Gantry crane identification method and device, electronic equipment and storage medium

Through spherical neighborhood processing and QB-SHOT encoding method based on point cloud data, the problem of information loss in port crane recognition is solved, the recognition accuracy and robustness are improved, and it is suitable for port crane recognition in port environments.

CN119049034AActive Publication Date: 2024-11-29WUHAN UNIV OF TECH
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411079568.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-29
Estimated Expiration
2044-08-07

AI Technical Summary

Technical Problem

Traditional two-dimensional image vision methods and three-dimensional object recognition methods are susceptible to factors such as light and occlusion in port environments, resulting in insufficient recognition accuracy and robustness of portal crane recognition, and there is a problem of information loss during feature matching.

Method used

By obtaining point cloud data, determine key points and neighborhood points, establish a local reference coordinate system, construct a spherical neighborhood, calculate the angle cosine value, generate a histogram, and encode the SHOT descriptor using the quad-linear interpolation method and the QB-SHOT method. , a QB-SHOT descriptor is obtained to identify the gantry crane component.

Benefits of technology

Eliminate the influence of rotation and translation, improve the expression ability and recognition accuracy of descriptors, reduce the calculation amount, retain important feature information, and enhance the accuracy of feature matching.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119049034A_ABST
    Figure CN119049034A_ABST
Patent Text Reader

Abstract

The invention relates to a gantry crane identification method and device, electronic equipment and a storage medium, and belongs to the technical field of engineering machine.The gantry crane identification method comprises the steps that key points and neighborhood points are determined based on obtained point cloud data of a to-be-identified gantry crane, the method comprises the following steps: constructing a spherical neighborhood taking a key point as a center based on an established local reference coordinate system, dividing the spherical neighborhood to obtain a plurality of subspaces, calculating included angle cosine values of neighborhood points and the key point in the subspaces, obtaining a histogram based on the included angle cosine values, calculating the histogram by adopting a four-linear interpolation method to obtain an SHOT descriptor, and calculating the SHOT descriptor according to the SHOT descriptor. According to the method, a QB-SHOT method is adopted to encode the SHOT descriptor to obtain the QB-SHOT descriptor, and the gantry crane component corresponding to the key point is determined based on the QB-SHOT descriptor, so that important feature information is reserved, and the recognition precision of the gantry crane is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of engineering machinery, and in particular to a portal crane identification method, device, electronic equipment and storage medium. Background Art

[0002] With the development of port automation, unmanned operation and intelligence, higher requirements are placed on the recognition and positioning of gantry cranes. Traditional two-dimensional image vision methods are easily affected by environmental factors such as lighting and occlusion in ports, resulting in serious deficiencies in recognition accuracy and robustness. Existing 3D object recognition methods can be roughly divided into two categories: one is a recognition method based on global features, and the other is a recognition method based on local features.

[0003] In the three-dimensional object target recognition based on local features, feature description is the encoding of the surface geometry information and spatial distribution of the feature point neighborhood. It is the core step in the three-dimensional object recognition process. The feature descriptor is essentially the encoding of the feature point neighborhood information.

[0004] The B-SHOT feature descriptor is a binary encoding of the SHOT descriptor. The B-SHOT descriptor mainly divides the specific results based on the proportion of the numerical values ​​and values ​​of the members in the same group. However, members with large numerical differences may be assigned the same result, which will cause the problem of information loss during feature matching. DB-SHOT adds numerical comparison between members of the same group based on the B-SHOT feature descriptor, which increases the distinction between members of the same group to a certain extent. However, the same result can still appear in two different groups, which will also cause the problem of information loss during feature matching. Summary of the invention

