frame image fusion enhancement network; complementary information among continuous multi-frame images output by the feature space conversion module is mined and integrated through a multi-frame image fusion enhancement network, fine reconstruction of image details and improvement of image brightness are achieved, and noise in the images is eliminated; according to the technical scheme provided by the invention, the defects that the image brightness is difficult to improve while the noise is suppressed and the high-frequency details of the target cannot be well reserved can be overcome.

The invention belongs to the technical field of image processing, and discloses a side-scan sonar image feature extraction method and system, and the method employs an LF-Net network to carry out the feature point extraction of two adjacent side-scan sonar images, and employs a KNN algorithm to carry out the matching of the feature points extracted by the LF-Net. According to the method, a transfer learning mode is introduced based on the deep learning network LF-Net to solve the sonar image matching problem, side-scan sonar image feature point detection is carried out by constructing the pre-training actual measurement data matching model, and the problem that the generalization ability is poor due to the fact that the number of side-scan sonar image data is small is solved; the KNN algorithm is combined to realize accurate matching of acoustic image feature points, the matching result is subjected to statistical analysis to reduce the influence of mismatching, and the matching robustness is improved. According to the method, two adjacent side-scan sonar images can be accurately matched without too many side-scan sonar image data, and a brand new solution thought is provided for underwater sonar image matching in a complex scene.

The invention relates to the field of image processing, in particular to a fish and shrimp denoising enhancement and intelligent identification method based on a two-dimensional sonar image, which comprises the following steps: extracting a sonar image water background, dividing regions and calculating a signal-to-noise ratio, dynamically adjusting a noise threshold, and denoising to obtain a salient image. And a multi-rotation-angle convolution kernel set is constructed based on a size statistics preset ellipse parameter. And clustering salient image pixel points, setting a bounding rectangle as a suspected target area, and judging the consistency of continuous frame targets through an optical flow algorithm. And dynamically adjusting a convolution kernel weight enhancement image, training a YOLO model to recognize a target, superposing recognition results and providing statistical information. According to the method, the fish and shrimp targets with variable sizes and directions in the sonar image are accurately identified and tracked by utilizing dynamic noise threshold adjustment and a multi-angle convolution kernel set in combination with a denoising enhancement technology based on a signal-to-noise ratio and an optical flow algorithm, the limitation of a traditional method is effectively overcome, and reliable technical support is provided for target detection in a complex underwater environment.

The application belongs to the technical field of image processing, and discloses a side-scan sonar image feature extraction method and system, which extracts feature points of two adjacent side-scan sonar images by using an LF-Net network, and matches the feature points extracted by the LF-Net by using a KNN algorithm. The application introduces a transfer learning mode based on a deep learning network LF-Net to solve the sonar image matching problem, detects feature points of side-scan sonar images by constructing a pre-training measured data matching model, and solves the problem of poor generalization ability caused by the small amount of side-scan sonar image data. The application realizes accurate matching of sonar image feature points by combining the KNN algorithm, reduces the influence of false matching by statistically analyzing the matching results, and improves the robustness of matching. The application can accurately match two adjacent side-scan sonar images without too much side-scan sonar image data, and provides a new solution for underwater sonar image matching in complex scenes.

The application discloses a fish resource monitoring method and system based on sonar images and electronic equipment, and the fish resource monitoring method comprises the following steps: acquiring sonar images of a fish pond; detecting fish targets in more than two frames of the sonar images and tracking the fish targets; and determining the number of the fish targets in the fish pond according to the tracking result. Through the above steps, the fish resource monitoring method can accurately monitor the number of the fish targets in the fish pond, and does not cause adverse effects on the growth environment of the fish during the monitoring process.

