Vehicle measurement method, device and system, storage medium and program product

Abstract

The invention provides a vehicle measurement method, device and system, a storage medium and a program product, and belongs to the technical field of measurement. The vehicle measurement method comprises the steps that when a vehicle running in a channel enters a monitoring area of a first sensor, the first sensor is controlled to collect section contour point cloud data of the vehicle at a first time interval, and the first sensor is located on one side of the channel; a second sensor is controlled to collect section contour point cloud data of the vehicle at a second time interval, wherein the second sensor is located on the other side of the channel; performing point cloud splicing on the section contour point cloud data acquired by the first sensor and the section contour point cloud data acquired by the second sensor in a point cloud space to construct a point cloud data set; when the vehicle leaves the monitoring area of the second sensor, the first sensor and the second sensor are controlled to stop collecting the section contour point cloud data of the vehicle; measuring the length of the vehicle with a third sensor; and measuring the width and height of the vehicle according to the point cloud data set.

Description

Technical Field

[0001] This disclosure relates to the field of measurement technology, and in particular to a vehicle measurement method, apparatus and system, storage medium and program product. Background Technology

[0002] Currently, vehicle dimensions are primarily measured using sensors such as LiDAR. Basic data is obtained through multi-point scanning or interface scanning, and then the vehicle's dimensions are derived from this basic data. Summary of the Invention

[0003] The inventors noted that in related technologies, estimating vehicle dimensions by measuring several discrete points does not yield accurate measurement data.

[0004] Accordingly, this disclosure provides a vehicle measurement method that uses three sensors to accurately measure the vehicle profile, thereby accurately obtaining information on the vehicle's height, width, and length.

[0005] In a first aspect of this disclosure, a vehicle measurement method is provided, executed by a vehicle measurement device, comprising: when a vehicle traveling in a channel enters the monitoring area of ​​a first sensor, controlling the first sensor to acquire cross-sectional profile point cloud data of the vehicle at a first time interval, wherein the first sensor is located on one side of the channel and the height of the first sensor is greater than the height of the vehicle; controlling a second sensor to acquire cross-sectional profile point cloud data of the vehicle at a second time interval, wherein the second sensor is located on the other side of the channel, the second sensor and the first sensor are at the same height, and the first sensor is upstream of the second sensor in the channel direction; stitching the cross-sectional profile point cloud data acquired by the first sensor and the cross-sectional profile point cloud data acquired by the second sensor in a point cloud space to construct a point cloud dataset; when the vehicle leaves the monitoring area of ​​the second sensor, controlling the first sensor and the second sensor to stop acquiring cross-sectional profile point cloud data of the vehicle; measuring the length of the vehicle using a third sensor, wherein the third sensor is downstream of the second sensor in the channel direction; and measuring the width and height of the vehicle based on the point cloud dataset.

[0006] In some embodiments, measuring the width and height of the vehicle includes: processing the point cloud dataset to obtain a first horizontal distance between the first sensor and a first side of the vehicle near the first sensor, a second horizontal distance between the second sensor and a second side of the vehicle near the second sensor, and a vertical distance between the roof of the vehicle and the first or second sensor in a vertical direction; calculating the width of the vehicle based on a third horizontal distance between the first and second sensors in a specified direction, the first horizontal distance, and the second horizontal distance, wherein the specified direction is a direction perpendicular to the channel direction and parallel to the horizontal plane; and calculating the height of the vehicle based on the height of the first or second sensor and the vertical distance.

[0007] In some embodiments, calculating the width of the vehicle includes subtracting the first horizontal distance and the second horizontal distance from the third horizontal distance to obtain the width of the vehicle.

[0008] In some embodiments, calculating the height of the vehicle includes subtracting the vertical distance from the height of the first sensor or the second sensor to obtain the height of the vehicle.

[0009] In some embodiments, processing the point cloud dataset includes: filtering the point cloud dataset to obtain a dataset to be processed, wherein the filtering process employs at least one of statistical filtering, radius filtering, point cloud clustering filtering, pass-through filtering, voxel filtering, projection filtering, uniform sampling filtering, and bilateral filtering; and processing the dataset to be processed to obtain the first horizontal distance, the second horizontal distance, and the vertical distance.

[0010] In some embodiments, measuring the length of the vehicle using a third sensor includes: measuring a fourth horizontal distance between the front of the vehicle and the third sensor using the third sensor; and determining the length of the vehicle based on a fifth horizontal distance between the third sensor and the second sensor, and the fourth horizontal distance.

[0011] In some embodiments, determining the length of the vehicle includes subtracting the fourth horizontal distance from the fifth horizontal distance to obtain the length of the vehicle.

[0012] In some embodiments, before the vehicle enters the monitoring area of ​​the first sensor, the vehicle speed is measured using a fourth sensor; based on the vehicle speed and the first time interval, a first step length for stitching the cross-sectional contour point cloud data collected by the first sensor is determined; based on the vehicle speed and the second time interval, a second step length for stitching the cross-sectional contour point cloud data collected by the second sensor is determined.

[0013] In some embodiments, determining the first step length includes: calculating the product of the vehicle speed and the first time interval as the first step length; determining the second step length includes: calculating the product of the vehicle speed and the second time interval as the second step length.

[0014] In some embodiments, the third sensor and the fourth sensor are the same sensor.