[0005] In view of this, it is necessary to provide a gantry crane identification method, device, electronic equipment and storage medium to solve the technical problem of missing information when identifying a gantry crane. In order to solve the above problems, the present invention provides a portal crane identification method, comprising: Determine key points and neighborhood points based on the acquired point cloud data of the portal crane to be identified; A spherical neighborhood centered on the key point is constructed based on the established local reference coordinate system, the spherical neighborhood is divided to obtain a plurality of subspaces, and the cosine values ​​of the angles between the neighborhood points and the key point in the subspaces are calculated, and a histogram is obtained based on the cosine values ​​of the angles; The histogram is calculated by a quad-linear interpolation method to obtain a SHOT descriptor, the SHOT descriptor is encoded by a QB-SHOT method to obtain a QB-SHOT descriptor, and the portal crane component corresponding to the key point is determined based on the QB-SHOT descriptor.

[0006] In a possible implementation, establishing a local reference coordinate system includes: Obtaining neighborhood points within the neighborhood of the key point, and calculating the centroid of the neighborhood points based on the neighborhood points; Obtaining the key point, and determining a distance weight based on the key point and neighboring points; Constructing a covariance matrix based on the centroid of the neighborhood points, the distance weights, the key points and the neighborhood points, performing eigenvalue decomposition on the covariance matrix to obtain an eigenvector and an eigenvalue corresponding to the eigenvector; The x-axis, y-axis, and z-axis of the local reference coordinate system are determined based on the eigenvector and the eigenvalue.

[0007] In a possible implementation, constructing a spherical neighborhood centered on the key point based on the constructed local reference coordinate system includes: Determine the neighborhood radius of the neighborhood points and key points; A spherical neighborhood with the key point as the center and the neighborhood radius as the radius is constructed based on the local reference coordinate system.

[0008] In a possible implementation, the spherical neighborhood is divided to obtain a plurality of subspaces, including: The spherical neighborhood is divided along radial, latitude and longitude directions to obtain multiple subspaces.

[0009] In a possible implementation, calculating the cosine value of the angle between the neighborhood point and the key point in the subspace, and obtaining the histogram based on the cosine value of the angle includes: Calculating normals of key points in the subspace; Calculating the normal of the neighborhood points in the subspace; Determine the cosine value of the angle between the neighborhood point and the key point in the subspace based on the key point normal and the neighborhood point normal; The cosine values ​​of the angles between the neighborhood points and the key points are equally divided to obtain a histogram, wherein the histogram has the cosine value of the angle as the horizontal coordinate and the number as the vertical coordinate.

[0010] In a possible implementation, the adopting a quadrilinear interpolation method to calculate the histogram to obtain a SHOT descriptor includes: Obtaining a first descriptor of the key point based on the histogram, The first descriptor of the key point is calculated by using a quadrilinear interpolation method to obtain a SHOT descriptor of the key point, wherein the SHOT descriptor includes statistical information of a cosine value of an angle between a normal line of the neighborhood point and a normal line of the key point.

[0011] In a possible implementation, encoding the SHOT descriptor using the QB-SHOT method to obtain the QB-SHOT descriptor includes: Initializing the SHOT descriptor to obtain a value range of the SHOT descriptor; Preset a first interval threshold, a second interval threshold, a third interval threshold and a fourth interval threshold, wherein the second interval threshold is greater than the first interval threshold, the third interval threshold is greater than the second interval threshold, and the fourth interval threshold is greater than the third interval threshold; Divide the value range of the SHOT descriptor based on the first interval threshold, the second interval threshold, the third interval threshold, and the fourth interval threshold to obtain a first value range, a second value range, a third value range, and a fourth value range; The QB-SHOT method is used to perform binary conversion of double coding bits on the first value range, the second value range, the third value range and the fourth value range to obtain a first code and a second code, and the first code and the second code are synthesized to obtain a QB-SHOT descriptor, wherein, after the first value range is subjected to binary conversion of double coding bits, the first code and the second code are 0, after the second value range is subjected to binary conversion of double coding bits, the first code is 0 and the second code is 1, after the third value range is subjected to binary conversion of double coding bits, the first code is 1 and the second code is 0, and after the fourth value range is subjected to binary conversion of double coding bits, the first code and the second code are 1.

