阅读说明：本技术 一种识别行车物料的方法、装置、设备及可读存储介质 (Method, device and equipment for identifying traveling materials and readable storage medium ) 是由 潘剑峰 赵瑞佳 耿磊 于 2021-10-15 设计创作，主要内容包括：本发明公开一种识别行车物料方法、装置、设备及可读存储介质,属于机械设计、电气设计、激光扫描技术、计算机技术领域,特别涉及一种识别行车物料的方法,包括：采用激光扫描仪,按照预设时间间隔对预设角度范围的目标进行扫描,获取激光扫描仪采集的原始数据,对原始数据进行数据处理,得到能进行三维重建的点云数据；对扫描得到的目标图像检测目标的边缘信息；对点云数据进行匹配连接,使得各点云数据位于同一坐标系；根据得到的位于同一坐标系的点云数据建立目标实体表面模型。本发明通过对目标构建三维模型,能清楚反映物料目标位置,采用激光扫描仪搭配伺服电机以及行车进行扫描,有效减少企业的设备投入,降低企业的生产成本。(The invention discloses a method, a device, equipment and a readable storage medium for identifying traveling crane materials, which belong to the technical field of mechanical design, electrical design, laser scanning technology and computers, in particular to a method for identifying traveling crane materials, comprising the following steps: scanning a target in a preset angle range according to a preset time interval by adopting a laser scanner, acquiring original data acquired by the laser scanner, and performing data processing on the original data to obtain point cloud data capable of performing three-dimensional reconstruction; detecting edge information of a target for a target image obtained by scanning; matching and connecting point cloud data to enable the point cloud data to be located in the same coordinate system; and establishing a target entity surface model according to the obtained point cloud data positioned in the same coordinate system. According to the invention, the three-dimensional model is constructed for the target, the position of the material target can be clearly reflected, and the laser scanner is adopted to scan in combination with the servo motor and the travelling crane, so that the equipment investment of enterprises is effectively reduced, and the production cost of the enterprises is reduced.)

1. A method of identifying traveling materials, comprising:

scanning a target in a preset angle range according to a preset time interval by adopting a laser scanner, acquiring original data acquired by the laser scanner, and performing data processing on the original data to obtain point cloud data capable of performing three-dimensional reconstruction;

detecting edge information of a target for a target image obtained by scanning;

matching and connecting the point cloud data to enable the point cloud data to be located in the same coordinate system;

and establishing a target entity surface model according to the obtained point cloud data positioned in the same coordinate system.

2. The method of claim 1,

adopt laser scanner, scan the target of presetting the angle scope according to preset time interval, include:

install two-dimensional laser scanner on the driving, adopt control with servo motor that laser scanner connects rotates and the mode of control driving position, adjusts two-dimensional laser scanner's angle, according to presetting time interval, in presetting the angle range, right the target is scanned.

3. The method of claim 1,

the data processing of the raw data includes:

and carrying out data extraction, data filtering, coordinate calculation and format conversion operation on the original data.

4. The method of claim 1,

the data processing of the raw data includes:

extracting effective information from the original data, and converting the effective information into decimal data from a hexadecimal array;

and converting coordinate data in a polar coordinate form in the original data into rectangular coordinates.

5. The method of claim 1,

the data processing of the raw data includes:

and identifying and rejecting data under the conditions of low signal-to-noise ratio, measurement value overflow, reading error, glare and the condition that the measurement distance is greater than the maximum range, and replacing the rejected data by using data which is adjacent to the data and meets the reconstruction requirement.

6. The method of claim 1,

the matching connection of the point cloud data is performed to enable the point cloud data to be located in the same coordinate system, and the matching connection comprises the following steps:

and rotating and translating the point cloud data by adopting a data matching algorithm, so that the distance between any two point sets is minimum, and the point cloud data in the state of the minimum distance are positioned in the same coordinate system.

