Identification method, identification system and storage medium for partitions in open compartments

Abstract

The present invention discloses a method, system, and storage medium for identifying partitions within an open compartment. The method obtains the compartment point cloud data of the vehicle to be loaded by identifying the compartment area within the three-dimensional point cloud data of the vehicle to be loaded. The point cloud data within a preset spatial range within the point cloud data of the compartment to be loaded is then intercepted as the data set to be analyzed and converted into a two-dimensional compartment image. The two-dimensional compartment image is then divided along the horizontal axis of the coordinate system into multiple front-to-back tie bar identification blocks and multiple adjacent identification areas along the vertical axis of the coordinate system based on the position of the compartment front panel and preset tie bar spacing parameters. The standard deviation of each tie bar array is calculated and the tie bar position areas are obtained based on the standard deviation. This overcomes the problem of tie bar area identification bias caused by only obtaining a single tie bar position range when the tie bars within the compartment are connected at an angle or separated front-to-back in an X-shape, which can cause some of the dropped cargo to collide with the tie bars, resulting in a chaotic loading pattern.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional detection technology, and in particular to an identification method, an identification system and a storage medium for a partition in an open compartment. Background Art

[0002] At present, when factories carry out large-scale transshipment of various types of bagged goods and boxed goods, it is usually completed by means of transportation such as freight trucks or freight trains. In order to ensure the stability of the structure of the truck compartment, especially to prevent the compartment side panels from being deformed due to the squeezing of the goods, multiple tie bars are usually set between the side panels of the compartment. At present, in various types of cargo transshipment sites, more and more automatic loading equipment is used to replace manual loading. When the loading equipment is dropping or grabbing goods, it is necessary to avoid the tie bars in the compartment to prevent the loading mechanism from colliding with the tie bars or the dropped goods from hitting the tie bars. The current method of identifying the position of tie bars is still mainly manual sampling, which is relatively random and has large data errors. In addition, due to the different states of the tie bars in the compartment, there are postures such as the tie bars bending forward and backward or tilting, which makes it impossible to accurately obtain the position of these tie bars, thereby affecting the loading of goods in the compartment. Summary of the Invention

[0003] In view of the shortcomings of the prior art, the present invention provides a method for identifying partitions in an open compartment, which is used to obtain the position of the reinforcement in the compartment, comprising the following steps:

[0004] S1, identifying the compartment area in the three-dimensional point cloud data of the vehicle to be loaded, and obtaining the point cloud data of the compartment to be tested;

[0005] S2, intercepting point cloud data within a preset spatial range from the point cloud data of the vehicle compartment to be tested as a data set to be analyzed, and converting the data set to be analyzed into a two-dimensional image of the vehicle compartment in a two-dimensional rectangular coordinate system according to the posture, wherein the horizontal axis direction of the two-dimensional rectangular coordinate system is perpendicular to the front tailgate;

[0006] S3, dividing the two-dimensional interior image of the vehicle into a plurality of adjacent reinforcement identification blocks along the horizontal axis of the coordinate system based on the position of the front tailgate and the preset reinforcement spacing parameters, and dividing each reinforcement identification block into a plurality of adjacent identification areas along the vertical axis of the coordinate system. According to the preset recognition rules, point cloud data within each identification area is collected and analyzed to obtain the horizontal coordinates of the reinforcement position of the area;

[0007] S4, calculating the standard deviation of each reinforcement array, wherein the reinforcement array includes the horizontal coordinates of the reinforcement positions of each identification area within the same reinforcement identification block. If the standard deviation is greater than a preset value, the minimum and maximum values ​​in the reinforcement array are obtained as the reinforcement position area within the corresponding reinforcement identification block. If the standard deviation is less than the preset value, the middle value of the array is used as the reinforcement position of the corresponding reinforcement identification block.

[0008] Preferably, step S4 includes:

[0009] Calculate the difference between the horizontal coordinates of the corresponding reinforcement positions of two adjacent identification areas in each reinforcement array;

[0010] If the difference is greater than a first preset value, the larger value of the two reinforcement position horizontal coordinates in the reinforcement array is removed, and the smaller value is retained to continue to perform difference judgment with the reinforcement position horizontal coordinates of the adjacent identification area in the reinforcement array, until the difference between the reinforcement position horizontal coordinates of each adjacent identification area in the reinforcement array is no greater than the preset value.

[0011] Preferably, step S4 includes:

[0012] Calculate the standard deviation of the horizontal coordinates of the tie bars in each tie bar array;

[0013] If the standard deviation of the horizontal coordinates of the reinforcement positions in a reinforcement array is greater than a second preset value, the reinforcement in the reinforcement identification block corresponding to the reinforcement array is curved or x-shaped, and the minimum and maximum values ​​in the corresponding reinforcement array are obtained as the reinforcement position area of ​​the reinforcement identification block;

[0014] If the standard deviation of the horizontal coordinates of the reinforcement positions in a reinforcement array is not greater than a second preset value, the reinforcement in the reinforcement identification block corresponding to the reinforcement array is linear, and the middle value in the corresponding reinforcement array is obtained as the reinforcement position area of ​​the reinforcement identification block.

