Gate separation vehicle identification method, system and device based on point cloud and storage medium

Abstract

This invention provides a point cloud-based gate vehicle identification method, system, device, and storage medium. The method includes the following steps: A lidar is installed on one side of the road at the gate; the lidar collects point cloud information of vehicles passing through the gate in real time to obtain first point cloud data; the first point cloud data is clustered to obtain second point cloud data; the second point cloud data is identified based on a first neural network to obtain at least vehicle type information; the point cloud representing a local space of container trucks is truncated based on a preset height range to obtain fourth point cloud data; the fourth point cloud data is identified based on a second neural network to obtain container length information and container parking space information. This invention can locate and analyze each container truck passing through the gate, thereby improving the accuracy of vehicle identification information and obtaining container size and container parking space information, significantly improving the efficiency and detection accuracy of vehicles entering and exiting gates in container terminals or yards.

Description

Technical Field

[0001] This invention relates to the field of vehicle monitoring, and more specifically, to a point cloud-based gate vehicle identification system, method, device, and storage medium. Background Technology

[0002] Container terminals or yards are typically enclosed areas connected to external roads via gates. Container trucks entering and exiting the area need to register various information, such as license plate number, whether they are carrying containers, and container parking space information. Traditional terminals or yards usually require manual verification of this information when vehicles enter and exit, which is often inefficient and prone to occasional registration errors.

[0003] While existing technologies include methods for vehicle identification through video recognition, simple video recognition has a large margin of error and is prone to missing vehicles or failing to collect accurate container dimensions and container parking information, making it unsuitable for unmanned or smart terminal scenarios.

[0004] In view of this, the present invention provides a method, system, device and storage medium for gate vehicle identification based on point cloud.

[0005] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of the present invention, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] To address the problems in the prior art, the present invention aims to provide a point cloud-based gate vehicle identification method, system, device, and storage medium, which overcomes the difficulties of the prior art. It can locate and analyze each truck passing through the gate to improve the accuracy of vehicle identification information and obtain container size and container parking information, thereby significantly improving the efficiency and detection accuracy of vehicles entering and exiting the gate in container terminals or yards.

[0007] Embodiments of the present invention provide a gate vehicle identification method based on point cloud, comprising the following steps:

[0008] S110. A lidar is installed on one side of the road at the gate. The lidar collects point cloud information of vehicles passing through the gate in real time to obtain the first point cloud data.

[0009] S120. Cluster the first point cloud data to obtain the second point cloud data, and identify the second point cloud data based on the first neural network to obtain at least vehicle type information;

[0010] S130. Based on a preset height range, the point cloud representing the local space of the container truck is cropped to obtain fourth point cloud data; and

[0011] S140. Based on the second neural network, the fourth point cloud data is identified to obtain container length information and container pressure parking space information.

[0012] Preferably, in step S110, the lidar forms a side-view perspective based on the road at the gate.

[0013] Preferably, step S120 includes:

[0014] S121. Cluster the first point cloud data to obtain the second point cloud data;

[0015] S122. Based on the first neural network, perform vehicle type recognition on the second point cloud data to obtain vehicle type information;

[0016] S123. Perform horizontal plane fitting on the second point cloud data from both the top and bottom directions to obtain a first point cloud plane representing the top surface of the truck cab and a second point cloud plane representing the top surface of the container, wherein the second point cloud plane is higher than the first point cloud plane; and

[0017] S124. The ground clearance of the first point cloud plane is used as the top surface height information of the truck cab, and the ground clearance of the second point cloud plane is used as the top surface height information of the container.

[0018] Preferably, step S130 includes:

[0019] S131. The point cloud representing the local space of the container truck is first extracted from the second point cloud data to obtain the third point cloud data.

[0020] S132. A third segment is performed on the third point cloud data based on a preset height range to obtain the fourth point cloud data. The lower limit of the preset height range is higher than the ground clearance of the top surface of the truck flatbed and lower than the ground clearance of the top surface of the truck cab. The upper limit of the preset height range is the larger of the ground clearance of the top surface of the truck cab and the ground clearance of the top surface of the container.

[0021] Preferably, the lower limit of the preset height range is 5cm higher than the ground clearance of the top surface of the truck flatbed.

[0022] Preferably, step S140 includes:

[0023] S141. Based on the second neural network, the fourth point cloud data is identified to obtain the fifth point cloud data representing the container and the sixth point cloud data representing the truck body.

[0024] S142. Obtain container length information based on the fifth point cloud data, and obtain container pressure parking space information based on the positional relationship between the fifth point cloud data and the sixth point cloud data.