[0012] On the other hand, the present invention also provides a portal crane identification device, comprising: A key point determination module, used for determining key points and neighborhood points based on the acquired point cloud data of the portal crane to be identified; A histogram acquisition module is used to construct a spherical neighborhood centered on the key point based on the constructed local reference coordinate system, divide the spherical neighborhood to obtain multiple subspaces, and calculate the cosine value of the angle between the neighborhood point and the key point in the subspace, and obtain a histogram based on the cosine value of the angle; The portal crane identification module is used to calculate the histogram using a quad-linear interpolation method to obtain a SHOT descriptor, encode the SHOT descriptor using a QB-SHOT method to obtain a QB-SHOT descriptor, and determine the portal crane component corresponding to the key point based on the QB-SHOT descriptor.

[0013] In another aspect, the present invention further provides an electronic device, comprising: a processor and a memory; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps in the portal crane identification method described above are implemented.

[0014] On the other hand, the present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the gantry crane identification method as described above.

[0015] The beneficial effects of the present invention are as follows: a spherical neighborhood centered on a key point is constructed based on a local reference coordinate system, the key point and the neighborhood point are projected into the local reference coordinate system, the influence of rotation and translation is eliminated, the descriptor of the key point has rotation and translation invariance, the spherical neighborhood is divided to obtain multiple subspaces, the feature information in the local area can be more finely counted, the expression ability of the descriptor is improved, the distribution of normals of the neighborhood points in the local area is counted through a histogram, the geometric features of the surface of the gantry crane components can be effectively described, the histogram is calculated using a quadlinear interpolation method to obtain a SHOT descriptor, the SHOT descriptor is encoded using a QB-SHOT method, the amount of calculation is reduced while retaining important feature information, and the recognition accuracy of the gantry crane is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of an embodiment of a portal crane identification method provided by the present invention; Figure 2 A schematic diagram of a model point cloud and a scene point cloud of a portal crane identification method provided by the present invention; Figure 3 A schematic diagram of a portal crane after identification by the portal crane identification method provided by the present invention; Figure 4 A schematic structural diagram of an embodiment of a portal crane identification device provided by the present invention; Figure 5 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0018] The present invention discloses a portal crane identification method, device, electronic device and storage medium, which can be used in a computer. The method, device or computer-readable storage medium involved in the present invention can be integrated with the above-mentioned device or can be relatively independent.

[0019] A specific embodiment of the present invention discloses a portal crane identification method, which can be executed by a computer, specifically by one or more processors of the computer. Figure 1 is a flow chart of the portal crane identification method provided by the embodiment of the present invention, please refer to Figure 1 , portal crane identification methods include: S101, determining key points and neighborhood points based on the acquired point cloud data of the portal crane to be identified; S102, constructing a spherical neighborhood centered on the key point based on the constructed local reference coordinate system, dividing the spherical neighborhood to obtain multiple subspaces, and calculating the cosine value of the angle between the neighborhood point and the key point in the subspace, and obtaining a histogram based on the cosine value of the angle; S103, using a quad-linear interpolation method to calculate the histogram to obtain a SHOT descriptor, using a QB-SHOT method to encode the SHOT descriptor to obtain a QB-SHOT descriptor, and determining the portal crane component corresponding to the key point based on the QB-SHOT descriptor. Among them, key points, also known as feature points, are stable and distinctive point sets obtained by defining detection standards in 3D point cloud data. The number of key points is much smaller than the amount of data in the original point cloud or image. Combined with local feature descriptors, key point descriptors are often used to represent the original data without losing representativeness and descriptiveness, thereby speeding up subsequent recognition, tracking and other data processing speeds. The QB-SHOT method is used to binary encode the SHOT descriptor, which makes up for the information loss of the SHOT descriptor in the binary encoding process. After determining the portal crane components corresponding to the key points based on the QB-SHOT descriptor, other key points are selected in the point cloud data of the portal crane to be identified, and matched and identified, so that all portal crane components can be identified.

