Multi-beam underwater measurement method and system

Abstract

The present invention belongs to the technical field of underwater measurement, and provides a multi-beam underwater measurement method and system. The method includes: performing low-resolution detection on a target water area in a single-beam mode, and obtaining the water depth and terrain complexity of the target water area based on the obtained first detection data; screening a number of interference signal recognition models based on the water depth and terrain complexity, using each interference signal recognition model as a base model, and integrating all the base models into an integrated model; performing high-resolution detection on the target water area in a multi-beam mode, using the integrated model to identify interference signals in the obtained second detection data, attenuating or removing the identified interference signals to obtain third detection data; and determining the underwater terrain data of the target water area based on each processed third detection data. The present invention can accurately identify the interference signals of the multi-beam, ensuring the accuracy of the detected underwater terrain data.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater measurement, and more particularly, to a multi-beam underwater measurement method and system. Background Art

[0002] Underwater measurement technology plays a crucial role in many fields such as marine resource exploration, underwater engineering construction, and marine scientific research. Traditional underwater measurement technology mainly uses the single-beam ultrasonic measurement method, whose working principle is based on the acoustic ranging principle, that is, a single ultrasonic transducer emits sound waves towards an underwater target. When the sound waves encounter the target during propagation, they are reflected, and the transducer receives the reflected signal. According to the propagation time of the sound waves and the known speed of sound, the formula d = v×t / 2 (where d is the target distance, v is the speed of sound, and t is the round-trip time of the sound waves) is used to calculate the distance to the target, and then the position of the target is determined by combining the attitude and position information of the measurement device.

[0003] However, with the continuous improvement of the requirements for underwater measurement in related fields, the limitations of the single-beam measurement method have become increasingly prominent. First of all, its measurement efficiency is extremely low. Since only one point can be measured at a time, when measuring a large underwater area, it takes a lot of time and manpower, and the coverage range is very limited, making it difficult to meet the needs of large-scale projects for quickly obtaining data. Secondly, there are serious deficiencies in measurement accuracy. The water environment is complex and changeable, and factors such as temperature, salinity, and flow velocity will have a significant impact on the speed of sound, resulting in relatively high measurement errors. For example, in a sea area with large temperature changes, the speed of sound may change greatly, causing a large deviation in the target distance calculated based on a fixed speed of sound. Moreover, the single-beam measurement method has poor real-time performance. Its data processing process is relatively cumbersome. From signal acquisition to the final generation of available measurement data, it requires multiple processing steps, resulting in slow data processing speed and being unable to provide support for on-site decision-making in a timely manner, making it difficult to meet the current urgent needs for large-scale, high-precision real-time measurement.

[0004] In recent years, to overcome the defects of the single-beam measurement method, multi-beam ultrasonic measurement technology has emerged and gradually become a research hotspot. This technology can obtain data of multiple points in one measurement by simultaneously emitting multiple ultrasonic beams, greatly improving the measurement efficiency. Moreover, multiple beams measure the target area from different angles, and data comparison and correction can be carried out among them, thus significantly improving the measurement accuracy. However, multi-beam ultrasonic measurement technology faces a key problem in practical applications, that is, multi-beam signals are prone to interference with each other. Since multiple beams propagate simultaneously in space, their transmission and reception processes affect each other, resulting in a large amount of interference components being mixed into the received signals, which seriously reduces the measurement accuracy, unable to fully utilize the advantages of multi-beam measurement technology, and restricting the wide application of this technology in practical scenarios.

[0005] Therefore, it is of great practical significance and broad application prospects to provide a multi-beam underwater measurement method that can effectively solve the problem of multi-beam signal interference, further improve the measurement accuracy and efficiency, and meet the real-time requirements. Summary of the Invention

[0006] In view of the above technical problems, the present invention provides a multi-beam underwater measurement method, system, electronic device, computer storage medium, and computer program product to solve the problems of low measurement accuracy, complex equipment, and high cost in the prior art.

[0007] The present invention discloses a multi-beam underwater measurement method, which includes the following steps: S1, performing low-resolution detection on the target water area in single-beam mode, and obtaining the water depth and terrain complexity of the target water area based on the obtained first detection data; S2, screening a number of interference signal recognition models based on the water depth and the terrain complexity, using each of the interference signal recognition models as a base model, and integrating all the base models into an integrated model; performing high-resolution detection on the target water area in multi-beam mode, using the integrated model to identify interference signals in the obtained second detection data, attenuating or removing the identified interference signals to obtain third detection data; and determining the underwater terrain data of the target water area based on each of the processed third detection data.

