Novel laser squaring process

Abstract

The invention relates to a novel laser measurement process. The process comprises the following steps: acquiring point cloud data of a cargo-carrying vehicle through a laser radar; preprocessing the point cloud data, wherein the preprocessing comprises coordinate system conversion and noisy point filtering; calculating the volume of the cargo carrying vehicle according to the preprocessed point cloud data; and calculating the volume of the material according to the volume of the cargo-carrying vehicle and the volume of the no-load vehicle. The beneficial effects of the invention are that the method obtains the point cloud data of the cargo-carrying vehicle and the no-load vehicle through the laser radar, and can precisely calculate the volume of the cargo-carrying vehicle and the no-load vehicle in combination with the preprocessing means of coordinate system conversion, noise filtering and the like, thereby improving the measurement precision of the material volume.

Description

Technical Field

[0001] The present invention relates to the field of square measurement technology, and more specifically, to a novel laser square measurement process. Background Art

[0002] In the operation of biomass power plants, the measurement of raw materials is a key link, which is directly related to the cost of power generation and economic benefits. Traditional measurement methods usually rely on manual work, which is not only inefficient but also easily affected by human factors, resulting in a significant reduction in the accuracy of the measurement results. In addition, manual measurement also faces problems such as difficulty in night operations and high labor intensity, which seriously restrict the modernization process of biomass power plants. Summary of the invention

[0003] The purpose of the present invention is to propose a new laser measurement process to address the deficiencies of the prior art.

[0004] In the first aspect, a new laser measurement process is provided, including:

[0005] S1. Obtain point cloud data of cargo vehicles through laser radar;

[0006] S2. Preprocessing the point cloud data, wherein the preprocessing includes coordinate system conversion and noise filtering;

[0007] S3. Calculate the volume of the cargo vehicle based on the preprocessed point cloud data;

[0008] S4. acquiring point cloud data of the empty vehicle through a laser radar, and calculating the volume of the empty vehicle according to the point cloud data of the empty vehicle;

[0009] S5. Calculate the volume of the material based on the volume of the loaded vehicle and the volume of the empty vehicle.

[0010] Preferably, in S1, point cloud data of the cargo vehicle is acquired by a first radar above the vehicle and a second radar on the side and front of the vehicle.

[0011] Preferably, S2 comprises:

[0012] S201. Coordinate system conversion: When point cloud data is acquired by line scanning, in the object space coordinate system, the scanning forward direction is taken as the X axis, the Z axis is consistent with the zenith direction, and the laser scanner emission center is taken as the origin, thus forming a right-handed coordinate system; in this coordinate system, the external orientation elements are (XO, YO, ZO, φ, ω, κ), φ, ω, κ represent the rotation angles around the X axis, Y axis, and Z axis respectively; the distance s from the ground surface to the scanning center is measured by the laser scanner; the angle θ between the scanning line direction and the Z axis is recorded by the encoder, and the X axis direction coordinate is determined by the speed sensor. For each pulse:

[0013] x=0,y=-s*sinθ,z=-s*cosθ

[0014] S202, noise point filtering: Assume that the average distance between all points in the point cloud data and their nearest k neighboring points satisfies the Gaussian distribution, determine the distance threshold based on the mean and variance of the distance, and when the average distance between a point and its nearest k points is greater than the distance threshold, determine that the point is an interference point and remove it.

[0015] Preferably, S3 includes:

[0016] S301, point cloud data slicing: between the minimum value 0 and the maximum value H of the vertical direction of the point cloud, a set of horizontal planes with equal spacing h are used to sequentially slice the point cloud from top to bottom, and a series of horizontal point cloud slices S are obtained in sequence. i ;

[0017] S302, contour boundary determination: Use the bidirectional closest point search method to search the disordered plane point clouds S i Sort and generate the outer contour boundary polygon P of each point cloud slice scatter point i ;

[0018] S303, slice area calculation: calculate P respectively i The area enclosed, i.e. S i Area A i ;

[0019] S304, point cloud volume calculation: accumulate A i And multiply it by h to get the point cloud volume, that is, the volume V of the laser scanned object.

[0020] Preferably, in S1 and S4, before acquiring the point cloud data, the license plate of the vehicle is identified; and after acquiring the point cloud data, the point cloud data and the license plate number of the corresponding vehicle are stored in a database.