The invention discloses a three-dimensional sonar phase self-correction method, and relates to the technical field of underwater acoustic engineering and array signal process.The method comprises the steps that a three-dimensional sonar image is generated through sonar original multi-channel signals, a plurality of strong display point targets which can be separated from the three-dimensional sonar image are extracted, and the signal-to-noise ratio of the strong display point targets is higher than a threshold value; sound path distance difference phase compensation is carried out on echo signals of each strong display point target, a channel common phase deviation is estimated by using a compensated residual complex signal, then an image entropy and a target peak value are set as convergence criteria, the criteria are deeply combined with an iterative reweighting mechanism, step-by-step optimization is carried out to obtain the phase deviation estimation precision, and the estimation precision of the channel common phase deviation is improved. And finally, obtaining an optimal inherent phase deviation, and carrying out global phase correction on the multi-channel echo signal by using the optimal inherent phase deviation. According to the invention, real-time online self-correction can be realized, the problem of imaging blur caused by phase inconsistency between channels is effectively compensated, and the contrast ratio of three-dimensional sonar imaging and the target visualization quality are remarkably improved.

The present invention discloses a method and system for detecting underwater small targets in sonar images under complex backgrounds. The method comprises: denoising the collected sonar images using a multi-level median filtering method; performing complex terrain masking on the denoised sonar images to extract highlight texture maps and shadow texture maps of the terrain; performing high-order moment image segmentation on the denoised sonar images, and combining the complex terrain masking results to perform background suppression; clustering the processed connected domains using three different-sized detection windows to associate split targets and suppress ridge terrain; extracting highlight areas and shadow areas, calculating highlight pixel density and shadow pixel density respectively, and obtaining a detection score through pixel density weighted calculation to detect small targets. The method is not restricted by seabed terrain and adaptively adjusts the threshold according to the required false alarm rate and actual acoustic image intensity. It has the characteristics of high accuracy, low false alarm rate, and strong adaptability.

The present invention includes systems and methods for improving the process of detecting and classifying objects of interest using UUVs to survey the ocean. According to a particular embodiment, the present invention provides a more cost-efficient process by employing preconfigured heuristic operational scenarios, or supervised machine learning to fine-tune this process by integrating the use of environmental variables relating to the water in which data is gathered, and more particularly for classifying sonar images of the seafloor.

The invention discloses a sonar image imaging method, system and device based on a two-step interpolation method. The sonar image imaging method comprises the following steps: calculating a two-dimensional frequency domain system function; second-order approximation is carried out on the distance-direction instantaneous frequency, and a high-order phase approximation error is calculated; for the approximated function, calculating the maximum range migration of the scene and the multiple # imgabs0 # to be interpolated in the subsequent steps, and performing first zero padding on the front end and the rear end of the sonar data in a range direction time domain; performing high-order phase error compensation and range-direction matched filtering in a two-dimensional frequency domain for the zero-filled data; calculating the total number # imgabs 1 # of the range-direction frequency domain data, supplementing # imgabs 2 # zero values to the rear end of the range-direction frequency domain data, and converting the range-direction frequency domain data to a range-direction time domain; aiming at the data of the distance-Doppler domain, according to the distance migration amount corresponding to each distance target, adopting a rounding-off interpolation method to carry out distance migration correction; and carrying out azimuth matched filtering in the distance-Doppler domain and converting to a two-dimensional time domain to obtain a high-resolution image.

The application provides a sonar image target detection method and system, comprising the following steps: step 1: constructing a front-view sonar image dataset, collecting original images and preprocessing the original images; using a cross-domain image conversion model to generate synthetic sonar images; labeling the images and dividing them into a training set and a test set; step 2: constructing an improved YOLO network structure, including a backbone network, a neck network and a detection head; the backbone network outputs multi-scale feature maps to the neck network; the neck network introduces a high-level screening feature fusion pyramid module with a spatial attention mechanism, weights and fuses the features and suppresses noise, and outputs enhanced feature maps to the detection head; step 3: using the training set to train the model; using the validation set to evaluate the performance in terms of the average precision mean mAP and saving the optimal model; step 4: using the test set to load the optimal model for inference, obtaining the detection result, calculating the mAP for evaluation, and visualizing and rendering the result on the original image.