7. The method of claim 1,

the establishing of the target entity surface model according to the obtained point cloud data in the same coordinate system comprises the following steps:

and establishing a solid surface model for the target by adopting a triangulation method for the obtained point cloud data positioned in the same coordinate system.

8. A device for identifying traveling materials, comprising:

the system comprises a point cloud data acquisition module, a data processing module and a data processing module, wherein the point cloud data acquisition module is used for scanning a target with a preset angle range according to a preset time interval by adopting a laser scanner, acquiring original data acquired by the laser scanner, and processing the original data to obtain point cloud data capable of being subjected to three-dimensional reconstruction;

the edge information detection module is used for detecting the edge information of the target image obtained by scanning;

the coordinate conversion module is used for matching and connecting the point cloud data to ensure that the point cloud data are positioned in the same coordinate system;

and the modeling module is used for establishing a target entity surface model according to the obtained point cloud data in the same coordinate system.

9. The utility model provides an discernment driving material equipment which characterized in that includes:

the device comprises a laser scanner, a scanning mechanical device, a driving and controlling unit and a data acquisition unit, wherein the scanning mechanical device is connected with the laser scanner;

the laser scanner is used for generating and emitting a laser pulse signal, and the distance between the laser scanner and a target point is obtained by using the laser pulse signal;

the control unit is connected with the upper computer and used for receiving the control instruction sent by the upper computer, converting the received control instruction into a control signal and sending the control signal to the scanning mechanical device and the drive; the control unit is further configured to obtain pitch angle data;

the data acquisition unit is used for continuously receiving and storing the distance data obtained by the laser scanner and the pitch angle data obtained by the control unit.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a program which, when executed, is capable of implementing the method according to any one of claims 1-7.

Technical Field

The invention belongs to the technical fields of mechanical design, electrical design, laser scanning technology and computers, and particularly relates to a method, a device and equipment for identifying traveling crane materials and a readable storage medium.

Background

The grab crane, commonly known as a grab crane, is a hoisting machine equipped with a grab, and is widely used for loading various bulk cargo, logs, minerals, coal, sand and stone, earthwork and the like in ports, docks, station goods yards, mines and the like.

The grab bucket crane is used as an automatic material taking machine, the grabbing and discharging actions of the grab bucket crane are controlled by a crane driver, and no auxiliary personnel is needed, so that the heavy labor of workers is avoided, the auxiliary working time is saved, and the loading and unloading efficiency is greatly improved.

Coal dust is one of main raw material supplies of steel plants, and a grab bucket crane of a coal yard at present adopts a manual operation mode, needs a large amount of personnel, belongs to a labor-intensive area, is impacted by various aspects such as safety, quality and cost year by year, and has restriction on coal yard logistics management. In the manual operation process, the grab bucket has errors in the grabbing process due to human judgment, so the grab bucket is very easy to collide with a train carriage in the grabbing process, and equipment impact is caused. Simultaneously at the grabbing in-process, because manual control grab bucket snatchs, the volume of snatching the coal charge is uncontrolled, the condition of secondary adjustment can appear, and then causes handling efficiency low.

The inventor finds that in the prior art, the manual carrying efficiency is low, safety accidents are easy to happen during unloading, and equipment is prone to faults caused by improper manual operation.

Disclosure of Invention

In order to at least solve the technical problem, the invention provides a method, a device, equipment and a readable storage medium for identifying traveling materials.

According to a first aspect of the invention, there is provided a method of identifying a traveling material, comprising:

scanning a target in a preset angle range according to a preset time interval by adopting a laser scanner, acquiring original data acquired by the laser scanner, and performing data processing on the original data to obtain point cloud data capable of performing three-dimensional reconstruction;

detecting edge information of a target for a target image obtained by scanning;

matching and connecting the point cloud data to enable the point cloud data to be located in the same coordinate system;

and establishing a target entity surface model according to the obtained point cloud data positioned in the same coordinate system.

