High-precision sandstone volume measurement method
Through the technology combined with single-line lidar and TOF camera, we can identify the vehicle profile and take pictures of sand and gravel point clouds, and use the baffle plane algorithm to calculate the volume, solving the problem of large error in sand and gravel volume measurement in the existing technology, achieving high accuracy and simplicity Measurement of the volume of the rod.
Patent Information
- Application Number
- CN202411263427.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2024-11-12
AI Technical Summary
The existing sand and gravel volume measurement methods have large measurement errors and low accuracy, especially under the influence of factors such as vehicle driving speed changes, ground slopes and driving route bending, which lead to disputes between buyers and sellers.
Single-line lidar is used to identify the vehicle profile, combine TOF camera and camera technology, and obtain the height and length of the cargo box through license plate recognition, continuously take pictures to capture the sand and gravel point clouds in the cargo box, calculate the volume using the baffle plane algorithm and integral method, and smooth filtering and segmentation processing to ensure measurement accuracy.
It improves the efficiency, accuracy and completeness of sand and gravel volume measurement, avoids manual estimation errors, is robust, adapts to uneven road surfaces and driving speed changes, and reduces measurement errors.
Smart Images

Figure CN118936314A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a high-precision sand and gravel volume measurement method, belonging to the technical field of measurement and detection. Background Art
[0002] At present, the measurement of sand and gravel is done manually, mainly using the weight-volume conversion method based on standard measuring instruments and the height difference method between cargo loading and vehicle frame. Both methods cause measurement deviations due to subjective and objective factors, causing disputes between buyers and sellers. The existing measurement system based on line scanning radar has many factors that cause measurement errors and low measurement accuracy. Especially in the sand and gravel collection and storage industry, factors such as large changes in vehicle speed, slopes on the ground, and curved routes will also affect the accuracy of the measurement system. Summary of the invention
[0003] In order to overcome the defects in the prior art, the present invention aims to provide a high-precision sand and gravel volume measurement method.
[0004] The technical solution provided by the present invention to solve the above technical problems is: a high-precision sand and gravel volume measurement method, comprising the following steps:
[0005] Step 1: Obtain the outline of the vehicle through a single-line laser radar, identify and determine the outline of the vehicle, and track the vehicle determined to be a truck;
[0006] Step 2: When the vehicle is in place, the license plate of the vehicle is identified by the camera;
[0007] Step 3: Obtain the height H and length L of the cargo box of the vehicle from the vehicle information database according to the license plate information of the vehicle;
[0008] Step 4: Continuously take pictures with the TOF camera and determine the appropriate exposure according to the ambient light intensity at that time;
[0009] Step 5: Take a photo of the cargo box of the vehicle according to appropriate exposure to obtain a photo of the cargo box;
[0010] Step 6: Obtain the volume of sand and gravel in the cargo box based on the photograph of the cargo box.
[0011] A further technical solution is that the specific process of step 1 is:
[0012] Step 11: Obtain the outline of the vehicle through a single-line laser radar;
[0013] Step 12: Identify and determine the outline of the vehicle, and only vehicles that meet the outline characteristics of a truck are determined to be trucks;
[0014] Step 13: Capture the contour feature points of the truck and make displacement judgment;
[0015] Step 14: When the rear end of the vehicle drives out, a tracking cycle is completed.
[0016] A further technical solution is that the vehicle information database includes the license plate numbers of all vehicles that need to be measured and the cargo box height H and cargo box length L of the corresponding vehicles.
[0017] A further technical solution is that in step 4, images are continuously taken through the TOF camera according to the set initial exposure, and 9 sampling areas are evenly selected to calculate the brightness, point cloud density, and signal-to-noise ratio of each area. Each area is judged to meet the conditions through the set brightness, point cloud density, and signal-to-noise ratio. If one area does not meet the conditions, the exposure is adjusted in steps and resampled until the brightness, point cloud density, and signal-to-noise ratio of each area meet the conditions, and the appropriate exposure is determined.
[0018] A further technical solution is that the specific process of taking pictures of the cargo box of the vehicle in step 5 is: under the tracking guidance of the single-line laser radar combined with the vehicle displacement algorithm, the TOF camera takes pictures of one car section every time the vehicle travels a distance Δs until the entire cargo box length L is photographed.
[0019] A further technical solution is that in step 6, the segmented point cloud is processed to obtain the volume of each segmented part, and finally the volumes of each segment are summed up to obtain the total volume.