A method for accurately segmenting submarine cables from side-scan sonar images comprises the following steps: inputting an image I1, processing the image I1 using a cable feature automatic extraction filter based on a curvelet transform, extracting cable-related information, and obtaining a feature image I2; pixel-by-pixel multiplying the image I1 by the feature image I2 to obtain a feature image I3; using a Hough transform to find no less than three straight line segments in the feature image I3, recording the angle α of the longest line segment in the image, constructing linear structural units in the same direction as the cables in the image, performing noise elimination and binarization processing on the feature image I3 to obtain a binary image I4; performing cable morphology restoration on the binary image I4 to obtain a cable morphology restoration image I5, and retaining only the largest connected area in the image as the cable segmentation result for the submarine side-scan sonar image. The method solves the problems in side-scan sonar image segmentation that a large amount of data is required for training, high image clarity requirements are required, target color information needs to be obtained, and high image size requirements are required.

The present application relates to the field of image processing, especially to a fish and shrimp denoising enhancement and intelligent identification method based on two-dimensional sonar images, comprising: extracting a sonar image water body background, dividing regions and calculating a signal-to-noise ratio, dynamically adjusting a noise threshold, and obtaining a saliency image through denoising. Based on size statistics, preset ellipse parameters are constructed, and a multi-rotation angle convolution kernel set is constructed. The saliency image pixel points are clustered, and the circumscribed rectangle is set as a suspected target area. The consistency of the target in the continuous frame is judged through an optical flow algorithm. The convolution kernel weight is dynamically adjusted to enhance the image, the YOLO model is trained to identify the target, the identification result is superimposed, and statistical information is provided. Through the use of dynamic noise threshold adjustment and multi-angle convolution kernel set, combined with the denoising enhancement technology based on the signal-to-noise ratio and the optical flow algorithm, the fish and shrimp targets with variable size and direction in the sonar image are accurately identified and tracked, and the limitations of traditional methods are effectively overcome, providing reliable technical support for target detection in complex underwater environments.

The application provides a sonar image three-dimensional reconstruction method based on target shadow and gray scale, which comprises the following steps: Step 1, converting the original sonar image into a gray scale image; Step 2, carrying out denoising treatment on the image; Step 3, carrying out shadow edge calibration; Step 4, segmenting a target region; Step 5, eliminating small target regions; Step 6, solving the pitch angle of the target region; and Step 7, reconstructing the target region. The application uses the multi-beam forward-looking sonar imaging principle as a research object, analyzes the transmission, reflection and reception process of sound waves, realizes a reverse reasoning using sound propagation, and obtains the three-dimensional reconstruction of the target object in the sonar image.

1. Name of the product in this design: Graphical User Interface for Displaying Sonar Detection Information in Electronic Equipment. 2. Purpose of this design: An electronic device. 3. The key design feature of this product is its graphical user interface. 4. The picture or photo that best illustrates the key design points: Design 1 front view. 5. Design 1 is designated as the basic design. 6. Purpose of the graphical user interface: After the sonar is introduced into the water, it emits ultrasonic waves to the surrounding area (within a range of 130°×20°) through the sonar head, and acquires and displays environmental information and target distribution within the underwater sound wave range in real time. 7. Human-computer interaction method of graphical user interface: Design 1's main view is the sonar acquisition operation interface. By clicking various control buttons, sonar images are acquired. The sonar acquisition results can be viewed in real time on the interface. Clicking the hexagonal icon in the upper right corner enters the "Sonar Settings" interface of the changing state diagram of Design 1; Design 2's main view is the sonar acquisition operation interface. By clicking various control buttons, sonar images are acquired. The sonar acquisition results can be viewed in real time on the interface. Clicking the hexagonal icon in the upper right corner enters the "Sonar Settings" interface of the changing state diagram of Design 2.

