Method and system for measuring excavation depth of trailing suction dredger

Abstract

The invention relates to a trailing suction dredger excavation depth measuring method and system, and the method comprises the steps: obtaining multi-mode sensor data of a water area bottom layer, the multi-mode sensor data comprising multi-beam sonar data, laser scanning data and underwater visual image data; carrying out dynamic identification on the multi-modal sensor data, and generating a bottom layer feature identification result of the water area; utilizing the real-time water flow and sediment flow model to predict the flow trend of the bottom sediment of the water area, and generating a water flow prediction result; and dynamically adjusting a depth measurement strategy based on the underlying feature recognition result and the water flow prediction result, and optimizing measurement data in real time through a data correction algorithm in the measurement process to generate a depth measurement result. The method has the effect of improving the digging depth measurement precision of the trailing suction hopper dredger.

Description

Technical Field

[0001] The present application relates to the technical field of underwater detection, and in particular to a method and system for measuring the dredging depth of a trailing suction dredger. Background Art

[0002] At present, the depth measurement of trailing suction hopper dredgers mostly relies on fixed measurement strategies and predetermined measurement paths, but existing technologies usually fail to fully consider the dynamic changes of the water environment, especially the real-time changes in water flow and sediment flow trends. Traditional measurement methods often use fixed measurement frequencies and paths, which cannot be adjusted in real time according to actual conditions, which may lead to inaccurate or inefficient measurement data.

[0003] Existing technical solutions have failed to effectively solve the impact of dynamic changes in water flow and sediment flow on depth measurement, and cannot predict and dynamically adjust measurement strategies in real time, resulting in the measurement frequency and path not being able to adapt to the actual situation in the water area, which in turn affects the measurement accuracy and operation efficiency. Therefore, the existing technology has certain limitations when dealing with excavation operations in complex water environments, and urgently needs to be improved and optimized.

[0004] The above-mentioned existing technical solutions have the following defects: the existing technology fails to take into account the dynamic changes of the water environment and cannot dynamically adjust the depth measurement strategy according to the real-time water flow and sediment flow trends, resulting in the measurement frequency and path may not meet actual needs, so there is room for improvement. Summary of the invention

[0005] In order to improve the measurement accuracy of the dredging depth of a trailing suction hopper dredger, the present application provides a method and system for measuring the dredging depth of a trailing suction hopper dredger.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A method for measuring the excavation depth of a trailing suction hopper dredger, the method comprising: Acquiring multimodal sensor data of the bottom of the water area, wherein the multimodal sensor data includes multibeam sonar data, laser scanning data, and underwater visual image data; Dynamically identifying the multimodal sensor data to generate bottom-level feature identification results of the water area; Using a real-time water flow and sediment flow model, the flow trend of bottom sediments in the water area is predicted to generate a water flow prediction result; Based on the bottom feature recognition result and the water flow prediction result, the depth measurement strategy is dynamically adjusted, and during the measurement process, the measurement data is optimized in real time through a data correction algorithm to generate a depth measurement result.

[0007] By adopting the above technical solution, by acquiring multimodal sensor data of the bottom of the water area, including multi-beam sonar, laser scanning and underwater visual image data, the topographic information of the bottom of the water area can be collected comprehensively and accurately, covering a variety of physical characteristics, thereby providing multi-dimensional data support for subsequent depth measurement; by dynamically identifying the multimodal sensor data, various characteristics of the bottom of the water area can be analyzed in real time, the accuracy of bottom identification is improved, and the necessary basis is provided for adjusting the measurement strategy according to different water environments; by using the real-time water flow and sediment flow model to predict the flow trend of the bottom sediment, the changing law of water flow and sediment flow can be simulated, and the dynamic state of sediment can be grasped in advance, thereby providing a scientific basis for the dynamic adjustment of depth measurement; by dynamically adjusting the measurement strategy based on the bottom feature recognition results and the water flow prediction results, the measurement path, frequency and depth can be adjusted in real time according to the actual changes in water flow and sediment, thereby optimizing the efficiency and accuracy of the measurement, making the measurement process more flexible and intelligent; by using the data correction algorithm to optimize the measurement data in real time during the measurement process, the noise and error in the sensor data can be reduced, the accuracy and reliability of the measurement results can be further improved, and the depth measurement results finally generated can be ensured to have higher accuracy.

[0008] In one example, the present application may be further configured as follows: the acquiring of multimodal sensor data of the bottom of the water area includes: Using a multi-beam sonar sensor to measure the depths of multiple water layers at the bottom of the water area and collect reflected wave data to generate the multi-beam sonar data; Scanning and collecting three-dimensional geometric data of the bottom layer of the water area by a laser scanning sensor to generate the laser scanning data; The image data of the bottom material of the water area is collected by an underwater visual image collection system to generate the underwater visual image data.

[0009] By adopting the above technical solution, by using a multi-beam sonar sensor to measure the depth of multiple water layers at the bottom of the water area and collect reflected wave data, the bottom water depth and bottom quality characteristics can be obtained with high precision, which is especially suitable for fine measurement in deep water areas, ensuring that the depth data of the bottom of the water area is comprehensive and detailed, while being able to provide reflected wave information to help further analyze the bottom structure; by scanning the three-dimensional geometric morphological data of the bottom of the water area with a laser scanning sensor, the three-dimensional spatial structure of the bottom can be accurately obtained, and a high-resolution topographic map can be generated to help reveal information such as bottom undulations, obstacles, and sediment distribution, and provide data that is helpful for the bottom morphological analysis of the water area; by obtaining image data of the bottom material of the water area through an underwater visual image acquisition system, the details of the underwater material, such as the type, morphology, and changes of the bottom sediments, can be intuitively captured, which helps to classify and analyze the bottom material, thereby providing effective visual evidence to support the accurate identification of bottom features.

[0010] In one example, the present application may be further configured as follows: the dynamic recognition of the multimodal sensor data to generate the bottom-level feature recognition result of the water area includes: Calculating the thickness and density of bottom sediments in the water area using the multi-beam sonar data to generate preliminary identification results; Based on the preliminary recognition result, the texture features of the bottom material in the underwater visual image data are extracted using an image processing algorithm to generate the bottom material type of the water area; Combined with the laser scanning data, the fluctuations of the bottom layer of the water area are identified, and the structural distribution of the bottom sediments of the water area is inferred.

