A reservoir capacity estimation method and system based on an unmanned surveying ship and an airborne Lidar

Abstract

The application provides a reservoir capacity estimation method and system based on an unmanned surveying ship and an airborne Lidar, comprising: planning a first surveying path and a second surveying path; using the unmanned surveying ship to complete the measurement of underwater topographic data of the reservoir according to the first surveying path; simultaneously using the unmanned aerial vehicle with the airborne Lidar to complete the measurement of overwater and shore topographic data of the reservoir according to the second surveying path; obtaining the interval duration of the measurement time; planning a third surveying path, and again measuring the overwater and shore topographic data of the reservoir according to the third surveying path within the interval duration; pre-processing the obtained data, comprising: integrating the two measurement results to select the overwater and shore topographic data with higher quality; fusing the pre-processed underwater topographic data of the reservoir and the overwater and shore topographic data of the reservoir and constructing a three-dimensional model of the reservoir, and estimating the reservoir capacity according to the volume of the three-dimensional model of the reservoir. The application can improve the efficiency and accuracy of the estimation of the reservoir capacity.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of reservoir storage capacity measurement, in particular to a reservoir storage capacity estimation method and system based on an unmanned measurement ship and an airborne Lidar. BACKGROUND

[0002] Reservoir storage capacity measurement is an important part of water conservancy and hydropower engineering surveying and mapping and geographic information system technology, and plays a key role in the design, construction and management of reservoirs. There are mainly three traditional methods for measuring reservoir storage capacity: one is the water level-area method, which measures the water surface area at different water levels to estimate the storage capacity, which is simple to operate but has low precision; the second is the cross-section method, which measures the water depth of each cross-section by setting several cross-sections, and then calculates the total volume, which has high precision but is time-consuming and costly; the third is the remote sensing image method, which obtains two-dimensional images of water areas by satellite or airplane shooting, and then converts them into three-dimensional topographic maps using professional software, and calculates the storage capacity based on this, which has a wide coverage but poor accuracy in deep water areas and turbid water conditions. In addition, some studies have tried to use a single sensor (such as a single unmanned aerial vehicle equipped with a LiDAR device) for measurement, but due to factors such as flight height restrictions and weather conditions, the measurement results still have certain limitations.

[0003] As can be seen from the above, the existing measurement methods either have insufficient precision or are complex and costly to operate, especially in extreme weather conditions or complex topographic features of reservoir environments, the effect of traditional methods is more limited. These problems not only affect the efficiency of the measurement work, but also may lead to unreliable measurement results, thereby affecting the scientificity and effectiveness of reservoir management decisions. Therefore, it is urgent to provide an improved method for estimating reservoir storage capacity to achieve efficient and accurate estimation of reservoir storage capacity. SUMMARY

[0004] In view of the defects of the prior art, the present application provides a reservoir storage capacity estimation method and system based on an unmanned measurement ship and an airborne Lidar, which can effectively improve the efficiency and accuracy of reservoir storage capacity estimation.

[0005] The technical solution adopted by the present application is as follows:

[0006] In a first aspect, the present application provides a reservoir storage capacity estimation method based on an unmanned measurement ship and an airborne Lidar, comprising:

[0007] According to the reservoir building information and the reservoir geographic information, the first measurement path and the first measurement speed, the second measurement path and the second measurement speed are planned, so that the positions corresponding to the first measurement path and the second measurement path at the same time are greater than a preset distance apart;

[0008] The unmanned surveying ship is used to complete the measurement of the reservoir underwater topographic data according to a first measurement path; the first measurement time of the reservoir underwater topographic data measurement is calculated according to a first measurement speed; meanwhile, the unmanned aerial vehicle with the airborne Lidar is used to complete the measurement of the reservoir water and shore topographic data according to a second measurement path; the second measurement time of the reservoir water and shore topographic data measurement is calculated according to a second measurement speed; and the interval duration of the first measurement time and the second measurement time is calculated;

[0009] According to the reservoir construction information, the reservoir geographic information and the interval duration, the third measurement path and the third measurement speed are planned, so that the position corresponding to the same time of the third measurement path and the first measurement path is greater than a preset distance, and the unmanned aerial vehicle with the airborne Lidar is used to complete the measurement of the reservoir water and shore topographic data again according to the third measurement path within the interval duration;

[0010] The measured reservoir underwater topographic data and the reservoir water and shore topographic data are preprocessed, and the preprocessing includes: similarity matching of the reservoir water and shore topographic data of the same position measured twice, retaining one of the matched reservoir water and shore topographic data with similarity greater than a preset similarity, and selecting reservoir water and shore topographic data with higher data quality from the reservoir water and shore topographic data with similarity not greater than the preset similarity; and fusing the preprocessed reservoir underwater topographic data and the reservoir water and shore topographic data, constructing a reservoir three-dimensional model by using the fused data, and estimating the reservoir capacity according to the volume of the reservoir three-dimensional model.

[0011] By using the above scheme, the multi-source data of reservoir topographic measurement is obtained by combining the multi-beam sonar of the unmanned surveying ship and the airborne Lidar, the error of a single measurement method is eliminated, and the measurement accuracy is improved; considering that the measurement of the reservoir water and shore topographic data is greatly affected by the environment, the measurement is performed multiple times, and the measurement accuracy and efficiency are further improved; in the whole measurement process, no staff is needed to intervene, and the safety of the staff is guaranteed.