[0015] In some embodiments, stitching the cross-sectional contour point cloud data collected by the first sensor in a point cloud space includes: placing the first cross-sectional contour point cloud data collected by the first sensor at a first predetermined coordinate value on a predetermined coordinate axis in the point cloud space; determining the coordinate value of the i-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis based on the coordinate value of the (i-1)-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis and the first step length, where i is a natural number greater than 1; and placing the i-th cross-sectional contour point cloud data collected by the first sensor in the point cloud space based on the coordinate value of the i-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis.

[0016] In some embodiments, the coordinate value of the i-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis is the sum of the coordinate value of the (i-1)-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis and the first step length.

[0017] In some embodiments, stitching the cross-sectional contour point cloud data acquired by the second sensor in the point cloud space includes: placing the first cross-sectional contour point cloud data acquired by the second sensor at a second predetermined coordinate value on a predetermined coordinate axis in the point cloud space, wherein the difference between the second predetermined coordinate value and the first predetermined coordinate value is the distance between the second sensor and the first sensor in the channel direction; determining the coordinate value of the j-th cross-sectional contour point cloud data acquired by the second sensor on the predetermined coordinate axis based on the coordinate value of the (j-1)-th cross-sectional contour point cloud data acquired by the second sensor on the predetermined coordinate axis and the second step size, where j is a natural number greater than 1; and placing the j-th cross-sectional contour point cloud data acquired by the second sensor in the point cloud space based on the coordinate value of the j-th cross-sectional contour point cloud data acquired by the second sensor on the predetermined coordinate axis.

[0018] In some embodiments, the coordinate value of the j-th cross-sectional contour point cloud data acquired by the second sensor on the predetermined coordinate axis is the sum of the coordinate value of the (j-1)-th cross-sectional contour point cloud data acquired by the second sensor on the predetermined coordinate axis and the second step size.

[0019] In a second aspect of this disclosure, a vehicle measuring device is provided, comprising: a memory; and a processor coupled to the memory, the processor being configured to execute instructions stored in the memory to implement the vehicle measuring method as described in any of the above embodiments.

[0020] In a third aspect of this disclosure, a vehicle measurement system is provided, comprising: a vehicle measurement device as described in any of the above embodiments; a first sensor disposed on one side of a passage, configured to send a first indication message to the vehicle measurement device when a vehicle traveling in the passage enters the monitoring area of ​​the first sensor, and, under the control of the vehicle measurement device, acquire cross-sectional profile point cloud data of the vehicle at a first time interval and send the acquired cross-sectional profile point cloud data to the vehicle measurement device, wherein the height of the first sensor is greater than the height of the vehicle; a second sensor disposed on the other side of the passage, configured to acquire cross-sectional profile point cloud data of the vehicle at a second time interval and send the acquired cross-sectional profile point cloud data to the vehicle measurement device, and, when a vehicle leaves the monitoring area of ​​the second sensor, send a second indication message to the vehicle measurement device, wherein the second sensor and the first sensor are at the same height, and the first sensor is located upstream of the second sensor in the passage direction; and a third sensor, configured to measure the horizontal distance between the front of the vehicle and the third sensor when the vehicle leaves the monitoring area of ​​the second sensor, and send the measurement result to the vehicle measurement device, wherein the third sensor is located downstream of the second sensor in the passage direction.

[0021] In some embodiments, the third sensor is configured to, under the control of the vehicle measuring device, measure the vehicle speed before the vehicle enters the monitoring area of ​​the first sensor, and send the measurement result to the vehicle measuring device.

[0022] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions that, when executed by a processor, implement the vehicle measurement method as described in any of the above embodiments.

[0023] According to a fifth aspect of the present disclosure, a computer program product is provided, including computer instructions, wherein the computer instructions, when executed by a processor, implement the vehicle measurement method as described in any of the above embodiments.

[0024] Other features and advantages of this disclosure will become clear from the following detailed description of exemplary embodiments with reference to the accompanying drawings. Attached Figure Description

[0025] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is a schematic flowchart of a vehicle measurement method according to an embodiment of the present disclosure;

[0027] Figure 2 This is a front view of a gantry crane according to an embodiment of this disclosure;

[0028] Figure 3 This is a schematic diagram of point cloud stitching according to an embodiment of the present disclosure;

[0029] Figure 4 This is a top view of a gantry crane according to an embodiment of the present disclosure;

[0030] Figure 5 This is a top view of a gantry crane according to another embodiment of the present disclosure;

[0031] Figure 6 This is a schematic diagram of distance measurement according to an embodiment of the present disclosure;

[0032] Figure 7 This is a schematic diagram of the structure of a vehicle measuring device according to an embodiment of the present disclosure;

[0033] Figure 8 This is a schematic diagram of the structure of a vehicle measurement system according to an embodiment of the present disclosure;

[0034] Figure 9 This is a schematic flowchart of a vehicle measurement method according to another embodiment of the present disclosure;

[0035] Figure 10 This is a front view of the vehicle body outline according to an embodiment of the present disclosure;

[0036] Figure 11 This is a top view of the vehicle body outline according to an embodiment of the present disclosure. Detailed Implementation

[0037] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. The following description of at least one exemplary embodiment is merely illustrative and is in no way intended to limit this disclosure or its application or use. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0038] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps set forth in these embodiments do not limit the scope of this disclosure.

[0039] At the same time, it should be understood that, for ease of description, the dimensions of the various parts shown in the accompanying drawings are not drawn according to actual scale.