[0020] A further technical solution is that the specific process of step 6 is:
[0021] Step 61: Perform smoothing filtering, spatial filtering, and hole filling processing on the segmented point cloud to filter out interference points and debris;
[0022] Step 62: For the filtered point cloud, use an algorithm to extract the baffle of the cargo box and the baffle plane, and the algorithm will evaluate the extracted plane;
[0023] Step 63, cutting the point cloud along the direction of the cargo box, and the length of the point cloud after cutting is Δs;
[0024] Step 64, segmenting the sand and gravel point cloud to obtain the final sand and gravel point cloud to be tested;
[0025] Step 65: Obtain the bottom plane equation of the cargo box according to the baffle plane equation and the cargo box height, divide the point cloud into several cubes using the integration method, calculate the distance H from the point in each cube to the bottom plane of the cargo box, calculate the cross-sectional area and volume of the cube, and then add up all the values to obtain the volume of the segmented point cloud;
[0026] Step 66: sum the volumes of each segment to obtain the total volume.
[0027] A further technical solution is to use filtering or clustering algorithm to segment the sand and gravel point cloud in step 64.
[0028] The present invention has the following beneficial effects: The present invention improves the efficiency, accuracy and completeness of measurement by obtaining the point cloud volume through an area array TOF camera. It replaces the manual estimation method to avoid the generation of errors. And by using a robust baffle plane algorithm, it avoids the errors caused by the truck passing through uneven roads. By using a cargo box direction calculation method, it avoids the errors caused by the change of the truck's travel direction. By using an area array camera, it avoids the errors caused by the uneven speed of the truck. The present invention overcomes the various shortcomings of the prior art and the difficulties of the use environment. BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 It is a schematic diagram of the process of the present invention;
[0030] Figure 2 Take pictures of the notation scheme;
[0031] Figure 3 The schematic diagram of the system composition is shown in Figure 2.
[0032] Figure 4 This is the plane extraction and segmentation effect diagram. DETAILED DESCRIPTION
[0033] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0034] like Figure 3 As shown, the hardware components of the present invention are composed of a gantry, a TOF camera, a single-line laser radar, and a computer.
[0035] like Figure 1 As shown, a high-precision sand and gravel volume measurement method of the present invention comprises the following steps:
[0036] Step 1: Obtain the outline of the vehicle through a single-line laser radar, identify and determine the outline of the vehicle, and track the vehicle determined to be a truck;
[0037] Step 11: Obtain the outline of the vehicle through a single-line laser radar;
[0038] Step 12: Identify and determine the outline of the vehicle, and only vehicles that meet the outline characteristics of a truck are determined to be trucks;
[0039] Step 13: Capture the contour feature points of the truck and make displacement judgment;
[0040] Step 14: When the rear end of the vehicle drives out, a tracking cycle is completed;
[0041] Step 2: When the vehicle is in place, the license plate of the vehicle is identified by the camera;
[0042] Step 3: Obtain the height H and length L of the cargo box of the vehicle from the vehicle information database according to the license plate information of the vehicle;
[0043] The vehicle information database includes the license plate numbers of all vehicles that need to be measured and the cargo box height H and cargo box length L of the corresponding vehicles;
[0044] Step 4: Continuously take pictures with the TOF camera and determine the appropriate exposure according to the ambient light intensity at that time;
[0045] Specifically, the TOF camera continuously takes pictures according to the set initial exposure, and evenly selects 9 sampling areas, calculates the brightness, point cloud density, and signal-to-noise ratio of each area, and determines whether each area meets the conditions through the set brightness, point cloud density, and signal-to-noise ratio. If one area does not meet the conditions, the exposure is adjusted step by step and resampled until the brightness, point cloud density, and signal-to-noise ratio of each area meet the conditions, and the appropriate exposure is determined;
[0046] Step 5: Take a photo of the cargo box of the vehicle according to appropriate exposure to obtain a photo of the cargo box;
[0047] The length of the cargo box is L, and the target length of the TOF camera along the vehicle's travel direction (i.e., the Y-axis direction) is L0. Under the tracking guidance of the single-line laser radar combined with the vehicle displacement algorithm: every time the vehicle travels a distance of Δs (Δs is slightly less than L0), the TOF shoots a car segment until the entire cargo box length L is shot, and the point cloud data is stored in the computer memory;
[0048] Step 6: Obtain the volume of sand and gravel in the cargo box according to the photographed image of the cargo box, process each segment point cloud, and calculate the volume V of each segment part i , sum up the segment volumes to get the total volume
[0049] Step 61: Perform smoothing filtering, spatial filtering, and hole filling processing on the segmented point cloud to filter out interference points and debris;
[0050] Step 62: For the filtered point cloud, use an algorithm to extract the baffle of the cargo box and the baffle plane, and the algorithm will evaluate the extracted plane;
[0051] Step 63, cutting the point cloud along the direction of the cargo box, the length of the point cloud after cutting (along the direction of the cargo box) is Δs;
[0052] Step 64, segmenting the sand and gravel point cloud to obtain the final sand and gravel point cloud to be tested;
[0053] Step 65: Obtain the bottom plane equation of the cargo box according to the baffle plane equation and the cargo box height, divide the point cloud into several cubes using the integration method, calculate the distance H from each point in the cube to the bottom plane of the cargo box, calculate the cross-sectional area S and volume V of the cube p =HS, then add up all the values to get the volume of the segmented point cloud
[0054] Step 66: Sum the segment volumes to get the total volume
[0055] The above description is not intended to limit the present invention in any form. Although the present invention has been disclosed through the above embodiments, it is not intended to limit the present invention. Any technician familiar with the profession can make some changes or modifications to equivalent embodiments of equivalent changes using the technical contents disclosed above without departing from the scope of the technical solution of the present invention. However, any simple modification, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are within the scope of the technical solution of the present invention.