[0025] Preferably, step S110 is replaced by:

[0026] A detection component is set up on one side of the road at the gate. The detection component includes a jointly calibrated lidar and an image sensor. The lidar collects point cloud information of vehicles passing through the gate in real time to obtain the first point cloud data. The image sensor collects image information synchronously. The lidar and the image sensor form a side-view perspective based on the road at the gate.

[0027] Step S140 is replaced by:

[0028] S143. Based on the second neural network, the fourth point cloud data is identified to obtain the fifth point cloud data representing the container and the sixth point cloud data representing the truck body.

[0029] S144. Obtain container length information based on the fifth point cloud data, and obtain container pressure parking space information based on the positional relationship between the fifth point cloud data and the sixth point cloud data;

[0030] S145. Obtain image and text information and the position of each image and text information in the image from the image information through image and text recognition;

[0031] S146. Establish a mapping relationship between the graphic and textual information located within the local image range of the fifth point cloud data and the container, and establish a mapping relationship between the graphic and textual information located within the local image range of the sixth point cloud data and the truck body.

[0032] Embodiments of the present invention also provide a point cloud-based gate vehicle identification system for implementing the above-described point cloud-based gate vehicle identification method. The point cloud-based gate vehicle identification system includes:

[0033] The point cloud acquisition module has a lidar installed on one side of the road at the gate. The lidar collects point cloud information of vehicles passing through the gate in real time to obtain the first point cloud data.

[0034] The point cloud clustering module clusters the first point cloud data to obtain the second point cloud data, and identifies the second point cloud data based on the first neural network to obtain at least vehicle type information.

[0035] The point cloud capture module captures point clouds representing a local space of a container truck within a preset height range to obtain fourth point cloud data; and

[0036] The information generation module identifies the fourth point cloud data based on the third neural network to obtain container length information and container pressure parking space information.

[0037] Embodiments of the present invention also provide a point cloud-based gate vehicle identification device, comprising:

[0038] processor;

[0039] Memory, which stores the processor's executable instructions;

[0040] The processor is configured to execute the steps of the point cloud-based gate vehicle identification method described above by executing executable instructions.

[0041] Embodiments of the present invention also provide a computer-readable storage medium for storing a program that, when executed, implements the steps of the point cloud-based gate vehicle identification method described above.

[0042] The point cloud-based gate vehicle identification method, system, device, and storage medium of the present invention can locate and analyze each truck passing through the gate, thereby improving the accuracy of vehicle identification information and obtaining container size and container parking information, which greatly improves the efficiency and detection accuracy of vehicles entering and exiting the gate in container terminals or yards. Attached Figure Description

[0043] Other features, objects, and advantages of the present invention will become more apparent from the following detailed description of non-limiting embodiments with reference to the accompanying drawings.

[0044] Figure 1 This is a flowchart of the point cloud-based gate vehicle identification method of the present invention.

[0045] Figures 2 to 5 This is a schematic diagram of the first implementation process of the point cloud-based gate vehicle identification method of the present invention.

[0046] Figure 6 This is a schematic diagram of the mapping relationship for the second implementation process of the point cloud-based gate vehicle identification method of the present invention.

[0047] Figure 7 This is a schematic diagram of the laser calibration stage in the point cloud-based gate vehicle identification method of the present invention.

[0048] Figure 8 This is a schematic diagram of the laser vehicle separation stage in the point cloud-based gate vehicle separation identification method of the present invention.

[0049] Figure 9 This is a schematic diagram of the point cloud-based gate vehicle identification system of the present invention.

[0050] Figure 10 This is a schematic diagram of the point cloud-based gate vehicle identification device of the present invention.

[0051] Figure 11 This is a schematic diagram of the structure of a computer-readable storage medium according to an embodiment of the present invention. Detailed Implementation

[0052] The following specific examples illustrate the implementation methods of this application. Those skilled in the art can easily understand the other advantages and effects of this application from the content disclosed herein. This application can also be implemented or applied through other different specific embodiments, and various details in this application can be modified or changed according to different viewpoints and application systems without departing from the spirit of this application. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.

[0053] The embodiments of this application will now be described in detail with reference to the accompanying drawings, so that those skilled in the art can easily implement the application. This application may be embodied in many different forms and is not limited to the embodiments described herein.

[0054] In this application, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics represented in connection with that embodiment or example, which are included in at least one embodiment or example of this application. Furthermore, the specific features, structures, materials, or characteristics represented may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate different embodiments or examples represented in this application, as well as features of different embodiments or examples.

[0055] Furthermore, the terms "first" and "second" are used for illustrative purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the representation of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0056] To clearly illustrate this application, devices unrelated to the description are omitted, and the same or similar constituent elements throughout the specification are given the same reference numerals.

[0057] Throughout this specification, when it is said that a device is "connected" to another device, this includes not only "direct connection" but also "indirect connection" by placing other components in between. Furthermore, when it is said that a device "comprises" a certain constituent element, unless otherwise stated otherwise, this does not exclude other constituent elements, but rather implies that other constituent elements may be included.