[0040] Techniques, methods, and equipment known to those skilled in the art may not be discussed in detail, but where appropriate, such techniques, methods, and equipment should be considered part of the specification.

[0041] In all examples shown and discussed herein, any specific values ​​should be interpreted as merely exemplary and not as limitations. Therefore, other examples of exemplary embodiments may have different values.

[0042] It should be noted that similar labels and letters in the following figures indicate similar items; therefore, once an item is defined in one figure, it does not need to be discussed further in subsequent figures.

[0043] Figure 1 This is a schematic flowchart of a vehicle measurement method according to an embodiment of the present disclosure. In some embodiments, the vehicle measurement method described below is executed by a control device in a vehicle measurement apparatus, including steps 11-16.

[0044] In step 11, when a vehicle traveling in the channel enters the monitoring area of ​​the first sensor, the first sensor is controlled to collect the cross-sectional profile point cloud data of the vehicle at a first time interval.

[0045] It should be noted that the first sensor is located on one side of the channel, and the height of the first sensor is greater than the height of the vehicle.

[0046] For example, the first sensor is a lidar device whose scanning line plane is perpendicular to the channel direction (i.e., the direction of vehicle travel).

[0047] In step 12, the second sensor is controlled to acquire point cloud data of the vehicle's cross-sectional profile at a second time interval.

[0048] It should be noted that the second sensor is located on the other side of the channel, and the second sensor is at the same height as the first sensor. The first sensor is located upstream of the second sensor in the channel direction.

[0049] For example, the second sensor is a lidar device whose scanning line plane is perpendicular to the channel direction (i.e., the direction of vehicle travel).

[0050] In some embodiments, the first sensor and the second sensor may be single-line lidar devices that can emit laser pulses in different bands and at a first time interval and a second time interval, respectively.

[0051] In some embodiments, such as Figure 2 As shown, a gantry 201 is set up on the channel, and a sensor, namely sensor 21 and sensor 22, is installed on each side of the top of the gantry 201. When the vehicle 202 passes through the gantry 201, sensor 21 and sensor 22 respectively collect the cross-sectional contour point cloud data of the vehicle 202.

[0052] In step 13, the point cloud data of the cross-sectional contour collected by the first sensor and the point cloud data of the cross-sectional contour collected by the second sensor are stitched together in the point cloud space to construct a point cloud dataset.

[0053] In some embodiments, before point cloud stitching, the cross-sectional contour point cloud data collected by the first and second sensors are filtered to remove environmental point cloud data such as ground and gantry, so as to improve the measurement accuracy of vehicle dimensions.

[0054] In some embodiments, the vehicle speed is measured using a speed sensor before the vehicle enters the monitoring area of ​​the first sensor. For example, the speed sensor includes sensor devices such as reflective photoelectric sensors.

[0055] It's important to note that obtaining vehicle speed is crucial for improving the quality of the generated vehicle contour image and preventing severe stretching or compression. Furthermore, without speed measurement, the system defaults to uniform vehicle movement and allows for point cloud stitching using a fixed step size. After obtaining the vehicle's length data, the length of the vehicle contour point cloud data is scaled proportionally (e.g., if the measured vehicle length is 12 meters, and the point cloud contour stitched at a fixed step size is 20 meters, then the length of the contour point cloud is proportionally compressed to 12 meters). This method does not affect the measurement accuracy of the vehicle's length, width, and height.

[0056] Next, based on the vehicle speed and the first time interval, the first step length for stitching the cross-sectional profile point cloud data acquired by the first sensor is determined. Based on the vehicle speed and the second time interval, the second step length for stitching the cross-sectional profile point cloud data acquired by the second sensor is determined.

[0057] In some embodiments, the product of the vehicle speed and the first time interval is used as the first step length. The product of the vehicle speed and the second time interval is used as the second step length.

[0058] For example, if the vehicle speed is v, the first time interval is t1, and the second time interval is t2, then the first step length s1 is as shown in formula (1), and the second step length s2 is as shown in formula (2).

[0059] (1)

[0060] (2)

[0061] In some embodiments, the step of stitching the cross-sectional contour point cloud data collected by the first sensor into a point cloud space includes steps S11-S13.

[0062] S11. Place the first cross-sectional contour point cloud data collected by the first sensor at the first predetermined coordinate value on the predetermined coordinate axis in the point cloud space.

[0063] For example, the first cross-sectional contour point cloud data collected by the first sensor is placed at x=0 on the x-coordinate axis in the point cloud space.

[0064] S12. Based on the coordinate values ​​of the (i-1)th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis and the first step length, determine the coordinate values ​​of the i-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis, where i is a natural number greater than 1.

[0065] In some embodiments, the coordinate value of the i-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis is the sum of the coordinate value of the (i-1)-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis and the first step length.

[0066] S13. Based on the coordinate values ​​of the i-th cross-sectional contour point cloud data collected by the first sensor on the predetermined coordinate axis, place the i-th cross-sectional contour point cloud data collected by the first sensor in the point cloud space.

[0067] For example, such as Figure 3 As shown, the coordinate value of the (i-1)th cross-sectional contour point cloud data P_i-1 collected by the first sensor on the x-axis is x_i-1. The first step length is s1. Then the coordinate value of the i-th cross-sectional contour point cloud data P_i collected by the first sensor on the x-axis is x_i, as shown in formula (3).