Claims
1. A high-precision sand and gravel volume measurement method, characterized in that: The following steps are involved: Step 1: Obtain the outline of the vehicle through a single-line laser radar, identify and determine the outline of the vehicle, and track the vehicle determined to be a truck; Step 2: When the vehicle is in place, the license plate of the vehicle is identified by the camera; Step 3: Obtain the height H and length L of the cargo box of the vehicle from the vehicle information database according to the license plate information of the vehicle; Step 4: Continuously take pictures with the TOF camera and determine the appropriate exposure according to the ambient light intensity; Step 5: Take a photo of the cargo box of the vehicle according to appropriate exposure to obtain a photo of the cargo box; Step 6: Obtain the volume of sand and gravel in the cargo box based on the photograph of the cargo box.
2. A high-precision sand and gravel volume measurement method according to claim 1, characterized in that: The specific process of step 1 is as follows: Step 11: Obtain the outline of the vehicle through a single-line laser radar; Step 12: Identify and determine the outline of the vehicle, and only vehicles that meet the outline characteristics of a truck are determined to be trucks; Step 13: Capture the contour feature points of the truck and make displacement judgment; Step 14: When the rear end of the vehicle drives out, a tracking cycle is completed.
3. A high-precision sand and gravel volume measurement method according to claim 1, characterized in that: The vehicle information database includes the license plate numbers of all vehicles that need to be measured and the cargo box height H and cargo box length L of the corresponding vehicles.
4. A high-precision sand and gravel volume measurement method according to claim 1, characterized in that: In the step 4, the TOF camera is used to continuously take pictures according to the set initial exposure, and 9 sampling areas are evenly selected to calculate the brightness, point cloud density, and signal-to-noise ratio of each area. It is determined that each area meets the conditions based on the set brightness, point cloud density, and signal-to-noise ratio. If one area does not meet the conditions, the exposure is adjusted in steps and resampled until the brightness, point cloud density, and signal-to-noise ratio of each area meet the conditions, and the appropriate exposure is determined.
5. A high-precision sand and gravel volume measurement method according to claim 1, characterized in that: The specific process of taking pictures of the cargo box of the vehicle in step 5 is as follows: under the tracking guidance of the single-line laser radar combined with the vehicle displacement algorithm, the TOF camera takes pictures of one compartment segment every time the vehicle travels a distance Δs until the entire cargo box length L is photographed.
6. A high-precision sand and gravel volume measurement method according to claim 5, characterized in that: In step 6, the segmented point cloud is processed to obtain the volume of each segmented part, and finally the volumes of each segment are summed up to obtain the total volume.
7. A high-precision sand and gravel volume measurement method according to claim 6, characterized in that: The specific process of step 6 is as follows: Step 61: Perform smoothing filtering, spatial filtering, and hole filling processing on the segmented point cloud to filter out interference points and debris; Step 62: For the filtered point cloud, use an algorithm to extract the baffle of the cargo box and the baffle plane, and the algorithm will evaluate the extracted plane; Step 63, cutting the point cloud along the direction of the cargo box, and the length of the point cloud after cutting is Δs; Step 64, segmenting the sand and gravel point cloud to obtain the final sand and gravel point cloud to be tested; Step 65: Obtain the bottom plane equation of the cargo box according to the baffle plane equation and the cargo box height, divide the point cloud into several cubes using the integration method, calculate the distance H from the point in each cube to the bottom plane of the cargo box, calculate the cross-sectional area and volume of the cube, and then add up all the values to obtain the volume of the segmented point cloud; Step 66: sum the volumes of each segment to obtain the total volume.
8. A high-precision sand and gravel volume measurement method according to claim 7, characterized in that: In step 64, filtering or clustering algorithm is used to segment the sand and gravel point cloud.