[0058] When we say that a device is "above" another device, this can mean that it is directly above the other device, or it can mean that other devices are present in between. Conversely, when we say that a device is "directly" "above" another device, there are no other devices present in between.

[0059] While the terms first, second, etc., are used in some instances to denote various elements in this invention, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, first interface and second interface, etc., are used. Furthermore, as used herein, the singular forms “a,” “an,” and “the” are intended to also include the plural forms, unless the context indicates otherwise. It should be further understood that the terms “comprising,” “including,” indicate the presence of features, steps, operations, elements, components, items, kinds, and / or groups, but do not exclude the presence, occurrence, or addition of one or more other features, steps, operations, elements, components, items, kinds, and / or groups. The terms “or” and “and / or” as used herein are to be interpreted inclusively, or mean any one or any combination thereof. Therefore, “A, B, or C” or “A, B, and / or C” means “any one of: A; B; C; A and B; A and C; B and C; A, B, and C.” An exception to this definition will only occur if the combination of elements, functions, steps, or operations is inherently mutually exclusive in some way.

[0060] The technical terms used herein are for reference only to specific embodiments and are not intended to limit the scope of this application. The singular form used herein includes the plural form unless the statement explicitly indicates otherwise. The word "comprising" as used in the specification means to specify a particular characteristic, region, integer, step, operation, element, and / or component, and does not exclude the presence or addition of other characteristics, regions, integers, steps, operations, elements, and / or components.

[0061] Although not explicitly defined, all terms, including technical and scientific terms used herein, shall have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. Terms defined in commonly used dictionaries shall be further interpreted as having a meaning consistent with the relevant technical literature and the content of this present application, and shall not be over-interpreted as having an ideal or overly formulaic meaning unless otherwise defined.

[0062] Figure 1 This is a flowchart of the point cloud-based gate vehicle identification method of the present invention. Figure 1 As shown, an embodiment of the present invention provides a gate vehicle identification method based on point cloud, comprising the following steps:

[0063] S110. A lidar is installed on one side of the road at the gate. The lidar collects point cloud information of vehicles passing through the gate in real time to obtain the first point cloud data.

[0064] S120. Cluster the first point cloud data to obtain the second point cloud data, and identify the second point cloud data based on the first neural network to obtain at least vehicle type information.

[0065] S130. Based on a preset height range, the point cloud representing the local space of the container truck is cropped to obtain fourth point cloud data.

[0066] S140. Based on the second neural network, the fourth point cloud data is identified to obtain container length information and container pressure parking space information.

[0067] In a preferred embodiment, in step S110, the lidar forms a side-view perspective based on the road at the gate, but is not limited thereto.

[0068] In a preferred embodiment, step S120 includes:

[0069] S121. Cluster the first point cloud data to obtain the second point cloud data. In this embodiment, the second point cloud data can be obtained by using an existing point cloud density clustering algorithm (e.g., K-Means algorithm) on the first point cloud data, but it is not limited to this.

[0070] S122. Based on the first neural network, vehicle type identification is performed on the second point cloud data to obtain vehicle type information. In this embodiment, an existing trained point cloud-based vehicle type identification neural network is used, but it is not limited thereto.

[0071] S123. Perform horizontal plane fitting on the second point cloud data from both top and bottom directions to obtain a first point cloud plane representing the top surface of the truck cab and a second point cloud plane representing the top surface of the container. The second point cloud plane is higher than the first point cloud plane. In this embodiment, existing plane fitting algorithms can be used to find the first and second point cloud planes on the second point cloud data. Since the height of the container is greater than that of the truck cab when it is in the vehicle-mounted state, this embodiment uses existing plane fitting algorithms to first perform plane fitting from bottom to top on the second point cloud data to find the first point cloud plane representing the top surface of the truck cab, and then first perform plane fitting from top to bottom on the second point cloud data to find the second point cloud plane representing the top surface of the container.

[0072] S124. The height above the ground of the first cloud plane is used as the top surface height information of the truck cab, and the height above the ground of the second cloud plane is used as the top surface height information of the container, but not limited to this.

[0073] In a preferred embodiment, step S130 includes:

[0074] S131. The point cloud representing the local space of the container truck is first extracted from the second point cloud data to obtain the third point cloud data.

[0075] S132. A third segment is performed on the third point cloud data based on a preset height range to obtain the fourth point cloud data. The lower limit of the preset height range is higher than the ground clearance of the top surface of the truck flatbed and lower than the ground clearance of the top surface of the truck cab. The upper limit of the preset height range is the larger of the ground clearance of the top surface of the truck cab and the ground clearance of the top surface of the container, but is not limited to this value.