Further, in the above-mentioned case,

adopt laser scanner, scan the target of presetting the angle scope according to preset time interval, include:

install two-dimensional laser scanner on the driving, adopt control with servo motor that laser scanner connects rotates and the mode of control driving position, adjusts two-dimensional laser scanner's angle, according to presetting time interval, in presetting the angle range, right the target is scanned.

Further, in the above-mentioned case,

the data processing of the raw data includes:

and carrying out data extraction, data filtering, coordinate calculation and format conversion operation on the original data.

Further, in the above-mentioned case,

the data processing of the raw data includes:

extracting effective information from the original data, and converting the effective information into decimal data from a hexadecimal array;

and converting coordinate data in a polar coordinate form in the original data into rectangular coordinates.

Further, in the above-mentioned case,

the data processing of the raw data includes:

and identifying and rejecting data under the conditions of low signal-to-noise ratio, measurement value overflow, reading error, glare and the condition that the measurement distance is greater than the maximum range, and replacing the rejected data by using data which is adjacent to the data and meets the reconstruction requirement.

Further, in the above-mentioned case,

the matching connection of the point cloud data is performed to enable the point cloud data to be located in the same coordinate system, and the matching connection comprises the following steps:

and rotating and translating the point cloud data by adopting a data matching algorithm, so that the distance between any two point sets is minimum, and the point cloud data in the state of the minimum distance are positioned in the same coordinate system.

Further, in the above-mentioned case,

the establishing of the target entity surface model according to the obtained point cloud data in the same coordinate system comprises the following steps:

and establishing a solid surface model for the target by adopting a triangulation method for the obtained point cloud data positioned in the same coordinate system.

According to a second aspect of the invention, a device for identifying a traveling material comprises:

the system comprises a point cloud data acquisition module, a data processing module and a data processing module, wherein the point cloud data acquisition module is used for scanning a target with a preset angle range according to a preset time interval by adopting a laser scanner, acquiring original data acquired by the laser scanner, and processing the original data to obtain point cloud data capable of being subjected to three-dimensional reconstruction;

the edge information detection module is used for detecting the edge information of the target image obtained by scanning;

the coordinate conversion module is used for matching and connecting the point cloud data to ensure that the point cloud data are positioned in the same coordinate system;

and the modeling module is used for establishing a target entity surface model according to the obtained point cloud data in the same coordinate system.

According to a third aspect of the invention, there is provided a traveling material identification device,

the method comprises the following steps: the device comprises a laser scanner, a scanning mechanical device, a driving and controlling unit and a data acquisition unit, wherein the scanning mechanical device is connected with the laser scanner;

the laser scanner is used for generating and emitting a laser pulse signal, and the distance between the laser scanner and a target point is obtained by using the laser pulse signal;

the control unit is connected with the upper computer and used for receiving the control instruction sent by the upper computer, converting the received control instruction into a control signal and sending the control signal to the scanning mechanical device and the drive; the control unit is further configured to obtain pitch angle data;

the data acquisition unit is used for continuously receiving and storing the distance data obtained by the laser scanner and the pitch angle data obtained by the control unit. According to a fourth aspect of the present invention there is provided a computer readable storage medium storing a program which, when executed, is capable of carrying out the method of any one of the first aspects of the present invention.

The invention has the beneficial effects that: according to the invention, the three-dimensional model is constructed for the target, so that the target position of the material on the travelling crane is changed to be clear, and the object is clear at a glance. In addition, the laser scanner is adopted to scan by matching with the servo motor and the travelling crane, and point cloud data is collected, so that the equipment investment of an enterprise can be effectively reduced, and the production cost of the enterprise is reduced. The data precision of gathering can reach the millimeter level, satisfies industrial production's demand completely, improves the precision of snatching the material greatly, improves the operating efficiency.