[0021] As a preference, it also includes:

[0022] S6. Identify the type of material and display the type and volume of the material through a display device.

[0023] In the second aspect, a new laser measurement system is provided for executing any of the new laser measurement processes described in the first aspect, including: a laser scanning radar, a control gimbal and a display device.

[0024] In a third aspect, a novel laser measurement device is provided, which is used to execute any novel laser measurement process described in the first aspect, including:

[0025] An acquisition module, used to acquire point cloud data of a cargo vehicle through a laser radar;

[0026] A preprocessing module, used for preprocessing the point cloud data, wherein the preprocessing includes coordinate system conversion and noise filtering;

[0027] A first calculation module, used for calculating the volume of the cargo vehicle according to the preprocessed point cloud data;

[0028] The second calculation module is used to obtain point cloud data of the empty vehicle through a laser radar, and calculate the volume of the empty vehicle according to the point cloud data of the empty vehicle;

[0029] The third calculation module is used to calculate the volume of the material according to the volume of the loaded vehicle and the volume of the empty vehicle.

[0030] In a fourth aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the new laser measurement process as described in any one of the first aspects is implemented.

[0031] The beneficial effects of the present invention are as follows: the present invention obtains point cloud data of loaded vehicles and unloaded vehicles through laser radar, and combines pre-processing means such as coordinate system conversion and noise filtering to accurately calculate the volume of loaded vehicles and unloaded vehicles, thereby improving the measurement accuracy of material volume. In addition, the laser volume measurement process of the present invention realizes automatic identification of loaded vehicles and unloaded vehicles, automatic acquisition and processing of point cloud data, reduces manual intervention, and improves measurement efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 This is a schematic diagram of the entry process of the smart unattended material yard;

[0033] Figure 2 This is a schematic diagram of the exit process of the smart unattended material yard;

[0034] Figure 3 This is a schematic diagram of coordinate system transformation;

[0035] FIG4 is a schematic diagram of vehicle profile measurement;

[0036] Figure 5 This is a structural diagram of the material identification system. DETAILED DESCRIPTION

[0037] The present invention is further described below in conjunction with embodiments. The description of the following embodiments is only used to help understand the present invention. It should be noted that for ordinary persons in the art, without departing from the principle of the present invention, the present invention can also be modified in some ways, and these improvements and modifications also fall within the scope of protection of the claims of the present invention.

[0038] Embodiment 1:

[0039] Embodiment 1 of the present application provides a novel laser measurement process, including:

[0040] S1. Obtain point cloud data of cargo vehicles through LiDAR.

[0041] Laser measurement technology is a new remote sensing technology that can continuously and quickly collect coordinate information on the surface of the target object. This technology has the characteristics of high degree of automation, little influence from weather, short data production cycle, high accuracy, etc. It can be widely used in the fields of stockpile measurement, surveying, forest resource investigation, water conservancy and hydropower survey and design, tidal flat topography measurement, crop growth monitoring, etc.

[0042] The smart measurement system is a mobile laser measurement system consisting of a laser scanning radar, a control PTZ, a control display panel and related accessories. The system uses the classic Slam algorithm based on Kalman filtering to achieve real-time positioning and model building. The main technical features are:

[0043] 1) Fast measurement speed, flexible and convenient to use;

[0044] 2) The point cloud data is dense, and the measurement accuracy and resolution are very high;

[0045] 3) Able to work around the clock and less affected by weather, meteorology and other environmental factors;

[0046] 4) Modeling that meets complex structural objectives (such as complex ship-shaped structures):

[0047] 5) Diversity of data sources to meet the needs of data processing by various software.

[0048] In order to improve the accuracy of material measurement and the safety of personnel operations, this solution realizes automatic measurement based on lidar, and displays the measurement results in real time and pushes them to the corresponding system.

[0049] At present, most of the laser radars on the market use the basic principle of TOF to obtain spatial coordinates within the field of view. By emitting a laser beam to the object to be measured, the real distance information of the object is calculated based on the time it takes for the laser to return. The target surface coordinate data is obtained to perform various calculations or build a three-dimensional model.