[0011] By adopting the above technical solution, by using multi-beam sonar data to calculate the thickness and density of the bottom sediments in the water area, the distribution of sediments can be accurately evaluated, and accurate physical property data can be provided for subsequent sediment processing and depth measurement, thereby ensuring the high reliability and accuracy of the measurement results; by using image processing algorithms to extract the texture features of the bottom materials in the underwater visual image data based on the preliminary identification results, different types of materials in the bottom of the water area can be efficiently identified, especially using texture features to distinguish different sediments or biological substances, thereby providing quantitative support for the classification and identification of bottom materials; by combining laser scanning data to identify the ups and downs of the bottom of the water area, the structural distribution of the bottom sediments can be accurately inferred, which is helpful to depict the distribution pattern of sediments in the water area, especially for waters with complex terrain, it can improve the spatial resolution of the measurement and ensure that the depth measurement strategy is more in line with the actual bottom structure requirements.

[0012] In one example, the present application may be further configured as follows: based on the preliminary recognition result, the texture features of the bottom material in the underwater visual image data are extracted using an image processing algorithm to generate the bottom material type of the water area, including: Based on the preliminary recognition result, in the underwater visual image data, a gray level co-occurrence matrix is ​​used to extract texture features of the underlying material; Based on the texture features, the K nearest neighbor algorithm is used to classify the bottom material of the water area, and the bottom material type of the water area is identified.

[0013] By adopting the above technical scheme, by using the gray-level co-occurrence matrix to extract the texture features of the bottom material in the underwater visual image data, it is possible to effectively extract subtle texture information in the image, reveal the unique visual features of different bottom materials, and provide high-precision image feature data for material classification, thereby ensuring the accuracy and reliability of classification; by using the K-nearest neighbor algorithm to classify the bottom materials in the water area based on the extracted texture features, the bottom material type can be efficiently and automatically identified, thereby quickly and accurately determining the type and distribution of sediments in different areas, improving the automation level of classification processing, and providing reliable material distribution information for the dynamic adjustment of depth measurement strategies.

[0014] In one example, the present application may be further configured as follows: the flow trend of the bottom sediment of the water area is predicted by using the real-time water flow and sediment flow model, and the water flow prediction result is generated, including: Acquire water flow information and physical properties of bottom sediments in the water area, and construct the water flow and sediment model based on the water flow information and physical properties, wherein the water flow information includes real-time water flow speed, direction and environmental parameter data of the water area; Based on the real-time collected water flow data and the preliminary identification results, dynamic calculation is performed to predict the flow trend of the bottom sediment in the water area and generate calculation results; The water flow prediction result is generated according to the calculation result.

[0015] By adopting the above technical solution, by obtaining water flow information and the physical characteristics of the bottom sediments, and building a water flow and sediment model based on this information, a comprehensive understanding of the water environment can be achieved, providing a scientific basis for subsequent sediment flow trend prediction, and ensuring that the model has a high degree of accuracy and practicality; by performing dynamic calculations based on real-time water flow data and preliminary identification results, the flow trend of the bottom sediments can be predicted in real time, so that the system can respond quickly according to the changing water flow conditions, ensuring the timeliness and accuracy of the prediction results; through the generated calculation results, the water flow prediction results can be obtained, which provides a basis for further adjustment of the depth measurement strategy, so that the measurement work can adapt to the dynamic changes of the water area and improve the measurement accuracy and efficiency.

[0016] In one example, the present application may be further configured as follows: dynamically adjusting the depth measurement strategy based on the bottom feature recognition result and the water flow prediction result includes: Generating a depth measurement priority corresponding to the water area according to the bottom feature recognition result; Based on the water flow prediction result, dynamically adjust the depth measurement frequency of the water area measurement area; The measurement path and measurement depth of the water area are set according to the bottom feature recognition result and the water flow prediction result.

[0017] By adopting the above technical solution, by generating depth measurement priorities according to the underlying feature recognition results, it is possible to ensure that the most important or most changing areas are measured first, thereby improving measurement efficiency and accuracy and avoiding waste of resources; by dynamically adjusting the depth measurement frequency of the measurement area based on the water flow prediction results, the measurement frequency can be optimized in real time according to water flow changes, ensuring that the measurement process can adapt to the dynamic changes of the water environment and improving the adaptability and real-time performance of the measurement; by combining the underlying feature recognition results with the water flow prediction results to set the measurement path and measurement depth, the measurement area and path can be accurately selected to avoid invalid measurements and improve the efficiency and accuracy of the overall measurement work.

[0018] In one example, the present application may be further configured as follows: optimizing the measurement data in real time by using a data correction algorithm includes: Performing noise suppression on the measurement data based on a Kalman filter algorithm; In combination with the bottom feature recognition result, the measurement data is smoothed using the least square method; Based on the water flow prediction result, the measurement data of different time and space nodes are interpolated by using a spatiotemporal data interpolation algorithm.

[0019] By adopting the above technical solution, by suppressing the noise of the measurement data based on the Kalman filtering algorithm, the noise interference in the measurement data can be effectively reduced, the accuracy and reliability of the data can be improved, and the accuracy of the subsequent processing and analysis results can be ensured; by combining the underlying feature recognition results and using the least squares method to smooth the measurement data, abnormal fluctuations in the measurement data can be eliminated, making the data smoother and more stable, thereby improving the availability and accuracy of the measurement results; by using the spatiotemporal data interpolation algorithm based on the water flow prediction results to interpolate the measurement data of different time and space nodes, it is possible to fill the gaps in the measurement data, provide more comprehensive and continuous depth information, and enhance the consistency and accuracy of the measurement results in the spatiotemporal dimensions.

[0020] The second object of the invention is achieved by the following technical solutions: A system for measuring the excavation depth of a trailing suction hopper dredger, comprising: A data acquisition module is used to acquire multimodal sensor data of the bottom of the water area, wherein the multimodal sensor data includes multibeam sonar data, laser scanning data and underwater visual image data; An identification module, used for dynamically identifying the multimodal sensor data and generating an identification result of the bottom layer features of the water area; A prediction module, for predicting the flow trend of bottom sediments in the water area by using a real-time water flow and sediment flow model, and generating a water flow prediction result; The adjustment module is used to dynamically adjust the depth measurement strategy based on the bottom feature recognition result and the water flow prediction result, and during the measurement process, optimize the measurement data in real time through the data correction algorithm to generate the depth measurement result.