[0012] Preferably, the water quality sensor and the weather sensor installed on the unmanned surveying ship are used to collect the reservoir underground water quality data and weather data in real time when the unmanned surveying ship is measuring;

[0013] The preprocessing of the measured reservoir underwater topographic data and the reservoir water and shore topographic data further includes:

[0014] The first return signal received in the process of measuring the underwater topography data of the reservoir by using the unmanned surveying ship is filtered and amplified; the filtered and amplified first return signal, the underground water quality data of the reservoir and the meteorological data are input into a first quality evaluation model, and an evaluation result of whether the quality of the first return signal is qualified is output, and the first return signal with the unqualified evaluation result is removed; the first quality evaluation model adopts a neural network model, and is generated by training the first return signal received in the process of measuring by using the unmanned surveying ship, the historical underground water quality data of the reservoir and the historical meteorological data which are marked with whether the quality is qualified;

[0015] The second return signal received in the process of measuring the above-water and shore topography data of the reservoir by using the unmanned surveying ship is filtered and amplified; the filtered and amplified second return signal and the meteorological data corresponding to the time when the second return signal is received are input into a second quality evaluation model, and an evaluation result of whether the quality of the signal is qualified is output, and the second return signal with the unqualified evaluation result is removed; the second quality evaluation model adopts a neural network model, and is generated by training the second return signal received in the process of measuring by using the unmanned surveying ship, the historical underground water quality data of the reservoir and the historical meteorological data which are marked with whether the quality is qualified.

[0016] By adopting the above scheme, the influence of water quality and meteorological data on the emission and reception of pulse signals in the process of measuring the underground topography of the reservoir is considered, the quality evaluation threshold of the received signal under different water quality and meteorological data conditions is adaptively adjusted, the signal quality is more accurately judged, and the unqualified return signal is removed, so that the reliability and accuracy of the final data are ensured.

[0017] Preferably, the measurement of the above-water and shore topography data of the reservoir by using the unmanned aerial vehicle with the airborne Lidar according to the second measurement path further comprises:

[0018] In the process of measuring the above-water and shore topography data of the reservoir by using the unmanned aerial vehicle with the airborne Lidar according to the second measurement path, the image information of the reservoir in the forward direction of the second measurement path is collected in real time; the measurement topography classification in the image information of the reservoir is determined based on image analysis technology; the measurement topography classification includes water, vegetation, bare soil and buildings; the determined measurement topography classification is matched with the preset pulse parameters; each measurement topography classification is matched with the preset pulse parameters, including pulse frequency and intensity; in the process of measuring the above-water and shore topography data of the reservoir by using the unmanned aerial vehicle with the airborne Lidar according to the second measurement path, the matched pulse parameters are selected for pulse emission, and the return signal is received.

[0019] By adopting the above scheme, considering that different terrain classifications have different absorption and reflection effects on the pulse signal emitted by the airborne Lidar, the corresponding pulse parameters are automatically selected for emission according to the terrain classification result, the specificity and accuracy of signal reception are improved, and thus the accuracy of the final measurement result is ensured.

[0020] Preferably, it further comprises collecting reservoir environment data; the reservoir environment data comprises water quality data and meteorological data;

[0021] The fusion of the preprocessed reservoir underwater topographic data and the reservoir overwater and shore topographic data comprises: inputting the reservoir environment data, the preprocessed reservoir underwater topographic data and the reservoir overwater and shore topographic data into a multi-modal data fusion model, and utilizing the multi-modal data fusion model to fuse the reservoir underwater topographic data and the reservoir overwater and shore topographic data; wherein the multi-modal data fusion model adopts a neural network model, and is trained and generated by using the reservoir underwater topographic data and the reservoir overwater and shore topographic data fusion data corresponding to the calculated reservoir storage capacity data with the smallest difference between the historical and actual reservoir storage capacity data, the historical reservoir underwater topographic data, the historical reservoir overwater and shore topographic data and the historical reservoir environment data.

[0022] By adopting the above scheme, the influence of water quality and meteorological factors on the measurement result is considered, the multi-modal data fusion model is utilized to fuse the reservoir underwater topographic data and the reservoir overwater and shore topographic data, and thus the quality of data fusion is further improved, and the reliability and integrity of data are enhanced.

[0023] Preferably, it further comprises:

[0024] The reservoir important area and the reservoir non-important area are divided according to the reservoir building information and the reservoir geographic information;

[0025] For the reservoir important area, a plurality of unmanned measurement ships are adopted to record the measurement of the reservoir underwater topographic data by each unmanned measurement ship according to the first measurement path in different time periods; the preprocessing of the measured reservoir underwater topographic data and the reservoir overwater and shore topographic data further comprises: screening the highest-quality reservoir underwater topographic data from a plurality of groups of reservoir underwater topographic data corresponding to the same position in the first measurement path as the reservoir underwater topographic data of the current position.

[0026] By adopting the above scheme, the important area in the reservoir is considered, a plurality of unmanned measurement ships are adopted for synchronous measurement, the diversity and redundancy of data acquisition are increased, the risk of measurement failure caused by failure of a single device is reduced, the highest-quality reservoir underwater topographic data is screened as the data of the current position, and thus the high quality and consistency of the final data are ensured.

[0027] Preferably, the method further comprises: calculating the reservoir capacity by using numerical integration or volume rendering method.

[0028] By using the above scheme, the numerical integration or volume rendering method is selected to significantly improve the accuracy and efficiency of reservoir capacity calculation.

[0029] Preferably, in the process of measuring the underwater topographic data of the reservoir by using the unmanned surveying ship according to the first measurement path, the Kongsberg EM 2040 or Teledyne Reson T20-P type multi-beam sonar device is selected to complete the measurement; in the process of measuring the overwater and shore topographic data of the reservoir by using the unmanned aerial vehicle with the airborne Lidar according to the second measurement path, the Riegl VUX-1HA LiDAR sensor is selected to complete the measurement.

[0030] By using the above scheme, the multi-beam sonar device and the radar with high measurement accuracy are selected to complete the fine mapping of the reservoir topographic data and the overwater and shore topographic data with high precision, effectively reducing the measurement error and improving the reliability and accuracy of the measurement.