[0015] Preferably, the step S2 includes:

[0016] The second point cloud data located within the side panels of the carriage to be tested and whose distance from the side panels is greater than a preset value is intercepted from the point cloud data of the carriage to be tested, and converted into a two-dimensional side view image of the carriage in a second rectangular coordinate system through posture; the horizontal axis direction of the second rectangular coordinate system is perpendicular to the front panel of the carriage and points to the direction of the rear panel, and the vertical axis direction is parallel to the front panel of the carriage.

[0017] Preferably, the step S2 includes:

[0018] The first point cloud data located within the preset height of the car body tailgate in the point cloud data of the car body to be tested is intercepted, and it is converted into a two-dimensional car body top view image in a first rectangular coordinate system through posture; the horizontal axis direction of the first rectangular coordinate system is parallel to the side tailgate of the car body and points to the direction of the rear tailgate, and the vertical axis direction is parallel to the front tailgate of the car body.

[0019] The present invention also discloses an identification system for partitions in an open compartment, which is used to obtain the position of the reinforcement in the compartment, including: an identification module, which is used to identify the compartment area in the three-dimensional point cloud data of the vehicle to be loaded, and obtain the point cloud data of the compartment to be tested; a two-dimensional conversion module, which is used to intercept the point cloud data of the compartment to be tested that is located in a preset spatial range as a data set to be analyzed, and convert the data set to be analyzed into a two-dimensional compartment image in a two-dimensional rectangular coordinate system through posture, wherein the horizontal axis direction of the two-dimensional rectangular coordinate system is perpendicular to the front tailgate; an area separation module, which is used to convert the two-dimensional compartment image along the horizontal axis direction of the coordinate system according to the position of the front tailgate of the compartment and the preset reinforcement spacing parameters The method is as follows: the first embodiment of the present invention is to divide the reinforcement recognition block into a plurality of front-to-back reinforcement recognition blocks, and each reinforcement recognition block is divided into a plurality of adjacent recognition areas along the longitudinal axis of the coordinate system. The point cloud data in each recognition area is collected according to the preset recognition rules and the horizontal coordinates of the reinforcement position of the area are obtained after analysis; the position recognition module is used to calculate the standard deviation of each reinforcement array, and the reinforcement array contains the horizontal coordinates of the reinforcement position of each recognition area in the same reinforcement recognition block. If the standard deviation is greater than the preset value, the minimum and maximum values ​​in the reinforcement array are obtained as the reinforcement position area in the corresponding reinforcement recognition block. If the standard deviation is less than the preset value, the middle value of the array is used as the reinforcement position of the corresponding reinforcement recognition block.

[0020] Preferably, the position identification module specifically includes: a difference statistics module, which is used to calculate the difference between the horizontal coordinates of the corresponding reinforcement positions of two adjacent identification areas in each reinforcement array; a judgment module, which is used to remove the larger value of the two reinforcement position horizontal coordinates in the reinforcement array when the difference is greater than a first preset value, and retain the smaller value to continue to perform difference judgment with the reinforcement position horizontal coordinates of the adjacent identification area in the reinforcement array, until the difference between the reinforcement position horizontal coordinates of each adjacent identification area in the reinforcement array is no greater than the preset value.

[0021] Preferably, the position identification module also includes: a standard deviation calculation module, which is used to calculate the standard deviation of the horizontal coordinates of the reinforcement positions in each reinforcement array; a first position acquisition module, which is used to confirm that the reinforcement in the reinforcement identification block corresponding to the reinforcement array is curved or x-shaped when the standard deviation of the horizontal coordinates of the reinforcement positions in the reinforcement array is greater than a second preset value, and obtain the minimum value and the maximum value in the corresponding reinforcement array as the reinforcement position area of ​​the reinforcement identification block; a second position acquisition module, which is used to confirm that the reinforcement in the reinforcement identification block corresponding to the reinforcement array is linear when the standard deviation of the horizontal coordinates of the reinforcement positions in the reinforcement array is not greater than the second preset value, and obtain the middle value in the corresponding reinforcement array as the reinforcement position area of ​​the reinforcement identification block.

[0022] The present invention also discloses a device for identifying partitions in an open compartment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any of the above methods are implemented.

[0023] The present invention also discloses a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of any of the above methods are implemented.