[0008] Optionally, the first detection data includes distance data and position data, and the obtaining the water depth and terrain complexity of the target water area based on the obtained first detection data includes: calculating the average value of each of the distance data as the water depth; performing three-dimensional projection on the corresponding distance data according to each of the position data to obtain a three-dimensional projection map, and using a classifier to classify the three-dimensional projection map to obtain the terrain complexity.

[0009] Optionally, screening a number of interference signal recognition models based on the water depth and the terrain complexity, using each of the interference signal recognition models as a base model, and integrating all the base models into an integrated model includes: performing matching analysis on the water depth and the terrain complexity with the standard water depth and standard terrain complexity corresponding to each interference signal recognition model in the model library to obtain a first number of interference signal recognition models that meet the matching threshold value, and using them as base models; and randomly screening a second number of interference signal recognition models that do not meet the matching threshold value and using them as base models; where the second number is lower than the first number; and integrating all the screened base models into an integrated model.

[0010] Optionally, classifying the three-dimensional projection map using a classifier to obtain the terrain complexity includes: classifying the three-dimensional projection map using a classifier to obtain the terrain complexity and its classification confidence level; then the second quantity is determined by the following method: performing a comparison calculation based on the classification confidence level and preset reference data to obtain the second quantity; wherein, in the reference data, the second quantity is negatively correlated with the classification confidence level.

[0011] Optionally, before measuring the underwater terrain data of the target water area based on each of the processed third detection data, the method further includes: determining the recognition confidence level of the integrated model for the interference signal in the second detection data; if the recognition confidence level is lower than the confidence level threshold, adding an interference signal mark to the corresponding third detection data, and associating the recognition confidence level of the interference signal, the corresponding second detection data with the third detection data.

[0012] The present invention also discloses a multi-beam underwater measurement system, the system includes an ultrasonic wave transmitting module, an ultrasonic wave receiving module, and a signal processing module; the ultrasonic wave transmitting module uses a linear array transducer and is composed of multiple ultrasonic transducer units; the ultrasonic wave receiving module includes multiple receiving transducers for receiving the reflected ultrasonic wave signals; the signal processing module includes a filtering unit, an amplifying unit, and a digital signal processing unit; the filtering unit is used to eliminate noise and extract effective signals; the amplifying unit adjusts the gain of the signal to ensure that the signal intensity is appropriate; the digital signal processing unit processes the ultrasonic wave signals processed by the filtering unit and the amplifying unit to obtain the underwater terrain data of the target water area; the filtering unit has a processor and a memory, and the processor is used to call and execute the computer program in the memory to implement a multi-beam underwater measurement method as described above.

[0013] Optionally, the system further includes a control module, and the control module uses an embedded system to achieve high-precision timing control and data processing to coordinate the work of the ultrasonic wave transmitting module, the ultrasonic wave receiving module, and the signal processing module.

[0014] The present invention also discloses an electronic device, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, and the processor executes the computer program to implement the method as described in any one of the preceding items.

[0015] The present invention also discloses a computer storage medium, and the computer storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in any one of the preceding items.

[0016] The present invention also discloses a computer program product, which contains computer code that, when executed by a processor of an electronic device, implements the method described in any of the preceding items.

[0017] The beneficial effects of the present invention are at least as follows: For the multi-beam underwater measurement solution proposed by the present invention, it first uses a single beam to quickly determine the water depth and terrain characteristics of the target water area, thereby screening the base model and constructing a suitable integrated model to accurately identify interference signals with different characteristics, so as to solve the signal interference problem of multi-beams, give full play to the advantages of multi-beam technology, ensure the accuracy of the underwater terrain data obtained by detection, and can provide accurate data for on-site decision-making in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 is a flowchart of a multi-beam underwater measurement method disclosed in an embodiment of the present invention.

[0020] Figure 2 is a structural diagram of a multi-beam underwater measurement system disclosed in an embodiment of the present invention.

[0021] Figure 3 is a structural diagram of a signal processing module disclosed in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The following specific embodiments illustrate the implementation manners of the present application. Those skilled in the art can easily understand the other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of them. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the protection scope of the present application.

[0023] In addition, the technical features involved in different implementation manners of the present application described below can be combined with each other as long as they do not conflict with each other.

[0024] Such as Figure 1 、 Figure 2As shown in the figure, in view of the above technical problems, an embodiment of the present invention discloses a multi-beam underwater measurement method, and the method includes the following steps: S1, performing low-resolution detection on a target water area in a single-beam mode, and obtaining the water depth and terrain complexity of the target water area based on the obtained first detection data.

