Three-dimensional sonar target detection method and device based on fuzzy decoupling

Abstract

The invention discloses a three-dimensional sonar target detection method and device based on fuzzy decoupling, and the method comprises the steps: S1, reducing errors caused by different collection devices through maximum and minimum standardization based on a preprocessing module of an original point cloud; s2, performing fuzzy feature decoupling coding on the sonar original point cloud based on prior knowledge, establishing a point cloud decoupling membership function, and coding the discrete point cloud into a feature sequence by using a coding function; and S3, performing feature extraction on the two encoded decoupling features through a VFE module to obtain BEV features. S4, the BEV features are subjected to Gaussian thermodynamic diagram prediction through a backbone network and decoded into a first-stage proposal. And S5, combining the first-stage proposal with two-stage refinement based on Markov prediction to obtain a final three-dimensional calibration frame and the category and score thereof. Aiming at the problem of weak heterogeneity of a target in a three-dimensional sonar point cloud target identification task, the challenge of three-dimensional sonar weak heterogeneity identification is effectively solved through fuzzy decoupling feature coding, point-based Gaussian thermodynamic diagram prediction and Markov prediction-based two-stage refinement.

Description

Technical Field

[0001] The invention belongs to the field of image processing and underwater detection, and relates to a three-dimensional sonar target detection method and device based on fuzzy decoupling. Background Art

[0002] With the growing demand for marine resource exploration, the importance of underwater surveys has gradually increased. In this context, 3D acoustic imaging sonar, as one of the most attractive underwater technologies, has become the focus of attention in the industry because of its ability to generate point-based images beyond the optically visible range. In recent years, with the widespread application of 3D imaging sonar systems in underwater surveys, it covers many fields such as environmental research, navigation, underwater robot vision systems, and marine engineering. In these fields, underwater target detection systems play a vital role in helping humans identify objects more clearly.

[0003] 3D sonar systems based on sparse array imaging have become the main 3D sonar imaging technology due to their excellent performance. However, two key problems have emerged in the development of this technology. First, underwater 3D sonar imaging objects have various shapes, such as moving objects such as fish and divers. Their shapes are hidden and changeable, and they are usually accompanied by a large number of bubbles that emerge or exhale underwater. These bubbles contain rich information, which is crucial for object recognition and is also an important clue for human observers to identify objects. Therefore, how to effectively utilize the information around the target has become an urgent problem to be solved. Secondly, in the 3D sonar imaging process based on sparse arrays, speckle noise and sidelobe rise away from the main lobe also become significant. Although the 3D sonar system based on sparse array imaging can effectively reduce the number of elements in the planar array and improve imaging efficiency, it also causes the problem of sidelobe rise, which reduces the imaging quality to a certain extent. Therefore, it is particularly urgent to effectively extract target feature points and obtain efficient regression proposals in high-noise environments.

[0004] On the other hand, with the introduction of PointNet and the research boom in the fields of autonomous driving and home robots, more and more scholars have devoted themselves to the research of 3D object detection. On land, 3D imaging using LiDAR sensors has become the core of the main work, while underwater objects rely more on 3D sonar systems for imaging. The differences in the distribution of different media and objects lead to two significant differences in the recognition of upper and lower water surfaces. Therefore, when processing these different types of point clouds, directly using relatively mature 3D object algorithms based on optical point clouds has become incompetent. For object detection algorithms for 3D sonar images, it is necessary to combine their characteristics, especially the characteristics of diverse object shapes and weak uniformity in high-noise environments. Summary of the invention

[0005] The present invention aims to overcome the above-mentioned shortcomings of the prior art and provides a three-dimensional sonar target detection method based on fuzzy decoupling.

[0006] The purpose of the present invention is to cope with the challenges brought by the variable shape, high noise intensity and weak heterogeneity of moving objects in 3D sonar imaging. The present invention adaptively improves the network by imitating the idea of ​​human observation of three-dimensional sonar targets.

[0007] The technical solution adopted by the present invention to solve its technical problem is:

[0008] A first aspect of the present invention provides a three-dimensional sonar target detection method based on fuzzy decoupling, comprising the following steps:

[0009] S1 To solve the errors that may be caused by collecting point cloud images with different devices, the formula for normalizing the original point cloud is as follows:

[0010]

[0011] where p i represents the intensity of any point in the point cloud, represents the intensity of the preprocessed point cloud, p min and p max They represent the parts with the largest and smallest intensity in the entire point cloud respectively.