The invention discloses an unmanned ship full-coverage connection topological optimization path planning method and system for underwater target search and detection, a storage medium and electronic equipment, and the method comprises the steps: firstly carrying out the environment modeling and rasterization of a detection region, and obtaining a free grid set and neighborhood state information; the method comprises the following steps: establishing a mixed integer linear programming model containing geometric continuity constraints and topological structure rewards to obtain a global optimal rectangular decomposition scheme under the balance of geometric boundary cost and topological connection rewards; establishing a minimum turning spanning tree to minimize the turning times of the coverage path by judging the connection type and turning cost between the rectangles; and finally, generating a smooth coverage trajectory in combination with the kinematics constraint of the unmanned ship. According to the method, the problem of sonar image distortion caused by too many turning times in the existing coverage path planning method is solved, the global turning times of the coverage path are reduced, the problem of detection precision decline caused by the fact that acoustic imaging conditions are damaged due to frequent turning maneuvering in the traditional path is solved, and the detection path quality is optimized.

The invention belongs to the technical field of underwater sonar imaging and intelligent identification, and relates to a virtual sonar image generation method and system. The method comprises the following steps: mapping a real optical target image into a virtual sonar target image by adopting a vision-text fusion network; embedding the virtual sonar target image into the real sonar background image to generate a combined image; and background compensation and texture consistency adjustment are carried out on the combined image by using a virtual sonar image background reconstruction network to obtain a virtual sonar image with a background. According to the invention, the bottleneck that real sonar data acquisition is limited by environment, cost and equipment conditions is broken through; meanwhile, the target type and number can be flexibly expanded, and the problems that sonar samples are insufficient in category and unbalanced in distribution are effectively solved.

The invention discloses an underwater forward-looking sonar image target detection method and device, and the method comprises the steps: obtaining underwater forward-looking sonar data, carrying out the target detection of a current frame of forward-looking sonar image of the underwater forward-looking sonar data, and obtaining a first target detection result; based on the current frame of forward-looking sonar image, predicting a next frame of forward-looking sonar image of the current frame of forward-looking sonar image by a Kalman filter to obtain a prediction detection result; acquiring a next frame of forward-looking sonar image of the current frame of forward-looking sonar image as the current frame of forward-looking sonar image, and performing target detection on the current frame of forward-looking sonar image to obtain a second target detection result; and matching the prediction detection result with the second target detection result, and determining the trajectory of the target according to the matching result and the first target detection result. The method can effectively identify a shielded target or distinguish target tracks with similar features.

The application discloses a kind of side-scan sonar image seabed cable zero-sample rapid detection method, belong to seabed cable detection technical field, comprising the following steps: step one, establish neural network model;Step two, data fusion enhancement: to existing public side-scan sonar image data data fusion enhancement, generate experimental data set;Step three, data set annotation: to data set is marked;Step four, model training: neural network is trained;Step five, model test: using measured data to the network model after training is tested;The application, by establishing neural network model, and to existing public side-scan sonar image data data fusion enhancement, generate experimental data set, to data set is marked and neural network is trained, using measured data to the network model after training is tested, this method combines data enhancement method, realizes the zero-sample training and rapid detection of neural network.

The application belongs to the technical field of computer vision and target detection, and discloses a sonar target detection method based on neural architecture search technology, which comprises the following steps: constructing and preprocessing a data set; performing neural architecture search based on Zero-shot of the maximum differential entropy principle to obtain an optimal CNN-Transformer backbone architecture; generating high-quality Query through Query selection based on different scale features of various targets of a sonar image extracted by the CNN-Transformer backbone network; decoding Query by a decoder part to predict a sonar target; training through a hybrid loss function of multi-task collaborative optimization; and outputting position, category and confidence information of the target. The sonar target detection performance is significantly improved through architecture innovation, noise-resistant design and theoretical breakthrough by using the above sonar target detection method based on neural architecture search technology.