[0025] In this step, the multi-beam underwater measurement device of the present invention can switch between the single-beam mode and the multi-beam mode. Single-beam measurement is relatively simple and can initially reflect the general situation of the water area. Therefore, the present invention first uses the single-beam mode to carry out low-resolution detection work on the target water area. That is, the multi-beam measurement device emits only one beam for measurement each time, and the interval between adjacent detection positions is significantly larger than that in the multi-beam measurement mode, that is, sparse sampling measurement is carried out on the target water area. In this way, the first detection data of the target water area is obtained.

[0026] Based on the obtained first detection data, the water depth information of the target water area is calculated. At the same time, based on these water depth information, the terrain complexity of the water area is evaluated, for example, it is judged whether it is a flat terrain or a complex terrain with undulations, ravines, etc. The terrain complexity can be represented in the form of a terrain complexity level, a terrain complexity value, etc. The higher the level or value, the more complex the corresponding terrain.

[0027] S2, screening out a number of interference signal recognition models based on the water depth and the terrain complexity, using each of the interference signal recognition models as a base model, and integrating all the base models into an integrated model.

[0028] In this step, different water depths and terrain complexities will cause interference signals with different characteristics during multi-beam measurement. Therefore, the present invention has pre-constructed and trained multiple interference signal recognition models for different water depths and terrain complexities respectively to form a model library. Regarding the characteristics of interference signals and the requirements for interference signal recognition models under different water depths and terrain complexities, the details are as follows: 1) When the beam propagates in the shallow water area, due to the relatively thin water layer, the path of the sound wave from emission to reception is relatively short, and it is easier for the beams to interact with each other. At the same time, the bottom reflection in the shallow water area is relatively strong, and the reflected wave and the direct wave may produce complex interference phenomena between different beams, resulting in the interference signal showing strong periodicity and regularity, and the signal intensity is relatively large.

[0029] In view of the characteristics of strong and periodic interference signals in the shallow water area, a model that can capture the periodicity and regularity of the signal is suitable. For example, the frequency domain analysis model based on Fourier transform can effectively extract the frequency characteristics of the interference signal, and identify the interference signal by detecting specific frequency components in the spectrum. In addition, some simple linear models, such as the autoregressive model (AR), can also model and predict the interference signals in the shallow water area with certain regularity.

[0030] 2) When the beam propagates in deep water areas, the increase in water depth makes the acoustic wave propagation path longer, and the interference signals between beams are more significantly affected by factors such as water body absorption and scattering. This will cause the intensity of the interference signals to gradually weaken, and the attenuation and distortion of the signals to be more obvious. Moreover, the environment in deep water areas is relatively stable and the noise level is relatively low. However, due to the influence of hydrological conditions such as thermoclines and haloclines during the long-distance propagation of acoustic waves, complex situations such as frequency offset and phase change may occur in the interference signals between beams, and their spectral characteristics will change with the water depth.

[0031] The complex changes of interference signals in deep water areas require more powerful models to handle. The convolutional neural network (CNN) in deep learning can automatically extract the features of interference signals through convolutional layers and pooling layers, and has good adaptability to complex features such as frequency offset and phase change of signals. At the same time, the recurrent neural network (RNN) and its variant, the long short-term memory network (LSTM), can process time series information and have better recognition ability for interference signals that change with time and depth in deep water areas.

[0032] 3) In a flat underwater terrain environment, the interference signals between beams are relatively stable and uniform. Due to the consistency of the terrain, the reflection and scattering of acoustic waves are relatively regular. The interference signals are mainly generated by the characteristics of the water body itself and the inherent interaction between beams. Their spatial distribution is relatively uniform, and the amplitude and phase changes of the signals are relatively small, and the spectral characteristics are also relatively stable.

[0033] For the relatively simple and stable interference signals in flat terrain, traditional machine learning models such as support vector machines (SVM) and decision trees can usually achieve good recognition effects. These models can accurately identify interference signals by learning a small number of features because the interference signal features in flat terrain are relatively easy to extract and describe.

[0034] 4) When the underwater terrain is complex, such as the existence of mountains, canyons, reefs, etc., the beam will encounter irregular reflecting surfaces and scatterers during propagation. This will cause the interference signals between beams to become very complex, and the interference degrees of beams at different positions are different, and the spatial distribution of the interference signals shows obvious non-uniformity. For example, near mountains, the beam may undergo strong reflection and diffraction, generating complex multipath effects, making the interference signals contain the superposition of reflected waves from multiple different paths, and the amplitude and phase of the signals will change violently, and the spectrum will become more complex, possibly showing multiple peaks and bandwidth broadening phenomena.