[0024] The present invention discloses a method, system, and storage medium for identifying partitions within an open compartment. The method obtains point cloud data of the compartment to be loaded by identifying the compartment area within the three-dimensional point cloud data of the vehicle to be loaded. The method then intercepts the point cloud data within a preset spatial range within the point cloud data as the dataset to be analyzed and converts it into a two-dimensional compartment image. The two-dimensional compartment image is then divided along the horizontal axis of the coordinate system into multiple front-to-back tie bar identification blocks and multiple adjacent identification areas along the vertical axis of the coordinate system based on the position of the compartment front panel and preset tie bar spacing parameters. The horizontal coordinates of each tie bar position are analyzed and obtained. The standard deviation of each tie bar array is calculated and the tie bar position areas are determined based on the standard deviation. This overcomes the problem of tie bar area identification errors caused by only identifying a single position range, such as the middle position of the tie bar, when the tie bars within the compartment are connected at an angle or separated front and back in an X-shape. This can cause some of the dropped cargo to collide with the tie bars, resulting in a chaotic loading pattern.

[0025] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned by practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1 The figure is a flow chart of a method for identifying partitions in an open compartment disclosed in one embodiment of the present invention.

[0028] Figure 2 This is a schematic diagram of three-dimensional point cloud data of a vehicle to be loaded according to an embodiment of the present invention.

[0029] Figure 3 This is a schematic diagram of three-dimensional point cloud data of another vehicle to be loaded disclosed in an embodiment of the present invention.

[0030] Figure 4 This is a two-dimensional top view image of the vehicle body with the floor removed, disclosed in one embodiment of the present invention.

[0031] Figure 5 This is a schematic diagram of a specific flow of step S3 disclosed in one embodiment of the present invention.

[0032] Figure 6 This is a schematic diagram of a specific flow of step S4 disclosed in one embodiment of the present invention. DETAILED DESCRIPTION

[0033] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the described embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0034] Unless otherwise defined, technical or scientific terms used herein shall have the ordinary meaning as understood by persons of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in the present patent application specification and claims do not denote any order, quantity, or importance, but are merely used to distinguish different components. Similarly, terms such as "a" or "an" do not denote a limitation of quantity, but rather denote the presence of at least one.

[0035] As attached Figure 1 As shown, this embodiment discloses a method for identifying partitions in an open compartment, which can be used to identify and obtain the position of tie bars in an open compartment with an open top on a freight train or a freight car. The method may specifically include the following steps.

[0036] Step S1, identify the compartment area in the 3D point cloud data of the vehicle to be loaded, and obtain the point cloud data of the compartment to be tested. The 3D point cloud data of the vehicle can be obtained by scanning with a laser camera installed on the loading lane. Figure 2 and 3 As shown in .

[0037] Step S2: intercept the point cloud data within a preset spatial range from the point cloud data of the vehicle compartment to be tested as the data set to be analyzed, and convert the data set to be analyzed into a two-dimensional vehicle interior image in a two-dimensional rectangular coordinate system through posture, wherein the horizontal axis direction of the two-dimensional rectangular coordinate system is perpendicular to the front tailgate.

[0038] In one embodiment, in step S2 , the car body point cloud data may be converted into a two-dimensional car body top view image for subsequent analysis of the reinforcement positions.

[0039] Specifically, the first point cloud data located within the preset height of the car tailgate in the point cloud data of the car to be tested is intercepted, and it is converted into a two-dimensional car body top view image in the first rectangular coordinate system through posture; the horizontal axis direction of the first rectangular coordinate system is parallel to the side tailgate of the car body and points to the direction of the rear tailgate, and the vertical axis direction is parallel to the front tailgate of the car body.

[0040] The 3D point cloud data acquired by the laser pan / tilt system is converted into a side view image representing the side of the vehicle. Data on the guardrail height and guardrail top position of the vehicle to be loaded are obtained from this side view image. The 3D point cloud data of the vehicle compartment extending from the guardrail top down to a position at a predetermined ratio of the minimum guardrail height is then captured as the point cloud data to be measured. This point cloud data is then converted into a 2D overhead view image of the compartment through posture conversion.

[0041] In a specific embodiment, the three-dimensional point cloud data of the vehicle is obtained through a laser pan-tilt platform, and the three-dimensional point cloud data of the vehicle is converted into a side view image through posture, and the guardrail height array Truck_y_array_min and the position of the upper side of the guardrail Truck_y_up_array_min are measured. Then, a preset proportion of 65% of the minimum guardrail height extending downward from the upper side of the guardrail is intercepted. The selected 65% proportion of the guardrail area is set in advance, and of course other proportions can also be set. Then, the top view image is converted through posture, which removes the bottom of the car and includes most of the point cloud data inside the car, especially the reinforcement data, as shown in the attached figure. Figure 4 As shown in FIG, the point cloud data that can be used to measure the reinforcement relatively ideally is finally obtained, that is, the two-dimensional top view image of the car body without removing the car body floor.

[0042] In another embodiment, in step S2 , the car body point cloud data may be converted into a two-dimensional car body side view image for subsequent analysis of the reinforcement positions.