[0020] Compared with the prior art, the portal crane identification method provided in this embodiment determines the key points and neighborhood points based on the acquired point cloud data of the portal crane to be identified, constructs a spherical neighborhood centered on the key point based on the constructed local reference coordinate system, divides the spherical neighborhood to obtain multiple subspaces, eliminates the influence of rotation and translation, makes the descriptor invariant to rotation and translation, divides the spherical neighborhood into multiple subspaces, can more finely count the feature information in the local area, improves the expression ability of the descriptor, calculates the cosine value of the angle between the neighborhood point and the key point in the subspace, obtains the histogram based on the cosine value of the angle, and obtains the histogram through the histogram. Figure 1 statistics the distribution of normals of neighborhood points in the local area, which can effectively describe the geometric features of the surface of the portal crane components. The four-linear interpolation method is used to calculate the histogram to obtain the SHOT descriptor. The calculation accuracy and stability of the descriptor are improved through four-linear interpolation, thereby improving the accuracy of subsequent point cloud processing. The QB-SHOT method is used to encode the SHOT descriptor to obtain the QB-SHOT descriptor. Based on the QB-SHOT descriptor, the portal crane components corresponding to the key points are determined, which reduces the amount of calculation while retaining important feature information and improves the accuracy of feature matching.

[0021] In some embodiments, in step S101, the laser radar point cloud technology acquires the three-dimensional spatial information of the portal crane to be identified by emitting a laser beam and receiving a reflected signal, and forms point cloud data, so that the collected data is not affected by factors such as light, weather, and occlusion. The model point cloud and scene point cloud of the portal crane to be identified are obtained based on the point cloud data. For schematic diagrams of the model point cloud and the scene point cloud, please refer to Figure 2 ,like Figure 2 As shown, Figure 2 The left side is the scene point cloud. Figure 2 The right side is the model point cloud. After the scene point cloud is obtained by laser radar scanning, the scene point cloud is processed and useless points in the model point cloud are removed to obtain the model point cloud. A key point P is selected as the reference point in the model point cloud of the portal crane to be identified, and all the neighborhood points in the neighborhood of the key point P are determined. .

[0022] In some embodiments, in step S102, a spherical neighborhood centered on the key point is constructed based on the established local reference coordinate system. First, the local reference coordinate system is established. The process is as follows: determine the key point And the neighboring points: , , , The location coordinates of the neighboring points are used to calculate the centroid of the neighboring points. The calculation formula for the centroid of the neighboring points is: , The distance weight is determined based on the key points and neighborhood points. The distance weight is calculated as follows: , in, is the distance weight; The covariance matrix is ​​constructed based on the centroid, distance weight, key points and neighborhood points of the neighborhood points. The calculation formula of the covariance matrix is: , in, is the covariance matrix, is the neighborhood radius, For all points in the neighborhood, is the centroid of all neighborhood points, is the distance from the neighborhood point to the centroid, is the transpose of the matrix; Perform eigenvalue decomposition on the covariance matrix to obtain the eigenvector , , , and the eigenvalues ​​corresponding to the eigenvectors , , , , based on the eigenvectors and eigenvalues, determine the x-axis, y-axis, and z-axis of the local reference coordinate system, that is, select the two eigenvectors with the largest eigenvalues and As the z-axis and x-axis of the local reference coordinate system, calculate the eigenvector and The cross product of is used as the y-axis of the local reference coordinate system. After obtaining the x-axis, y-axis, and z-axis of the reference coordinate system, the establishment of the local reference coordinate system is preliminarily completed. Secondly, a spherical neighborhood centered on the key point is constructed based on the local reference coordinate system, that is, the key point P and the neighborhood point are projected into the local reference coordinate system (LRF), and the neighborhood radius r of the neighborhood point and the key point is determined. Based on the local reference coordinate system, a spherical neighborhood space with a radius of r and the key point as the center is constructed. The local reference coordinate system (LRF) increases the uniqueness of the descriptor and transforms the key point from the local surface to the local reference coordinate system, so that the descriptor has rotation and translation invariance. The spherical neighborhood is divided into 2, 2, and 8 equal parts along the radial, latitude, and longitude directions, respectively, to obtain 32 subspaces; Calculate the cosine value of the angle between the neighborhood point and the key point in the subspace, and obtain the histogram based on the cosine value of the angle. First, for each subspace, calculate the normal of the key point in the subspace and the normal of the neighborhood points in the subspace , based on the normal of the key point and the normal of the neighborhood point, determine the cosine value of the angle between the neighborhood point and the key point in the subspace , the calculation formula of the cosine of the angle is: , in, is the normal of the key point, is the normal of the neighborhood point in the subspace, is the z-axis of the local reference coordinate system; Secondly, the cosine values ​​of the angles between the neighborhood points and the key points are equally divided to obtain a histogram. The cosine values ​​of the angles are equally divided into 11 spaces. The neighborhood points are assigned to the corresponding intervals, and the number of neighborhood points in each interval is counted to form a histogram. An 11-dimensional histogram with as the horizontal axis and the number as the vertical axis.