Drawings

The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which,

FIG. 1 is a flow chart of a method for identifying traveling materials according to the present invention;

FIG. 2 is a schematic view of a polar coordinate system according to the present invention;

FIG. 3 is a flow chart of a data filtering processing method according to the present invention;

FIG. 4 is a schematic structural diagram of a device for identifying traveling materials according to the present invention;

fig. 5 is a schematic structural diagram of a device for identifying traveling crane materials according to the present invention.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative only and should not be construed as limiting the invention.

In order to more clearly illustrate the invention, the invention is further described below with reference to preferred embodiments and the accompanying drawings. Similar parts in the figures are denoted by the same reference numerals. It is to be understood by persons skilled in the art that the following detailed description is illustrative and not restrictive, and is not to be taken as limiting the scope of the invention.

In a first aspect of the present invention, there is provided an identification method, as shown in fig. 1, including:

step 101: scanning a target in a preset angle range according to a preset time interval by adopting a laser scanner, acquiring original data acquired by the laser scanner, and performing data processing on the original data to obtain point cloud data capable of performing three-dimensional reconstruction;

in the invention, a two-dimensional laser scanner installed on a traveling crane is adopted to scan a target within an angle range of 145 degrees at preset time intervals. The data processing of the raw data comprises: data extraction, data filtering, coordinate calculation and format conversion. The laser scanner scans the target surface from different positions in a servo motor rotation and traveling mode. The method can effectively overcome the problem that the scanning view field of the laser scanner is limited to incomplete target acquisition data, and can acquire complete information of the target, namely the surface of the coal material of the train carriage.

Further, effective information is extracted from the original data collected by the laser scanner, and the effective information is converted into decimal data from a hexadecimal array. The original data collected by the laser scanner is a hexadecimal array, and the effective information, namely the distance information of the target, only occupies one part of the hexadecimal array, so that the effective information in the data needs to be extracted and converted into a relatively intuitive decimal number.

The coordinate data in the form of polar coordinates is converted into rectangular coordinates, as shown in fig. 2, the polar coordinate point P coordinate is (ρ, α, θ), where ρ is a distance value, α and θ are a horizontal and a pitch scanning angle, respectively, and converted into rectangular coordinates, which can be expressed as:

in the present invention, since the laser scanner completes scanning of a 145 ° range by stepping a certain interval, a set of data numbered 1, 2, 3, …, i, … is generated during scanning, the obtained data is in polar coordinate form, and the point P coordinate is (ρ, α, θ), where ρ is a distance value and α and θ are a horizontal and a pitch scanning angle, respectively. Because of poor readability of polar coordinates, it is necessary to convert the polar coordinates into rectangular coordinates, which can be expressed as:

the coordinates obtained by the laser scanner are transformed by a rotation matrix:

wherein:

a₁＝cosθ·cosβ+sinθ·sinα·sinβ

a₂＝-cosαsinβ

a₃＝-sinθcosβ+cosθsinαsinβ

b₁＝cosαcosβ-sinθsinαcosβ

b₂＝cosαcosβ

b₃＝-sinθcosβ-cosθsinαsinβ

c₁＝sinθcosα

c₂＝sinα

c₃＝cosθcosα

if the geodetic coordinate system is O-UVW, the coordinate of the arbitrary point P in the new coordinate system is as follows:

since the data point coordinates obtained by the laser scanner all use the laser emission center as the origin, the obtained data point coordinates must be converted in order to obtain the point cloud model constructed by the geodetic coordinate system.

The data filtering process, as shown in fig. 3, includes: and identifying and rejecting data under the conditions of low signal-to-noise ratio, measurement value overflow, reading error, glare and the condition that the measurement distance is greater than the maximum range, and replacing the rejected data by using data which is adjacent to the data and meets the reconstruction requirement.

And the data obtained by the data filtering processing is point cloud data which can be subjected to three-dimensional reconstruction.