[0043] Specifically, the second point cloud data of the car point cloud data to be tested, which is located within the two side railings of the car and has a distance greater than a preset value from the two side railings, is intercepted and converted into a two-dimensional car body side view image in a second rectangular coordinate system through posture; the horizontal axis of the second rectangular coordinate system is perpendicular to the front railing of the car body and points in the direction of the rear railing, and the vertical axis is parallel to the front railing of the car body. The specific point cloud data conversion and interception method is similar to the conversion into a car body top view image described in the previous embodiment, and will not be repeated here. Unlike the previous embodiment in which the car point cloud data is converted into a two-dimensional car body top view image, in this example, the car point cloud data in the figure is converted into a two-dimensional car body side view image, and then the second point cloud data is converted into a two-dimensional car body side view image in a second rectangular coordinate system by removing the point cloud data of the two side railings on both sides of the car body, thereby completing the superposition of the car body reinforcement point cloud and other data in the two-dimensional rectangular coordinate system. The above-mentioned preset values ​​can be set in advance as needed to remove the side rails or point cloud data that is too close to the side rails, thereby preventing recognition errors.

[0044] Step S3: Divide the two-dimensional interior image of the vehicle into a plurality of front-to-back reinforcement identification blocks along the horizontal axis of the coordinate system according to the position of the front tailgate of the vehicle and the preset reinforcement spacing parameters, and divide each reinforcement identification block into a plurality of adjacent identification areas along the vertical axis of the coordinate system. Collect the point cloud data in each identification area according to the preset recognition rules, analyze the data and obtain the horizontal coordinate of the reinforcement position of the area.

[0045] The following discussion takes the conversion of the point cloud data of the carriage to be tested into a two-dimensional carriage side view image in the second rectangular coordinate system through posture as an example. If it is converted into a two-dimensional carriage side view image, similar steps can be used for processing.

[0046] Specifically, the front tailgate position in the overhead image of the vehicle body is identified, and the first tie bar measurement starting position is obtained based on the front tailgate position. The first tie bar measurement starting position is divided into multiple adjacent data collection areas with the same preset length along the vehicle body width direction; the tie bar position data in each data collection area is obtained to form a first tie bar position group, and the first tie bar identification position is obtained from the first tie bar position group according to the set screening rules. Specifically, as shown in the attached figure, Figure 5 As shown, this step may include the following contents.

[0047] Step S31: Identify and obtain the front tailgate position from the vehicle body overhead image, measure the vehicle body width, and obtain a first tie-bar measurement starting position within the vehicle body at a first set distance from the front tailgate. The first tie-bar measurement starting position is located on one side tailgate. The front tailgate position can be identified and obtained from the vehicle body overhead image, and the vehicle body width can be measured. The first tie-bar measurement starting position within the vehicle body at a first set distance from the front tailgate is obtained. The first tie-bar measurement starting positions include the first and second side tailgate positions, respectively, located on the two side tailgates.

[0048] This step may also include first checking and judging whether the position of the guardrails on both sides is normal, as follows:

[0049] Identify the front tailgate position in the overhead image of the vehicle body, and identify the first two-side identification object spacing at a first measured distance from the front tailgate position in the vehicle body area in the overhead image of the vehicle body, where the first measured distance is the minimum reinforcement spacing distance.

[0050] If the distance between the two side identification objects is less than the minimum limit value of the vehicle width, then the second distance between the two side identification objects at a second measured distance from the front tailgate position in the vehicle body area is obtained, and the second measured distance is greater than the first measured distance and less than twice the minimum tie bar spacing distance.

[0051] If the distance between the second two-side identification objects is not less than the minimum limit value of the vehicle width, the distance between the second two-side identification objects is used as the width of the car body, and the side railing at the second measurement distance from the front railing is used as the starting position of the first reinforcement measurement. According to the car body width and the preset collection distance, it is divided into multiple adjacent data collection areas with the same preset length along the car body width direction. The width of each data collection area is a preset collection distance. Otherwise, a notification of the presence of cargo in the car body is output.

[0052] Step S32, obtaining the collection spacing according to the width of the car body, and obtaining multiple adjacently arranged data collection areas along the width direction of the car body from the starting position of the first reinforcement measurement; the data collection area is an area within the car body area with the collection spacing as the width and the preset length as the length, starting from the vertical surface of the side railing where the starting position of the first reinforcement measurement is located and extending toward the rear railing.

[0053] By dividing the width into n equal parts of the acquisition interval according to the vehicle width. In order to avoid missing measurements, the method of measuring from the guardrails on both sides can be selected during measurement. From the first side fence to the second side fence, the starting coordinates of an area are obtained at each acquisition interval, until the distance from the second side fence is no more than 1.5 times the acquisition interval, and according to the starting coordinates of each area, the reinforcement data are collected in the corresponding data collection area to form a first reinforcement data set. The data collection area is a rectangular area with the starting coordinate position of the corresponding area as the centerline starting point, the acquisition interval as the width, the preset length as the length, and extending in the direction of the rear tailgate. Then, from the second side fence to the first side fence, the starting coordinates of an area are obtained at each acquisition interval, until the distance from the first side fence is no more than 1.5 times the acquisition interval, and according to the starting coordinates of each area, the reinforcement data are collected in the corresponding data collection area to form a second reinforcement data set.