[0021] By adopting the above technical solution, by acquiring multimodal sensor data of the bottom of the water area, including multi-beam sonar, laser scanning and underwater visual image data, the topographic information of the bottom of the water area can be comprehensively and accurately collected, covering a variety of physical characteristics, such as water layer depth, bottom morphology and bottom characteristics, thereby providing multi-dimensional data support for subsequent depth measurement; by dynamically identifying multimodal sensor data, various characteristics of the bottom of the water area can be analyzed in real time, the accuracy of bottom identification is improved, and the necessary basis is provided for adjusting the measurement strategy according to different water environments; by using real-time water flow and sediment flow models, the flow trend of the bottom sediment is predicted , it can simulate the changing laws of water flow and sediment flow, grasp the dynamic state of sediment in advance, and thus provide a scientific basis for the dynamic adjustment of depth measurement; by dynamically adjusting the measurement strategy based on the underlying feature recognition results and water flow prediction results, the measurement path, frequency and depth can be adjusted in real time according to the actual changes in water flow and sediment, thereby optimizing the measurement efficiency and accuracy, making the measurement process more flexible and intelligent; by using data correction algorithms to optimize measurement data in real time during the measurement process, it can reduce noise and errors in sensor data, further improve the accuracy and reliability of measurement results, and ensure that the final depth measurement results have higher accuracy.

[0022] In summary, this application includes the following beneficial technical effects: 1. By acquiring multimodal sensor data of the bottom of the water area, including multi-beam sonar, laser scanning and underwater visual image data, the topographic information of the bottom of the water area can be collected comprehensively and accurately, covering a variety of physical characteristics, such as water layer depth, bottom morphology and bottom characteristics, thereby providing multi-dimensional data support for subsequent depth measurement; by dynamically identifying multimodal sensor data, various characteristics of the bottom of the water area can be analyzed in real time, improving the accuracy of bottom identification, and providing the necessary basis for adjusting measurement strategies according to different water environments; 2. By using the real-time water flow and sediment flow model to predict the flow trend of the bottom sediment, the changing laws of water flow and sediment flow can be simulated, and the dynamic state of the sediment can be grasped in advance, thereby providing a scientific basis for the dynamic adjustment of the depth measurement; by dynamically adjusting the measurement strategy based on the bottom feature recognition results and water flow prediction results, the measurement path, frequency and depth can be adjusted in real time according to the actual changes in water flow and sediment, thereby optimizing the measurement efficiency and accuracy, making the measurement process more flexible and intelligent; by using the data correction algorithm to optimize the measurement data in real time during the measurement process, the noise and error in the sensor data can be reduced, and the accuracy and reliability of the measurement results can be further improved, ensuring that the final depth measurement results have higher accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a method for measuring the excavation depth of a trailing suction dredger in one embodiment of the present application; Figure 2 This is a flowchart for implementing step S10 in a method for measuring the excavation depth of a trailing suction dredger in one embodiment of the present application; Figure 3 It is a flowchart for implementing step S20 in a method for measuring the excavation depth of a trailing suction dredger in one embodiment of the present application; Figure 4 It is a flowchart for implementing step S22 in a method for measuring the excavation depth of a trailing suction dredger in one embodiment of the present application; Figure 5 It is a flowchart for implementing step S30 in a method for measuring the excavation depth of a trailing suction dredger in one embodiment of the present application; Figure 6 It is a flowchart for implementing step S40 in a method for measuring the excavation depth of a trailing suction dredger in one embodiment of the present application; Figure 7 This is a flowchart of implementing step S40 in a method for measuring the excavation depth of a trailing suction dredger in one embodiment of the present application; Figure 8 This is a principle block diagram of a system for measuring the excavation depth of a trailing suction dredger in one embodiment of the present application; DETAILED DESCRIPTION The present application is further described in detail below in conjunction with the accompanying drawings.

[0024] In one embodiment, if Figure 1 As shown, the present application discloses a method for measuring the excavation depth of a trailing suction dredger, which specifically includes the following steps: S10: Acquire multimodal sensor data of the bottom of the water area, where the multimodal sensor data includes multi-beam sonar data, laser scanning data, and underwater visual image data.

[0025] Specifically, first, the multi-beam sonar sensor is used to measure the bottom of the water area with sound waves. The sonar sensor sends multiple sound beams and receives the reflected waves returned by the bottom water area. By using the sound wave reflection data at different angles, the depth information of multiple water layers at the bottom of the water area can be obtained. For example, if a water area with a multi-layer structure is measured, the time difference of the reflected sound wave signal can accurately distinguish the depth of each water layer and draw an elevation map of the bottom of the water area. At the same time, the laser scanning sensor scans the three-dimensional geometric shape of the bottom by emitting a laser beam and calculating the return time of the light wave, so that detailed three-dimensional morphological data of the bottom can be obtained, such as gullies and bulges at the bottom. For example, in turbid water bodies, laser scanning can penetrate a certain depth of water layers to form a clear bottom shape map, especially in areas with sediments or obstacles, laser scanning data can accurately describe the complex terrain of the bottom. In addition, the image data obtained by the underwater visual image acquisition system can provide texture information of the bottom sediments. The underwater camera captures the details of the bottom material through high-definition images, such as the shape and distribution of materials such as sand, mud, and stones. These image information can provide important basis for subsequent material type identification and analysis. For example, different types of sediments can be identified through image processing algorithms, and their specific physical properties can be determined.

[0026] S20: Dynamically identify the multimodal sensor data to generate bottom-level feature recognition results of the water area.

[0027] Specifically, after acquiring the data from the multimodal sensor, a data fusion algorithm is used to conduct a comprehensive analysis of the multi-beam sonar, laser scanning data and underwater visual image data to identify the different characteristics of the bottom sediments, such as thickness, density, texture, etc. These data are converted into feature recognition results of the bottom layer of the water area through algorithm processing. The recognition results can indicate the type and distribution of the bottom sediments of the water area. For example, the type of bottom material can be determined by analyzing the texture features in the underwater image through an image processing algorithm, or the structure and characteristics of the bottom material can be inferred by the sediment thickness and density measured by multi-beam sonar data, thereby providing data support for subsequent sediment analysis and flow trend prediction.