The present application relates to underwater target detection technical field, specifically to a kind of target identification method and system based on sonar image auxiliary optical image;Method includes: obtaining underwater optical image and sonar image, input double-flow multi-scale feature extraction backbone network, generate optical multi-scale feature map and sonar multi-scale feature map;Through optical-sonar adaptive feature fusion module, multi-scale feature map is handled, and enhanced multimodal fusion feature is generated;Multi-modal fusion feature is input detection head, and underwater target detection result is output;The present application effectively solves optical-sonar image modal heterogeneity and spatial mismatch problem, significantly improves the precision and robustness of underwater target detection.

The invention relates to a multi-beam data screening optimization processing method based on image sonar. Aiming at the problems of weak target signal annihilation and insufficient image sharpness caused by a traditional arithmetic average method, the method adopts a maximum value screening strategy to carry out multi-beam data fusion. The method comprises the following specific steps: carrying out preprocessing and TVG compensation on sonar original echo data; obtaining a plurality of beam data through parallel beam forming; for each distance unit, traversing and comparing the signal intensity of all beams, and selecting the maximum value as the final pixel value of the unit; and then median filtering noise reduction and configurable point picking processing are carried out. According to the method, the detection probability of a weak target and a point target can be remarkably improved, a sonar image with high contrast and high sharpness is generated, and meanwhile, different detection tasks are flexibly adapted by integrating multiple fusion and point selection modes. The method is efficient in calculation, is easy to realize on embedded platforms such as a DSP (Digital Signal Processor), an FPGA (Field Programmable Gate Array) and the like, and has good engineering application value.

The invention discloses an underwater target tracking method and system fusing sonar and a camera. According to the underwater target tracking method, underwater tracking is conducted on a tracking target through the underwater target tracking system composed of an underwater holder fixing platform, the underwater camera, the sonar, a switch, an image processor and an underwater steering engine. In the target tracking process, an optical image and a sonar image are collected respectively, and the processed optical image and sonar image are obtained after optical image sectorization preprocessing, acousto-optic registration and image enhancement are carried out in sequence; performing high and low frequency decomposition and adaptive weighted fusion on the processed optical image and sonar image to obtain a final fused image; and the mass center position of the tracked target is obtained based on the final fusion image, and a combined control strategy is provided to drive the holder to steer stably and quickly, so that the underwater camera and the sonar can be continuously aligned with the tracked target.

The application discloses a kind of based on dual attention mechanism's underwater side-scan sonar image recognition method and system, comprising: obtaining the monitoring image of underwater side-scan sonar equipment collection;Monitoring image is input to the EDA-Net model of pre-set and obtains underwater target detection result, wherein, EDA-Net model includes improved backbone network, improved neck network and head network;The improved backbone network is based on YOLOv11 framework construction, wherein double path heteromeric attention module is set;Improved neck network is provided with bottleneck convolution-parameterless attention module;The head network is used for target detection according to the feature map output by improved neck network.This application can more accurately identify target detail texture characteristics under the condition of small sample, multi-scale data set, improve the recognition accuracy and stability of model to multi-scale target in complex underwater environment.

The invention discloses an underwater target detection method for generating a virtual sonar based on a physical model and an optical image. The underwater target detection method comprises the following steps: acquiring the optical image; based on a physical model of sonar imaging and an imaging principle, generating a virtual sonar image from the optical image; multi-modal feature extraction is carried out; carrying out multi-modal feature fusion; and performing target detection on the multi-modal fusion feature map by using a deep learning model, and outputting a target detection result. According to the invention, the technical problems of high system cost and difficult deployment of a traditional multi-modal detection method are effectively solved, the detection effect of optical and sonar multi-modal fusion can be achieved only by using a common optical camera, the hardware cost and the application threshold are greatly reduced, and the detection efficiency is improved. According to the method, the target detection accuracy and the robustness in a complex and changeable environment can be remarkably improved, the detection operation is simple, rapid and real-time detection can be realized, the generalization ability is relatively high, and the method has extremely high application value and economic benefits for underwater target detection.