[0012] S2 In order to imitate human observers and improve the utilization of information around the target, the present invention first performs fuzzy feature decoupling encoding on the sonar original point cloud based on prior knowledge, and the steps are as follows:

[0013] S21 point cloud data is represented as Γ={(x,y,z) n}, where N∈(1,2,3,...,N), and the voxel resolution is (V ω ,V ζ ,V η ). Here, W, H and L represent the width, height and length of the scene, respectively. After voxelizing the entire sonar scene, the first step is to assign all points to their respective voxels. The main steps include establishing fuzzy membership functions, partitioning the original point cloud, and performing parallel fuzzy coding conversion of the decoupled point cloud Γ0 into Γ1.

[0014] In the parallel decoupling process of S22 point cloud, the decision is mainly based on the echo intensity of the point cloud itself and the information of the surrounding K nearest neighbors. The comprehensive intensity of a point is defined as follows:

[0015]

[0016] Here, r k represents the k points closest to r.

[0017] S23 object points typically have higher echo intensity, contrasting with the lower echo intensity associated with noise and bubbles. Points above the bright spot threshold are classified as "bright spots", while the likelihood of a point being considered an object is positively correlated with its intensity when it is below the bright spot threshold. The twin point clouds are decoupled through a fuzzy model. Due to the concentration of objects and noise, local twin sample imbalance may occur, which may lead to a mismatch in the number of twin point clouds. To address this issue, a dynamic balancing strategy is implemented based on the fuzzy set designed by Zadeh for object points. This membership function is defined as follows:

[0018]

[0019] Here, a represents the sonar bright spot threshold, while α and β represent the adjustment functions in the Cauchy distribution.

[0020] After S24 classification, the average x, y and z coordinates of the point cloud, the average x, y and z intensities, and the offset of the physical center of the three-dimensional space grid are calculated to form two point cloud feature codes, each consisting of 9 indicators.

[0021] S3 extracts the encoded features through the VFE module to obtain BEV features. The process of the VFE module is as follows:

[0022] S31 inputs the point cloud with the above 9 features into the fully connected network module FC (fully connected layer FC+batch normalization layer BN+ReLU activation function) to obtain m-dimensional point-by-point features.

[0023] S32 performs unit-by-unit aggregation on the m-dimensional features obtained in the previous step through maximum pooling to obtain local aggregated features.

[0024] S33 respectively concatenates point-by-point features and local aggregation features to obtain aggregation features

[0025] S34 finally aggregates the features through a maximum pooling to obtain the final features and puts them back to the original position according to the position of the original point cloud to obtain a multi-map-view features.

[0026] After S4 extracts the complete features, it regresses the heat map through the backbone network and the projection of the final target's 3D box on the BEV view. The center point of the heat map is the center point of the target. At the same time, the length, width, height of the 3D box and the height of the center point are predicted to form a stage of prediction. The loss function based on the Gaussian heat map is defined as follows:

[0027] S41 Here, the numerical value of the Gaussian heat map generated for a certain category is displayed using the sigmoid function. In addition, the method sets the Gaussian radius as follows:

[0028]

[0029] Here, R Gaussian is the Gaussian radius of each category in the heat map, is the minimum allowed Gaussian radius. In this study, we set w and l are the width and length of the bounding box, respectively, and Λ is the Gaussian radius function. Finally, the 3D bounding box of the target is obtained by decoding the predicted Gaussian heat map and combining it with the output (w, h, l) of the detection head and the height of the center point.

[0030] S42 The first-stage loss of the present invention is defined as follows:

[0031]

[0032] Here, α and β are hyperparameters, and K is the number of positive targets in the ground truth. In this study, α = 2, β = 4. Factor The weight used to share the total loss by controlling the positive and negative samples. The larger α is, The smaller it is, the more effectively the weight of negative samples is reduced, while the weight of positive samples is relatively increased. For other target attributes, various variables are combined into a feature vector of the ground truth value: GT = (u g ,v g ,d g ,w g ,h g ,l g ) and the detected true value: DT=(u d ,v d ,d d ,w d ,h d ,l d ). Therefore, Loss reg is defined as follows:

[0033]

[0034] The final first-stage loss of S43 is expressed as follows:

[0035]

[0036] Here, l and Loss weights, which are adaptive weights. In this method, l = 1,

[0037] S5 finally uses Markov prediction in the second stage to extract additional point clouds from the original point cloud, extract features through the S2 step, and obtain the final proposal through a multi-head perceptron regression.