[0076] In a preferred embodiment, the lower limit of the preset height range is 5cm higher than the ground clearance of the top surface of the truck flatbed, but is not limited thereto.

[0077] In a preferred embodiment, step S140 includes:

[0078] S141. Based on the second neural network, the fourth point cloud data is identified to obtain the fifth point cloud data representing the container and the sixth point cloud data representing the truck body.

[0079] S142. Obtain container length information based on the fifth point cloud data, and obtain container pressure parking space information based on the positional relationship between the fifth point cloud data and the sixth point cloud data, but not limited to this.

[0080] In a preferred embodiment, step S110 is replaced by:

[0081] A detection component is set up on one side of the road at the gate. The detection component includes a jointly calibrated lidar and an image sensor. The lidar collects point cloud information of vehicles passing through the gate in real time to obtain the first point cloud data. The image sensor collects image information simultaneously. The lidar and the image sensor form a side-view perspective based on the road at the gate.

[0082] Step S140 is replaced with:

[0083] S143. Based on the second neural network, identify the fourth point cloud data to obtain the fifth point cloud data representing the container and the sixth point cloud data representing the truck body.

[0084] S144. Obtain container length information based on the fifth point cloud data, and obtain container pressure parking space information based on the positional relationship between the fifth point cloud data and the sixth point cloud data.

[0085] S145. Obtain image and text information and the position of each image and text information in the image through image and text recognition.

[0086] S146. Establish a mapping relationship between the graphic and textual information within the local image range of the fifth point cloud data and the container, and establish a mapping relationship between the graphic and textual information within the local image range of the sixth point cloud data and the truck body, but not limited to this.

[0087] This invention utilizes LiDAR, achieving high positioning accuracy and a small blind spot. It can directly establish a standard coordinate system without perspective transformation, resulting in better recognition performance compared to visual recognition technologies. Furthermore, this invention exhibits high stability and can also provide auxiliary information such as truck length, container parking space information, and non-truck passage information. Moreover, the algorithm employs multiple truncation steps to reduce computational load and improve calculation speed.

[0088] Figures 2 to 5 This is a schematic diagram of the first implementation process of the point cloud-based gate vehicle identification method of the present invention. Figures 2 to 5 As shown, the first embodiment of the present invention includes:

[0089] First, such as Figure 2 As shown, a lidar 12 is installed on one side of the road 10 at the gate. The lidar 12 is connected to a remote server 13. The lidar forms a side-view perspective based on the road at the gate. As the truck 11 carrying the container 14 passes through the gate, the lidar collects the point cloud information of the vehicles passing through the gate in real time and obtains the first point cloud data.

[0090] Then, as Figure 3 As shown, the first point cloud data is clustered to obtain the second point cloud data 21. Based on a trained first neural network for vehicle type identification, the second point cloud data 21 is used to identify the vehicle type (truck). The second point cloud data 21 is fitted with horizontal planes in both the top and bottom directions to obtain a first point cloud plane S1 representing the top surface of the truck cab and a second point cloud plane S2 representing the top surface of the container. The second point cloud plane S2 is higher than the first point cloud plane S1. The height of the first point cloud plane above the ground is used as the height information of the top surface of the truck cab, and the height of the second point cloud plane above the ground is used as the height information of the top surface of the container, but this is not a limitation.

[0091] Next, as Figure 4As shown, the point cloud representing the local space of the container truck is first cropped from the second point cloud data 21 to obtain the third point cloud data. A third crop is then performed from the third point cloud data based on a preset height range to obtain the fourth point cloud data 22. The lower limit of the preset height range is higher than the ground clearance of the top surface of the container truck flatbed but lower than the ground clearance of the top surface of the container truck cab (e.g., the lower limit of the preset height range is 5cm higher than the ground clearance of the top surface of the container truck flatbed). The upper limit of the preset height range is the larger of the ground clearance of the top surface of the container truck cab and the ground clearance of the container top surface, but is not limited to this value.

[0092] Finally, as Figure 5 As shown, the fourth point cloud data 22 is identified based on the second neural network to obtain the fifth point cloud data 24 representing the container and the sixth point cloud data 23 representing the truck body. The container length information is obtained from the fifth point cloud data, and the container loading position information is obtained from the positional relationship between the fifth and sixth point cloud data (currently, the length of standard containers and the installation positions of containers of different sizes on trucks are industry standards; the container position can be obtained by comparing the fifth point cloud data 24 and the sixth point cloud data 23, which will not be elaborated here).