[0031] In a second aspect, the present application provides a reservoir capacity estimation system based on an unmanned surveying ship and an airborne Lidar, comprising:

[0032] The measurement parameter planning module is configured to plan the first measurement path and the first measurement speed, the second measurement path and the second measurement speed according to the reservoir construction information and the reservoir geographic information, so that the positions corresponding to the first measurement path and the second measurement path at the same time are greater than a preset distance apart;

[0033] The measurement data acquisition module is configured to complete the measurement of the underwater topographic data of the reservoir by using the unmanned surveying ship according to the first measurement path; calculate the first measurement time of the measurement of the underwater topographic data of the reservoir according to the first measurement speed; simultaneously complete the measurement of the overwater and shore topographic data of the reservoir by using the unmanned aerial vehicle with the airborne Lidar according to the second measurement path, calculate the second measurement time of the measurement of the overwater and shore topographic data of the reservoir according to the second measurement speed; and calculate the interval duration of the first measurement time and the second measurement time.

[0034] The measurement data redundancy acquisition module is configured to plan the third measurement path and the third measurement speed according to the reservoir construction information, the reservoir geographic information and the interval duration, so that the positions corresponding to the third measurement path and the first measurement path at the same time are greater than a preset distance apart, and the overwater and shore topographic data of the reservoir is measured again by using the unmanned aerial vehicle with the airborne Lidar according to the third measurement path within the interval duration.

[0035] The reservoir capacity estimation module is used for preprocessing the measured reservoir underwater topographic data and the reservoir overwater and bank topographic data, and the preprocessing comprises: similarity matching the reservoir overwater and bank topographic data of the same position obtained by two times of measurement, retaining one data of a set of reservoir overwater and bank topographic data with similarity greater than a preset similarity, and selecting reservoir overwater and bank topographic data with higher data quality from the reservoir overwater and bank topographic data with similarity not greater than the preset similarity; fusing the preprocessed reservoir underwater topographic data and the reservoir overwater and bank topographic data, constructing a reservoir three-dimensional model by using the fused data, and estimating the reservoir capacity according to the volume of the reservoir three-dimensional model.

[0036] By using the above scheme, the multi-modal measurement data is obtained by the cooperative operation of the unmanned measurement ship and the airborne Lidar, the errors existing in a single measurement mode are eliminated, the high-quality data is retained for fusion by combining multiple measurements and data preprocessing, the three-dimensional model constructed finally is more accurate and reliable, and thus the accuracy of reservoir capacity calculation is realized.

[0037] In a third aspect, the present application provides a computer readable storage medium comprising a stored computer program, wherein the computer readable storage medium controls a device in which the computer readable storage medium is located to execute the method as described above when the computer program is run.

[0038] In a fourth aspect, the present application provides a computer device comprising a memory, a processor and a program stored on the memory and executable by the processor, wherein the program is executed by the processor to implement the steps of the method as described above.

[0039] The reservoir capacity estimation method and system based on the unmanned measurement ship and the airborne Lidar provided by the present application have the following advantages:

[0040] 1. The multi-source data of the reservoir and the bank topography is obtained by the measurement of the unmanned measurement ship and the airborne Lidar, and the measurement accuracy is improved. At the same time, considering the actual environmental factors and the measurement process time, multiple overwater measurements are selected, the redundancy of the measurement data is increased to ensure the accuracy and efficiency of the measurement data. In the whole measurement process, no staff is needed to intervene, the efficiency is improved, and the personal safety of the staff is ensured.

[0041] 2. The influence of environmental factors on the quality of measurement data is considered, and the neural network algorithm is combined to adaptively adjust the quality evaluation threshold of the received signal under different water quality and weather data conditions according to the environmental data, and the measurement data with unqualified quality is removed to ensure the reliability and accuracy of the measurement data.

[0042] 3. Considering the influence of different types of terrain on the absorption and reflection of the transmitted pulse signal, the corresponding pulse parameters are automatically selected according to the terrain classification results for transmission, the pertinence and accuracy of signal reception are improved, and the accuracy of the final measurement data is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 A flowchart of a reservoir capacity estimation method based on an unmanned measurement ship and an airborne Lidar in an embodiment of the present application;

[0044] Figure 2 A structural schematic diagram of a reservoir capacity estimation system based on an unmanned measurement ship and an airborne Lidar in an embodiment of the present application. DETAILED DESCRIPTION

[0045] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0046] As shown in Figure 1 The embodiment of the present application discloses a reservoir capacity estimation method based on an unmanned measurement ship and an airborne Lidar, and the specific steps include:

[0047] S1. Planning measurement parameters according to reservoir building information and reservoir geographic information; including: planning a first measurement path and a first measurement speed, a second measurement path and a second measurement speed, so that the positions corresponding to the first measurement path and the second measurement path at the same time are greater than a preset distance apart;

[0048] In order to measure the reservoir capacity in all aspects, the unmanned surveying ship equipped with a multi-beam sonar device is responsible for scanning the underwater topography of the reservoir, and the unmanned aerial vehicle with an onboard LiDAR is responsible for fine mapping of the water surface and the shore area of the reservoir. The key components installed on the unmanned surveying ship include a high-performance microprocessor as a central controller, an industrial-grade GPS module to ensure positioning accuracy, and a multi-beam sonar device to realize deep water detection. The multi-beam sonar device can select different brands and models according to the budget and project requirements, such as Kongsberg EM 2040 and Teledyne Reson T20-P. For the unmanned aerial vehicle, in addition to the basic flight platform, it also needs to be equipped with a high-resolution LiDAR sensor, a three-axis stabilized gimbal, and sufficient battery endurance. In this embodiment, the LiDAR sensor selected is Riegl VUX-1HA, which is suitable for high-speed scanning of large and complex terrains due to its long-range measurement capability and high data density. In addition to Riegl VUX-1HA, the LiDAR carried by the unmanned aerial vehicle also has multiple options, such as Velodyne PuckLITE and Hesai Pandar series.