[0028] S30: Using the real-time water flow and sediment flow model, the flow trend of the bottom sediment in the water area is predicted to generate a water flow prediction result.

[0029] Specifically, after obtaining real-time water flow information and water area environmental parameters, the movement trend of bottom sediments can be predicted by constructing a water flow and sediment flow model. First, the water flow and sediment model is input by real-time monitoring of the speed and direction of the water flow and the environmental parameters of the water area (such as temperature, salinity, flow rate, etc.). For example, if the water flow speed is fast and the flow direction is relatively fixed in a certain water area, combined with the physical properties of sediment particles, it can be predicted that the bottom sediments will be eroded or transported in this area; while in areas with slower water flow, sediments may be deposited. In addition, the model can be calibrated through field monitoring and historical data, and the model parameters can be updated in real time to cope with the impact of water flow changes on the flow trend of bottom sediments. Based on this model, dynamic calculations can predict the flow path and deposition trend of sediments in different regions. For example, it is predicted that sediment in a certain area will migrate downstream with the water flow, or that deposition may occur in a specific depth area of ​​a certain water area.

[0030] S40: Based on the bottom feature recognition results and water flow prediction results, the depth measurement strategy is dynamically adjusted, and during the measurement process, the measurement data is optimized in real time through the data correction algorithm to generate the depth measurement results.

[0031] Specifically, after obtaining the bottom feature recognition results and water flow prediction results, the measurement strategy can be dynamically adjusted based on this information. For example, in areas where the sediments are relatively stable and the water flow is slow, the measurement frequency can be reduced because the bottom changes are small; while in areas where the water flow is strong or the sediment thickness changes greatly, the measurement frequency needs to be increased to capture subtle changes. During the measurement process, the measurement data is optimized by using a data correction algorithm. Common methods such as the Kalman filter algorithm are used to suppress noise, the least squares method can be used to smooth the measurement data, and the spatiotemporal interpolation algorithm can fill in the data gaps between different time and space nodes, thereby improving the accuracy of the measurement results and generating more accurate depth measurement results.

[0032] By adopting the above technical solution, by acquiring multimodal sensor data of the bottom of the water area, including multi-beam sonar, laser scanning and underwater visual image data, the topographic information of the bottom of the water area can be comprehensively and accurately collected, covering a variety of physical characteristics, such as water layer depth, bottom morphology and bottom characteristics, thereby providing multi-dimensional data support for subsequent depth measurement; by dynamically identifying multimodal sensor data, various characteristics of the bottom of the water area can be analyzed in real time, the accuracy of bottom identification is improved, and the necessary basis is provided for adjusting the measurement strategy according to different water environments; by using real-time water flow and sediment flow models, the flow trend of the bottom sediment is predicted , it can simulate the changing laws of water flow and sediment flow, grasp the dynamic state of sediment in advance, and thus provide a scientific basis for the dynamic adjustment of depth measurement; by dynamically adjusting the measurement strategy based on the underlying feature recognition results and water flow prediction results, the measurement path, frequency and depth can be adjusted in real time according to the actual changes in water flow and sediment, thereby optimizing the measurement efficiency and accuracy, making the measurement process more flexible and intelligent; by using data correction algorithms to optimize measurement data in real time during the measurement process, it can reduce noise and errors in sensor data, further improve the accuracy and reliability of measurement results, and ensure that the final depth measurement results have higher accuracy.

[0033] In one embodiment, if Figure 2 As shown, in step S10, the multimodal sensor data of the bottom of the water area is obtained, which specifically includes: S11: Use a multi-beam sonar sensor to measure the depth of multiple water layers at the bottom of the water area and collect reflected wave data to generate multi-beam sonar data.

[0034] Specifically, a multi-beam sonar sensor is used to transmit multiple sound beams to the bottom of the water area and receive sound wave signals reflected by water layers of different depths. The reflected wave data of each sound beam can provide different depth information of the bottom of the water. Through these reflected wave data, the depth of multiple water layers can be calculated. For example, in deep water areas, if there are many water layers, the sonar equipment can use the reflected signal of each beam to measure the depth changes of multiple layers, and calculate the distance of each water layer based on the return time difference, and use these data to generate a bottom depth map of the water area. The advantage of multi-beam sonar technology is that it can cover a larger range of water areas at the same time, can obtain bottom layer data more quickly than single-beam sonar, and can accurately draw the contour map of the bottom terrain. The reflected wave data is processed through time domain analysis to form specific depth information.

[0035] S12: Scan and collect three-dimensional geometric data of the bottom layer of the water area through a laser scanning sensor to generate laser scanning data.

[0036] Specifically, the optical scanning sensor measures the bottom geometry by emitting a laser beam and receiving the laser signal reflected from the bottom of the water area. The laser scanning device can obtain three-dimensional data of the bottom of the water area by constantly changing the scanning angle. For example, if there are obvious undulations or structures at the bottom of the water area, laser scanning can clearly capture these changes and record the elevation data of the bottom. In specific operations, the laser beam will be emitted downward, passing through the surface of objects in the water surface and underwater environment and returning. By measuring the time the laser returns, the system can accurately calculate the distance of the underlying objects, and generate a detailed three-dimensional geometric data map through multiple scans. This map can reflect the terrain features such as ups and downs, gullies, and protrusions at the bottom of the water area, and then help determine the distribution of the bottom sediments. For example, the sediments are thicker in some places, and depressions may be formed in some places due to water erosion.

[0037] S13: Collect image data of bottom materials in the water area through the underwater visual image acquisition system to generate underwater visual image data.

[0038] Specifically, the underwater visual image acquisition system uses an underwater high-definition camera to capture images of the bottom of the water area. The camera is installed on an underwater device and faces the bottom of the water to shoot. The system captures image data of underwater materials through optical sensors. These image data can show the physical characteristics of the bottom sediments, such as sand, stones, and mud. For example, in clearer waters, high-definition underwater cameras can clearly show the distribution and material of objects on the bottom of the water. The underwater image acquisition system can provide high-definition images and even provide high-resolution material texture information in some areas, such as the size and shape of sediment particles. If there are obvious sediment types in the image (such as large rocks or clay layers), it can help identify the material composition and sedimentary characteristics of the bottom.