[0035] Interference signals in complex terrains require models with greater flexibility and powerful characterization capabilities. Deep learning models such as deep neural networks (DNNs) can learn complex feature representations through the non-linear transformation of multiple layers of neurons and are capable of better handling the spatial inhomogeneity and complex spectral characteristics of interference signals. In addition, some model fusion-based methods, such as models that combine CNN and RNN, can also utilize the ability of CNN to extract spatial features and the ability of RNN to process time series information simultaneously, thereby more comprehensively identifying the interference signals between beams in complex terrains.

[0036] Based on different water depths and different terrain complexities, select appropriate algorithms to build models (for example, initially integrate models adapted to different water depths and models adapted to different terrain complexities to obtain a composite model, i.e., the interference signal recognition model), and select the measured multi-beam detection data that adapts to the corresponding water depth and terrain complexity. Identify the interference signals in the measured multi-beam detection data based on methods such as manual or machine annotation (i.e., form training labels), and then form training data. Use this training data to train the corresponding interference signal recognition model. After associating all the trained interference signal recognition models with the corresponding water depth and terrain complexity (i.e., subsequent standard water depth and standard terrain complexity), put them into the aforementioned model library together.

[0037] Then, using the water depth and terrain complexity obtained in step S1 as a basis, screen out suitable interference signal recognition models from the pre-established model library. These screened models are the base models. Integrate all the screened base models to construct an ensemble model. By specifically screening and integrating the interference signal recognition models, the finally obtained ensemble model can better adapt to the specific conditions of the target water area and improve the recognition ability of multi-beam measurement interference signals in this water area.

[0038] S3. Conduct high-resolution detection of the target water area in multi-beam mode, use the ensemble model to identify the interference signals in the obtained second detection data, and attenuate or remove the identified interference signals to obtain the third detection data.

[0039] In this step, conduct high-resolution detection of the target water area in multi-beam mode. At this time, the device will simultaneously emit multiple beams to obtain a large amount of more detailed second detection data. Although the multi-beam mode can improve the measurement efficiency and accuracy, interference signals will be generated between the beams, affecting the measurement results. This is because the acoustic beams emitted by the transducer are not completely ideal narrow beams and have certain side lobes and beam widths. When multiple beams work simultaneously, the side lobes of adjacent beams may overlap, resulting in interference signals from other beams being mixed into the received signal.

[0040] Therefore, the present invention further processes these second detection data using the integrated model constructed in step S2 to identify interference signals therein. Once an interference signal is identified, corresponding measures are taken to attenuate or directly remove it, thereby obtaining purified third detection data.

[0041] The multi-beam underwater measurement system of the present invention can be installed by hoisting, that is, installation carriers (such as high towers) are set on both sides of the water area, a steel cable is arranged between the two installation carriers, and the multi-beam underwater measurement system is installed on the steel cable through a positioning host, and then the multi-beam underwater measurement system is driven to move on the steel cable through a transmission mechanism to achieve detection of different water areas. A reference station can also be arranged at a suitable position around the water area.

[0042] S4. Determine the underwater terrain data of the target water area based on each of the processed third detection data.

[0043] In this step, the underwater terrain data of the target water area is determined based on each of the third detection data obtained after being processed in step S3. For example, detailed information such as the water depth and terrain undulation at different positions is calculated, and finally, complete and accurate underwater terrain data of the target water area is formed, meeting the requirements for high-precision underwater terrain data in fields such as marine resource exploration, underwater engineering construction, and marine scientific research.

[0044] The multi-beam underwater measurement solution proposed by the present invention first uses a single beam to quickly determine the water depth and terrain characteristics of the target water area, thereby screening the base model and constructing a suitable integrated model to accurately identify interference signals with different characteristics, so as to solve the signal interference problem of the multi-beam, give full play to the technical advantages of the multi-beam, ensure the accuracy of the detected underwater terrain data, and provide accurate data for on-site decision-making in a timely manner.

[0045] Optionally, the first detection data includes distance data and position data, and the obtaining of the water depth and terrain complexity of the target water area based on the obtained first detection data includes: calculating the average value of each of the distance data and using it as the water depth; performing three-dimensional projection on the corresponding distance data according to each of the position data to obtain a three-dimensional projection map, and using a classifier to classify the three-dimensional projection map to obtain the terrain complexity.