[0023] In some embodiments, in step S103, the histogram is calculated using a quad-linear interpolation method to obtain a SHOT descriptor. First, the histograms of 32 subspaces are counted and combined to obtain the first descriptor of the key point, so as to obtain a 352-dimensional SHOT descriptor of the key point. Secondly, the first descriptor of the key point is calculated using a quad-linear interpolation method to obtain the SHOT descriptor of the key point. The specific steps are as follows: for each key point, four directions around the key point are determined according to the normal of the key point, and then the gradient histograms in the four directions are calculated. Next, the quad-linear interpolation method is used to calculate the S of the point. The HOT descriptor uses the gradient histograms in four directions as the values ​​of the interpolation points, and calculates the distances and weights of the key points in the four directions, and then calculates the SHOT descriptor of the key points. The SHOT descriptor contains the statistical information of the cosine value of the angle between the normal of the neighborhood point and the normal of the key point. The SHOT descriptor takes into account the normal vector and curvature information of the point cloud data and performs weighting in the calculation. At the same time, a local coordinate system is established in the process of obtaining the SHOT descriptor, which makes the SHOT descriptor more robust. Therefore, the SHOT feature descriptor has better robustness to noise and local shape changes in the point cloud. In the calculation process of SHOT descriptor, for the neighborhood space of a key point, if its subspace does not contain neighborhood points, the corresponding histogram statistics will be recorded as 0. However, point cloud data is usually distributed in the form of surface points. Some key points will have a neighborhood point number of 0 in the neighborhood subspace, resulting in some elements of the SHOT feature vector being 0. The non-zero elements in the SHOT feature vector indicate that there are neighborhood points at the corresponding position. Based on the non-zero items and distribution intervals of the SHOT feature vector, the QB-SHOT method is used to encode the SHOT descriptor to obtain the QB-SHOT descriptor. Treat them as a group and divide the non-zero values ​​into intervals according to the value of the SHOT descriptor. The interval it falls into is encoded as , iterate in sequence, and finally encode the descriptor as , where QB-SHOT is a SHOT feature descriptor with interval double coding bits, that is, the new coding rule is used to perform binary conversion of the double coding bits on the SHOT descriptor. The specific process is: initialize the SHOT descriptor and obtain the SHOT descriptor Range , a first interval threshold, a second interval threshold, a third interval threshold and a fourth interval threshold are preset, wherein the second interval threshold is greater than the first interval threshold, the third interval threshold is greater than the second interval threshold, the fourth interval threshold is greater than the third interval threshold, the first interval threshold is 0, the second interval threshold is greater than 0 and less than or equal to 0.34, the third interval threshold is greater than 0.34 and less than or equal to 0.67, and the fourth interval threshold is greater than 0.67 and less than or equal to 1, and the value range of the SHOT descriptor is divided based on the first interval threshold, the second interval threshold, the third interval threshold and the fourth interval threshold to obtain a first value range, a second value range, a third value range and a fourth value range, that is, the value of the SHOT descriptor Divide into intervals , , , In the process, the QB-SHOT method is used to perform binary conversion of double coding bits on the first value range, the second value range, the third value range and the fourth value range to obtain the first coding bit. and the second code , after performing binary conversion of double coding bits on the first value range, the values ​​of the first code and the second code are 0, after performing binary conversion of double coding bits on the second value range, the value of the first code is 0, and the value of the second code is 1, after performing binary conversion of double coding bits on the third value range, the value of the first code is 1, and the value of the second code is 0, after performing binary conversion of double coding bits on the fourth value range, the values ​​of the first code and the second code are 1; The process of performing binary conversion of double coded bits is: when When , it means that the number of neighborhood points in the interval is 0, then ; when and When , ; when and When , ; when and When , ; The first code and the second code are synthesized to obtain a SHOT feature descriptor based on interval double coding bits, that is, the QB-SHOT descriptor. This encoding method can make up for the loss of information to a certain extent. For example, two groups {0.21, 0.37, 0, 0} and {0.98, 0.82, 0, 0} will be encoded as {1, 1, 0, 0, 0, 0, 0} using the DB-SHOT rule. Using QB-SHOT, the former group will be encoded as {0, 1, 1, 0, 0, 0, 0}, and the latter group will be encoded as {1, 1, 1, 1, 0, 0, 0, 0}, which increases the distinguishability of the encoding results, reduces the probability of false matching, and simplifies the binary encoding rules to a certain extent.