[0049] In order to complete the measurement, the measurement path and measurement speed of the unmanned surveying ship and the unmanned aerial vehicle need to be planned in advance according to the reservoir construction information and the reservoir geographic information. Specifically, according to the position information, area information, structure information of the reservoir, and obstacle or building information in the reservoir recorded in the reservoir construction information and the reservoir geographic information, a measurement route is designed for the unmanned surveying ship to ensure that the measurement range covers all the underground water area of the reservoir, which is recorded as the first measurement path. To ensure that the multi-beam sonar device can effectively transmit and receive signals at each path position, a corresponding measurement speed is designed, which can be determined according to the transmission speed of the pulse signal and the depth of the underground water area of the reservoir or the most commonly used speed recorded in the historical measurement process, which is recorded as the first measurement speed.

[0050] In order to improve the measurement efficiency, the unmanned aerial vehicle with onboard LiDAR is used to measure the terrain data of the reservoir water surface and the shore area while the unmanned surveying ship is measuring. Considering that the unmanned surveying ship and the unmanned aerial vehicle at adjacent positions may interfere with each other during measurement, when planning the measurement path of the unmanned aerial vehicle covering the reservoir ground water area and the shore area, it is ensured that the positions corresponding to the first measurement path and the second measurement path at the same time are more than a preset distance apart, which is recorded as the second measurement path. The preset distance can be determined according to the interference range of different frequency signals transmitted by the onboard LiDAR and the multi-beam sonar device. To ensure that the multi-beam sonar device can effectively transmit and receive signals at each path position, a corresponding measurement speed is designed, which can be determined according to the transmission speed of the signal and the preset flight height or the most commonly used speed recorded in the historical measurement process, which is recorded as the second measurement speed.

[0051] And considering the hidden danger of obstacles existing underground of the reservoir, and the influence of variable environmental data on the reservoir underwater topographic survey is greater than that on the reservoir underwater topographic survey, the first measurement speed of the unmanned surveying ship is less than the second measurement speed of the unmanned aerial vehicle.

[0052] S2, using the unmanned surveying ship to complete the reservoir underwater topographic data measurement according to the first measurement path; calculating the first measurement time of the reservoir underwater topographic data measurement according to the first measurement speed; at the same time, using the unmanned aerial vehicle with airborne Lidar to complete the reservoir water and shore topographic data measurement according to the second measurement path, calculating the second measurement time of the reservoir water and shore topographic data measurement according to the second measurement speed; calculating the interval time of the first measurement time and the second measurement time.

[0053] Specifically, according to the control of the staff to send start instruction to the unmanned surveying ship and the unmanned aerial vehicle, the built-in program will automatically adjust the attitude to make it move smoothly along the first measurement path, and control the sonar device to emit pulse sound waves to the surrounding regularly, capture the echo generated when encountering obstacles, complete the reservoir underwater topographic data measurement, that is, the reservoir underwater topographic data. At the same time, the unmanned aerial vehicle receiving the start instruction ascends according to the second measurement path, and the LiDAR continuously emits laser pulses to the ground. After each successful hit, the reflection signal will be transmitted back to the receiving end, completing the reservoir water and shore topographic data measurement, that is, the reservoir water and shore topographic data.

[0054] In addition, during the whole measurement process, the first measurement time of the reservoir underwater topographic data measurement is calculated according to the first measurement speed, the second measurement time of the reservoir water and shore topographic data measurement is calculated according to the second measurement speed; the interval time of the first measurement time and the second measurement time is calculated, and the interval time is combined.

[0055] S3, according to the reservoir building information, the reservoir geographic information and the interval time, planning the third measurement path and the third measurement speed, so that the third measurement path and the first measurement path correspond to the position distance greater than the preset distance at the same time, and the unmanned aerial vehicle with airborne Lidar is used to complete the reservoir water and shore topographic data measurement again according to the third measurement path within the interval time.

[0056] Considering the influence of variable environmental data on the reservoir underwater topographic survey, the first measurement speed of the unmanned surveying ship is less than the second measurement speed of the unmanned aerial vehicle, and the interval time of the measurement completion allows the unmanned aerial vehicle to obtain the reservoir water and shore topographic data again, realizing the acquisition of redundant reservoir water and shore topographic data.

[0057] Specifically, according to the reservoir building information, the reservoir geographic information and the interval time length, a third measurement path and a third measurement speed of the unmanned aerial vehicle are planned, so that the third measurement path is greater than a preset distance from a position corresponding to a same time of the first measurement path and the third path avoids signal interference, and the reservoir overwater and shore terrain data is measured again by the unmanned aerial vehicle with the airborne Lidar according to the third measurement path within the interval time length. Wherein, in order to ensure the success of the unmanned aerial vehicle measurement, the third measurement speed is less than the unmanned aerial vehicle measurement speed threshold.

[0058] S4, the measured reservoir underwater terrain data and the reservoir overwater and shore terrain data are preprocessed, the preprocessing includes: similarity matching of the reservoir overwater and shore terrain data of the same position measured twice, retaining one of the matched reservoir overwater and shore terrain data with similarity greater than a preset similarity, selecting the reservoir overwater and shore terrain data with higher data quality from the reservoir overwater and shore terrain data with similarity not greater than the preset similarity;

[0059] Specifically, the preprocessing includes filtering amplification processing, noise reduction processing, redundant data screening processing and measurement data integration processing of the spatial position corresponding to the planning path alignment, etc. Wherein, for the reservoir overwater and shore terrain data, the similarity of the reservoir overwater and shore terrain data of the same position (such as: the same position in the second path and the third path) measured twice is compared, and one of the matched reservoir overwater and shore terrain data with similarity greater than a preset similarity is retained, and the reservoir overwater and shore terrain data with higher data quality is selected from the reservoir overwater and shore terrain data with similarity not greater than the preset similarity.

[0060] Wherein, the preset similarity can be artificially set, such as: more than 95%; the quality of the measurement data in the measurement process can be determined according to the received signal quality index, the signal quality index includes signal-to-noise ratio, signal strength, etc., one of which can be selected as the evaluation standard or the weighted result of several quality index parameters can be evaluated.

[0061] S5, the preprocessed reservoir underwater terrain data and the reservoir overwater and shore terrain data are fused, the reservoir three-dimensional model is constructed by using the fused data, and the reservoir capacity is estimated according to the volume of the reservoir three-dimensional model.