[0046] In this embodiment, after low-resolution detection of the target water area in single-beam mode, first detection data including distance data and position data is obtained. Among them, the distance data refers to the distance between the transducer and the reflection point calculated according to the time of flight of the sound wave reflected by the sound wave emitted by the single-beam transducer when it encounters an underwater object or the bottom. Since the water depth at different measurement points may vary to a certain extent, by calculating the average value of each distance data, it is used to more accurately represent the overall water depth situation of the target water area.

[0047] When performing low-resolution detection and obtaining distance data, the underwater position corresponding to the distance data can also be determined according to the orientation of the single beam (i.e., the emission orientation angle), that is, the position data (such as longitude and latitude). Combining this position information with the corresponding distance data and projecting it in three-dimensional space, a three-dimensional projection map of the target water area is obtained, which intuitively shows the depth conditions at different positions in the target water area.

[0048] Then, a classifier is used to classify the three-dimensional projection map. The classifier divides the terrain complexity of the target water area into different categories according to features such as the undulation and shape of the terrain in the three-dimensional projection map, such as simple terrain (such as a flat water bottom), moderately complex terrain (with some small undulations or obstacles), and complex terrain (such as the existence of high mountains and deep valleys), and then obtains the terrain complexity of the target water area.

[0049] By performing three-dimensional projection and classification on the target water area, the terrain complexity of the target water area can be accurately evaluated, providing an important basis for constructing a suitable interference signal recognition model in the follow-up, enabling the measurement method to better adapt to different terrain conditions, and improving the accuracy and reliability of the measurement.

[0050] Next, taking the random forest classifier as an example, the process of classifying the three-dimensional projection map of the target water area to obtain the terrain complexity is as follows: 1. Initialization: Initialize the experience replay pool D for storing training-related data.

[0051] Use randomly generated values as the initial parameter values of the current random forest classifier 。

[0052] Set hyperparameters such as the number of decision trees n.

[0053] 2. Data preprocessing - Feature extraction: For each three-dimensional projection map s ∈ S in the dataset: Calculate the height difference h: Find the depths of the highest and lowest points in the projection map and subtract them to obtain the height difference h.

[0054] Calculate the slope change p: Analyze the slopes at different positions of the projection map through an algorithm to obtain the slope change index p.

[0055] Calculate the terrain roughness r: Use a related algorithm to obtain the terrain roughness index r.

[0056] Form a feature vector fs with (h, p, r).

[0057] 3. Model training: The first layer of loop: Initialize the training epoch parameter and loop until the set total number of epochs E.

[0058] Observe the current training status, such as the loss value, as the initial state .

[0059] Second - layer loop: Initialize the batch parameter batch, and loop until the set total number of batches B.

[0060] Randomly select a batch of projection maps and corresponding labels from the dataset to form a training subset.

[0061] Train a random forest classifier based on the feature vectors.

[0062] Make predictions on the training subset to obtain the predicted classes .

[0063] According to the comparison between the predicted classes and the true labels Calculate the loss value loss as the reward value (high reward for correct prediction, low reward for wrong prediction).

[0064] Observe the state after training, such as the updated loss value, etc., as the next state .

[0065] Put the quadruple ( , training action, loss, ) into the experience replay pool D.

[0066] Randomly select a batch of sample quadruples from the experience replay pool for gradient descent to update the parameters of the current random forest classifier .

[0067] Judge whether the current batch value is a multiple of a specific value C. If so, perform additional optimization and adjustment on the classifier.

[0068] The second - round loop ends.

[0069] The first - round loop ends.

[0070] 4. Classification prediction: For the three - dimensional projection map of the target water area to be classified : Calculate its height difference, slope change, and terrain roughness according to the above - mentioned feature extraction method to form a feature vector .

[0071] Input into the trained random forest classifier.

[0072] The classifier outputs the terrain complexity category (simple, medium, or complex, or the corresponding numerical value) corresponding to the target projection map through the internal decision - tree calculation and voting mechanism.

[0073] Optionally, several interference signal recognition models are screened based on the water depth and the terrain complexity. Each of the interference signal recognition models is used as a base model, and all the base models are integrated into an integrated model, including: matching and analyzing the water depth and the terrain complexity with the standard water depth and the standard terrain complexity corresponding to each interference signal recognition model in the model library, to obtain a first quantity of interference signal recognition models that meet the matching threshold value, and using them as base models; and randomly screening a second quantity of interference signal recognition models that do not meet the matching threshold value, and also using them as base models; wherein, the second quantity is lower than the first quantity; integrating all the screened base models into an integrated model.