[0039] In one embodiment, if Figure 3 As shown, in step S20, the multimodal sensor data is dynamically identified to generate the bottom feature identification result of the water area, which specifically includes: S21: Use multibeam sonar data to calculate the thickness and density of bottom sediments in the water area and generate preliminary identification results.

[0040] Specifically, the depth information of multiple water layers at the bottom of the water area can be calculated through the reflected wave data in the multi-beam sonar data. Combined with the return signal detected by the sonar, the system calculates the depth of each layer of sediment according to the propagation time and wave speed of the reflected wave, and then determines the thickness of the sediment. Then, the density of the sediment is calculated using the intensity reflection value of the sonar data. The density can be calculated by establishing an empirical model based on the reflection intensity and the known physical properties of the water body. For example, in areas with denser sediments, the intensity of the reflected wave is higher, while in areas with loose sediments, the intensity of the reflected wave is lower. In this way, the sediment density in different areas can be inferred. Using these calculation results, a preliminary identification result is formed to reflect the thickness and density distribution of the bottom sediments in the water area.

[0041] S22: Based on the preliminary recognition results, the texture features of the bottom material in the underwater visual image data are extracted using an image processing algorithm to generate the bottom material type of the water area.

[0042] Specifically, after obtaining the preliminary recognition results, the texture of the bottom material in the underwater visual image data can be extracted through image processing algorithms. First, by analyzing the images captured by the underwater camera, image analysis techniques such as the grayscale co-occurrence matrix algorithm are used to extract the texture features of the bottom material, such as granularity, uniformity, and contrast, which can reflect the physical properties of the material. For example, if a relatively smooth texture appears in the image, it may indicate that the bottom layer is fine sand or clay, while a relatively rough texture may indicate that the bottom layer is rock or large-grained sediment. Then, a classification algorithm based on these texture features, such as the K nearest neighbor algorithm or support vector machine, is used to classify different texture features and identify the sediment type of the bottom layer. For example, different materials such as sand layers, mud layers, and stones under water can be identified through image processing, and a material type map of the bottom layer of the water area can be generated based on these recognition results.

[0043] S23: Combined with laser scanning data, identify the fluctuations of the bottom layer of the water area and infer the structural distribution of the bottom sediments that generated the water area.

[0044] Specifically, by analyzing the laser scanning data, the undulations of the bottom layer can be identified, such as the bumps, gullies or protrusions on the bottom. By performing differential calculations on the elevation information of the laser scanning data, the shape and change trend of the bottom layer can be obtained, thereby identifying the topographic undulations of the bottom layer of the water area. For example, if there is a more obvious depression in a certain area, this may indicate that the sediments are thin or the sediments are transported due to strong water flow. Further, combined with the sediment thickness and density information of the water area, the structural distribution of the sediments in the area can be inferred, such as which areas have denser sediments and which areas have looser sediments. It is even possible to infer the reasons for the formation of sediments, such as the influence of factors such as water flow velocity and sedimentation time. Ultimately, through these inferences, a structural distribution map of the bottom sediments of the water area can be obtained to assist in the subsequent sediment flow prediction and optimization of depth measurement strategies.

[0045] In one embodiment, if Figure 4 As shown, in step S22, based on the preliminary recognition result, the texture features of the bottom material in the underwater visual image data are extracted using an image processing algorithm to generate the bottom material type of the water area, specifically including: S221: Based on the preliminary recognition results, the gray level co-occurrence matrix is ​​used to extract the texture features of the underlying material in the underwater visual image data.

[0046] Specifically, based on the preliminary recognition results, the texture features of the underlying material in the underwater visual image are extracted through the image processing algorithm. In this process, the grayscale co-occurrence matrix is ​​used as the core algorithm tool. First, each frame of the underwater image is converted into a grayscale image, and each pixel value in the image is mapped to a grayscale level. Then, a fixed-size window is defined and the window is slid in the image to calculate the co-occurrence matrix of the grayscale value pairs in each window. The elements of the co-occurrence matrix represent the joint frequency of the grayscale values ​​of two pixels at a specific spatial distance. In this way, the texture features in the image, such as contrast, uniformity, energy, correlation, etc., can be extracted. These features can reflect the surface morphology and structure of the underlying material. For example, if the underlying material is sand, the texture of the image will show a more uniform distribution, and the contrast in the grayscale co-occurrence matrix will be lower; if the underlying material is rock or rough material, the texture will show greater changes, and the contrast and energy of the grayscale co-occurrence matrix will be higher. Finally, by extracting these texture features, the surface characteristics of the underlying material are obtained.

[0047] S222: Based on the texture features, the K nearest neighbor algorithm is used to classify the bottom material of the water area, and the bottom material type of the water area is identified.

[0048] Specifically, the texture features extracted in the previous step are used to classify the bottom materials of the water area through the K nearest neighbor algorithm. First, the texture features extracted by the gray level co-occurrence matrix are used as input data, and a training set is constructed in combination with pre-labeled sample data, such as the known types of bottom materials, such as sand, mud, rock, etc. Then, for each image data to be classified, the Euclidean distance between the sample to be classified and the sample in the training set is calculated, and the K samples with the smallest distance are selected, and the categories to which these neighbor samples belong are used for voting to determine the category of the sample to be classified. For example, if the texture features of an image are most similar to the sand sample in the training set, and most of the K neighbors are sand categories, then the image is judged to be sand. In this way, the material type of the bottom of the water area can be accurately identified, such as distinguishing different sediments such as mud, sand, and rock.

[0049] In one embodiment, if Figure 5 As shown, in step S30, the flow trend of the bottom sediment in the water area is predicted by using the real-time water flow and sediment flow model to generate a water flow prediction result, which specifically includes: S31: Obtain water flow information and physical properties of bottom sediments in the water area, and build a water flow and sediment model based on the water flow information and physical properties. The water flow information includes real-time water flow speed, direction and environmental parameter data of the water area.