[0050] Civilian laser radars include area scanning and single-line laser radars. Considering the application scenarios of volume measurement, measuring high-precision volume data requires point cloud data of sufficient density and accurate point cloud data. The more mature solution currently uses 2D radar + PTZ / cart for push scanning. This not only obtains high-density point cloud data, but also saves a lot of work in point cloud stitching.

[0051] S2. Preprocessing the point cloud data, wherein the preprocessing includes coordinate system conversion and noise filtering.

[0052] S2 includes:

[0053] S201. Coordinate system conversion: When point cloud data is acquired by line scanning, in the object space coordinate system, the scanning forward direction is taken as the X-axis, the Z-axis is consistent with the zenith direction, and the laser scanner emission center is taken as the origin, thereby forming a right-handed coordinate system; in this coordinate system, the external orientation elements are (XO, YO, ZO, φ, ω, κ), φ, ω, κ represent the rotation angles around the X-axis, Y-axis, and Z-axis respectively, which are used to describe the scanner posture; the distance s from the ground surface to the scanning center is measured by the laser scanner; the angle θ between the scanning line direction and the Z-axis is recorded by the encoder, and the X-axis direction coordinate is determined by the speed sensor. For each pulse, there is:

[0054] x=0,y=-s*sinθ,z=-s*cosθ

[0055] S202, noise point filtering: Assume that the average distance between all points in the point cloud data and their nearest k neighboring points satisfies the Gaussian distribution, determine the distance threshold based on the mean and variance of the distance, and when the average distance between a point and its nearest k points is greater than the distance threshold, determine that the point is an interference point and remove it.

[0056] Specifically, S202 includes:

[0057] S2021. Traverse the point cloud and calculate the average distance between each point and its k nearest neighbor points.

[0058] S2022. Calculate the mean μ and standard deviation σ of all average distances, then the distance threshold dth can be expressed as:

[0059] dth=μ+α*σ

[0060] Among them, α is a constant, which can be called the proportional coefficient.

[0061] S2023. Traverse the point cloud again and remove points whose average distance to k neighboring points is greater than dth.

[0062] S3. Calculate the volume of the cargo vehicle based on the preprocessed point cloud data.

[0063] The point cloud is sliced ​​along a certain coordinate axis, and then the area of ​​the upper and lower surfaces of the slice is calculated. The total volume is obtained by accumulating the slice volume. This method is affected by the slice thickness. The thinner the slice, the higher the calculation accuracy. The basic idea and process of the "slicing method" based on algorithms and programming calculations can be summarized as "laser scanning of spatial objects → point cloud data slicing → contour boundary determination → slice area calculation → point cloud volume calculation" in five steps, specifically:

[0064] S301, point cloud data slicing: Between the minimum value 0 and the maximum value H of the point cloud longitudinal direction, a set of (set to n+1) horizontal planes with equal spacing h are used to sequentially slice the point cloud from top to bottom, and a series of horizontal point cloud slices S are obtained in sequence. i .

[0065] S302, contour boundary determination: Use the bidirectional closest point search method to search the disordered plane point clouds S i Sort and generate the outer contour boundary polygon P of each point cloud slice scatter point i (i=0, 1, ..., m).

[0066] S303, slice area calculation: calculate P respectively i The area enclosed, i.e. S i Area A i (i=0, 1, ..., m).

[0067] S304, point cloud volume calculation: accumulate A i And multiply it by h to get the point cloud volume, that is, the volume V of the laser scanned object.

[0068] S4. Obtain point cloud data of the empty vehicle through a laser radar, and calculate the volume of the empty vehicle based on the point cloud data of the empty vehicle.

[0069] As shown in Figure 4, the volume measurement is also divided into two parts: empty load volume and full load volume. The specific measurement operation process is: engineering vehicle full load measurement (such as S3) - engineering vehicle empty load measurement (S4) - volume calculation.

[0070] S5. Calculate the volume of the material based on the volume of the loaded vehicle and the volume of the empty vehicle.

[0071] Embodiment 2:

[0072] Based on Example 1, Example 2 of the present application provides a more specific novel laser measurement process, including:

[0073] S1. Obtain point cloud data of cargo vehicles through LiDAR.

[0074] In S1, point cloud data of the cargo vehicle is acquired through a first radar above the vehicle and a second radar on the side and front of the vehicle.