[0054] Step S33, obtain the reinforcement position data identified in each data collection area to form a first reinforcement position group, and obtain the first reinforcement identification position from the first reinforcement position group according to the set screening rules. Specifically, the first reinforcement data set and the second reinforcement data set are merged and saved in the first reinforcement position group, and the first reinforcement identification position is obtained from the first reinforcement position group according to the set screening rules. That is, after the above two traversals, 2n measurement data values ​​with a collection interval of half the distance from the side guardrail are obtained, and the x value is obtained and saved in the same array to form the first reinforcement position group. The set screening rule can be configured to select the reinforcement point cloud closest to the front tailgate in the reinforcement position group, and the first reinforcement identification position is the cross-sectional area in the car parallel to the front tailgate where the reinforcement point cloud obtained by the set screening rule is located.

[0055] In step S34, the next tie-reinforcement measurement starting position is sequentially determined along the longitudinal direction of the vehicle body based on the first tie-reinforcement identification position and the minimum tie-reinforcement spacing. Multiple adjacent data collection areas of the same set length are then divided along the vehicle body width from the next tie-reinforcement measurement starting position. Tie-reinforcement position data in each collection area is obtained to form the next tie-reinforcement position group. The tie-reinforcement identification position is then obtained from the next tie-reinforcement position group according to the set filtering rules until data collection for each area within the two-dimensional vehicle body overhead image is complete, forming the position data for each tie-reinforcement within the vehicle body. After obtaining the measurement data for the first tie-reinforcement, the position information for the next n tie-reinforcements is sequentially measured and obtained.

[0056] Step S4, calculate the standard deviation of each reinforcement array, wherein the reinforcement array contains the horizontal coordinates of the reinforcement positions of each identification area in the same reinforcement identification block. If the standard deviation is greater than a preset value, the minimum and maximum values ​​in the reinforcement array are obtained as the reinforcement position area in the corresponding reinforcement identification block. If the standard deviation is less than the preset value, the middle value of the array is used as the reinforcement position of the corresponding reinforcement identification block.

[0057] In this embodiment, in many three-dimensional point clouds of the carriage, there are often missing reinforcement point cloud data. For example, when the surface of the steel pipe is smooth and reflective, the reinforcement will be missing. At the same time, there will also be discrete point cloud data as errors caused by some minor obstacles or errors. These need to be processed in advance, as shown in the attached figure. Figure 6 The specific contents are as follows.

[0058] Step S41, calculating the difference between the horizontal coordinates of the corresponding reinforcement positions of two adjacent identification areas in each reinforcement array.

[0059] In step S42, if the difference is greater than a first preset value, the larger value of the two reinforcement position horizontal coordinates in the reinforcement array is removed, and the smaller value is retained to continue to perform difference judgment with the reinforcement position horizontal coordinates of adjacent identification areas in the reinforcement array, until the difference between the reinforcement position horizontal coordinates of each adjacent identification area in the reinforcement array is no greater than the preset value.

[0060] Specifically, the subtraction value of adjacent positions in the first reinforcement position array is , and the presence of discrete values ​​is determined: . Here, the first preset value is set to 0.5 meters. If , it is considered that a discrete value exists. The larger value is removed, and the smaller value is continued to be summed with the subsequent values ​​to calculate the difference judgment, and finally the resulting values ​​are formed into a new array.

[0061] Then, the standard deviation of the new array is obtained, and the standard deviation is used to determine whether the reinforcement is tilted or has multiple sections arranged up and down, such as an X-shaped reinforcement.

[0062] Step S43, calculating the standard deviation of the horizontal coordinates of the tie bars in the tie bar array.

[0063] In step S44, if the standard deviation of the horizontal coordinates of the reinforcement positions in a reinforcement array is greater than a second preset value, the reinforcement in the reinforcement identification block corresponding to the reinforcement array is curved or X-shaped, and the minimum and maximum values ​​in the corresponding reinforcement array are obtained as the reinforcement position area of ​​the reinforcement identification block.

[0064] In step S45, if the standard deviation of the horizontal coordinates of the reinforcement positions in a reinforcement array is not greater than a second preset value, the reinforcement in the reinforcement identification block corresponding to the reinforcement array is linear, and the middle value in the corresponding reinforcement array is obtained as the reinforcement position area of ​​the reinforcement identification block.