[0050] Specifically, it is necessary to first obtain the water flow information in the water area in real time through water flow sensors, flow meters, environmental monitoring devices and other equipment, including environmental parameters such as water flow speed, direction, temperature, salinity, fluid viscosity, etc. This information accurately reflects the dynamic characteristics of the water flow by measuring the flow velocity and direction of the water area. At the same time, environmental parameter data helps to judge the flow state of the water body and its impact on the sediment. For example, lower temperature and higher viscosity may reduce the fluidity of the sediment. The acquired data will be used as input, combined with the physical properties of the bottom sediments, such as particle size, density, shape and hardness, to construct a mathematical model of water flow and sediment flow. Commonly used models include fluid dynamics models and sediment transport equations. When constructing the model, the classic Navier-Stokes equation can be used to describe the motion state of the water flow, while taking into account the sedimentation, migration and aggregation behavior of the sediment, so as to establish a mathematical model that can reflect the interaction between water flow and sediment, and help predict the motion state of the bottom sediments in the water area under different flow velocities, flow directions and environmental conditions.

[0051] S32: Based on the real-time collected water flow data and preliminary identification results, dynamic calculations are performed to predict the flow trend of the bottom sediments in the water area and generate calculation results.

[0052] Specifically, first, the real-time water flow data and preliminary identification results are used as input parameters, such as the distribution and characteristics of materials such as soil, sand, and gravel, and are substituted into the constructed water flow and sediment model, and calculated by numerical simulation methods. During the calculation process, the water flow parameters are dynamically updated considering the instability of the water flow, and the water flow data is corrected in real time using the time series analysis method to adapt to the changes in water flow speed and direction. The flow trend of sediments is predicted by simulating the driving force, dragging force, sedimentation force and other forces of water flow on different sediments. For example, in the case of fast water flow, smaller particles may be carried away, while larger particles may settle to the bottom of the water; in an environment with slow water flow, the mobility of particles is low, and more sediments will gather at the bottom. By predicting these flow trends, the movement trajectory, flow direction and accumulation of bottom sediments can be generated.

[0053] S33: Generate water flow prediction results based on the calculation results.

[0054] Specifically, by further processing the calculation results, combining historical data and real-time monitored water flow conditions, and using time series analysis or regression analysis and other methods, we can predict future water flow conditions. For example, we can use the ARIMA model to predict water flow changes, taking into account short-term fluctuations and long-term trends in water flow, and obtain predicted values ​​of water flow speed and direction in the next few hours, days, or even months. Ultimately, based on these water flow prediction results, accurate flow rate and direction forecasts can be obtained.

[0055] In one embodiment, if Figure 6 As shown, in step S40, the depth measurement strategy is dynamically adjusted based on the bottom feature recognition result and the water flow prediction result, specifically including: S41: Generate depth measurement priorities corresponding to the water area according to the bottom feature recognition results.

[0056] Specifically, after obtaining the bottom feature recognition results, the measurement priority is determined by analyzing the bottom features of different areas and combining the overall situation of the water area. For example, in different areas of the bottom of the water area, the sediments in some areas are more complex, which may have a greater impact on the accuracy of water depth measurement, so the measurement priority of these areas is higher; while in some areas where the sediments are more evenly distributed or more stable, the measurement priority is relatively low. In specific operations, a weight value can be assigned to each measurement area. The weight value is calculated based on the bottom feature recognition results, such as the particle size, distribution density, and fluctuation of the sediments. These factors directly affect the measurement accuracy and frequency. For example, the bottom sand area may require more frequent depth measurements due to the rapid changes in water flow, while the soil or rock area is relatively stable, and the measurement frequency can be appropriately reduced. During the calculation, the weighted average method is used to comprehensively consider the complexity of the bottom features, the physical properties of the sediments, and the flow trend to obtain the measurement priority of each area.

[0057] S42: Based on the water flow prediction results, dynamically adjust the depth measurement frequency of the water area measurement area.

[0058] Specifically, the water flow prediction results are used to dynamically adjust the measurement frequency according to the flow velocity, flow direction and predicted water flow change trend in different water areas. For example, when it is predicted that the water flow velocity in a certain area will change sharply or the water flow will tend to be stable within a certain period of time, the measurement frequency will be adjusted accordingly. In areas with faster water flow, the bottom sediment may change rapidly. At this time, the measurement frequency needs to be increased to ensure the accuracy and timeliness of the measurement data; while in areas with slower or more stable water flow, the distribution of sediments changes relatively little, and the measurement frequency can be appropriately reduced. By matching the water flow prediction results with the existing measurement data, the water flow intensity of each area in different time periods is calculated. This data is combined with an adaptive measurement frequency model to dynamically adjust the allocation of measurement tasks according to the water flow velocity and direction. For example, the real-time water flow velocity in a certain area is 2.0m / s, and according to the water flow prediction model, it is calculated that the water flow in this area will accelerate to 3.0m / s in the next 30 minutes. According to this trend, the measurement frequency will be increased from once every 20 minutes to once every 10 minutes, especially in areas with strong water flow, to ensure that the dynamic changes of sediments with water flow can be tracked. In areas with relatively stable water flow, for example, when the water flow velocity is 0.5m / s and it is expected that there will be no significant changes in the next 30 minutes, the measurement frequency can be maintained at once every 30 minutes.

[0059] S43: According to the bottom feature recognition result and the water flow prediction result, the measurement path and measurement depth of the water area are set.

[0060] Specifically, the optimal measurement path and measurement depth are designed by combining the bottom feature recognition results and the water flow prediction results. First, based on the bottom feature recognition results, the areas with more complex or more variable sediments are identified as the key areas of the measurement path. For example, in a specific area, the thickness of the bottom sediment is 4 meters and the water flow speed is 1.2m / s. It is expected that the water flow will gradually accelerate to 2.0m / s in the next hour. In order to ensure the accuracy of the measurement, the measurement path can be set to a measurement point every 50 meters; secondly, combined with the water flow prediction results, the water flow dynamics in these areas are judged to ensure that the measurement path can cover areas with large water flow changes to avoid missing important measurement data. For example, in areas with faster water flow, a shallower measurement depth can be selected for more precise depth measurement, while in areas with slower water flow, a deeper measurement path can be used to improve the accuracy of the data. In actual operation, the setting of the measurement path can be based on the "shortest path" principle, combined with the water flow prediction model, to calculate the optimal measurement route for each area, and to determine the optimal measurement depth of each measurement path through an algorithm.