[0075] After the vehicle enters the entrance weighbridge, the camera recognizes the vehicle's license plate, starts lidar measurement, obtains the (X, Y, Z) coordinate information of each point of the vehicle, and stores it in the local database.

[0076] S2. Preprocessing the point cloud data, wherein the preprocessing includes coordinate system conversion and noise filtering.

[0077] S3. Calculate the volume of the cargo vehicle based on the preprocessed point cloud data.

[0078] S4. Obtain point cloud data of the empty vehicle through a laser radar, and calculate the volume of the empty vehicle based on the point cloud data of the empty vehicle.

[0079] After the vehicle enters the exit weighbridge, the camera recognizes the vehicle's license plate, starts lidar measurement, obtains the (X, Y, Z) coordinate information of each point of the vehicle, and stores it in the local database.

[0080] S5. Calculate the volume of the material based on the volume of the loaded vehicle and the volume of the empty vehicle.

[0081] S6. Display the type and volume of the material through the display device.

[0082] At present, material identification in factories mainly relies on manual experience and judgment, but there are about 20 types of materials, and there are multiple materials mixed, the physical form of the same material varies greatly, etc., which makes manual material identification difficult and the proportion of various materials difficult to judge. In this regard, in S6, the embodiment of the present application provides a method for automatically identifying the type of material.

[0083] The intelligent material identification system provided in the embodiment of the present application is based on a computing server cluster to build a fuel AI intelligent identification and analysis system to solve the problems of difficult judgment and high risk during manual identification. The material identification process includes:

[0084] S601. Data acquisition

[0085] First, obtain the image information of the object to be identified and mark the fuel type. After the marking is completed, the data is stored in the database. When a conflict occurs, manual inspection is carried out to obtain a more accurate marking.

[0086] Because there are many types of materials and many forms of the same fuel, in order to improve the accuracy of material identification, a large amount of sample data needs to be labeled to achieve accurate identification of material categories.

[0087] S602. Data preprocessing and feature extraction

[0088] The data set has many data irregularities, such as missing data, uneven distribution, abnormal data, and mixed insignificant data. Therefore, we need to further process the collected data, including processing missing values, processing deviating values, data normalization, data conversion, etc., to complete "data preprocessing". After preprocessing, the data can be used for feature extraction, data dimensionality reduction, and other operations.

[0089] S603, model training and verification

[0090] First, start with a simple algorithm, implement it quickly, and verify it on a cross-validation set; output a learning curve to determine whether more data or more features will help optimize the model; finally, manually detect the common features of samples that were incorrectly classified or predicted in the cross-validation set, adjust the model based on actual conditions, continuously adjust and verify the errors on the cross-validation set, find the best results, and optimize the model.

[0091] Model training is the most important step in machine learning tasks, including model structure design, model hyperparameter adjustment, etc.

[0092] S604. Model evaluation

[0093] During the model evaluation stage, different evaluation indicators can be selected according to different problems such as classification, regression, and sorting.

[0094] S605, Online Testing

[0095] Deploy the model and put it into use.

[0096] In addition, if Figure 5 As shown in the figure, the material identification system is designed as follows: the front-end video information is transmitted back to the back-end server in real time through the local area network to monitor the material category, and the monitoring results are transmitted to the fuel system. The entire system is divided into two parts: the front-end camera and the back-end platform. The front-end is equipped with a mobile camera. When the vehicle unloads the material, photos are taken manually and uploaded to the back-end platform for category analysis. The analysis results will be synchronized to the fuel system in real time.

[0097] The above-mentioned material recognition system can simultaneously recognize multiple materials within the visual range of the camera and output the material proportions.

[0098] It should be noted that the parts in this embodiment that are the same or similar to those in Embodiment 1 can be referenced to each other and will not be described in detail in this application.

[0099] Embodiment 3:

[0100] Based on Examples 1 and 2, Example 3 of the present application provides an unmanned smart park solution that integrates computer management and communication networks, automatic image recognition and processing, and automatic control, realizing four core capabilities of smart command, smart weighing, smart measurement, and intelligent material identification, improving the digital level of the enterprise, and creating an industry benchmark.