[0065] Specifically, the front reinforcement array is obtained through the above steps, and the standard deviation is calculated. In some freight cars, the reinforcement may be bent or two reinforcements may be staggered in an x-shape. In this embodiment, the second preset value is set to 4, that is, when , it can be accurately judged that the reinforcement as a whole is bent or x-shaped, rather than misjudgment due to interference. Then, the reinforcement position area is obtained according to the specific shape of the reinforcement, so as to effectively control the subsequent loader to avoid the reinforcement position area when moving the pallet or putting the material package. The method of judging the reinforcement position area according to the standard deviation of the horizontal coordinate of the reinforcement position is: when <4, the array takes the array median value Rope_x_median_1 and saves it in the reinforcement array Rope_position_x. When >4, the array takes the array minimum value Rope_x_min_1 and the maximum value Rope_x_max_1 and saves them in the reinforcement array Rope_position_x. If =4, any of the above two methods can be selected for processing.

[0066] The method disclosed in this embodiment for identifying partitions within an open compartment obtains point cloud data of the compartment to be loaded by identifying the compartment area within the three-dimensional point cloud data of the vehicle to be loaded. The point cloud data within a preset spatial range within the point cloud data of the compartment to be loaded is then intercepted as the data set to be analyzed and converted into a two-dimensional compartment interior image. The two-dimensional compartment interior image is then divided along the horizontal axis of the coordinate system into multiple front-to-back tie bar identification blocks and multiple adjacent identification areas along the vertical axis of the coordinate system based on the position of the compartment front panel and preset tie bar spacing parameters. The horizontal coordinates of each tie bar position are analyzed and obtained. The standard deviation of each tie bar array is calculated and the tie bar position areas are determined based on the standard deviation. This overcomes the problem of tie bar area identification errors caused by only identifying a single location range, such as the middle of the tie bar, when the tie bars within the compartment are connected at an angle or separated front and back in an X-shape. This can cause some of the dropped cargo to collide with the tie bars, resulting in a chaotic loading pattern.

[0067] In another embodiment, a recognition system for partitions in an open compartment is also disclosed, which is used to obtain the position of the reinforcement in the compartment, including: an identification module, which is used to identify the compartment area in the three-dimensional point cloud data of the vehicle to be loaded, and obtain the point cloud data of the compartment to be tested; a two-dimensional conversion module, which is used to intercept the point cloud data within a preset spatial range in the point cloud data of the compartment to be tested as a data set to be analyzed, and convert the data set to be analyzed into a two-dimensional compartment image in a two-dimensional rectangular coordinate system through posture, and the horizontal axis direction of the two-dimensional rectangular coordinate system is perpendicular to the front tailgate; an area separation module, which is used to convert the two-dimensional compartment image along the coordinate system according to the position of the front tailgate of the compartment and the preset reinforcement spacing parameters. The horizontal axis is divided into multiple front-to-back reinforcement identification blocks, and each reinforcement identification block is divided into multiple adjacent identification areas along the vertical axis of the coordinate system. The point cloud data in each identification area is collected according to the preset identification rules and analyzed to obtain the horizontal coordinates of the reinforcement position of the area; the position identification module is used to calculate the standard deviation of each reinforcement array, and the reinforcement array contains the horizontal coordinates of the reinforcement position of each identification area in the same reinforcement identification block. If the standard deviation is greater than the preset value, the minimum and maximum values ​​in the reinforcement array are obtained as the reinforcement position area in the corresponding reinforcement identification block. If the standard deviation is less than the preset value, the middle value of the array is used as the reinforcement position of the corresponding reinforcement identification block.

[0068] In this embodiment, the position identification module specifically includes: a difference statistics module, which is used to calculate the difference between the horizontal coordinates of the corresponding reinforcement positions of two adjacent front and rear identification areas in each reinforcement array; a judgment module, which is used to remove the larger value of the two reinforcement position horizontal coordinates in the reinforcement array when the difference is greater than a first preset value, and retain the smaller value to continue to perform difference judgment with the reinforcement position horizontal coordinates of the adjacent identification area in the reinforcement array, until the difference between the reinforcement position horizontal coordinates of each adjacent identification area in the reinforcement array is no greater than the preset value.

[0069] In this embodiment, the position identification module also includes: a standard deviation calculation module, which is used to calculate the standard deviation of the horizontal coordinates of the reinforcement positions in each reinforcement array; a first position acquisition module, which is used to confirm that the reinforcement in the reinforcement identification block corresponding to the reinforcement array is curved or x-shaped when the standard deviation of the horizontal coordinates of the reinforcement positions in the reinforcement array is greater than a second preset value, and obtain the minimum value and the maximum value in the corresponding reinforcement array as the reinforcement position area of ​​the reinforcement identification block; a second position acquisition module, which is used to confirm that the reinforcement in the reinforcement identification block corresponding to the reinforcement array is linear when the standard deviation of the horizontal coordinates of the reinforcement positions in the reinforcement array is not greater than the second preset value, and obtain the middle value in the corresponding reinforcement array as the reinforcement position area of ​​the reinforcement identification block.