[0061] Furthermore, the measurement path and measurement depth of the water area will directly affect the frequency of depth measurement, and thus affect the accuracy and timeliness of the measurement data. The selection of the measurement path and the setting of the measurement depth will, to a certain extent, determine the area that needs to be measured and the accuracy requirements of the measurement. These factors are closely related to the dynamic changes of the water flow, and thus determine the measurement frequency that needs to be adjusted. Assuming that the water flow prediction results in a certain area show higher flow rates and stronger turbulence, the measurement path will select multiple measurement points that pass through these high-flow areas, and the depth measurement of each measurement point will be more precise and frequent. If the water flow in the area where the measurement path passes is slower and the bottom characteristics are more uniform, the path selection can be relatively loose, the measurement depth will be fixed, and the measurement frequency will be reduced.

[0062] In one embodiment, if Figure 7 As shown, in step S40, the measurement data is optimized in real time by using a data correction algorithm, which specifically includes: S44: Suppressing noise of the measurement data based on the Kalman filter algorithm.

[0063] Specifically, when the Kalman filter algorithm is used to suppress noise in the measurement data, the signal of the measurement data is first modeled. Assuming that the measurement data contains a certain amount of noise, the Kalman filter algorithm can estimate the state of the system through two steps of prediction and correction, thereby effectively reducing the impact of noise on the measurement data. For example, the measured water depth data is 6.4 meters, 6.6 meters, 6.5 meters, 6.7 meters, etc. at each sampling. In the absence of noise suppression, the data will show large fluctuations. Through Kalman filtering, based on the previous prediction value and the current measurement value, the filter can estimate a more accurate water depth value, such as 6.55 meters, and the error is reduced to within 0.05 meters.

[0064] S45: Combining the underlying feature recognition results, the measurement data is smoothed using the least squares method.

[0065] Specifically, when using the least squares method to smooth the measured data in combination with the results of bottom-level feature recognition, it is first necessary to combine the results of bottom-level feature recognition. For example, assuming that through the multi-beam sonar measurement results, it is known that the bottom sediments in the area are relatively uniform or the bottom has large undulations, in this case, the least squares method can be applied to smooth the data. By constructing a mathematical model to fit the measured data, the error between the data and the fitting curve is minimized. Assuming that the measured water depth data is 6.1 meters, 6.5 meters, 6.8 meters, and 6.6 meters, and it is known that the bottom sediments in the area are relatively uniform, then through the linear fitting of the least squares method, the algorithm will fit a curve or straight line based on these measurement points and calculate the optimal smoothing value. For example, the smoothed water depth value is 6.4 meters. This eliminates the fluctuations in the original data caused by noise or measurement errors, and obtains a water depth value that is closer to the actual situation.

[0066] S46: Based on the water flow prediction result, the measurement data of different time and space nodes are interpolated by using the spatiotemporal data interpolation algorithm.

[0067] Specifically, based on the water flow prediction results, when the measurement data of different time and space nodes are interpolated by the spatiotemporal data interpolation algorithm, the water flow prediction results are first used to obtain the water flow speed, direction and environmental parameters that may affect the water depth change at different time points and different spatial positions. For example, assuming that the water flow prediction results of a certain area show that at time T0, the water depth measurement value at a certain location is 6.3 meters and the water flow speed is 1.0m / s, and at time T1, the water flow speed increases to 2.0m / s. The interpolation algorithm can infer the water depth value of the location at time T1 based on the measurement data and water flow changes at these two time points, such as 6.5 meters. At the same time, the interpolation algorithm can also combine the spatial changes to infer the water depth value between adjacent measurement points, so that smoother and continuous water depth data can be generated.

[0068] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0069] In one embodiment, a system for measuring the excavation depth of a trailing suction hopper dredger is provided, and the system for measuring the excavation depth of a trailing suction hopper dredger corresponds one-to-one to the method for measuring the excavation depth of a trailing suction hopper dredger in the above embodiment. Figure 8 As shown, the dredging depth measurement system of a trailing suction hopper dredger includes a data acquisition module, an identification module, a prediction module and an adjustment module. The detailed description of each functional module is as follows: The data acquisition module is used to acquire multimodal sensor data of the bottom of the water area. The multimodal sensor data includes multi-beam sonar data, laser scanning data and underwater visual image data; The recognition module is used to dynamically recognize multimodal sensor data and generate bottom-level feature recognition results of the water area; The prediction module is used to predict the flow trend of bottom sediments in the water area using the real-time water flow and sediment flow model and generate water flow prediction results; The adjustment module is used to dynamically adjust the depth measurement strategy based on the underlying feature recognition results and water flow prediction results, and during the measurement process, optimize the measurement data in real time through the data correction algorithm to generate the depth measurement results.

[0070] Optionally, the data acquisition module includes: A reflection submodule is used to measure the depth of multiple water layers at the bottom of the water area using a multi-beam sonar sensor and collect reflection wave data to generate multi-beam sonar data; The scanning submodule is used to scan and collect three-dimensional geometric data of the bottom of the water area through a laser scanning sensor to generate laser scanning data; The image acquisition submodule is used to collect image data of the bottom material of the water area through the underwater visual image acquisition system to generate underwater visual image data.

[0071] Optionally, the identification module includes: The thickness calculation submodule is used to calculate the thickness and density of the bottom sediments in the water area using multi-beam sonar data and generate preliminary identification results; The image processing submodule is used to extract the texture features of the bottom material in the underwater visual image data based on the preliminary recognition results by using the image processing algorithm to generate the bottom material type of the water area; The structural analysis submodule is used to combine laser scanning data to identify the fluctuations of the bottom layer of the water area and infer the structural distribution of the bottom sediments of the generated water area.

[0072] Optionally, the image processing submodule includes: Extracting texture units for extracting texture features of underlying materials using a gray-level co-occurrence matrix in underwater visual image data based on preliminary recognition results; The classification unit is used to classify the bottom material of the water area based on texture features using the K nearest neighbor algorithm to identify the bottom material type of the water area.