[0074] In this embodiment, the model library stores multiple different interference signal recognition models, and each model corresponds to parameters such as a standard water depth and a standard terrain complexity range. Compare and analyze the water depth and the terrain complexity of the target water area actually measured in step S1 with the standard water depth and the standard terrain complexity corresponding to each interference signal recognition model in the model library. For example, model A is applicable to shallow water areas (standard water depth is 0 - 20 meters) and areas with relatively simple terrain (standard terrain complexity is low). If the water depth of the target water area is 15 meters and the terrain complexity is evaluated as low, it meets the matching conditions of this model. Set a matching threshold value. When the matching degree between the actual water depth and terrain complexity and the model standard parameters reaches or exceeds this threshold value, the model is screened out. The number of models that meet the conditions is recorded as the first quantity, and these screened models are used as base models.

[0075] Through this matching method, the interference signal recognition models that are theoretically most suitable for the actual environmental conditions of the target water area can be preferentially selected. Because models with a high matching degree with the water depth and terrain complexity of the target water area are more likely to accurately identify the interference signals generated during the multibeam measurement of this water area.

[0076] Since the water depth and the terrain complexity of the target water area in the aforementioned step S1 are roughly estimated through low-resolution detection, the actual water depth and terrain complexity of the local area of the target water area may have a large gap from the rough detection results. For example, deep trench areas underwater may be crossed during coefficient sampling. Therefore, when performing multibeam detection on areas with a large gap, the integrated model constructed only based on the first quantity of interference signal recognition models that meet the matching threshold value in the aforementioned may not be able to accurately identify the interference signals in the second detection data.

[0077] Thus, in addition to the above models that meet the matching threshold, the present invention also sets a second number (the second number is lower than the first number) of models randomly selected from the interference signal recognition models that do not meet the matching threshold as the base models. For example, if the first number is 10, the second number can be set to 3. Adding a small number of models that do not meet the matching threshold to the base model set can increase the diversity of the models, thereby effectively dealing with the recognition of interference signals in the second detection data corresponding to the waters with a large gap from the rough detection results. That is, the integrated model has stronger generalization ability, can handle some unexpected interference situations, and improves the reliability and comprehensiveness of the overall interference signal recognition.

[0078] Finally, since a single interference signal recognition model may have limitations, by integrating multiple base models into an integrated model, the integrated model can analyze and judge interference signals from multiple perspectives, reduce the risk of misjudgment or missed judgment of a single model, and thus more effectively process the interference signals generated in multibeam measurement, improving the accuracy and reliability of the entire underwater measurement.

[0079] Integrate all the first number of base models screened by the previous matching analysis and the second number of base models randomly screened together to construct an integrated model. The construction method of the integrated model can adopt, for example, the voting method, the weighted average method, etc., to synthesize the output results of multiple base models to obtain a more accurate interference signal recognition result, which will not be elaborated here. Of course, the stacking method (Stacking), the boosting method (Boosting), etc. can also be used, which will not be elaborated here.

[0080] It should be noted that after obtaining the multiple base models, various combinations of these base models should be made, and then the test data is used to test and evaluate each model combination to select the optimal model combination, and the multiple base models corresponding to the optimal model combination are integrated into an integrated model.

[0081] Optionally, the step of using the classifier to classify the three-dimensional projection map to obtain the terrain complexity includes: using the classifier to classify the three-dimensional projection map to obtain the terrain complexity and its classification confidence; then the second number is determined by the following method: based on the classification confidence and the preset control data for comparison calculation, the second number is obtained; where, in the control data, the second number is negatively correlated with the classification confidence.

[0082] In this embodiment, when using the classifier to classify the three-dimensional projection map of the target water area to determine the terrain complexity, the classifier not only gives the category of the terrain complexity (such as simple, medium or complex), but also outputs a classification confidence related to the classification result, and the classification confidence reflects the degree of certainty of the classifier about its judgment result.

[0083] There are various ways for a classifier to calculate confidence. For example, in the case of a probability-based method, for a multi-classification problem, the classifier can output the probabilities of each class. The class with the highest probability is the classification result, and this probability value can be used as the classification confidence. For instance, when the classifier determines that the terrain complexity of a certain water area is "complex", it gives a confidence of 0.8, which means the classifier is 80% certain that this judgment is correct. Generally speaking, the higher the confidence, the more reliable the classification result; the lower the confidence, the greater the uncertainty of the classification result.