[0070] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from the other embodiments. Similarities between the various embodiments can be referred to in detail. Regarding the open-type compartment partition recognition system disclosed in this embodiment, since it corresponds to the open-type compartment partition recognition method disclosed in the previous embodiment, the description is relatively simple. For relevant details, refer to the method description.

[0071] In other embodiments, a device for identifying partitions in an open compartment is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the various steps of the method for identifying partitions in an open compartment as described in the above embodiments are implemented.

[0072] The device for identifying an open compartment partition may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of a device for identifying an open compartment partition and does not limit the device for identifying an open compartment partition. The device may include more or fewer components than shown, or a combination of certain components, or different components. For example, the device for identifying an open compartment partition may also include input / output devices, network access devices, buses, and the like.

[0073] The processor may be a central processing unit, or other general-purpose processor, digital signal processor, application-specific integrated circuit, off-the-shelf programmable gate array or other programmable logic device, discrete gate or transistor logic device, discrete hardware component, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor serves as the control center of the device for identifying the partition in the open vehicle compartment, and connects various parts of the device for identifying the partition in the open vehicle compartment using various interfaces and lines.

[0074] The memory can be used to store the computer programs and / or modules. The processor implements the various functions of the device for identifying partitions in an open vehicle compartment by running or executing the computer programs and / or modules stored in the memory and accessing the data stored in the memory. The memory can primarily include a program storage area and a data storage area. The program storage area can store an operating system, at least one application required for a function, and the like. Furthermore, the memory can include high-speed random access memory and non-volatile memory.

[0075] If the device for identifying partitions in open-type vehicles is implemented as a software functional unit and sold or used as a standalone product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can also implement all or part of the process steps in the above-described method embodiments by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by a processor, the computer program can implement the steps of each of the above-described methods for identifying partitions in open-type vehicles. The computer program includes computer program code, which can be in source code form, object code form, an executable file, or some intermediate form. The computer-readable medium can include any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a removable hard drive, a magnetic disk, an optical disk, computer memory, read-only memory, random access memory, an electric carrier signal, a telecommunications signal, and a software distribution medium. It should be noted that the content of the computer-readable medium can be appropriately expanded or reduced based on the requirements of legislation and patent practice within a jurisdiction. For example, in some jurisdictions, legislation and patent practice do not require that computer-readable media include electric carrier signals and telecommunications signals.

[0076] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

[0077] In short, the above description is only a preferred embodiment of the present invention, and all equivalent changes and modifications made according to the scope of the patent application of the present invention should fall within the scope of the patent of the present invention.

Claims

1. A method for identifying partitions in an open compartment, for obtaining the position of tie bars in the compartment, characterized in that: The steps include: S1, identifying the compartment area in the three-dimensional point cloud data of the vehicle to be loaded, and obtaining the point cloud data of the compartment to be tested; S2, intercepting point cloud data within a preset spatial range from the point cloud data of the vehicle compartment to be tested as a data set to be analyzed, and converting the data set to be analyzed into a two-dimensional image of the vehicle compartment in a two-dimensional rectangular coordinate system according to the posture, wherein the horizontal axis direction of the two-dimensional rectangular coordinate system is perpendicular to the front tailgate; S3, dividing the two-dimensional interior image of the vehicle into a plurality of adjacent reinforcement identification blocks along the horizontal axis of the coordinate system based on the position of the front tailgate and the preset reinforcement spacing parameters, and dividing each reinforcement identification block into a plurality of adjacent identification areas along the vertical axis of the coordinate system. According to the preset recognition rules, point cloud data within each identification area is collected and analyzed to obtain the horizontal coordinates of the reinforcement position of the area; S4, calculating the standard deviation of each reinforcement array, wherein the reinforcement array includes the horizontal coordinates of the reinforcement positions of each identification area within the same reinforcement identification block. If the standard deviation is greater than a preset value, the minimum and maximum values ​​in the reinforcement array are obtained as the reinforcement position area within the corresponding reinforcement identification block. If the standard deviation is less than the preset value, the middle value of the array is used as the reinforcement position of the corresponding reinforcement identification block.

2. The method for identifying partitions in an open compartment according to claim 1, characterized in that: The step S4 comprises: Calculate the difference between the horizontal coordinates of the corresponding reinforcement positions of two adjacent identification areas in each reinforcement array; If the difference is greater than a first preset value, the larger value of the two reinforcement position horizontal coordinates in the reinforcement array is removed, and the smaller value is retained to continue to perform difference judgment with the reinforcement position horizontal coordinates of the adjacent identification area in the reinforcement array, until the difference between the reinforcement position horizontal coordinates of each adjacent identification area in the reinforcement array is no greater than the preset value.