[0068] x_i = x_i-1 + s1 (3)

[0069] For example, the first cross-sectional contour point cloud data collected by the first sensor is placed at x=0 on the x-axis of the point cloud space; the second cross-sectional contour point cloud data collected by the first sensor is placed at x=s1 on the x-axis of the point cloud space, where s1 is the stitching step size corresponding to the first sensor; the third cross-sectional contour point cloud data collected by the first sensor is placed at x=2s1 on the x-axis of the point cloud space, and so on. It can be understood that the stitching step size will change accordingly as the vehicle speed v changes.

[0070] In some embodiments, the step of stitching the cross-sectional contour point cloud data collected by the second sensor in the point cloud space includes steps S21-S23.

[0071] S21. Place the first cross-sectional contour point cloud data collected by the second sensor at the second predetermined coordinate value on the predetermined coordinate axis in the point cloud space, wherein the difference between the second predetermined coordinate value and the first predetermined coordinate value is the distance between the second sensor and the first sensor in the channel direction.

[0072] For example, if the distance between the second sensor and the first sensor in the channel direction is d, and the first cross-sectional contour point cloud data collected by the first sensor is placed at x=0 on the x-coordinate axis in the point cloud space, then the first cross-sectional contour point cloud data collected by the second sensor is placed at x=d on the x-coordinate axis in the point cloud space.

[0073] S22. Based on the coordinate values ​​of the (j-1)th cross-sectional contour point cloud data collected by the second sensor on the predetermined coordinate axis and the second step size, determine the coordinate values ​​of the j-th cross-sectional contour point cloud data collected by the second sensor on the predetermined coordinate axis, where j is a natural number greater than 1.

[0074] In some embodiments, the coordinate value of the j-th cross-sectional contour point cloud data acquired by the second sensor on the predetermined coordinate axis is the sum of the coordinate value of the (j-1)-th cross-sectional contour point cloud data acquired by the second sensor on the predetermined coordinate axis and the second step size.

[0075] S23. Based on the coordinate values ​​of the j-th cross-sectional contour point cloud data collected by the second sensor on the predetermined coordinate axis, place the j-th cross-sectional contour point cloud data collected by the second sensor in the point cloud space.

[0076] For example, the first cross-sectional contour point cloud data collected by the second sensor is placed at position x=d on the x-axis of the point cloud space, the second cross-sectional contour point cloud data collected by the second sensor is placed at position x=d+s2 on the x-axis of the point cloud space, where s2 is the stitching step size corresponding to the second sensor, the third cross-sectional contour point cloud data collected by the first sensor is placed at position x=d+2s2 on the x-axis of the point cloud space, and so on.

[0077] In step 14, when the vehicle leaves the monitoring area of ​​the second sensor, the first and second sensors are controlled to stop collecting cross-sectional contour point cloud data of the vehicle.

[0078] In step 15, the length of the vehicle is measured using a third sensor, which is located downstream of the second sensor in the channel direction.

[0079] In some embodiments, a third sensor is used to measure the horizontal distance len1 between the front of the vehicle and the third sensor. The length of the vehicle is determined based on the horizontal distance len2 between the third sensor and the second sensor, and the horizontal distance len1.

[0080] In some embodiments, the length L of the vehicle is obtained by subtracting the horizontal distance len1 from the horizontal distance len2.

[0081] For example, the length L of the vehicle is shown in formula (4).

[0082] L = len2 – len1 (4)

[0083] Figure 4 This is a top view of a gantry crane according to an embodiment of this disclosure. Figure 4 As shown, a first sensor 21 and a second sensor 22 are respectively installed on both sides of the top of the gantry 201. The arrows indicate the channel direction, i.e., the vehicle's travel direction. The scan line plane 211 of the first sensor 21 and the scan line plane 221 of the second sensor 22 are perpendicular to the channel direction. The first sensor 21 is located upstream of the second sensor 22 in the channel direction. The first sensor 21 and the second sensor 22 are used to collect point cloud data of the vehicle's cross-sectional profile.

[0084] For example, in the channel direction, the distance between the first sensor 21 and the second sensor 22 is d. The first sensor 21 and the second sensor 22 can be lidar devices, and the scanning planes of the first sensor 21 and the second sensor 22 are both perpendicular to the channel direction (i.e., the vehicle's travel direction).

[0085] The third sensor 23 is located downstream of the second sensor 22 in the channel direction and is used to measure the length of the vehicle.

[0086] For example, the third sensor 23 can be a lidar device with its scan line plane parallel to the horizontal plane.

[0087] In addition, the fourth sensor 24 is a speed sensor used to measure the vehicle speed.

[0088] For example, the fourth sensor 24 can be a sensor device such as a reflective photoelectric sensor.

[0089] In some embodiments, the third sensor 23 and the fourth sensor 24 can be the same sensor. That is, the same sensor is used to measure the length of the vehicle and the vehicle speed.

[0090] Figure 5 This is a top view of a gantry crane according to another embodiment of this disclosure. Figure 5 and Figure 4 The difference is that, in Figure 5 In the illustrated embodiment, the third sensor 51 is located downstream of the second sensor 22 in the channel direction and is used to measure the length of the vehicle and its speed. For example, the third sensor 51 may be a lidar device with its scan line plane parallel to the horizontal plane.

[0091] In step 16, the width and height of the vehicle are measured based on the point cloud dataset.

[0092] In some embodiments, the steps of measuring the width and height of the vehicle include steps S31-S33.