[0038] S51 The second stage predicts the score and refinement of the bounding box based on the prediction results of SonarPoint in the first stage. The present invention uses the score Y as shown below:

[0039] Υ=min(1,max(0.2·IOU i -0.5))(8)

[0040] Here, IOU i is the IOU value between the i-th predicted box and the ground truth.

[0041] S52Then the loss function of the second stage is defined as follows:

[0042]

[0043] here, is the prediction score. The final score is defined as follows:

[0044]

[0045] here, is the second stage prediction score, is the first stage prediction score.

[0046] The second aspect of the present invention relates to a three-dimensional sonar target detection method device based on fuzzy decoupling, including a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, they are used to implement the three-dimensional sonar target detection method based on fuzzy decoupling of the present invention.

[0047] The third aspect of the present invention relates to a computer-readable storage medium, characterized in that a program is stored thereon, and when the program is executed by a processor, a three-dimensional sonar target detection method based on fuzzy decoupling of the present invention is implemented.

[0048] The present invention aims at the problem of weak heterogeneity of targets in the three-dimensional sonar point cloud target recognition task, and effectively solves the challenge of three-dimensional sonar weak heterogeneity recognition through fuzzy decoupled feature encoding, point-based Gaussian heat map prediction and two-stage refinement based on Markov prediction.

[0049] The working principle of the present invention is as follows: a fuzzy parallel decoupling method is proposed, which performs fuzzy correlation analysis on tiny features in the auxiliary point cloud in the object neighborhood space, especially useful information in underwater environments, such as bubbles and side lobes, thereby enhancing the network's perception of weakly heterogeneous objects. In order to solve the problem of high noise levels destroying the coherence between points, the present invention is based on the Mamba backbone network structure to enhance long-range dependencies while maintaining low complexity. Finally, through Markov refinement, the potential information between points is stimulated, while reducing irrelevant interference with the 3D bounding box, achieving efficient recognition of weakly heterogeneous sonar targets.

[0050] The innovation of the present invention is that a 3D sonar target detection method based on fuzzy decoupling is proposed, which effectively solves the problem of weak heterogeneity target recognition in 3D sonar point cloud images.

[0051] The present invention has the following beneficial effects:

[0052] 1. Currently, there are major challenges in processing weak heterogeneous sonar point clouds caused by high noise. This paper proposes a novel fuzzy decoupling module, which is different from the traditional foreground-background segmentation method. Using sonar prior knowledge, this module simultaneously extracts valuable information about the target and its surroundings, mitigating the heterogeneity caused by noise and sonar sidelobes.

[0053] 2. Currently, there are major challenges in processing weak heterogeneous sonar point clouds caused by missing and occlusions. The present invention proposes a two-stage refinement based on Markov prediction, in which the original point cloud is additionally extracted in the second stage to obtain more details through Markov prediction.

[0054] 3. Currently, there are major challenges in processing weak heterogeneous sonar point clouds caused by ground resolution. The present invention proposes a prediction method based on the Gaussian heat map of sonar point clouds. Through the regression method of the bird's-eye view Gaussian heat map, the high requirements for the image resolution of the backbone network are reduced, thereby increasing the perception ability of weak heterogeneous images. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 The flowchart of target detection for weakly heterogeneous 3D sonar point cloud images is presented.

[0056] Figure 2 Schematic diagram of fuzzy parallel decoupling encoding within a single voxel grid.

[0057] Figure 3 Flowchart of the extraction layer for voxel-wise multiple feature encoding. DETAILED DESCRIPTION

[0058] In order to better understand the above technical solution, the technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0059] Example 1

[0060] like Figure 1 As shown, a three-dimensional sonar target detection method based on fuzzy decoupling, the implementation process specifically includes the following steps:

[0061] S1 To solve the errors that may be caused by collecting point cloud images with different devices, the formula for normalizing the original point cloud is as follows:

[0062]

[0063] where p i represents the intensity of any point in the point cloud, represents the intensity of the preprocessed point cloud, p min and p max They represent the parts with the largest and smallest intensity in the entire point cloud respectively.