[0093] Figure 6 This is a schematic diagram illustrating the effect of a second implementation of the point cloud-based gate vehicle identification method of the present invention. Figures 2 to 6 As shown, the second embodiment of the present invention includes the steps described in this embodiment (the first few steps of the second embodiment are illustrated using the accompanying drawings of the first embodiment, but are not limited thereto):

[0094] First, such as Figure 2 As shown, a detection component is installed on one side of the road 10 at the gate. The detection component is connected to a remote server 13 and includes a jointly calibrated LiDAR 12 and an image sensor. As a truck 11 carrying a container 14 passes through the gate, the LiDAR collects point cloud information of the vehicles passing through the gate in real time, obtaining the first point cloud data. The image sensor (not shown in the figure) simultaneously collects image information. The LiDAR and image sensor form a side-view perspective based on the road at the gate. The LiDAR and image sensor are jointly calibrated using an existing joint calibration algorithm, ensuring a correspondence between the pixels in the image sensor and the laser points in the LiDAR point cloud; this will not be elaborated further here.

[0095] Then, as Figure 3As shown, the first point cloud data is clustered to obtain the second point cloud data 21. Based on a trained first neural network for vehicle type identification, the second point cloud data 21 is used to identify the vehicle type (truck). The second point cloud data 21 is fitted with horizontal planes in both the top and bottom directions to obtain a first point cloud plane S1 representing the top surface of the truck cab and a second point cloud plane S2 representing the top surface of the container. The second point cloud plane S2 is higher than the first point cloud plane S1. The height of the first point cloud plane above the ground is used as the height information of the top surface of the truck cab, and the height of the second point cloud plane above the ground is used as the height information of the top surface of the container, but this is not a limitation.

[0096] Next, as Figure 4 As shown, the point cloud representing the local space of the container truck is first cropped from the second point cloud data 21 to obtain the third point cloud data. A third crop is then performed from the third point cloud data based on a preset height range to obtain the fourth point cloud data 22. The lower limit of the preset height range is higher than the ground clearance of the top surface of the container truck flatbed but lower than the ground clearance of the top surface of the container truck cab (e.g., the lower limit of the preset height range is 5cm higher than the ground clearance of the top surface of the container truck flatbed). The upper limit of the preset height range is the larger of the ground clearance of the top surface of the container truck cab and the ground clearance of the container top surface, but is not limited to this value.

[0097] Finally, as Figure 5 As shown, the fourth point cloud data 22 is identified based on the second neural network to obtain the fifth point cloud data 24 representing the container and the sixth point cloud data 23 representing the truck body. The container length information is obtained from the fifth point cloud data 24, and the container loading position information is obtained from the positional relationship between the fifth point cloud data 24 and the sixth point cloud data 23 (currently, the length of standard containers and the installation positions of containers of different sizes on trucks are industry standards; the container position can be obtained by comparing the fifth point cloud data 24 and the sixth point cloud data 23, which will not be elaborated here).

[0098] And, as Figure 6 As shown, the remote server 13 obtains two text / image information entries, "A123456" and "B654321", from the image information through text / image recognition, along with the position of each entry in the image. A mapping relationship is established between the text / image information ("A123456") located within the local image range of the fifth point cloud data and the container 14, and a mapping relationship is established between the text / image information ("B654321") located within the local image range of the sixth point cloud data and the vehicle body of the truck 11. This achieves accurate tracking of vehicles and containers at the gate, but is not limited to this method.

[0099] The complete system for this project includes a lidar unit, a processor, and computer programs stored in memory and capable of running on the processor. Specifically, a lidar unit is installed above the gate lane to detect oncoming vehicles from a side-view perspective. Figure 7 This is a schematic diagram illustrating the steps of the laser calibration stage in the point cloud-based gate vehicle identification method of the present invention. For example... Figure 7 As shown, the laser calibration process of this invention is as follows:

[0100] 1. Install the laser driver and related software, and use ROS to collect and publish laser data.

[0101] 2. Record the gate passage operation data so that the laser data includes the overall operating environment, as well as the trucks that pass through the gate and the containers they carry.

[0102] 3. Play back the recorded data, and play the laser data of vehicles passing through the gate on the development server.

[0103] 4. Establish a standard coordinate system. Use the method of defining a plane by 3 points. Calculate the transformation matrix twice to make the x-axis of the reference lidar correspond to the movement direction of the trolley, the y-axis correspond to the forward movement direction of the container truck under the quay crane, and the z-axis be perpendicular to the ground.

[0104] 5. Extract the effective area and observe the laser image obtained after rotating in step 4. By selecting key points in the x, y, and z axes, determine the effective area for vehicle identification within the lane in this coordinate system.

[0105] 6. Statistical analysis of key parameters: Based on the laser data recorded in step 2, statistical analysis of data parameters such as the dimensions of various container trucks, flatbed trucks, containers and other vehicles, and analysis and provision of various key position parameters when vehicles pass by.