[0093] S31, such as Figure 6 As shown, the point cloud dataset 61 is processed to obtain the horizontal distance wm1 between the first sensor 21 and the first side of the vehicle closest to the first sensor, the horizontal distance wm2 between the second sensor 22 and the second side of the vehicle closest to the second sensor, and the vertical distance hm between the roof of the vehicle and the first sensor or the second sensor in the vertical direction.

[0094] S32. Calculate the width of the vehicle based on the horizontal distances ws, wm1, and wm2 of the first sensor 21 and the second sensor 22 in a specified direction, wherein the specified direction is a direction perpendicular to the channel direction and parallel to the horizontal plane.

[0095] In some embodiments, the width W of the vehicle is obtained by subtracting the horizontal distances wm1 and wm2 from the horizontal distance ws, as shown in formula (5).

[0096] W = ws – wm1 – wm2 (5)

[0097] S33. Calculate the height of the vehicle based on the height hs of the first sensor 21 or the second sensor 22 and the vertical distance hm.

[0098] In some embodiments, the height hs of the first sensor or the second sensor is subtracted from the vertical distance hm to obtain the height H of the vehicle, as shown in formula (6).

[0099] H = hs – hm (6)

[0100] In some embodiments, the point cloud dataset is filtered before calculating the width and height of the vehicle to remove any noise points that may be present.

[0101] In some embodiments, the step of processing the point cloud dataset in step S31 above includes steps S41-S42.

[0102] S41. Filter the point cloud dataset to obtain the dataset to be processed.

[0103] For example, filtering can employ at least one of the following: statistical filtering, radius filtering, point cloud clustering filtering, pass-through filtering, voxel filtering, projection filtering, uniform sampling filtering, and bilateral filtering.

[0104] It should be noted that after obtaining the point cloud data of the vehicle, outliers in the point cloud data need to be removed by filtering. These outliers may be noise caused by reflections, flying birds, mosquitoes, etc., which will affect the measurement results of the vehicle's length, width and height.

[0105] For example, in statistical filtering, the average distance between the nth point cloud data and every point cloud data in the neighborhood of the nth point cloud data is calculated. N is the total number of point cloud data in the point cloud dataset. If the average distance is greater than the first threshold, the nth point cloud data is deleted.

[0106] For example, the standard deviation of the distance between the nth point cloud data and every point cloud data in the neighborhood of the nth point cloud data is calculated, and the corresponding first threshold is the weighted sum of the average distance and the standard deviation of the distance. For example, the weight of the average distance is 1, and the weight of the standard deviation of the distance is 3.

[0107] This statistical filtering process can effectively remove discrete noise points caused by environmental interference or equipment noise.

[0108] For example, in radius filtering, the amount of point cloud data in the neighborhood of the m-th point cloud data in the first dataset to be processed is counted. M represents the total number of point cloud data in the first dataset to be processed. If the amount of point cloud data is less than the second threshold, then the m-th point cloud data is deleted.

[0109] It's important to note that in radius filtering, if the number of neighboring points of a point is less than a set minimum threshold, that point is considered to be in a sparse region and may be noise, thus being removed. This effectively removes noise points from the vehicle's contour edges while preserving the vehicle's main contour features.

[0110] For example, in point cloud clustering and filtering, Euclidean distance clustering is performed on the point cloud data of the vehicle body, and smaller point cloud data clusters are filtered out based on the size of the clusters.

[0111] S42. Based on the dataset to be processed, obtain the first horizontal distance, the second horizontal distance, and the vertical distance.

[0112] In the vehicle detection method provided in the above embodiments of this disclosure, the vehicle outline can be accurately measured by using three sensors, thereby accurately obtaining the vehicle's height, width and length information. This provides accurate measurement results for application scenarios such as vehicle detection and height and width restriction management.

[0113] In some embodiments, images of the vehicle contour point cloud dataset from multiple angles, such as front view, top view, and side view, can be further saved to provide users with an intuitive visual presentation. In addition, a PCD file of the vehicle contour point cloud before filtering is stored. This PCD file contains all measurement data during the vehicle's passage through the gantry, facilitating historical data review and 3D contour display for users.

[0114] Figure 7 This is a schematic diagram of the structure of a vehicle measuring device according to an embodiment of the present disclosure.

[0115] like Figure 7 As shown, the vehicle measurement device 70 is presented in the form of a general-purpose computing device. The vehicle measurement device 70 includes a memory 71, a processor 72, and a bus 73 connecting different system components.

[0116] The memory 71 may include, for example, system memory, non-volatile storage media, etc. The system memory may store, for example, an operating system, application programs, a boot loader, and other programs. The system memory may include volatile storage media, such as random access memory (RAM) and / or cache memory. The non-volatile storage media may store, for example, instructions for a corresponding embodiment of at least one vehicle measurement method being executed. Non-volatile storage media include, but are not limited to, disk storage, optical storage, flash memory, etc.

[0117] The processor 72 can be implemented using a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete hardware components such as discrete gates or transistors. Accordingly, each module, such as the acquisition module, the calculation module, and the adjustment module, can be implemented by executing instructions in the central processing unit (CPU) running memory to perform the corresponding steps, or by implementing dedicated circuits that perform the corresponding steps.

[0118] For example, processor 72 is configured for memory-based instruction execution implementation such as Figure 1 The method involved in any of the embodiments.

[0119] Bus 73 can use any of the various bus architectures. For example, bus architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MCA) bus, and the Peripheral Component Interconnect (PCI) bus.