[0062] Specifically, the data fusion algorithm such as weighted average, Kalman filter or optimization algorithm can be used to complete the preprocessing of the reservoir underwater topographic data and the reservoir water and shore topographic data; including: extracting the key features of the preprocessed reservoir underwater topographic data and the reservoir water and shore topographic data; using the feature matching algorithm or according to the spatial relationship of the planned route arranged in the vertical relationship of the same position, finding the corresponding points or similar areas in the two groups of data, and weighting the found key features; the fused data is converted into point cloud coordinate format by a specific algorithm (such as a three-dimensional reconstruction algorithm), and a three-dimensional model of the reservoir is constructed by using the generated point cloud coordinates, and the volume of the reservoir three-dimensional model is calculated by using numerical integration or volume rendering method to obtain the reservoir capacity.

[0063] In one specific embodiment, considering the influence of different water quality data and meteorological data on reservoir underground topographic measurement or meteorological data on reservoir water and shore topographic measurement, the receiving signal quality judgment threshold is adaptively adjusted under poor water quality or bad weather to effectively remove noise and outliers; the method further comprises:

[0064] When measuring by the unmanned measurement ship, the water quality sensor and the meteorological sensor installed on the unmanned measurement ship are used to collect real-time reservoir underground water quality data and meteorological data; when measuring by the unmanned aerial vehicle with lidar, the meteorological sensor installed on the unmanned aerial vehicle is used to collect real-time meteorological data;

[0065] The preprocessing of the measured reservoir underwater topographic data and the reservoir water and shore topographic data further comprises:

[0066] The first return signal received in the process of measuring the reservoir underwater topographic data by the unmanned measurement ship is filtered and amplified; the filtered and amplified first return signal, the reservoir underground water quality data and meteorological data corresponding to the time when the first return signal is received are input into the first quality evaluation model, and the evaluation result of whether the first return signal quality is qualified is output, and the first return signal with unqualified evaluation result is removed;

[0067] The first quality evaluation model adopts a neural network model, which is trained by labeling the history of receiving the first return signal in the process of measuring by the unmanned measurement ship, the history of reservoir underground water quality data and the history of meteorological data; wherein the first quality evaluation threshold existing in the first quality evaluation model is adaptively adjusted according to the reservoir underground water quality data and meteorological data.

[0068] The second return signal received in the process of measuring the water surface and shore terrain data of the reservoir by the unmanned surveying ship is filtered and amplified; the filtered and amplified second return signal and the meteorological data corresponding to the time of the received second return signal are input into the second quality evaluation model, and the evaluation result of whether the signal quality is qualified or not is output, and the second return signal with the evaluation result of unqualified signal quality is removed;

[0069] The second quality evaluation model adopts a neural network model, and is trained by the second return signal received in the process of measuring the reservoir by the unmanned surveying ship, historical reservoir groundwater quality data and historical meteorological data marked with whether the quality is qualified or not, wherein the second quality evaluation threshold existing in the second quality evaluation model is adaptively adjusted according to the meteorological data.

[0070] In one specific embodiment, considering the influence of different measurement terrain classifications on reservoir underground terrain measurement or meteorological data on reservoir water surface and shore terrain measurement, the measurement signal emission strategy is adjusted to adapt to different terrains and reflection conditions of the reservoir, and the signal reception quality is improved; the method further comprises:

[0071] For the process of measuring the water surface and shore terrain data of the reservoir by the unmanned aerial vehicle with the airborne Lidar according to the second measurement path, the camera device also carried on the unmanned aerial vehicle is used to collect the image information of the reservoir in the area in the forward direction of the second measurement path in real time;

[0072] The measurement terrain classification in the reservoir image information is determined based on image analysis technology; the measurement terrain classification includes water body, vegetation, bare soil and building; the preset pulse parameters are matched according to the determined measurement terrain classification; each measurement terrain classification is preset with pulse parameters matched therewith, including pulse frequency and intensity; specifically, the pulse parameters matched with each measurement terrain classification can be determined according to the received return signal quality under different pulse frequencies and intensities under the condition of the same measurement terrain type in history, and the pulse frequency and intensity corresponding to the strongest return signal quality are selected or determined according to the expert experience recommendation. In the process of measuring the water surface and shore terrain data of the reservoir by the unmanned aerial vehicle with the airborne Lidar according to the second measurement path, the matched pulse parameters are selected for pulse emission, and the corresponding return signal is received.

[0073] In addition, the process of measuring the underwater terrain data of the reservoir by the unmanned surveying ship according to the first measurement path further comprises:

[0074] The measurement topography classification of different regions of the reservoir underground water area is determined in advance according to the reservoir construction information and historical reservoir underwater image data information; when the unmanned measurement ship drives to a specific region in the reservoir underground water area according to the first measurement path, the preset pulse parameters are matched according to the measurement topography classification of the specific region; during the measurement process of the reservoir underwater topography data by the unmanned measurement ship according to the first measurement path, the matched pulse parameters are selected for pulse signal emission, and the corresponding return signal is received.

[0075] In one specific embodiment, considering the influence of the accuracy of multi-source measurement data in the measurement data fusion process, the fusion weights of different multi-source measurement data are adjusted to achieve more accurate data fusion; the method further comprises: collecting reservoir environment data; the reservoir environment data includes water quality data and meteorological data;

[0076] The fusion of the preprocessed reservoir underwater topography data and the reservoir water and shore topography data includes:

[0077] The multi-modal data fusion model is selected to dynamically fuse the reservoir underwater topography data and the reservoir water and shore topography data as the fusion method, instead of directly selecting the weighted fusion method in the above embodiment.