Step 102: detecting edge information of a target for a target image obtained by scanning;

according to the method, the limiting conditions are obtained, the spatial relation information between the limiting conditions and the region boundaries is calculated, and the relation information between adjacent points is calculated, so that the boundary position and the direction of the target are determined. Due to the influence of laser divergence characteristics, light spots of laser emitted by a laser scanner reaching the surface of the coal material are much larger than light spots emitted actually, which can cause the blurring and the missing of a target boundary, and the identification of the coal material position information of a train carriage is influenced by taking a target as a coal yard as an example. To correctly estimate the boundary direction and position, the internal or external boundary position and direction of the region are determined by calculating the spatial relationship between the constraint and the region boundary and calculating the relationship between the adjacent points.

Step 103: matching and connecting point cloud data to enable the point cloud data to be located in the same coordinate system;

in the invention, a laser scanner scans the surface of a coal material from different positions through servo motor rotation and traveling movement to obtain scanning results of different positions, a data matching algorithm is adopted to carry out rapid matching on collected data Point clouds, wherein the data matching algorithm can be an ICP (Iterative Closest Point) algorithm, the basic principle of the ICP algorithm is to complete data pairing according to space geometric transformation, Point clouds to be registered are selected, and the distance between two Point sets is minimized by using the optimization idea of a least square method, particularly through rotating and translating the Point cloud data, so that the effect that the Point cloud data are located in the same coordinate system is achieved.

Step 104: and establishing a target entity surface model according to the obtained point cloud data positioned in the same coordinate system.

In the invention, a solid surface model is established for the target by a triangulation method for point cloud data in the same coordinate system.

Further, let the original image be represented as I ═ f (x, y), (x, y) ∈ D, where D is the region where the image is located, I is the gray scale value, x is the abscissa of the three-dimensional point cloud data in the rectangular coordinate system, y is the ordinate of the three-dimensional point cloud data in the rectangular coordinate system, and let the DT mesh representing the gray scale image have N triangles in total, and be represented as { T ═ y ∈_iI-0, …, N-1, where T is_iIs the (i + 1) th triangle. The approximation function of the image is G,

approximation function g_i(x, y) may be constructed on a plane defined by 3 vertices of each triangle. If linear interpolation is used, i.e. taking g_i(x, y) is the solution of the plane equation for linear interpolation of the gray values at the 3 vertices of the ith triangle.

Defining a criterion for the representation of the function C on D

C＝C(T_i)≤C₀

The "gray-scale error" herein refers to an error between an original image and an image represented by an approximation function, and the criterion function C is defined as a maximum value of an absolute error between the two, that is, a maximum value

The maximum value of the absolute error is less than or equal to a preset threshold value, and if the maximum value of the absolute error is less than or equal to the preset threshold value, the iteration is stopped; otherwise, the position where the maximum of the absolute error occursI.e. the data point that should be prioritized when the new layer is approached. Along with the iteration and the continuous increase of the number of the triangles, the area of each triangle is continuously reduced, the triangular surface can continuously approach the image curved surface until the criterion is met, and the iteration is stopped.

After iteration is completed, a three-dimensional point cloud picture of the coal yard can be generated, an operator can visually see the storage condition of the coal materials in the train carriage according to the point cloud picture, the three-dimensional scanning recognition software also sends the three-dimensional point cloud data to the data processing software, and the data processing software can obtain the driving grabbing point position meeting the conditions through calculation so as to facilitate automatic grabbing and positioning of subsequent driving.

In another embodiment of the present invention, when the method according to the first aspect of the present invention is used for performing a target three-dimensional scan, a three-dimensional cloud chart of a material area may be displayed above an interface displayed by a system, a data record during system operation is provided on the left lower side of the interface, which is convenient for an operator to monitor an operation process and troubleshoot faults, a current position of a cart, a start and end position of the scan, and a scanning range of left and right sides may be checked on the right lower side of the interface, a scanning frame number represents a communication state with a PLC (Programmable Logic Controller), and when the cart moves, a digital value may start to jump. In the 'display coordinate' area, the cart coordinate, the trolley coordinate and the grab bucket height coordinate input by the user can be respectively obtained, and then when the situation that the user clicks a 'display grabbing point position' button is detected, the position of the point position input by the user in the three-dimensional graph is displayed.