[0064] S2 In order to imitate human observers and improve the utilization of information around the target, the present invention first performs fuzzy feature decoupling encoding on the sonar original point cloud based on prior knowledge, and the steps are as follows:

[0065] S21 point cloud data is represented as Γ={(x,y,z) n}, where n∈(1,2,3,...,N), and the voxel resolution is (V ω ,V ζ ,V η ). Here, W, H and L represent the width, height and length of the scene, respectively. After voxelizing the entire sonar scene, the first step is to assign all points to their respective voxels. The main steps include establishing fuzzy membership functions, partitioning the original point cloud, and performing parallel fuzzy coding conversion of the decoupled point cloud Γ0 into Γ1.

[0066] In the parallel decoupling process of S22 point cloud, the decision is mainly based on the echo intensity of the point cloud itself and the information of the surrounding K nearest neighbors. The comprehensive intensity of a point is defined as follows:

[0067]

[0068] Here, r k represents the k points closest to r.

[0069] S23 object points typically have higher echo intensity, contrasting with the lower echo intensity associated with noise and bubbles. Points above the bright spot threshold are classified as "bright spots", while the likelihood of a point being considered an object is positively correlated with its intensity when it is below the bright spot threshold. The twin point clouds are decoupled through a fuzzy model. Due to the concentration of objects and noise, local twin sample imbalance may occur, which may lead to a mismatch in the number of twin point clouds. To address this issue, a dynamic balancing strategy is implemented based on the fuzzy set designed by Zadeh for object points. This membership function is defined as follows:

[0070]

[0071] Here, a represents the sonar bright spot threshold, while α and β represent the adjustment functions in the Cauchy distribution.

[0072] S24 Figure 2 As shown, after classification, the average x, y and z coordinates of the point cloud, the average x, y and z intensities and the offset of the physical center of the three-dimensional space grid are calculated to form two point cloud feature codes, each consisting of 9 indicators.

[0073] S3 extracts the encoded features through the VFE module to obtain BEV features. The process of the VFE module is as follows:

[0074] S31 Figure 3 As shown, the point cloud with the above 9 features is input into the fully connected network module FC (fully connected layer FC+batch normalization layer BN+ReLU activation function) to obtain m-dimensional point-by-point features.

[0075] S32 performs unit-by-unit aggregation on the m-dimensional features obtained in the previous step through maximum pooling to obtain local aggregated features.

[0076] S33 respectively concatenates point-by-point features and local aggregation features to obtain aggregation features

[0077] S34 finally aggregates the features through a maximum pooling to obtain the final features and puts them back to the original position according to the position of the original point cloud to obtain a multi-map-view features.

[0078] After S4 extracts the complete features, it regresses the heat map through the backbone network and the projection of the final target's 3D box on the BEV view. The center point of the heat map is the center point of the target. At the same time, the length, width, height of the 3D box and the height of the center point are predicted to form a stage of prediction. The loss function based on the Gaussian heat map is defined as follows:

[0079] S41 Here, the numerical value of the Gaussian heat map generated for a certain category is displayed using the sigmoid function. In addition, the method sets the Gaussian radius as follows:

[0080]

[0081] Here, R Gaussian is the Gaussian radius of each category in the heat map, is the minimum allowed Gaussian radius. In this study, we set w and l are the width and length of the bounding box, respectively, and Λ is the Gaussian radius function. Finally, the 3D bounding box of the target is obtained by decoding the predicted Gaussian heat map and combining it with the output (w, h, l) of the detection head and the height of the center point.

[0082] S42 The first-stage loss of the present invention is defined as follows:

[0083]

[0084] Here, α and β are hyperparameters, and K is the number of positive targets in the ground truth. In this study, α = 2, β = 4. Factor The weight used to share the total loss by controlling the positive and negative samples. The larger α is, The smaller it is, the more effectively the weight of negative samples is reduced, while the weight of positive samples is relatively increased. For other target attributes, various variables are combined into a feature vector of the ground truth value: GT = (u g ,v g ,d g ,w g ,h g ,l g ) and the detected true value: DT=(u d ,v d ,d d ,w d ,h d ,l d ). Therefore, Loss reg is defined as follows:

[0085]

[0086] The final first-stage loss of S43 is expressed as follows:

[0087]

[0088] Here, l and Loss weights, which are adaptive weights. In this method, l = 1,

[0089] S5 finally uses Markov prediction in the second stage to extract additional point clouds from the original point cloud, extract features through the S2 step, and obtain the final proposal through a multi-head perceptron regression.