[0120] The interfaces 74, 75, and 76 of the vehicle measuring device 70, as well as the memory 71 and processor 72, can be connected via bus 73. Input / output interface 74 provides a connection interface for input / output devices such as displays, mice, and keyboards. Network interface 75 provides a connection interface for various networked devices. Storage interface 76 provides a connection interface for external storage devices such as floppy disks, USB flash drives, and SD cards.

[0121] Various aspects of this disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations thereof, can be implemented by computer-readable program instructions.

[0122] These computer-readable program instructions are provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable device to produce a machine, such that execution of the instructions by the processor produces means for implementing the functions specified in one or more boxes of the flowchart and / or block diagram.

[0123] These computer-readable program instructions may also be stored in a computer-readable storage medium. These instructions cause a computer to work in a particular manner to produce an article of manufacture, including instructions that implement the functions specified in one or more boxes in a flowchart and / or block diagram.

[0124] This disclosure may take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects.

[0125] This disclosure also provides a computer-readable storage medium storing computer instructions that, when executed by a processor, implement... Figure 1The method involved in any of the embodiments.

[0126] This disclosure also provides a computer program product, including computer instructions, wherein the computer instructions, when executed by a processor, implement as follows: Figure 1 The method involved in any of the embodiments.

[0127] Figure 8 This is a schematic diagram of the structure of a vehicle measurement system according to an embodiment of this disclosure. Figure 8 As shown, the vehicle measurement system includes a vehicle measuring device 80, a first sensor 81, a second sensor 82, and a third sensor 83. The vehicle measuring device 80 is... Figure 7 The vehicle measuring device involved in any of the embodiments.

[0128] A first sensor 81 is disposed on one side of the passage and is configured to send a first indication message to a vehicle measuring device 80 when it detects a vehicle traveling in the passage entering the monitoring area of ​​the first sensor. Based on the first indication message, the vehicle measuring device 80 controls the first sensor 81 and the second sensor 82 to collect cross-sectional profile point cloud data of the vehicle. Under the control of the vehicle measuring device 80, the first sensor 81 collects the cross-sectional profile point cloud data of the vehicle at first time intervals and sends the collected cross-sectional profile point cloud data to the vehicle measuring device 80.

[0129] It should be noted that the height of the first sensor 81 is greater than the height of the vehicle.

[0130] The second sensor 82 is located on the other side of the channel and is configured to collect cross-sectional profile point cloud data of the vehicle at a second time interval according to the control of the vehicle measuring device 80, and send the collected cross-sectional profile point cloud data to the vehicle measuring device 80. When the vehicle is detected to have left the monitoring area of ​​the second sensor 82, the sensor 82 sends a second instruction message to the vehicle measuring device 80 so that the vehicle measuring device 80 controls the first sensor 81 and the second sensor 82 to stop collecting cross-sectional profile point cloud data of the vehicle.

[0131] It should be noted that the second sensor 82 and the first sensor 81 are at the same height, and the first sensor 81 is located upstream of the second sensor 82 in the channel direction.

[0132] The third sensor 83 is configured to measure the horizontal distance between the front of the vehicle and the third sensor 83 when the vehicle leaves the monitoring area of ​​the second sensor 82, under the control of the vehicle measuring device 80, and send the measurement result to the vehicle measuring device 80 so that the vehicle measuring device 80 can calculate the length of the vehicle based on the measurement result.

[0133] It should be noted that the third sensor 83 is located downstream of the second sensor 82 in the channel direction.

[0134] In some embodiments, the third sensor 83 is configured to measure the vehicle speed before the vehicle enters the monitoring area of ​​the first sensor, under the control of the vehicle measuring device 80, and send the measurement result to the vehicle measuring device 80, so that the vehicle measuring device 80 can use the vehicle speed information to determine the first step length for stitching the cross-sectional profile point cloud data collected by the first sensor, and the second step length for stitching the cross-sectional profile point cloud data collected by the second sensor.

[0135] The following specific examples illustrate this disclosure.

[0136] For example, using such Figure 8 The vehicle measurement system shown measures the length, height, and width of a vehicle. The corresponding processing flow is as follows: Figure 9 As shown.

[0137] In step 91, before the vehicle enters the monitoring area of ​​the sensor, the vehicle speed is measured using a third sensor.

[0138] Next, based on the vehicle speed and the first time interval, the first step length for stitching the cross-sectional profile point cloud data acquired by the first sensor is determined. Based on the vehicle speed and the second time interval, the second step length for stitching the cross-sectional profile point cloud data acquired by the second sensor is determined.

[0139] In step 92, when the vehicle enters the monitoring area of ​​the first sensor, the first sensor is controlled to collect the cross-sectional profile point cloud data of the vehicle at a first time interval, and the second sensor is controlled to collect the cross-sectional profile point cloud data of the vehicle at a second time interval.

[0140] In step 93, the collected cross-sectional contour point cloud data is filtered to remove environmental point cloud data.

[0141] In step 94, point cloud stitching is performed.

[0142] That is, the point cloud data of the cross-sectional contour collected by the first sensor is stitched together in the point cloud space using the first step length, and the point cloud data of the cross-sectional contour collected by the second sensor is stitched together in the point cloud space using the second step length, so as to construct a point cloud dataset.

[0143] In step 95, it is determined whether the vehicle has left the measurement area of ​​the second sensor.