[0106] Figure 8 This is a schematic diagram illustrating the steps of the laser vehicle separation stage in the point cloud-based gate vehicle separation recognition method of the present invention. For example... Figure 8 As shown, the laser sorting process of the present invention is as follows:

[0107] 7. Initialize the vehicle data queue, and initialize a queue data structure containing a series of data such as the front edge position, rear edge position, distance between the vehicle head and the container, container length, and maximum length of the vehicle.

[0108] 8. Subscribe to real-time laser source data. Subscribe to raw laser data in real time through the ROS system.

[0109] 9. Coordinate transformation and filtering: Using the transformation matrix generated in step 4, the laser data is rotated and shifted, and then the effective area obtained in step 5 is filtered.

[0110] 10. First clustering: The laser data obtained in step 9 is clustered using the DBSCAN algorithm. DBSCAN (Density-Based Spatial Clustering of Applications with Noise) is a density-based spatial clustering algorithm. This algorithm divides regions with sufficient density into clusters and discovers clusters of arbitrary shapes in a noisy spatial database. It defines a cluster as the largest set of density-connected points.

[0111] 11. Identify the work vehicles. Analyze the different clusters obtained in step 10 based on the data characteristics of the point cloud and assign them to work vehicles, non-work vehicles, etc. in the current lane.

[0112] 12. Capture the working vehicle. Based on the current working vehicle boundary obtained in step 11 and the statistical height of the flatbed truck, further capture the laser data.

[0113] 13. Second clustering: The DBSCAN algorithm is used to cluster the laser data of the current operating vehicles obtained in step 11.

[0114] 14. Identify truck cabs and containers. Analyze the different clusters obtained in step 14 based on the data characteristics of the point cloud and assign them to truck cabs, containers, etc.

[0115] 15. Update the vehicle data queue. Based on the results obtained in steps 11 and 14, update the queue data in step 7.

[0116] 16. Determine if a vehicle passage event has been triggered. Based on the data from step 15 and the key parameters obtained in step 6, determine whether a vehicle passage event has been triggered. If so, send a vehicle passage signal.

[0117] 17. Repeat steps 8 to 16 to continuously monitor the vehicle passage situation at the gate and send a vehicle passage signal.

[0118] Figure 9 This is a schematic diagram of the point cloud-based gate vehicle identification system of the present invention. Figure 9 As shown, the point cloud-based gate vehicle identification system 5 of the present invention includes:

[0119] The point cloud acquisition module 51 is equipped with a lidar on one side of the road at the gate. The lidar collects point cloud information of vehicles passing through the gate in real time to obtain the first point cloud data.

[0120] The point cloud clustering module 52 clusters the first point cloud data to obtain the second point cloud data, and identifies the second point cloud data based on the first neural network to obtain at least vehicle type information.

[0121] The point cloud capture module 53 captures the point cloud representing the local space of the truck based on a preset height range. The lower limit of the preset height range is lower than the top surface height of the truck head, and the upper limit is higher than the top surface height of the container, so as to obtain the fourth point cloud data.

[0122] The information generation module 54 identifies the fourth point cloud data based on the third neural network to obtain container length information and container pressure parking space information.

[0123] In a preferred embodiment, the lidar forms a side-view perspective based on the road at the gate, but is not limited thereto.

[0124] In a preferred embodiment, the point cloud clustering module 52 is configured to cluster the first point cloud data to obtain the second point cloud data; perform vehicle type recognition on the second point cloud data based on the first neural network to obtain vehicle type information; perform horizontal plane fitting on the second point cloud data from both the top and bottom directions to obtain a first point cloud plane representing the top surface of the truck cab and a second point cloud plane representing the top surface of the container, wherein the second point cloud plane is higher than the first point cloud plane; and use the ground clearance of the first point cloud plane as the top surface height information of the truck cab and the ground clearance of the second point cloud plane as the top surface height information of the container, but not limited thereto.

[0125] In a preferred embodiment, the point cloud capture module 53 is configured to perform a third capture from the third point cloud data based on a preset height range to obtain fourth point cloud data. The lower limit of the preset height range is higher than the ground clearance of the top surface of the truck flatbed and lower than the ground clearance of the top surface of the truck cab. The upper limit of the preset height range is the larger of the ground clearance of the top surface of the truck cab and the ground clearance of the top surface of the container, but is not limited thereto.

[0126] In a preferred embodiment, the lower limit of the preset height range is 5cm higher than the ground clearance of the top surface of the truck flatbed, but is not limited thereto.

[0127] In a preferred embodiment, the information generation module 54 is configured to identify the fourth point cloud data based on the second neural network to obtain the fifth point cloud data representing the container and the sixth point cloud data representing the truck body; obtain the container length information based on the fifth point cloud data, and obtain the container parking space information based on the positional relationship between the fifth point cloud data and the sixth point cloud data, but is not limited thereto.