[0090] S51 The second stage predicts the score and refinement of the bounding box based on the prediction results of SonarPoint in the first stage. The present invention uses the score Y as shown below:

[0091] Υ=min(1,max(0.2·IOU i -0.5))(8)

[0092] Here, IOU i is the IOU value between the i-th predicted box and the ground truth.

[0093] S52Then the loss function of the second stage is defined as follows:

[0094]

[0095] here, is the prediction score. The final score is defined as follows:

[0096]

[0097] here, is the second stage prediction score, is the first stage prediction score.

[0098] Example 2

[0099] The present embodiment relates to a three-dimensional sonar target detection device based on fuzzy decoupling, comprising a memory and one or more processors, wherein the memory stores executable code, and when the one or more processors execute the executable code, they are used to implement a three-dimensional sonar target detection method based on fuzzy decoupling of embodiment 1.

[0100] Example 3

[0101] This embodiment relates to a computer-readable storage medium on which a program is stored. When the program is executed by a processor, a three-dimensional sonar target detection method based on fuzzy decoupling of the present invention is implemented.

[0102] Finally, it should be noted that the specific scheme and embodiment described above in conjunction with the illustrations are only a preferred implementation of the present invention. Technical personnel in this profession can make slight changes and modifications to the technical content described without departing from the technical scope of the present invention. However, modifications and deformations made without departing from the spirit and principles of the present invention should fall within the scope of the technical scheme of the present invention.

Claims

1. A three-dimensional sonar target detection method based on fuzzy decoupling; comprising the following steps: S1 normalizes the original point cloud to solve the errors that may be caused by collecting point cloud images with different devices; In order to imitate human observers and improve the utilization of information around the target, S2 first performs fuzzy feature decoupling encoding on the sonar raw point cloud based on prior knowledge; S3 extracts the encoded features through the VFE module to obtain BEV features; After S4 extracts the complete features, it regresses the heat map through the backbone network and the projection of the final target's 3D box on the BEV view. The center point of the heat map is the center point of the target. At the same time, the length, width, height of the 3D box and the height of the center point are predicted to form a one-stage prediction. S5 finally uses Markov prediction in the second stage to extract additional point clouds from the original point cloud, extract features through the S2 step, and obtain the final proposal through a multi-head perceptron regression.

2. A three-dimensional sonar target detection method based on fuzzy decoupling as claimed in claim 1, characterized in that: The formula for normalizing the original point cloud in step S1 is as follows: where p i represents the intensity of any point in the point cloud, represents the intensity of the preprocessed point cloud, p min and p max They represent the parts with the largest and smallest intensity in the entire point cloud respectively.

3. A three-dimensional sonar target detection method based on fuzzy decoupling as claimed in claim 1, characterized in that: Step S2 includes: S21 point cloud data is represented as Γ={(x,y,Z) n }, where n∈(1,2,3,...,N), and the voxel resolution is (V ω ,V ζ ,V η ); Here, W, H and L represent the width, height and length of the scene respectively; After voxelizing the entire sonar scene, all points are first assigned to their respective voxels. The steps include establishing a fuzzy membership function, dividing the original point cloud, and performing parallel fuzzy coding conversion of the decoupled point cloud Γ0 into Γ1; In the parallel decoupling process of the point cloud, S22 makes decisions based on the echo intensity of the point cloud itself and the information of the surrounding K nearest neighbors; the comprehensive intensity of a point is defined as follows: Here, r k represents the k points closest to r; S23 object points usually have higher echo intensity, in contrast to the lower echo intensity associated with noise and bubbles; points above the bright spot threshold are classified as "bright spots", while the likelihood of a point being considered an object is positively correlated with its intensity when it is below the bright spot threshold; the twin point clouds are decoupled through a fuzzy model. Due to the concentration of objects and noise, local dual sample imbalance occurs, resulting in a mismatch in the number of dual point clouds;, based on the fuzzy set designed by Zadeh for object points, a dynamic balancing strategy is implemented. This membership function is defined as follows: Here, a represents the sonar bright spot threshold, while α and β represent the adjustment functions in the Cauchy distribution; After S24 classification, the average x, y and z coordinates of the point cloud, the average x, y and z intensities, and the offset of the physical center of the three-dimensional space grid are calculated to form two point cloud feature codes, each consisting of 9 indicators.