In another embodiment of the invention, the coordinates input by the user are obtained and used as an obvious reference object, the position corresponding to the driving coordinates is controlled and the vehicle is parked, and the difference value of the actual driving position is compensated into the right X/Y/Z compensation value of the parameter setting. The lower right corner of interface is equipped with six function button of coal injection raw materials three-dimensional scanning system for realize scanning system's different functions through clicking the function button, the function button includes: starting scanning, log query, parameter setting, data loading, point cloud display and exiting the system. The starting scanning button is used for automatically generating a scanning data file of the current coal material area in the database folder.

And the log query button is used for viewing the running record of the software in the time range by setting the time range. Therefore, a user can monitor the scanning system according to the operation record, and in addition, the system can be timely checked and detected according to the operation record when a fault occurs, so that the maintenance and detection efficiency is improved.

The parameter setting button is used for entering a parameter setting interface and setting and changing parameters such as compensation values, minimum angles, maximum angles, model colors, detection heights and the like of the left side and the right side of the laser scanning head.

And the data loading button is used for automatically jumping to a selected file window, and the point cloud data file which is automatically generated after the scanning is finished is placed in the folder. And automatically loading point cloud data corresponding to the file according to the file opened by the user.

And the point cloud display button is used for displaying the loaded point cloud data in an image.

In a second aspect of the present invention, there is provided a traveling material identification device, as shown in fig. 4, including:

a point cloud data acquisition module 401, configured to scan a target in a preset angle range at preset time intervals by using a laser scanner, acquire original data acquired by the laser scanner, and perform data processing on the original data to obtain point cloud data capable of performing three-dimensional reconstruction;

in the present invention, the point cloud data acquisition module 401 scans a target within an angle range of 145 ° at preset time intervals by using a two-dimensional laser scanner mounted on a traveling crane. The data processing of the raw data comprises: data extraction, data filtering, coordinate calculation and format conversion. The laser scanner scans the target surface from different positions in a servo motor rotation and traveling mode. The method can effectively overcome the problem that the scanning view field of the laser scanner is limited to incomplete target acquisition data, and can acquire complete information of the target, namely the surface of the coal material of the train carriage.

Further, effective information is extracted from the original data collected by the laser scanner, and the effective information is converted into decimal data from a hexadecimal array. The original data collected by the laser scanner is a hexadecimal array, and the effective information, namely the distance information of the target, only occupies one part of the hexadecimal array, so that the effective information in the data needs to be extracted and converted into a relatively intuitive decimal number.

Converting coordinate data in a polar coordinate form into rectangular coordinates, wherein coordinates of a coordinate point P are (rho, alpha and theta), rho is a distance value, alpha and theta are respectively a horizontal scanning angle and a pitching scanning angle, converting the coordinate data into the rectangular coordinates, and expressing the coordinate data as:

in the present invention, since the laser scanner in the point cloud data acquisition module 401 completes the scanning of the 145 ° range by stepping a certain interval, a set of data numbered 1, 2, 3, …, i, … is generated during the scanning process, the obtained data is in the form of polar coordinates, the coordinates of the point P are (ρ, α, θ), where ρ is a distance value, and α and θ are the horizontal and pitch scanning angles, respectively. Because of poor readability of polar coordinates, it is necessary to convert the polar coordinates into rectangular coordinates, which can be expressed as:

the coordinates obtained by the laser scanner are transformed by a rotation matrix:

wherein:

a₁＝cosθ·cosβ+sinθ·sinα·sinβ

a₂＝-cosαsinβ

a₃＝-sinθcosβ+cosθsinαsinβ

b₁＝cosαcosβ-sinθsinαcosβ

b₂＝cosαcosβ

b₃＝-sinθcosβ-cosθsinαsinβ

c₁＝sinθcosα

c₂＝sinα

c₃＝cosθcosα

if the geodetic coordinate system is O-UVW, the coordinate of the arbitrary point P in the new coordinate system is as follows:

since the data point coordinates obtained by the laser scanner all use the laser emission center as the origin, the obtained data point coordinates must be converted in order to obtain the point cloud model constructed by the geodetic coordinate system.