[0144] If the vehicle has not left the measurement area of ​​the second sensor, return to step 92. Otherwise, proceed to step 96.

[0145] In step 96, the length of the vehicle is measured using a third sensor.

[0146] For example, the length of the vehicle can be calculated using the formula (4) above.

[0147] In step 97, the point cloud dataset in the point cloud space is filtered.

[0148] For example, statistical filtering algorithms and radius filtering algorithms can be used to filter point cloud datasets.

[0149] In step 98, the width and height of the vehicle are calculated.

[0150] For example, the width of the vehicle can be calculated using the formula (5) above, and the height of the vehicle can be calculated using the formula (6) above.

[0151] In step 99, the data is saved and output.

[0152] It should be noted that the system saves images of the vehicle outline point cloud dataset from multiple angles, including front view, top view, and side view, providing users with an intuitive visual presentation.

[0153] For example, a front view of the vehicle's body outline. Figure 10 As shown, the top view of the vehicle's body outline is as follows: Figure 11 As shown.

[0154] It should also be noted here that, as Figure 2 As shown, two sensors are installed on the top of the gantry crane. If only one sensor is installed on the top of the gantry crane, for example, if the sensor is placed at the center of the top of the gantry crane, only the width of the vehicle can be measured, but the height of the vehicle cannot be accurately measured, and a complete outline view of the vehicle body cannot be obtained.

[0155] By implementing this disclosure, the following beneficial effects can be obtained.

[0156] 1) Visualize measurement results, enabling intuitive display of the results and facilitating historical data tracing and reproduction. Filtering removes noise from point cloud data, improving the accuracy and reliability of the measurement results and ensuring they more accurately reflect the actual dimensions of the vehicle.

[0157] 2) The visualization function of this system allows users to understand the outline of the vehicle directly through images, rather than relying solely on abstract numerical values.

[0158] For example, at vehicle inspection stations, staff can quickly determine whether a vehicle is oversized, overweight, or overlength based on the generated contour images, without relying solely on data for estimation. This not only improves work efficiency but also reduces misjudgments caused by data interpretation errors. Simultaneously, the introduction of filtering effectively enhances the reliability of measurement results, avoiding unnecessary disputes and losses due to measurement errors.

[0159] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0160] The description in this disclosure is provided for illustrative and descriptive purposes only and is not intended to be exhaustive or to limit the disclosure to its forms. Many modifications and variations will be apparent to those skilled in the art. The embodiments were chosen and described in order to better illustrate the principles and practical application of this disclosure and to enable those skilled in the art to understand this disclosure and to design various embodiments with various modifications suitable for a particular purpose.

Claims

1. A vehicle measurement method performed by a vehicle measurement device, comprising: controlling a first sensor to collect cross-sectional profile point cloud data of a vehicle at a first time interval when the vehicle driving in a passageway enters a monitoring area of the first sensor, wherein the first sensor is located at one side of the passageway, and a height of the first sensor is greater than a height of the vehicle; controlling a second sensor to collect cross-sectional profile point cloud data of the vehicle at a second time interval, wherein the second sensor is located at another side of the passageway, a height of the second sensor is the same as the height of the first sensor, and the first sensor is located upstream of the second sensor in a passageway direction; performing point cloud registration on the cross-sectional profile point cloud data collected by the first sensor and the cross-sectional profile point cloud data collected by the second sensor in a point cloud space to construct a point cloud data set; controlling the first sensor and the second sensor to stop collecting the cross-sectional profile point cloud data of the vehicle when the vehicle leaves the monitoring area of the second sensor; measuring a length of the vehicle by using a third sensor, wherein the third sensor is located downstream of the second sensor in the passageway direction; measuring a width and a height of the vehicle according to the point cloud data set.

2. The vehicle measurement method according to claim 1, wherein The measuring of the width and the height of the vehicle comprises: processing the point cloud data set to obtain a first horizontal distance from the first sensor to a first side surface of the vehicle close to the first sensor, a second horizontal distance from the second sensor to a second side surface of the vehicle close to the second sensor, and a vertical distance from a roof of the vehicle to the first sensor or the second sensor in a vertical direction; calculating the width of the vehicle according to a third horizontal distance of the first sensor and the second sensor in a specified direction, the first horizontal distance, and the second horizontal distance, wherein the specified direction is perpendicular to the passageway direction and parallel to a horizontal plane; calculating the height of the vehicle according to the height of the first sensor or the second sensor and the vertical distance.

3. The vehicle measurement method according to claim 2, wherein The calculating of the width of the vehicle comprises: subtracting the first horizontal distance and the second horizontal distance from the third horizontal distance to obtain the width of the vehicle.

4. The vehicle measurement method according to claim 2, wherein The calculating of the height of the vehicle comprises: subtracting the vertical distance from the height of the first sensor or the second sensor to obtain the height of the vehicle.

5. The vehicle measurement method according to claim 2, wherein The processing of the point cloud data set comprises: performing filtering processing on the point cloud data set to obtain a to-be-processed data set, wherein the filtering processing adopts at least one of statistical filtering, radius filtering, point cloud clustering filtering, straight-through filtering, voxel filtering, projection filtering, uniform sampling filtering, and bilateral filtering; processing the to-be-processed data set to obtain the first horizontal distance, the second horizontal distance, and the vertical distance.

6. The vehicle measurement method according to claim 1, wherein The measuring of the length of the vehicle by using the third sensor comprises: measuring a fourth horizontal distance between a front end of the vehicle and the third sensor by using the third sensor; According to a fifth horizontal distance between the third sensor and the second sensor, and the fourth horizontal distance, a length of the vehicle is determined.