[0128] In a preferred embodiment, the point cloud acquisition module 51 is configured to set up a detection component on one side of the road at the gate. The detection component includes a jointly calibrated lidar and an image sensor. The lidar acquires point cloud information of vehicles passing through the gate in real time to obtain first point cloud data, and the image sensor acquires image information synchronously. The lidar and image sensor form a side-view perspective based on the road at the gate. The information generation module 54 is configured to identify the fourth point cloud data based on the second neural network to obtain fifth point cloud data representing the container and sixth point cloud data representing the truck body; obtain container length information based on the fifth point cloud data, and obtain container parking space information based on the positional relationship between the fifth and sixth point cloud data; obtain graphic information and the position of each graphic information in the image through graphic recognition; establish a mapping relationship between the graphic information located within the local image range of the fifth point cloud data and the container, and establish a mapping relationship between the graphic information located within the local image range of the sixth point cloud data and the truck body, but is not limited thereto.

[0129] The point cloud-based gate vehicle identification system of the present invention can locate and analyze each truck passing through the gate to improve the accuracy of vehicle identification information, and obtain container size and container parking information, which greatly improves the efficiency and detection accuracy of vehicles entering and exiting the gate in container terminals or yards.

[0130] This invention also provides a point cloud-based gate vehicle identification device, including a processor and a memory storing executable instructions for the processor. The processor is configured to execute steps of a point cloud-based gate vehicle identification method via the executable instructions.

[0131] As described above, the point cloud-based gate vehicle identification device of the present invention can locate and analyze each truck passing through the gate, thereby improving the accuracy of vehicle identification information and obtaining container size and container parking information, which greatly improves the efficiency and detection accuracy of vehicles entering and exiting the gate in container terminals or yards.

[0132] Those skilled in the art will understand that various aspects of the present invention can be implemented as systems, methods, or program products. Therefore, various aspects of the present invention can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "platform."

[0133] Figure 10 This is a schematic diagram of the point cloud-based gate vehicle identification device of the present invention. See below for reference. Figure 10 To describe an electronic device 600 according to this embodiment of the present invention. Figure 10The electronic device 600 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0134] like Figure 10 As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different platform components (including storage unit 620 and processing unit 610), a display unit 640, etc.

[0135] The storage unit stores program code, which can be executed by the processing unit 610 to perform the steps described in the above-described section on the electronic prescription transfer processing method according to various exemplary embodiments of the present invention. For example, the processing unit 610 can perform actions such as... Figure 1 The steps are shown in the figure.

[0136] Storage unit 620 may include a readable medium in the form of a volatile storage unit, such as random access memory (RAM) 6201 and / or cache memory 6202, and may further include a read-only memory (ROM) 6203.

[0137] Storage unit 620 may also include a program / utility 6204 having a set (at least one) program module 6205, such program module 6205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0138] Bus 630 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0139] Electronic device 600 can also communicate with one or more external devices 700 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 600, and / or with any device that enables electronic device 600 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 650. Furthermore, electronic device 600 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 660. Network adapter 660 can communicate with other modules of electronic device 600 via bus 630. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms.

[0140] This invention also provides a computer-readable storage medium for storing a program that, when executed, implements the steps of a point cloud-based gate vehicle identification method. In some possible implementations, various aspects of the invention can also be implemented as a program product comprising program code that, when run on a terminal device, causes the terminal device to perform the steps described in the above-described electronic prescription processing method section of this specification according to various exemplary embodiments of the invention.

[0141] As shown above, when the program of the computer-readable storage medium of this embodiment is executed, it can locate and analyze each container truck passing through the gate, thereby improving the accuracy of vehicle allocation information and obtaining container size and container parking information, which greatly improves the efficiency and detection accuracy of vehicles entering and exiting the gate in container terminals or yards.

[0142] Figure 11 This is a schematic diagram of the structure of the computer-readable storage medium of the present invention. (Reference) Figure 11 As shown, a program product 800 for implementing the above-described method according to an embodiment of the present invention is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0143] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0144] Computer-readable storage media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable storage medium may also be any readable medium other than a readable storage medium that can transmit, propagate, or transfer a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0145] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0146] In summary, the point cloud-based gate vehicle identification method, system, device, and storage medium of the present invention can locate and analyze each truck passing through the gate, thereby improving the accuracy of vehicle identification information and obtaining container size and container parking information, which greatly improves the efficiency and detection accuracy of vehicles entering and exiting the gate in container terminals or yards.

[0147] The above description, in conjunction with specific preferred embodiments, provides a further detailed explanation of the present invention. It should not be construed that the specific implementation of the present invention is limited to these descriptions. For those skilled in the art, various simple deductions or substitutions can be made without departing from the concept of the present invention, and all such modifications and substitutions should be considered within the scope of protection of the present invention.