And filtering the data, comprising: and identifying and rejecting data under the conditions of low signal-to-noise ratio, measurement value overflow, reading error, glare and the condition that the measurement distance is greater than the maximum range, and replacing the rejected data by using data which is adjacent to the data and meets the reconstruction requirement.

And the data obtained by the data filtering processing is point cloud data which can be subjected to three-dimensional reconstruction.

An edge information detection module 402, configured to detect edge information of a target for a scanned target image;

in the present invention, the edge information detecting module 402 is configured to obtain a constraint condition, calculate spatial relationship information between the constraint condition and a region boundary, and calculate relationship information between adjacent points, so as to determine a boundary position and a direction of a target. Due to the influence of laser divergence characteristics, light spots of laser emitted by a laser scanner reaching the surface of coal, namely the target surface, are much larger than light spots emitted actually, so that the target boundary can be blurred and lost, and the identification of the coal position information of the train carriage is influenced by taking the target as a coal yard as an example. To correctly estimate the boundary direction and position, the internal or external boundary position and direction of the region are determined by calculating the spatial relationship between the constraint and the region boundary and calculating the relationship between the adjacent points.

A coordinate conversion module 403, configured to perform matching connection on the point cloud data, so that the point cloud data are located in the same coordinate system;

in the invention, a laser scanner in a Point cloud data acquisition module 401 scans the surface of a coal material from different positions through servo motor rotation and traveling movement to obtain scanning results of different positions, a coordinate conversion module 403 performs fast matching on the acquired data Point cloud by adopting a data matching algorithm, wherein the data matching algorithm can be an ICP (Iterative Closest Point) algorithm, the basic principle of the ICP algorithm is to complete data pairing according to space geometric transformation, select Point cloud to be registered, and use the optimization thought of a least square method, particularly, through rotating and translating the Point cloud data, the distance between two Point sets is minimum, so that the effect that the Point cloud data are located in the same coordinate system is achieved.

And the modeling module 404 is configured to establish a target entity surface model according to the obtained point cloud data located in the same coordinate system.

In the present invention, the modeling module 404 is specifically configured to establish a solid surface model for the target by using a triangulation method for the point cloud data in the same coordinate system.

Further, the modeling module 404 sets the original image to be represented as I ═ f (x, y), (x, y) ∈ D, where D is the region where the image is located, I is the gray scale value, x is the abscissa of the three-dimensional point cloud data in the rectangular coordinate system, y is the ordinate of the three-dimensional point cloud data in the rectangular coordinate system, and then sets the DT mesh used to represent the gray scale image to have N triangles, which are represented as { T ═ T ∈ £ D_iI-0, …, N-1, where T is_iIs the (i + 1) th triangle. The approximation function of the image is G,

approximation function g_i(x, y) may be constructed on a plane defined by 3 vertices of each triangle. If linear interpolation is used, i.e. taking g_i(x, y) is the solution of the plane equation for linear interpolation of the gray values at the 3 vertices of the ith triangle.

Defining a criterion for the representation of the function C on D

C＝C(T_i)≤C₀

The "gray-scale error" herein refers to an error between an original image and an image represented by an approximation function, and the criterion function C is defined as a maximum value of an absolute error between the two, that is, a maximum value

The maximum value of the absolute error is less than or equal to a preset threshold value, and if the maximum value of the absolute error is less than or equal to the preset threshold value, the iteration is stopped; otherwise, the position where the maximum of the absolute error occursI.e. the data point that should be prioritized when the new layer is approached. Along with the iteration and the continuous increase of the number of the triangles, the area of each triangle is continuously reduced, the triangular surface can continuously approach the image curved surface until the criterion is met, and the iteration is stopped.