7. The vehicle measurement method according to claim 6, wherein The determining the length of the vehicle comprises: The fifth horizontal distance is subtracted by the fourth horizontal distance, to obtain the length of the vehicle.

8. The vehicle measurement method according to any one of claims 1-7, further comprising: Before the vehicle enters a monitoring area of the first sensor, a vehicle speed of the vehicle is measured by a fourth sensor; According to the vehicle speed and the first time interval, a first step length for splicing the cross-sectional profile point cloud data collected by the first sensor is determined; According to the vehicle speed and the second time interval, a second step length for splicing the cross-sectional profile point cloud data collected by the second sensor is determined.

9. The vehicle measurement method according to claim 8, wherein The determining the first step length comprises: A product of the vehicle speed and the first time interval is calculated as the first step length; The determining the second step length comprises: A product of the vehicle speed and the second time interval is calculated as the second step length.

10. The vehicle measurement method according to claim 8, wherein The third sensor and the fourth sensor are the same sensor.

11. The vehicle measurement method according to claim 8, wherein, The point cloud splicing of the cross-sectional profile point cloud data collected by the first sensor in the point cloud space comprises: The first cross-sectional profile point cloud data collected by the first sensor is placed at a first predetermined coordinate value on a predetermined coordinate axis in the point cloud space; According to a coordinate value of the i-1th cross-sectional profile point cloud data collected by the first sensor on the predetermined coordinate axis, and the first step length, a coordinate value of the ith cross-sectional profile point cloud data collected by the first sensor on the predetermined coordinate axis is determined, i being a natural number greater than 1; According to the coordinate value of the ith cross-sectional profile point cloud data collected by the first sensor on the predetermined coordinate axis, the ith cross-sectional profile point cloud data collected by the first sensor is placed in the point cloud space.

12. The vehicle measurement method according to claim 11, wherein The coordinate value of the ith cross-sectional profile point cloud data collected by the first sensor on the predetermined coordinate axis is a sum of the coordinate value of the i-1th cross-sectional profile point cloud data collected by the first sensor on the predetermined coordinate axis and the first step length.

13. The vehicle measurement method of claim 11, wherein, The point cloud splicing of the cross-sectional profile point cloud data collected by the second sensor in the point cloud space comprises: The first cross-sectional profile point cloud data collected by the second sensor is placed at a second predetermined coordinate value on a predetermined coordinate axis in the point cloud space, wherein a difference between the second predetermined coordinate value and the first predetermined coordinate value is a distance between the second sensor and the first sensor in the channel direction; According to a coordinate value of the j-1th cross-sectional profile point cloud data collected by the second sensor on the predetermined coordinate axis, and the second step length, a coordinate value of the jth cross-sectional profile point cloud data collected by the second sensor on the predetermined coordinate axis is determined, j being a natural number greater than 1; According to the coordinate value of the jth cross-sectional profile point cloud data collected by the second sensor on the predetermined coordinate axis, the jth cross-sectional profile point cloud data collected by the second sensor is placed in the point cloud space.

14. The vehicle measurement method of claim 13, wherein, The coordinate value of the jth cross-sectional profile point cloud data collected by the second sensor on the predetermined coordinate axis is the sum of the coordinate value of the j-1th cross-sectional profile point cloud data collected by the second sensor on the predetermined coordinate axis and the second step length.

15. A vehicle measurement device, comprising: a memory; a processor coupled to the memory, the processor configured to implement the vehicle measurement method of any one of claims 1-14 based on instructions stored in the memory.

16. A vehicle measurement system, comprising: the vehicle measurement device of claim 15; a first sensor disposed on one side of the passage, configured to send first indication information to the vehicle measurement device when detecting that a vehicle driving in the passage enters a monitoring area of the first sensor, collect cross-sectional profile point cloud data of the vehicle at a first time interval according to control of the vehicle measurement device, and send the collected cross-sectional profile point cloud data to the vehicle measurement device, wherein the height of the first sensor is greater than the height of the vehicle; a second sensor disposed on the other side of the passage, configured to collect cross-sectional profile point cloud data of the vehicle at a second time interval according to control of the vehicle measurement device, and send the collected cross-sectional profile point cloud data to the vehicle measurement device, send second indication information to the vehicle measurement device when detecting that the vehicle leaves a monitoring area of the second sensor, wherein the height of the second sensor is the same as that of the first sensor, and the first sensor is upstream of the second sensor in the passage direction; a third sensor configured to measure a horizontal distance between a vehicle head of the vehicle and the third sensor when the vehicle leaves the monitoring area of the second sensor according to control of the vehicle measurement device, and send the measurement result to the vehicle measurement device, wherein the third sensor is downstream of the second sensor in the passage direction.

17. The vehicle measurement method of claim 16, wherein, the third sensor is configured to measure a vehicle speed of the vehicle before the vehicle enters the monitoring area of the first sensor according to control of the vehicle measurement device, and send the measurement result to the vehicle measurement device.

18. A computer readable storage medium, wherein, A computer readable storage medium stores computer instructions, which, when executed by a processor, implement the vehicle measurement method of any one of claims 1-14.

19. A computer program product, comprising computer instructions, wherein the computer instructions, when executed by a processor, implement the vehicle measurement method of any one of claims 1-14.

Images