[0078] The reservoir environment data, the preprocessed reservoir underwater topography data and the reservoir water and shore topography data are input into the multi-modal data fusion model, and the multi-modal data fusion model is used to fuse the reservoir underwater topography data and the reservoir water and shore topography data; wherein the multi-modal data fusion model adopts a neural network model, and the reservoir underwater topography data and the reservoir water and shore topography data fusion data corresponding to the calculated reservoir storage capacity data with the smallest difference between the historical and actual reservoir storage capacity data, the historical reservoir underwater topography data, the historical reservoir water and shore topography data and the historical environment data are trained and generated.

[0079] In addition, after obtaining the reservoir storage capacity, the obtained reservoir storage capacity and the actual reservoir storage capacity are compared to determine whether the difference between the two is greater than a preset difference; if the difference is greater than the preset difference, the multi-modal data fusion model is selected for incremental learning optimization, and the optimized multi-modal data fusion model is used to re-fuse the reservoir underwater topography data and the reservoir water and shore topography data, and the obtained reservoir storage capacity and the actual reservoir storage capacity are repeatedly calculated and compared to determine whether the difference between the two is greater than the preset difference, until the difference is greater than the preset difference, and the optimization of the multi-modal data fusion model is stopped.

[0080] In one specific embodiment, in order to further guarantee the accuracy of the measurement data, the redundancy of the measurement data can be increased to select measurement data with better quality and improve the accuracy of the final reservoir storage capacity; the method further comprises:

[0081] According to the reservoir building information and the reservoir geographic information, important areas and non-important areas of the reservoir are divided; the important areas can be artificially predetermined.

[0082] For the important areas of the reservoir, multiple unmanned surveying ships are used to record the measurement of the underwater topographic data of the reservoir by each unmanned surveying ship according to the first measurement path in different time periods; that is, in different time periods, the measurement data completed by different unmanned surveying ships in the important areas of the reservoir are recorded respectively.

[0083] The preprocessing of the measured underwater topographic data of the reservoir and the overwater and shore topographic data of the reservoir further includes: for multiple groups of underwater topographic data of the reservoir corresponding to the same position in the first measurement path, the underwater topographic data with the highest quality is selected as the underwater topographic data of the current position.

[0084] In one specific embodiment, the volume of the three-dimensional model of the reservoir is calculated by numerical integration or volume rendering to estimate the reservoir capacity.

[0085] In one specific embodiment, in the process of measuring the underwater topographic data of the reservoir by the unmanned surveying ship according to the first measurement path, a Kongsberg EM 2040 or a Teledyne Reson T20-P type multi-beam sonar device is selected to complete the measurement; in the process of measuring the overwater and shore topographic data of the reservoir by the unmanned aerial vehicle with an onboard Lidar according to the second measurement path, a Riegl VUX-1HA LiDAR sensor is selected to complete the measurement.

[0086] As shown in Figure 2 FIG. 1, a reservoir capacity estimation system based on unmanned surveying ships and onboard Lidars specifically includes:

[0087] The measurement parameter planning module 101 is configured to plan the first measurement path and the first measurement speed, the second measurement path and the second measurement speed according to the reservoir building information and the reservoir geographic information, so that the positions corresponding to the first measurement path and the second measurement path at the same time are greater than a preset distance apart;

[0088] The measurement data acquisition module 102 is configured to measure the underwater topographic data of the reservoir by the unmanned surveying ship according to the first measurement path; calculate the first measurement time of the measurement of the underwater topographic data of the reservoir according to the first measurement speed; simultaneously measure the overwater and shore topographic data of the reservoir by the unmanned aerial vehicle with an onboard Lidar according to the second measurement path, calculate the second measurement time of the measurement of the overwater and shore topographic data of the reservoir according to the second measurement speed; and calculate the interval duration of the first measurement time and the second measurement time.

[0089] The measurement data redundancy obtaining module 103 is configured to plan a third measurement path and a third measurement speed according to the reservoir construction information, the reservoir geographic information and the interval time length, so that the third measurement path and the first measurement path correspond to positions with a distance greater than a preset distance at the same time, and the reservoir overwater and bank terrain data is measured again by using the UAV with the onboard Lidar according to the third measurement path within the interval time length.

[0090] The reservoir capacity estimation module 104 is configured to preprocess the measured reservoir underwater terrain data and the reservoir overwater and bank terrain data, and the preprocessing includes: performing similarity matching on the reservoir overwater and bank terrain data of the same position obtained by two measurements, retaining one of the matched reservoir overwater and bank terrain data with a similarity greater than a preset similarity, and selecting the reservoir overwater and bank terrain data with higher data quality from the reservoir overwater and bank terrain data with a similarity not greater than the preset similarity; fusing the preprocessed reservoir underwater terrain data and the reservoir overwater and bank terrain data, constructing a reservoir three-dimensional model by using the fused data, and estimating the reservoir capacity according to the volume of the reservoir three-dimensional model.

[0091] In one specific embodiment, the system further includes a measurement parameter obtaining module 105 configured to collect reservoir underground water quality data and weather data in real time by using the water quality sensor and the weather sensor installed on the unmanned measurement ship when the unmanned measurement ship measures.

[0092] The reservoir capacity estimation module 104 in the system is further configured to perform filtering and amplification processing on the received first return signal in the process of measuring the reservoir underwater terrain data by using the unmanned measurement ship; input the filtered and amplified first return signal, the reservoir underground water quality data and the weather data into a first quality evaluation model, output an evaluation result of whether the first return signal quality is qualified, and eliminate the first return signal with the evaluation result of unqualified quality; the first quality evaluation model adopts a neural network model, and is generated by training the first return signal received in the process of measuring by using the unmanned measurement ship, historical reservoir underground water quality data and historical weather data with the quality of qualified or unqualified.

[0093] In one specific embodiment, the measurement data acquisition module 102 in the system is further configured to, for a reservoir water surface and bank terrain data measurement process using a UAV with an onboard Lidar along a second measurement path, collect reservoir image information in a forward direction of the second measurement path in real time; determine a measurement terrain classification in the reservoir image information based on image analysis technology; the measurement terrain classification includes water, vegetation, bare soil, and buildings; match preset pulse parameters according to the determined measurement terrain classification; each measurement terrain classification is preset with pulse parameters matched therewith, including pulse frequency and intensity; and in the reservoir water surface and bank terrain data measurement process using the UAV with the onboard Lidar along the second measurement path, the matched pulse parameters are selected for pulse emission, and the corresponding received return signals are received.