3. The method for identifying partitions in an open vehicle compartment according to claim 2, characterized in that: The step S4 comprises: Calculate the standard deviation of the horizontal coordinates of the tie bars in each tie bar array; If the standard deviation of the horizontal coordinates of the reinforcement positions in a reinforcement array is greater than a second preset value, the reinforcement in the reinforcement identification block corresponding to the reinforcement array is curved or x-shaped, and the minimum and maximum values ​​in the corresponding reinforcement array are obtained as the reinforcement position area of ​​the reinforcement identification block; If the standard deviation of the horizontal coordinates of the reinforcement positions in a reinforcement array is not greater than a second preset value, the reinforcement in the reinforcement identification block corresponding to the reinforcement array is linear, and the middle value in the corresponding reinforcement array is obtained as the reinforcement position area of ​​the reinforcement identification block.

4. The method for identifying partitions in an open vehicle compartment according to claim 3, characterized in that: The step S2 comprises: The second point cloud data located within the side panels of the carriage to be tested and whose distance from the side panels is greater than a preset value is intercepted from the point cloud data of the carriage to be tested, and converted into a two-dimensional side view image of the carriage in a second rectangular coordinate system through posture; the horizontal axis direction of the second rectangular coordinate system is perpendicular to the front panel of the carriage and points to the direction of the rear panel, and the vertical axis direction is parallel to the front panel of the carriage.

5. The method for identifying partitions in an open vehicle compartment according to claim 3, characterized in that: The step S2 comprises: The first point cloud data located within the preset height of the car body tailgate in the point cloud data of the car body to be tested is intercepted, and it is converted into a two-dimensional car body top view image in a first rectangular coordinate system through posture; the horizontal axis direction of the first rectangular coordinate system is parallel to the side tailgate of the car body and points to the direction of the rear tailgate, and the vertical axis direction is parallel to the front tailgate of the car body.

6. An identification system for partitions in open compartments, used to obtain the position of the reinforcement in the compartment, characterized in that: include: An identification module is used to identify the compartment area in the three-dimensional point cloud data of the vehicle to be loaded and obtain the point cloud data of the compartment to be tested; a two-dimensional conversion module, configured to intercept the point cloud data within a preset spatial range from the point cloud data of the vehicle compartment to be tested as a data set to be analyzed, and convert the data set to be analyzed into a two-dimensional image of the vehicle compartment in a two-dimensional rectangular coordinate system according to the posture, wherein the horizontal axis of the two-dimensional rectangular coordinate system is perpendicular to the front tailgate; The region segmentation module is used to divide the two-dimensional interior image of the vehicle into multiple adjacent reinforcement identification blocks along the horizontal axis of the coordinate system based on the position of the front tailgate and the preset reinforcement spacing parameters, and to divide each reinforcement identification block into multiple adjacent identification areas along the vertical axis of the coordinate system. According to the preset recognition rules, the point cloud data within each identification area is collected and analyzed to obtain the horizontal coordinates of the reinforcement position in the area; The position identification module is used to calculate the standard deviation of each reinforcement array. The reinforcement array contains the horizontal coordinates of the reinforcement positions of each identification area within the same reinforcement identification block. If the standard deviation is greater than a preset value, the minimum and maximum values ​​in the reinforcement array are obtained as the reinforcement position area within the corresponding reinforcement identification block. If the standard deviation is less than the preset value, the middle value of the array is used as the reinforcement position of the corresponding reinforcement identification block.

7. The identification system for partitions in an open vehicle compartment according to claim 6, characterized in that: The location identification module specifically includes: The difference statistics module is used to calculate the difference in the horizontal coordinates of the corresponding reinforcement positions of two adjacent identification areas in each reinforcement array; A judgment module is used to remove the larger value of the two reinforcement position horizontal coordinates in the reinforcement array when the difference is greater than a first preset value, and retain the smaller value to continue to perform difference judgment with the reinforcement position horizontal coordinates of the adjacent identification area in the reinforcement array until the difference between the reinforcement position horizontal coordinates of each adjacent identification area in the reinforcement array is no greater than the preset value.

8. The system for identifying partitions in an open vehicle compartment according to claim 7, characterized in that: The location identification module also includes: A standard deviation calculation module is used to calculate the standard deviation of the horizontal coordinates of the reinforcement positions in each reinforcement array; A first position acquisition module is configured to, when a standard deviation of the horizontal coordinates of the reinforcement positions in the reinforcement array is greater than a second preset value, determine that the reinforcement in the reinforcement identification block corresponding to the reinforcement array is curved or x-shaped, and obtain the minimum and maximum values ​​in the corresponding reinforcement array as the reinforcement position area of ​​the reinforcement identification block; The second position acquisition module is used to confirm that the reinforcement in the reinforcement identification block corresponding to the reinforcement array is linear when the standard deviation of the horizontal coordinates of the reinforcement positions in the reinforcement array is not greater than a second preset value, and obtain the middle value in the corresponding reinforcement array as the reinforcement position area of ​​the reinforcement identification block.

9. A device for identifying partitions in an open vehicle compartment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images