After iteration is completed, a three-dimensional point cloud picture of the coal yard can be generated, an operator can visually see the storage condition of the coal materials in the train carriage according to the point cloud picture, the three-dimensional scanning recognition software also sends the three-dimensional point cloud data to the data processing software, and the data processing software can obtain the driving grabbing point position meeting the conditions through calculation so as to facilitate automatic grabbing and positioning of subsequent driving.

In a third aspect of the present invention, there is provided a traveling material identification device, as shown in fig. 5, including:

laser scanner 501, scanning mechanism and driver 502, control unit 503, data acquisition unit 504.

Among them, the laser scanner 501 includes: laser diode, spectroscope, optical signal receiver and rotatory speculum.

The laser diode is used for generating and emitting laser pulse signals, the laser pulse signals are divided into two beams through the spectroscope, one beam enters the optical signal receiver, the other beam enters the rotating reflector and is emitted to a target to be scattered, part of scattered light is reflected back to the optical signal receiver, the time interval between the emitted laser pulses and the echo laser pulses is recorded by the timer, and the distance from the scanner to the target point can be obtained by multiplying the time interval by the light speed. Due to the rotation of the reflecting mirror, the scanner can scan within the angle range of 145 degrees, and the scanner completes the scanning within the range of 145 degrees at certain intervals of stepping from the same starting point in the right-left anticlockwise direction every time, so that the distance measurement data given in the form of scanning lines is obtained.

In another embodiment of the present invention, the laser scanner 501 is provided with an encoder for measuring the pulse emission angle, and the precise clock control encoder measures the horizontal angle and the pitch angle of each laser pulse synchronously while obtaining the scanning point distance.

In the invention, the laser scanner 501 is installed on the train, so that the laser scanner 501 can scan the whole train carriage along with the movement of the train carriage, thereby obtaining point cloud models of all train carriages. The technical scheme of the invention effectively overcomes the technical problems that the scanning range of the laser scanner is limited and the positions of all target points of the whole train carriage cannot be comprehensively collected.

In another embodiment of the present invention, the area to be scanned is divided into a small target area, the laser scanner 501 sends five pulses to each target area, obtains five echo pulses, obtains five measurement results, and obtains an average measurement value of the area by processing the five measurement results, and the average measurement value is used as the measurement distance of the target area. Meanwhile, the laser scanner 501 moves along with the traveling vehicle to scan the coal of all the train carriages, so that three-dimensional point cloud data of the coal of all the train carriages can be obtained. By adopting the scheme, the efficiency of scanning identification can be improved, the time consumed when each coal material point is measured can be avoided to be long, the scheme is simple in post-processing, and the coal material position information can be easily acquired in real time.

The scanning mechanism and drive 502 includes: support, rotation axis, servo motor. For movably adjusting the position and orientation of the laser scanner.

The control unit 503 is composed of a control system with a single chip microcomputer as a core. The single chip microcomputer is connected with the upper computer and used for receiving control instructions sent by the upper computer, wherein the control instructions include but are not limited to starting scanning, stopping scanning, setting a scanning range and setting a scanning speed, the received instructions are converted into control signals of the servo motor, and the control signals are sent to the servo motor; the single chip microcomputer is also used for sending the current pitch angle to the upper computer.

The data acquisition unit 504 is configured to constantly receive and store distance data obtained by the laser scanner 501 and pitch angle data obtained by the control unit 503.

In the present invention, the data acquisition unit 504 is specifically configured to continuously receive and store distance data obtained by the laser scanner 502 and continuously receive and store pitch angle data obtained by the single chip microcomputer, so as to obtain a spatial position of the target point. As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.

It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

It should be understood that the above detailed description of the technical solution of the present invention with the help of preferred embodiments is illustrative and not restrictive. On the basis of reading the description of the invention, a person skilled in the art can modify the technical solutions described in the embodiments, or make equivalent substitutions for some technical features; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.