[0024] Based on the QB-SHOT descriptor, determine the portal crane component corresponding to the key point, match the QB-SHOT descriptor of the key point with the portal crane component descriptor stored in the database, find the portal crane component descriptor that is most similar to the QB-SHOT descriptor of the key point, and then determine the portal crane component to which the key point P belongs. Select other key points and neighboring points from the point cloud data of the portal crane to be identified, encode and match them, and finally identify all portal crane components. For the schematic diagram of the portal crane after identification, please refer to Figure 3 ,like Figure 3 As shown, the slashes in the image represent incorrect matches, and the more slashes there are, the lower the recognition rate.

[0025] In order to better implement the portal crane identification method in the embodiment of the present invention, based on the portal crane identification method, correspondingly, Figure 4 As shown, the embodiment of the present invention further provides a portal crane identification device, and the portal crane identification device 400 includes: A key point determination module 401 is used to determine key points and neighborhood points based on the acquired point cloud data of the portal crane to be identified; A histogram acquisition module 402 is used to construct a spherical neighborhood centered on the key point based on the constructed local reference coordinate system, divide the spherical neighborhood to obtain multiple subspaces, and calculate the cosine value of the angle between the neighborhood point and the key point in the subspace, and obtain a histogram based on the cosine value of the angle; The portal crane identification module 403 is used to calculate the histogram using the quad-linear interpolation method to obtain the SHOT descriptor, encode the SHOT descriptor using the QB-SHOT method to obtain the QB-SHOT descriptor, and determine the portal crane component corresponding to the key point based on the QB-SHOT descriptor.