Claims

1. A gate vehicle identification method based on point cloud, characterized in that, Includes the following steps: S110. A detection component is set on one side of the road at the gate. The detection component includes a jointly calibrated lidar and an image sensor. The lidar collects point cloud information of vehicles passing through the gate in real time to obtain first point cloud data. The image sensor collects image information synchronously. The lidar and the image sensor form a side-view perspective based on the road at the gate. S120. Cluster the first point cloud data to obtain second point cloud data; perform vehicle type recognition on the second point cloud data based on the first neural network to obtain vehicle type information; perform horizontal plane fitting on the second point cloud data from both the top and bottom directions to obtain a first point cloud plane representing the top surface of the truck head and a second point cloud plane representing the top surface of the container, wherein the second point cloud plane is higher than the first point cloud plane; use the ground clearance of the first point cloud plane as the top surface height information of the truck head and the ground clearance of the second point cloud plane as the top surface height information of the container. S130. The point cloud representing the local space of the container truck is first extracted from the second point cloud data to obtain the third point cloud data; the third point cloud data is then extracted a second time based on a preset height range to obtain the fourth point cloud data, wherein the lower limit of the preset height range is higher than the ground clearance of the top surface of the container truck flatbed and lower than the ground clearance of the top surface of the container truck cab, and the upper limit of the preset height range is the larger of the ground clearance of the top surface of the container truck cab and the ground clearance of the top surface of the container. as well as S140. Based on the second neural network, the fourth point cloud data is identified to obtain the fifth point cloud data representing the container and the sixth point cloud data representing the truck body; the container length information is obtained based on the fifth point cloud data, and the container pressure position information is obtained based on the positional relationship between the fifth point cloud data and the sixth point cloud data; the image and text information and the position of each image and text information in the image are obtained from the image information through image and text recognition; a mapping relationship is established between the image and text information located within the local image range of the fifth point cloud data and the container, and a mapping relationship is established between the image and text information located within the local image range of the sixth point cloud data and the truck body.

2. The point cloud-based gate vehicle identification method according to claim 1, characterized in that, In step S110, the lidar forms a side-view perspective based on the road at the gate.

3. The point cloud-based gate vehicle identification method according to claim 1, characterized in that, The lower limit of the preset height range is 5cm higher than the ground clearance of the top surface of the truck flatbed.

4. A point cloud-based gate vehicle identification system, characterized in that, The system includes: The point cloud acquisition module has a detection component set on one side of the road at the gate. The detection component includes a jointly calibrated lidar and an image sensor. The lidar acquires point cloud information of vehicles passing through the gate in real time to obtain the first point cloud data. The image sensor acquires image information synchronously. The lidar and the image sensor form a side-view perspective based on the road at the gate. The point cloud clustering module clusters the first point cloud data to obtain second point cloud data; it performs vehicle type recognition on the second point cloud data based on a first neural network to obtain vehicle type information; it performs horizontal plane fitting on the second point cloud data from both the top and bottom directions to obtain a first point cloud plane representing the top surface of the truck cab and a second point cloud plane representing the top surface of the container, wherein the second point cloud plane is higher than the first point cloud plane; the ground clearance of the first point cloud plane is used as the top surface height information of the truck cab, and the ground clearance of the second point cloud plane is used as the top surface height information of the container. The point cloud capture module performs a first capture of the point cloud representing a local space of the container truck from the second point cloud data to obtain third point cloud data; and performs a second capture of the third point cloud data based on a preset height range to obtain fourth point cloud data. The lower limit of the preset height range is higher than the ground clearance of the top surface of the container truck flatbed and lower than the ground clearance of the top surface of the container truck cab, while the upper limit of the preset height range is the larger of the ground clearance of the top surface of the container truck cab and the ground clearance of the container top surface. The information generation module identifies the fourth point cloud data based on the second neural network to obtain fifth point cloud data representing the container and sixth point cloud data representing the truck body; it obtains container length information based on the fifth point cloud data and container pressure position information based on the positional relationship between the fifth and sixth point cloud data; it obtains image and text information and the position of each image and text information in the image through image and text recognition; it establishes a mapping relationship between the image and text information located within a local image range of the fifth point cloud data and the container, and establishes a mapping relationship between the image and text information located within a local image range of the sixth point cloud data and the truck body.

5. A point cloud-based gate vehicle identification device, characterized in that, include: processor; A memory in which executable instructions of the processor are stored; The processor is configured to perform the steps of the point cloud-based gate vehicle identification method according to any one of claims 1 to 3 by executing the executable instructions.

6. A computer-readable storage medium for storing a program, characterized in that, When the program is executed, it implements the steps of the point cloud-based gate vehicle identification method as described in any one of claims 1 to 3.

Images