[0101] The unmanned smart park solution includes a smart command system, a smart weighing system, an intelligent energy meter system, and an intelligent material identification system. Among them, the smart command system is based on technologies and capabilities such as video surveillance systems, license plate recognition systems, and the Internet of Things to achieve intelligent IoT of park equipment, automatic command and control, and create an unmanned demonstration park. The smart weighing system connects the ground scale through the control system, links the gate, license plate recognition device, anti-cheating system and other modes, and fully and intelligently detects the weighing of the ground scale and automatically obtains the vehicle weight result. The intelligent energy meter system realizes intelligent measurement based on laser scanning technology, which can be suitable for operation under various complex conditions, effectively improves the efficiency and measurement accuracy of fuel measurement, ensures that the construction progress and cost are effectively controlled, and effectively protects the interests of the factory, the boss, and the transportation vehicles. The intelligent material identification system uses artificial intelligence to complete the judgment of material categories and proportions, and automatically pushes them to the fuel system.

[0102] like Figure 1 As shown in the figure, with the goal of building an unmanned factory area including four modules: smart guard system, smart measurement system, smart material identification system, and smart large screen system, the entry process of the smart unmanned park is designed, as follows:

[0103] S1. Vehicle entry

[0104] S101. After the vehicle arrives at the park, it must go to the security booth, where the security guard will issue a safety helmet. The vehicle must then drive to the stop line and wait to enter.

[0105] S102. The driver drives into the gate according to the red and green instructions when the traffic light turns green.

[0106] The control logic of the traffic light is:

[0107] 1. Assign the initial state of the barrier gate i=0, j=0 (i, j represent the values ​​of the entrance and exit barriers respectively). When the barrier gate value is 0, the traffic light is green and the weighbridge is idle.

[0108] 2. When the barrier value is 0, the vehicle can enter the venue. After the barrier is raised and lowered, the values ​​of both barriers become 1;

[0109] 3. After the vehicle is finished and drives out, the exit barrier completes one lift and fall, the value is -1, the barrier value returns to the initial value 0, and the traffic light turns green

[0110] S103, the license plate recognition device completes the license plate recognition, and a voice prompt is given: Please enter the vehicle, and the license plate number is displayed on the screen of the license plate recognition device.

[0111] S104: Release the vehicle, and the vehicle enters the parking frame.

[0112] S2, automatic weighing

[0113] S201. The infrared anti-cheating system detects whether the vehicle is parked correctly and provides a voice prompt.

[0114] Specifically, the infrared positioning anti-cheating system + voice subsystem indicates whether the vehicle is parked properly. The voice broadcast is: The vehicle has been parked correctly, please get off the car and go to the QR code scanner to show the QR code and scan it!

[0115] S202. After the vehicle stops correctly, the voice system instructs the driver to get off the vehicle and scan the code to register the supplier information. After the driver presents the supplier's QR code, he scans the code by himself through a barcode scanner. The display screen presents: license plate-supplier association information and links the voice subsystem to broadcast the scan code registration result, and prompts the driver to wait on the spot.

[0116] Among them, the voice broadcast prompt is: Supplier-license plate registration is successful, weighing has started, please do not get on the car!

[0117] S203. After the code is scanned, the system reads the scale data, automatically fills in and displays the weighing result on the display screen, and simultaneously links the voice subsystem to broadcast the weighing result.

[0118] For example, after the code is scanned, the weighing management module detects the scale data. After the scale data stabilizes to the specified time requirement (the up and down fluctuation value does not exceed the threshold), the data is taken as the full load weight data for storage. The voice broadcast is: Weighing completed, the weight this time is 1000KG, start the volume measurement, please wait! In addition, the weighing result is displayed on the display screen.

[0119] S3, volume measurement

[0120] After weighing is completed, the volume measurement program is started, the radar is controlled to start scanning and modeling, the measurement results are automatically filled in and displayed on the display screen, and the voice subsystem is synchronously linked to broadcast the measurement results.

[0121] S3 includes:

[0122] S301, the radar above the vehicle scans the length, width and height of the vehicle

[0123] S302: The right front radar of the vehicle is started synchronously to measure the height of the vehicle compartment from the ground

[0124] S303: The measurement system performs point cloud data segmentation to obtain the (length, width, height) of the vehicle in the loaded state and the (length, width, height) of the initial cargo.