4. A three-dimensional sonar target detection method based on fuzzy decoupling as claimed in claim 1, characterized in that: Step S3: S31 inputs the point cloud with the above 9 features into the fully connected network module FC (fully connected layer FC+batch normalization layer BN+ReLU activation function) to obtain m-dimensional point-by-point features; S32 aggregates the m-dimensional features obtained in the previous step unit by unit through the maximum pooling to obtain local aggregate features; S33 respectively concatenates point-by-point features and local aggregation features to obtain aggregation features S34 finally aggregates the features through a maximum pooling to obtain the final features and places them back to the original position according to the position of the original point cloud to obtain a multi-map-view features.

5. The three-dimensional sonar target detection method based on fuzzy decoupling according to claim 1, characterized in that: In step S4, the loss function based on the Gaussian heat map is defined as follows: S41 Here, the numerical values ​​of the Gaussian heat map generated for a certain category are displayed using the sigmoid function; in addition, the method sets the Gaussian radius as follows: Here, R Gaussian is the Gaussian radius of each category in the heat map, is the minimum allowed Gaussian radius; in this study, w and l are the width and length of the bounding box, respectively, and Λ is the Gaussian radius function; finally, the 3D bounding box of the target is obtained by decoding the predicted Gaussian heat map and combining it with the output (w, h, l) of the detection head and the height of the center point; The first-stage loss of S42 is defined as follows: Here, α and β are hyperparameters, K is the number of positive targets in the ground truth; the factor The weight used to share the total loss by controlling the positive and negative samples; the larger α is, The smaller it is, the more effectively the weight of negative samples is reduced, while the weight of positive samples is relatively increased; for other target attributes, various variables are merged into a feature vector of the ground truth value: GT = (u g ,v g ,d g ,w g ,h g ,l g ) and the detected true value: DT=(u d ,v d ,d d ,w d ,h d ,l d ); therefore, Loss reg is defined as follows: The final first-stage loss of S43 is expressed as follows: Here, l and Loss weights, which are adaptive weights.

6. A three-dimensional sonar target detection method based on fuzzy decoupling as claimed in claim 1, characterized in that: Step S5; comprising: S51 The second stage predicts the score and refinement of the bounding box based on the prediction results of SonarPoint in the first stage; using the score Υ as shown below: Y=min(1,max(0.2·IOU i -0.5))(8) Here, IOU i is the IOU value between the i-th predicted box and the ground truth; S52Then the loss function of the second stage is defined as follows: here, is the prediction score; the final score is defined as follows: here, is the second stage prediction score, is the first stage prediction score.

7. The three-dimensional sonar target detection method based on fuzzy decoupling according to claim 1, characterized in that: The fuzzy decoupling coding based on prior knowledge in step S2, first, performs voxel-level division on the point cloud scene and performs fuzzy division through the fuzzy membership function defined in S23, and second, encodes the decoupled point cloud to form a unique point cloud coding feature in the grid; In step S4, the one-stage proposal reasoning based on Gaussian heat map is performed, and the result is displayed in a bird's-eye view of the map perspective. The preliminary prediction result is refined in step S5; The two-stage network based on Markov prediction and its loss function in step S5, first, refine the two-stage point cloud based on the original point cloud through Markov prediction; second, combine the one-stage result in step S4 to give the final score information of the three-dimensional marking box.

8. A three-dimensional sonar target detection method and device based on fuzzy decoupling, characterized in that: It comprises a memory and one or more processors, wherein the memory stores executable codes, and when the one or more processors execute the executable codes, they are used to implement a three-dimensional sonar target detection method based on fuzzy decoupling as described in any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, a three-dimensional sonar target detection method based on fuzzy decoupling as described in any one of claims 1 to 7 is implemented.

Images