[0073] Optionally, the prediction module includes: Construct submodules to obtain water flow information and physical properties of bottom sediments in the water area, and construct water flow and sediment models based on the water flow information and physical properties. The water flow information includes real-time water flow speed, direction and environmental parameter data of the water area; The dynamic calculation submodule is used to perform dynamic calculations based on the real-time collected water flow data and preliminary identification results, predict the flow trend of the bottom sediments in the water area, and generate calculation results; The prediction submodule is used to generate water flow prediction results based on the calculation results.

[0074] Optionally, the adjustment module includes: A priority determination submodule is used to generate depth measurement priorities corresponding to the water area according to the bottom feature recognition results; The frequency adjustment submodule is used to dynamically adjust the depth measurement frequency of the water area measurement area based on the water flow prediction results; The path adjustment submodule is used to set the measurement path and measurement depth of the water area according to the bottom feature recognition results and water flow prediction results; A noise suppression submodule, used for suppressing noise of measurement data based on a Kalman filter algorithm; The smoothing submodule is used to combine the underlying feature recognition results and use the least square method to smooth the measurement data; The interpolation submodule is used to interpolate the measurement data of different time and space nodes based on the water flow prediction results through the spatiotemporal data interpolation algorithm.

[0075] The specific definition of a system for measuring the excavation depth of a trailing suction hopper dredger can be found in the above definition of a method for measuring the excavation depth of a trailing suction hopper dredger, which will not be repeated here. Each module in the above-mentioned system for measuring the excavation depth of a trailing suction hopper dredger can be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0076] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0077] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for measuring the excavation depth of a trailing suction hopper dredger, characterized in that: The method for measuring the excavation depth of a trailing suction dredger comprises: Acquiring multimodal sensor data of the bottom of the water area, wherein the multimodal sensor data includes multibeam sonar data, laser scanning data, and underwater visual image data; Dynamically identifying the multimodal sensor data to generate bottom-level feature identification results of the water area; Using a real-time water flow and sediment flow model, the flow trend of bottom sediments in the water area is predicted to generate a water flow prediction result; Based on the bottom feature recognition result and the water flow prediction result, the depth measurement strategy is dynamically adjusted, and during the measurement process, the measurement data is optimized in real time through a data correction algorithm to generate a depth measurement result.

2. The method for measuring the excavation depth of a trailing suction hopper dredger according to claim 1, characterized in that: The obtaining of multimodal sensor data of the bottom of the water area comprises: Using a multi-beam sonar sensor to measure the depths of multiple water layers at the bottom of the water area and collect reflected wave data to generate the multi-beam sonar data; Scanning and collecting three-dimensional geometric data of the bottom layer of the water area by a laser scanning sensor to generate the laser scanning data; The image data of the bottom material of the water area is collected by an underwater visual image collection system to generate the underwater visual image data.

3. The method for measuring the excavation depth of a trailing suction hopper dredger according to claim 1, characterized in that: The dynamically identifying the multimodal sensor data to generate the bottom-level feature identification result of the water area includes: Calculating the thickness and density of bottom sediments in the water area using the multi-beam sonar data to generate preliminary identification results; Based on the preliminary recognition result, the texture features of the bottom material in the underwater visual image data are extracted using an image processing algorithm to generate the bottom material type of the water area; Combined with the laser scanning data, the fluctuations of the bottom layer of the water area are identified, and the structural distribution of the bottom sediments of the water area is inferred.

4. The method for measuring the excavation depth of a trailing suction hopper dredger according to claim 3, characterized in that: Based on the preliminary recognition result, the texture features of the bottom material in the underwater visual image data are extracted by using an image processing algorithm to generate the bottom material type of the water area, including: Based on the preliminary recognition result, in the underwater visual image data, a gray level co-occurrence matrix is ​​used to extract texture features of the underlying material; Based on the texture features, the K nearest neighbor algorithm is used to classify the bottom material of the water area, and the bottom material type of the water area is identified.

5. The method for measuring the dredging depth of a trailing suction hopper dredger according to claim 3, characterized in that: The real-time water flow and sediment flow model is used to predict the flow trend of the bottom sediment in the water area, and the water flow prediction result is generated, including: Acquire water flow information and physical properties of bottom sediments in the water area, and construct the water flow and sediment model based on the water flow information and physical properties, wherein the water flow information includes real-time water flow speed, direction and environmental parameter data of the water area; Based on the real-time collected water flow data and the preliminary identification results, dynamic calculation is performed to predict the flow trend of the bottom sediment in the water area and generate calculation results; The water flow prediction result is generated according to the calculation result.

6. The method for measuring the excavation depth of a trailing suction hopper dredger according to claim 1, characterized in that: The dynamically adjusting the depth measurement strategy based on the bottom feature recognition result and the water flow prediction result includes: Generating a depth measurement priority corresponding to the water area according to the bottom feature recognition result; Based on the water flow prediction result, dynamically adjust the depth measurement frequency of the water area measurement area; The measurement path and measurement depth of the water area are set according to the bottom feature recognition result and the water flow prediction result.

7. The method for measuring the dredging depth of a trailing suction hopper dredger according to claim 1, characterized in that: The real-time optimization of measurement data by a data correction algorithm comprises: Performing noise suppression on the measurement data based on a Kalman filter algorithm; In combination with the bottom feature recognition result, the measurement data is smoothed using the least square method; Based on the water flow prediction result, the measurement data of different time and space nodes are interpolated by using a spatiotemporal data interpolation algorithm.

8. A system for measuring the excavation depth of a trailing suction hopper dredger, characterized in that: The excavation depth measurement system of a trailing suction dredger comprises: A data acquisition module is used to acquire multimodal sensor data of the bottom of the water area, wherein the multimodal sensor data includes multibeam sonar data, laser scanning data and underwater visual image data; An identification module, used for dynamically identifying the multimodal sensor data and generating an identification result of the bottom layer features of the water area; A prediction module, for predicting the flow trend of bottom sediments in the water area by using a real-time water flow and sediment flow model, and generating a water flow prediction result; The adjustment module is used to dynamically adjust the depth measurement strategy based on the bottom feature recognition result and the water flow prediction result, and during the measurement process, optimize the measurement data in real time through the data correction algorithm to generate the depth measurement result.

Images