[0125] S304, the upper camera recognizes the material for the first time

[0126] S305, voice broadcast: Vehicle-supplier-cargo length, width, height! This measurement is over, please leave the site!

[0127] S306. Display the (length, width, height) of the initial goods on the display screen.

[0128] S4. Material identification

[0129] When measuring, AI is used to automatically identify the material category and specific gravity to complete the first identification. After the materials are poured, the identification results are manually confirmed and submitted to the system.

[0130] S5, pouring

[0131] The quality inspector logs into the system through a tablet, selects the license plate number, obtains the material category and material proportion results, and selects whether the AI ​​recognition is accurate. If it is inaccurate, a category name and proportion box will pop up for the quality inspector to manually select and enter. After clicking Submit, the driver's signature interface will pop up, and the driver will sign and confirm and the content will be synchronized to the system.

[0132] It should be noted that the initial material identification results were manually confirmed and corrected by quality inspectors. After the accuracy was improved to 95%, it was switched to automatic mode and the identification results were directly filled in.

[0133] In addition, if Figure 2 As shown in the figure, the exit process of the smart unmanned park is based on the entry process. After the quantity is completed, an electronic signature confirmation function is added. After the driver confirms and signs the supply information, the system controls the exit gate to release. The details are as follows:

[0134] S1. Vehicle exit

[0135] S101, the control platform determines whether there is an operating vehicle on the scale. When there is no operating vehicle on the scale, the traffic light turns green;

[0136] The control logic is:

[0137] 1. Assign the initial state of the barrier gate i=0, j=0 (i, j represent the values ​​of the entrance and exit barriers respectively). When the barrier gate value is 0, the traffic light is green and the weighbridge is idle.

[0138] 2. When the barrier value is 0, the vehicle can enter the venue. After the barrier is raised and lowered, the values ​​of both barriers become 1;

[0139] 3. After the vehicle completes the operation and drives out, the exit barrier completes one lifting and lowering of the barrier, the value is -1, the barrier value returns to the initial value 0, and the traffic light turns green.

[0140] S102, the license plate recognition device completes the license plate recognition, and a voice announcement is made: Please enter the vehicle, and the license plate number is displayed on the screen.

[0141] S2, automatic weighing

[0142] S201. Indicate whether the vehicle is parked properly through the infrared positioning anti-cheating system + voice subsystem.

[0143] After confirming the vehicle's parking specifications, a voice announcement will be made: The vehicle has been parked correctly, drivers please get off and go to the waiting area to wait for weighing!

[0144] For example, after the vehicle is stable, the weighing management module detects the scale data. After the scale data stabilizes to the specified time requirement (the up and down fluctuation value does not exceed the threshold), the data is taken as the unloaded weight data for storage. Voice broadcast: Weighing completed, this weight is 1000KG, please wait for the vehicle to be weighed!

[0145] S202. The display screen presents: supplier - license plate - empty weight data.

[0146] S3, volume measurement

[0147] S301. The radar above the vehicle scans the length, width and height of the vehicle.

[0148] S302. The system automatically compares the full load data and calculates the length, width and height of the cargo.

[0149] S303, Voice broadcast: Measurement completed, this weight is 1000KG, please sign to confirm!

[0150] S304. The display screen presents: supplier - license plate - empty volume data.

[0151] In addition, the following information is presented on the electronic screen: supplier, license plate, material type, cargo weight, and cargo volume. The driver confirms, signs the order, and clicks Submit.

[0152] S4. Leave

[0153] S401. After the electronic signature is signed, the gate lifts the bar to allow the vehicle to pass, and the vehicle drives away.

[0154] S402. The order data is pushed to the fuel system in the form of pictures.

[0155] S403, this measurement: supplier, material type, license plate, cargo weight, cargo volume information is pushed to the fuel system.

[0156] In addition, the vehicle drives to the security office to return the helmet. The supply information: supplier, license plate, category, cargo weight, cargo volume information is sent to the supplier via SMS.

[0157] In addition, when this solution is in the pilot stage, it will not be pushed directly to the fuel system. Instead, a manual confirmation function will be added. After the recognition results are output, they will be confirmed and labeled by back-end personnel. Once the accuracy rate is increased to more than 98%, it will be officially put into commercial use.