[0094] and: filtering and amplifying the received second return signals in the reservoir water surface and bank terrain data measurement process using the unmanned measurement ship; inputting the filtered and amplified second return signals and the received second return signals and the corresponding meteorological data at the time into a second quality assessment model to output an assessment result of whether the signal quality is qualified or not, and eliminating the second return signals with an assessment result of unqualified signal quality; the second quality assessment model uses a neural network model and is trained and generated by using historical second return signals received in a historical measurement process using the unmanned measurement ship, historical reservoir groundwater quality data, and historical meteorological data.

[0095] In one specific embodiment, the reservoir storage capacity estimation module 104 in the system is further configured to input the environmental data of the reservoir, the preprocessed reservoir underwater terrain data, and the reservoir water surface and bank terrain data into a multi-modal data fusion model, and perform data fusion on the reservoir underwater terrain data and the reservoir water surface and bank terrain data using the multi-modal data fusion model; wherein the multi-modal data fusion model uses a neural network model and is trained and generated by using reservoir underwater terrain data and reservoir water surface and bank terrain data fusion data corresponding to calculated reservoir storage capacity data with the smallest difference between historical and actual reservoir storage capacity data, historical reservoir underwater terrain data, historical reservoir water surface and bank terrain data, and historical environmental data.

[0096] In one specific embodiment, the measurement data acquisition module 102 in the system is further configured to divide the reservoir into important areas and non-important areas according to reservoir building information and reservoir geographic information; for the important areas of the reservoir, use multiple unmanned measurement ships to record the reservoir underwater terrain data measured by each unmanned measurement ship along the first measurement path at different time periods; and the reservoir storage capacity estimation module 104 in the system is further configured to filter the reservoir underwater terrain data with the highest quality from multiple groups of reservoir underwater terrain data corresponding to the same position in the first measurement path as the reservoir underwater terrain data of the current position.

[0097] The embodiment of the present application further discloses a computer readable storage medium.

[0098] Specifically, the computer readable storage medium stores a computer program capable of being loaded and executed by the processor to implement the reservoir capacity estimation method based on the unmanned surveying ship and the airborne Lidar, and the computer readable storage medium includes, for example, a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various storage program code mediums.

[0099] The embodiment of the present application further discloses a computer device.

[0100] Specifically, the computer device includes a memory and a processor, and the memory stores a computer program capable of being loaded and executed by the processor to implement the reservoir capacity estimation method based on the unmanned surveying ship and the airborne Lidar.

[0101] The above are preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in the specification (including the abstract and the drawings) can be replaced by other equivalent or similar features, unless specifically described. That is, each feature is only an example of a series of equivalent or similar features, unless specifically described.

Claims

1. A method for estimating reservoir capacity based on unmanned survey vessels and airborne LiDAR, characterized in that, include: Based on the reservoir's structural information and geographical information, a first measurement path and a first measurement speed, and a second measurement path and a second measurement speed are planned, so that the distance between the corresponding positions of the first measurement path and the second measurement path at the same time is greater than a preset distance. The underwater topographic data of the reservoir is measured using an unmanned survey vessel following a first measurement path; the first measurement time for measuring the underwater topographic data of the reservoir is calculated according to a first measurement speed; simultaneously, the topographic data of the reservoir surface and shoreline is measured using an unmanned aerial vehicle equipped with an airborne LiDAR following a second measurement path; the second measurement time for measuring the topographic data of the reservoir surface and shoreline is calculated according to a second measurement speed; and the interval between the first measurement time and the second measurement time is calculated. Based on reservoir construction information, reservoir geographic information and interval duration, a third measurement path and a third measurement speed are planned so that the distance between the corresponding positions of the third measurement path and the first measurement path at the same time is greater than the preset distance. Within the interval duration, a UAV equipped with airborne LiDAR is used to complete the measurement of the reservoir's water surface and shore topography data again according to the third measurement path. The underwater topographic data of the reservoir and the surface and shore topographic data of the reservoir obtained by measurement are preprocessed. The preprocessing includes: performing similarity matching on the surface and shore topographic data of the reservoir at the same location obtained by two measurements, retaining one data point from a set of surface and shore topographic data with a similarity greater than a preset similarity, and selecting the surface and shore topographic data with higher data quality from the set of surface and shore topographic data with a self-similarity not greater than the preset similarity; fusing the preprocessed underwater topographic data and the surface and shore topographic data of the reservoir, constructing a three-dimensional model of the reservoir using the fused data, and estimating the reservoir capacity based on the volume of the three-dimensional model of the reservoir. It also includes: collecting reservoir environmental data; the reservoir environmental data includes water quality data and meteorological data; The process of fusing preprocessed underwater topographic data with surface and shore topographic data includes: inputting reservoir environmental data, preprocessed underwater topographic data, and surface and shore topographic data into a multimodal data fusion model; and using the multimodal data fusion model to fuse the underwater topographic data with the surface and shore topographic data. The multimodal data fusion model employs a neural network model, which is generated by training on the reservoir capacity data corresponding to the calculated underwater topographic data and surface and shore topographic data corresponding to the reservoir capacity data with the smallest discrepancy between historical and actual reservoir capacity data, as well as historical underwater topographic data, historical surface and shore topographic data, and historical reservoir environmental data.