[0084] Multiple sets of control data between the second quantity and the classification confidence are pre-constructed, and these control data show a negative correlation. The higher the classification confidence, the lower the second quantity calculated based on the control data, that is, the water depth and terrain complexity of the aforementioned determined target water area are relatively more accurate and reliable. At this time, a smaller number of interference signal recognition models that do not meet the matching threshold value are set to be added to avoid the integration model from being too large and to reduce the impact of the interference signal recognition results of these models on the final recognition result; conversely, the lower the classification confidence, the higher the second quantity, that is, a larger number of interference signal recognition models with the second quantity that do not meet the matching threshold value are set to be added to effectively identify interference signals in the case where the difference from the rough detection result is relatively large.

[0085] Optionally, before determining the underwater terrain data of the target water area based on each of the processed third detection data, the method further includes: determining the recognition confidence of the interference signals in the second detection data by the integration model. If the recognition confidence is lower than the confidence threshold, an interference signal mark is added to the corresponding third detection data, and the recognition confidence of the interference signal, the corresponding second detection data, and the third detection data are associated.

[0086] In this embodiment, in the multi-beam underwater measurement method, after using the integration model to identify interference signals in the second detection data, it is necessary to determine the confidence of the integration model in the interference signal recognition result. The way for the integration model to calculate the recognition confidence can be calculated based on the voting situation of different base models, the probability values output by the model, etc. Taking the weighted voting method as an example, the calculation method of the recognition confidence is illustrated: The weight corresponding to each base model is set to , and .

[0087] Let the set of base models that judge this signal as an interference signal be S, then the recognition confidence . For example, there are 3 base models with weights . Among them, base model 1 and base model 2 judge this signal as an interference signal, then the recognition confidence C = 0.4 + 0.3 = 0.7.

[0088] Compare the obtained recognition confidence with a pre-set confidence threshold. If the recognition confidence is lower than this threshold, it indicates that the recognition result of the integrated model for this interference signal is not very reliable and there is a large uncertainty. At this time, add an interference signal mark to the corresponding third detection data. The role of this mark is to identify that there may be interference signals in this data that have not been accurately recognized or processed. For example, a specific symbol, numerical value, or label can be used to represent this mark, so that in subsequent determination of underwater terrain data in the target water area or other processing processes, these data with potential problems can be easily identified. In addition to adding the interference signal mark, it is also necessary to associate the recognition confidence of this interference signal, the corresponding second detection data, and this third detection data. This association can be achieved by establishing a data structure or a database table, storing these three data items (recognition confidence, second detection data, third detection data) together, and establishing the corresponding relationship between them.

[0089] With such a setting, in subsequent analysis or processing of determining the underwater terrain data of the target water area based on each third detection data, the analyst can see this mark and retrieve the recognition confidence and the original second detection data for further inspection or correction, so as to take more appropriate processing measures and improve the accuracy and reliability of the underwater terrain data determination.

[0090] As Figure 2 、 Figure 3 shown, an embodiment of the present invention also discloses a multi-beam underwater measurement system, and the system includes an ultrasonic wave transmitting module 1, an ultrasonic wave receiving module 2, and a signal processing module 3.

[0091] The ultrasonic wave transmitting module 1 adopts a linear array transducer and is composed of a plurality of ultrasonic transducer units.

[0092] The ultrasonic wave receiving module 2 includes a plurality of receiving transducers for receiving the reflected ultrasonic wave signals.

[0093] The signal processing module 3 includes a filtering unit 301, an amplifying unit 302, and a digital signal processing unit 303; the filtering unit 301 is used to eliminate noise and extract effective signals; the amplifying unit 302 performs gain adjustment on the signals to ensure that the signal intensity is appropriate; the digital signal processing unit 303 processes the ultrasonic wave signals processed by the filtering unit 301 and the amplifying unit 302 to obtain the underwater terrain data of the target water area; the filtering unit has a processor and a memory, and the processor is used to call and execute the computer program in the memory to implement a multi-beam underwater measurement method as described above.

[0094] Optionally, the system further includes a control module 4, which adopts an embedded system (such as ARM or FPGA) to achieve high-precision timing control and data processing, so as to coordinate the operations of the ultrasonic transmitting module 1, the ultrasonic receiving module 2, and the signal processing module 3, and ensure the synchronization and accuracy of the measurement process.

[0095] An embodiment of the present invention also discloses an electronic device, including: at least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, and the processor executes the computer program to implement the method as described in the foregoing embodiment.

[0096] An embodiment of the present invention also discloses a computer storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method as described in the foregoing embodiment.