[0158] It should be noted that the parts in this embodiment that are the same or similar to those in Embodiments 1 and 2 can be referenced to each other and will not be described in detail in this application.

Claims

1. A new laser measurement process, characterized in that: include: S1. Obtain point cloud data of cargo vehicles through laser radar; S2. Preprocessing the point cloud data, wherein the preprocessing includes coordinate system conversion and noise filtering; S3. Calculate the volume of the cargo vehicle based on the preprocessed point cloud data; S4. acquiring point cloud data of the empty vehicle through a laser radar, and calculating the volume of the empty vehicle according to the point cloud data of the empty vehicle; S5. Calculate the volume of the material based on the volume of the loaded vehicle and the volume of the empty vehicle.

2. The novel laser measurement process according to claim 1 is characterized in that: In S1, point cloud data of the cargo vehicle is acquired through a first radar above the vehicle and a second radar on the side and front of the vehicle.

3. The novel laser measurement process according to claim 2, characterized in that S2 include: S201. Coordinate system conversion: When point cloud data is acquired by line scanning, in the object space coordinate system, the scanning forward direction is taken as the X axis, the Z axis is consistent with the zenith direction, and the laser scanner emission center is taken as the origin, thus forming a right-handed coordinate system; in this coordinate system, the external orientation elements are (XO, YO, ZO, φ, ω, κ), φ, ω, κ represent the rotation angles around the X axis, Y axis, and Z axis respectively; the distance s from the ground surface to the scanning center is measured by the laser scanner; the angle θ between the scanning line direction and the Z axis is recorded by the encoder, and the X axis direction coordinate is determined by the speed sensor. For each pulse, there is: x=0,y=-s*sinθ,z=-s*cosθ S202, noise point filtering: Assume that the average distance between all points in the point cloud data and their nearest k neighboring points satisfies the Gaussian distribution, determine the distance threshold based on the mean and variance of the distance, and when the average distance between a point and its nearest k points is greater than the distance threshold, determine that the point is an interference point and remove it.

4. The novel laser measurement process according to claim 3, characterized in that S3 include: S301, point cloud data slicing: between the minimum value 0 and the maximum value H of the vertical direction of the point cloud, a set of horizontal planes with equal spacing h are used to sequentially slice the point cloud from top to bottom, and a series of horizontal point cloud slices S are obtained in sequence. i ; S302, contour boundary determination: Use the bidirectional closest point search method to search the disordered plane point clouds S i Sort and generate the outer contour boundary polygon P of each point cloud slice scatter point i ; S303, slice area calculation: calculate P respectively i The area enclosed, i.e. S i Area A i ; S304, point cloud volume calculation: accumulate A i And multiply it by h to get the point cloud volume, that is, the volume V of the laser scanned object.

5. The novel laser measurement process according to claim 4 is characterized in that: In S1 and S4, before acquiring the point cloud data, the license plate of the vehicle is recognized; and after acquiring the point cloud data, the point cloud data and the license plate number of the corresponding vehicle are stored in a database.

6. The novel laser measurement process according to claim 5, characterized in that: Also includes: S6. Identify the type of material and display the type and volume of the material through a display device.

7. A new laser square measurement system, characterized in that: Used to execute the new laser measurement process described in any one of claims 1 to 6, comprising: a laser scanning radar, a control pan and a display device.

8. A new type of laser measuring device, characterized in that: A novel laser measurement process for executing any one of claims 1 to 6, comprising: An acquisition module, used to acquire point cloud data of a cargo vehicle through a laser radar; A preprocessing module, used for preprocessing the point cloud data, wherein the preprocessing includes coordinate system conversion and noise filtering; A first calculation module, used for calculating the volume of the cargo vehicle according to the preprocessed point cloud data; The second calculation module is used to obtain point cloud data of the empty vehicle through a laser radar, and calculate the volume of the empty vehicle according to the point cloud data of the empty vehicle; The third calculation module is used to calculate the volume of the material according to the volume of the loaded vehicle and the volume of the empty vehicle.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is read and executed by a processor, the novel laser measurement process according to any one of claims 1 to 6 is implemented.

Images