2. The method for estimating reservoir capacity based on an unmanned survey vessel and airborne LiDAR as described in claim 1, characterized in that, Also includes: During the measurement by the unmanned survey vessel, water quality sensors and meteorological sensors installed on the unmanned survey vessel are used to collect real-time groundwater quality data and meteorological data of the reservoir. The preprocessing of the measured underwater topographic data of the reservoir with the above-water and shore topographic data of the reservoir also includes: The first return signal received during the process of obtaining underwater topographic data of a reservoir using an unmanned survey vessel is filtered and amplified. The filtered and amplified first return signal, reservoir groundwater quality data, and meteorological data are input into the first quality assessment model, which outputs the assessment result of whether the first return signal is qualified or not, and discards the first return signal with the assessment result of unqualified quality; the first quality assessment model adopts a neural network model, which is trained and generated by using the first return signal received during the measurement process of the unmanned measuring vessel with the quality marked as qualified or not. The second return signal received during the process of obtaining reservoir water surface and shore topographic data using unmanned survey vessels is filtered and amplified. The filtered and amplified second return signal and the meteorological data corresponding to the time of the received second return signal are input into a second quality assessment model, which outputs the assessment result of whether the signal quality is qualified or not, and the second return signal with the assessment result of unqualified signal quality is removed. The second quality assessment model adopts a neural network model, which is trained and generated by using historical second return signals received during the measurement process using unmanned survey vessels with quality marked as qualified or not, historical reservoir groundwater quality data and historical meteorological data.

3. The method for estimating reservoir capacity based on an unmanned survey vessel and airborne LiDAR as described in claim 1, characterized in that, The method of using a drone equipped with airborne LiDAR to complete the measurement of reservoir topographic data on the water surface and shoreline according to the second measurement path also includes: This method addresses the process of using an airborne LiDAR-equipped UAV to measure the topographic data of a reservoir's surface and shoreline along a second measurement path. Real-time image acquisition of the reservoir along the path's forward direction is performed. Image analysis techniques are used to determine the topographic classification within the reservoir images. This classification includes water bodies, vegetation, bare soil, and buildings. Preset pulse parameters are matched to each determined topographic classification. Each topographic classification has preset pulse parameters, including pulse frequency and intensity. During the measurement of the reservoir's surface and shoreline topographic data using the airborne LiDAR-equipped UAV along the second measurement path, the matched pulse parameters are selected for pulse transmission, and the corresponding return signals are received.

4. The method for estimating reservoir capacity based on an unmanned survey vessel and airborne LiDAR as described in claim 1, characterized in that, Also includes: The reservoir is divided into important and non-important areas based on its structural and geographical information. For key areas of the reservoir, multiple unmanned survey vessels are used to record underwater topographic data of the reservoir in different time periods. Each unmanned survey vessel completes the measurement of the underwater topographic data of the reservoir according to the first measurement path. The preprocessing of the underwater topographic data of the reservoir and the topographic data of the reservoir surface and shoreline also includes: selecting the highest quality underwater topographic data of the reservoir from multiple sets of underwater topographic data corresponding to the same location in the first measurement path as the underwater topographic data of the reservoir at the current location.

5. The method for estimating reservoir capacity based on an unmanned survey vessel and airborne LiDAR as described in claim 1, characterized in that, Also includes: The reservoir capacity is estimated by calculating the volume of the 3D model of the reservoir using numerical integration or volume rendering.

6. The method for estimating reservoir capacity based on an unmanned survey vessel and airborne LiDAR as described in claim 1, characterized in that, It also includes: during the process of using an unmanned survey vessel to complete the measurement of underwater topographic data of the reservoir according to the first measurement path, the Kongsberg EM 2040 or Teledyne Reson T20-P multibeam sonar device is used to complete the measurement; during the process of using an unmanned aerial vehicle with airborne LiDAR to complete the measurement of topographic data of the reservoir surface and shoreline according to the second measurement path, the Riegl VUX-1HA LiDAR sensor is used to complete the measurement.

7. A reservoir capacity estimation system based on an unmanned survey vessel and airborne LiDAR, characterized in that, The reservoir capacity estimation system based on unmanned survey vessels and airborne LiDAR implements the reservoir capacity estimation method based on unmanned survey vessels and airborne LiDAR as described in any one of claims 1-6. The system includes: The measurement parameter planning module is used to plan a first measurement path and a first measurement speed, and a second measurement path and a second measurement speed based on the reservoir structure information and reservoir geographic information, so that the distance between the corresponding positions of the first measurement path and the second measurement path at the same time is greater than a preset distance. The measurement data acquisition module is used to complete the measurement of underwater topographic data of the reservoir using an unmanned survey vessel according to a first measurement path; calculate the first measurement time for completing the underwater topographic data measurement of the reservoir according to a first measurement speed; simultaneously, use an unmanned aerial vehicle equipped with an airborne LiDAR to complete the measurement of the topographic data of the reservoir surface and shore according to a second measurement path; calculate the second measurement time for measuring the topographic data of the reservoir surface and shore according to a second measurement speed; and calculate the interval between the first measurement time and the second measurement time. The redundant measurement data acquisition module is used to plan a third measurement path and a third measurement speed based on reservoir building information, reservoir geographic information and interval duration, so that the distance between the corresponding positions of the third measurement path and the first measurement path at the same time is greater than a preset distance, and within the interval duration, the UAV with airborne LiDAR is used to complete the measurement of the reservoir water and shore topography data again according to the third measurement path. The reservoir capacity estimation module is used to preprocess the underwater topographic data and the surface and shore topographic data of the reservoir obtained by measurement. The preprocessing includes: performing similarity matching on the surface and shore topographic data of the reservoir obtained from two measurements at the same location; retaining one data point from a set of surface and shore topographic data with a similarity greater than a preset similarity; selecting the surface and shore topographic data with higher data quality from the set of surface and shore topographic data with a self-similarity not greater than the preset similarity; fusing the preprocessed underwater topographic data and the surface and shore topographic data; constructing a three-dimensional model of the reservoir using the fused data; and estimating the reservoir capacity based on the volume of the three-dimensional model.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device on which the computer-readable storage medium is located to perform the method as described in any one of claims 1 to 6.

9. A computer device, characterized in that, The computer device includes a memory, a processor, and a program stored in and executable on the memory, the program being executed by the processor to implement the steps of the method as described in any one of claims 1 to 6.

Images