[0097] An embodiment of the present invention also discloses a computer program product, which contains computer code, and when the computer code is executed by a processor of an electronic device, it implements the method as described in the foregoing embodiment.

[0098] The above-mentioned computer storage medium includes, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the above. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0099] It should be understood that various forms of the processes shown above can be used, steps can be reordered, added, or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0100] The above specific implementation manners do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A multi-beam underwater measurement method, characterized in that: The method includes the following steps: detecting the target water area in a low-resolution manner using a single-beam mode, and obtaining the water depth and terrain complexity of the target water area based on the obtained first detection data; screening a number of interference signal recognition models based on the water depth and the terrain complexity, using each of the interference signal recognition models as a base model, and integrating all the base models into an integrated model; detecting the target water area in a high-resolution manner using a multi-beam mode, using the integrated model to identify interference signals in the obtained second detection data, and attenuating or removing the identified interference signals to obtain third detection data; and determining the underwater terrain data of the target water area based on each of the processed third detection data.

2. The multi-beam underwater measurement method according to claim 1, characterized in that: If the first detection data includes distance data and position data, then obtaining the water depth and terrain complexity of the target water area based on the obtained first detection data includes: calculating the average value of each of the distance data as the water depth; performing three-dimensional projection on the corresponding distance data according to each of the position data to obtain a three-dimensional projection map, and using a classifier to classify the three-dimensional projection map to obtain the terrain complexity.

3. A multi-beam underwater measurement method according to claim 2, characterized in that: Screening a number of interference signal recognition models based on the water depth and the terrain complexity, using each of the interference signal recognition models as a base model, and integrating all the base models into an integrated model includes: performing matching analysis on the water depth and the terrain complexity with the standard water depth and standard terrain complexity corresponding to each interference signal recognition model in the model library to obtain a first number of interference signal recognition models that meet the matching threshold value, and using them as base models; and randomly screening a second number of interference signal recognition models that do not meet the matching threshold value and using them as base models as well, where the second number is lower than the first number; and integrating all the screened base models into an integrated model.

4. A multi-beam underwater measurement method according to claim 3, characterized in that: Using a classifier to classify the three-dimensional projection map to obtain the terrain complexity includes: using a classifier to classify the three-dimensional projection map to obtain the terrain complexity and its classification confidence level; then the second number is determined by the following method: performing comparison calculation based on the classification confidence level and preset reference data to obtain the second number; where in the reference data, the second number is negatively correlated with the classification confidence level.

5. A multi-beam underwater measurement method according to claim 1, characterized in that: Before determining the underwater terrain data of the target water area based on each of the processed third detection data, the method further includes: determining the recognition confidence level of the interference signals in the second detection data by the integrated model, if the recognition confidence level is lower than the confidence threshold, then adding an interference signal mark to the corresponding third detection data, and associating the recognition confidence level of the interference signal, the corresponding second detection data with the third detection data.

6. A multi-beam underwater measurement system, characterized in that: The system includes an ultrasonic transmitting module, an ultrasonic receiving module, and a signal processing module; the ultrasonic transmitting module uses a linear array transducer and is composed of multiple ultrasonic transducer units; the ultrasonic receiving module includes multiple receiving transducers for receiving the reflected ultrasonic signals; the signal processing module includes a filtering unit, an amplifying unit, and a digital signal processing unit; the filtering unit is used to eliminate noise and extract effective signals; the amplifying unit adjusts the gain of the signals to ensure appropriate signal intensity; the digital signal processing unit processes the ultrasonic signals processed by the filtering unit and the amplifying unit to obtain the underwater terrain data of the target water area; The filtering unit has a processor and a memory, and the processor is used to call and execute the computer program in the memory to implement a multi-beam underwater measurement method as described in any one of claims 1-5.

7. A multi-beam underwater measurement system according to claim 6, wherein: The system further includes a control module, and the control module uses an embedded system to achieve high-precision timing control and data processing to coordinate the operations of the ultrasonic transmitting module, the ultrasonic receiving module, and the signal processing module.

8. An electronic device, comprising: At least one processor, a memory, and a computer program stored in the memory and executable on the at least one processor, characterized in that: the processor executes the computer program to implement the method as described in any one of claims 1-5.

9. A computer storage medium storing a computer program, characterized in that: The computer program is executed by the processor to implement the method as described in any one of claims 1-5.

10. A computer program product, characterized in that: The computer program product contains computer code, and when the computer code is executed by the processor of an electronic device, the method as described in any one of claims 1-5 is implemented.

Images