[0026] like Figure 5 As shown, based on the portal crane identification method, the present invention also provides an electronic device 500, which can be a computing device such as a mobile terminal, a desktop computer, a notebook, a palm computer, and a server. The electronic device 500 includes a processor 501, a memory 502, and a display 503. Figure 5 Only some components of the electronic device 500 are shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0027] In some embodiments, the memory 502 may be an internal storage unit of the electronic device 500, such as a hard disk or memory of the electronic device 500. In other embodiments, the memory 502 may also be an external storage device of the electronic device 500, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 500. Further, the memory 502 may also include both an internal storage unit of the electronic device 500 and an external storage device. The memory 502 is used to store application software and various data installed in the electronic device 500, such as program codes installed in the electronic device 500. The memory 502 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a portal crane identification program is stored in the memory 502, and the portal crane identification program can be executed by the processor 501, thereby realizing the portal crane identification method of each embodiment of the present invention.

[0028] In some embodiments, the processor 501 may be a central processing unit (CPU), a microprocessor or other data processing chip, used to run program codes or process data stored in the memory 502, such as a portal crane identification method.

[0029] In some embodiments, the display 503 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 503 is used to display the identification information of the portal crane identification program and to display a visual user interface. The components 501-503 of the electronic device 500 communicate with each other via a system bus.

[0030] In some embodiments, when the processor 501 executes the gantry crane identification program in the memory 502, the various steps in the gantry crane identification method described in the above embodiments are implemented. Since the gantry crane identification method has been described in detail above, it will not be repeated here.

[0031] Accordingly, an embodiment of the present application also provides a computer-readable storage medium, which is used to store computer-readable programs or instructions. When the program or instructions are executed by a processor, the steps or functions in the gantry crane identification method provided in the above-mentioned method embodiments can be implemented.

[0032] In summary, the gantry crane identification method, device, electronic device and storage medium provided by the present invention determine the key points and neighborhood points based on the acquired point cloud data of the gantry crane to be identified, construct a spherical neighborhood centered on the key point based on the established local reference coordinate system, divide the spherical neighborhood to obtain multiple subspaces, and calculate the cosine value of the angle between the neighborhood point and the key point in the subspace, obtain a histogram based on the cosine value of the angle, calculate the histogram using the quadlinear interpolation method to obtain a SHOT descriptor, encode the SHOT descriptor using the QB-SHOT method to obtain a QB-SHOT descriptor, and determine the gantry crane component corresponding to the key point based on the QB-SHOT descriptor, thereby retaining important feature information and improving the identification accuracy of the gantry crane.

[0033] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware through a computer program, and the program can be stored in a computer-readable storage medium, wherein the computer-readable storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0034] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.

Claims

1. A portal crane identification method, characterized in that: include: Determine key points and neighborhood points based on the acquired point cloud data of the portal crane to be identified; A spherical neighborhood centered on the key point is constructed based on the established local reference coordinate system, the spherical neighborhood is divided to obtain a plurality of subspaces, and the cosine values ​​of the angles between the neighborhood points and the key point in the subspaces are calculated, and a histogram is obtained based on the cosine values ​​of the angles; The histogram is calculated by a quad-linear interpolation method to obtain a SHOT descriptor, the SHOT descriptor is encoded by a QB-SHOT method to obtain a QB-SHOT descriptor, and the portal crane component corresponding to the key point is determined based on the QB-SHOT descriptor.

2. The portal crane identification method according to claim 1, characterized in that: The establishing of the local reference coordinate system comprises: Obtaining neighborhood points within the neighborhood of the key point, and calculating the centroid of the neighborhood points based on the neighborhood points; Obtaining the key point, and determining a distance weight based on the key point and neighboring points; Constructing a covariance matrix based on the centroid of the neighborhood points, the distance weights, the key points and the neighborhood points, performing eigenvalue decomposition on the covariance matrix to obtain an eigenvector and an eigenvalue corresponding to the eigenvector; The x-axis, y-axis, and z-axis of the local reference coordinate system are determined based on the eigenvector and the eigenvalue.

3. The portal crane identification method according to claim 2, characterized in that: The method of constructing a spherical neighborhood centered on the key point based on the constructed local reference coordinate system includes: Determine the neighborhood radius of the neighborhood points and key points; A spherical neighborhood with the key point as the center and the neighborhood radius as the radius is constructed based on the local reference coordinate system.

4. The portal crane identification method according to claim 3, characterized in that: The spherical neighborhood is divided to obtain a plurality of subspaces, including: The spherical neighborhood is divided along radial, latitude and longitude directions to obtain multiple subspaces.

5. The portal crane identification method according to claim 4, characterized in that: The step of calculating the cosine value of the angle between the neighborhood point and the key point in the subspace, and obtaining a histogram based on the cosine value of the angle includes: Calculating normals of key points in the subspace; Calculating the normal of the neighborhood points in the subspace; Determine the cosine value of the angle between the neighborhood point and the key point in the subspace based on the key point normal and the neighborhood point normal; The cosine values ​​of the angles between the neighborhood points and the key points are equally divided to obtain a histogram, wherein the histogram has the cosine value of the angle as the horizontal coordinate and the number as the vertical coordinate.

6. The portal crane identification method according to claim 5, characterized in that: The method of using a quadrilinear interpolation method to calculate the histogram to obtain a SHOT descriptor includes: Obtaining a first descriptor of the key point based on the histogram, The first descriptor of the key point is calculated by using a quadrilinear interpolation method to obtain a SHOT descriptor of the key point, wherein the SHOT descriptor includes statistical information of a cosine value of an angle between a normal line of the neighborhood point and a normal line of the key point.

7. The portal crane identification method according to claim 6, characterized in that: The method of encoding the SHOT descriptor by using the QB-SHOT method to obtain the QB-SHOT descriptor includes: Initializing the SHOT descriptor to obtain a value range of the SHOT descriptor; Preset a first interval threshold, a second interval threshold, a third interval threshold and a fourth interval threshold, wherein the second interval threshold is greater than the first interval threshold, the third interval threshold is greater than the second interval threshold, and the fourth interval threshold is greater than the third interval threshold; Divide the value range of the SHOT descriptor based on the first interval threshold, the second interval threshold, the third interval threshold, and the fourth interval threshold to obtain a first value range, a second value range, a third value range, and a fourth value range; The QB-SHOT method is used to perform binary conversion of double coding bits on the first value range, the second value range, the third value range and the fourth value range to obtain a first code and a second code, and the first code and the second code are synthesized to obtain a QB-SHOT descriptor, wherein, after the first value range is subjected to binary conversion of double coding bits, the first code and the second code are 0, after the second value range is subjected to binary conversion of double coding bits, the first code is 0 and the second code is 1, after the third value range is subjected to binary conversion of double coding bits, the first code is 1 and the second code is 0, and after the fourth value range is subjected to binary conversion of double coding bits, the first code and the second code are 1.

8. A portal crane identification device, characterized in that: include: A key point determination module, used for determining key points and neighborhood points based on the acquired point cloud data of the portal crane to be identified; A histogram acquisition module is used to construct a spherical neighborhood centered on the key point based on the constructed local reference coordinate system, divide the spherical neighborhood to obtain multiple subspaces, and calculate the cosine value of the angle between the neighborhood point and the key point in the subspace, and obtain a histogram based on the cosine value of the angle; The portal crane identification module is used to calculate the histogram using a quad-linear interpolation method to obtain a SHOT descriptor, encode the SHOT descriptor using a QB-SHOT method to obtain a QB-SHOT descriptor, and determine the portal crane component corresponding to the key point based on the QB-SHOT descriptor.

9. An electronic device, characterized in that: including memory and processor; The memory stores a computer-readable program executable by the processor; When the processor executes the computer-readable program, the steps in the portal crane identification method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps in the portal crane identification method according to any one of claims 1-7.

Citation Information

Patent Citations

  • Industrial robot workpiece identification and pose estimation method based on three-dimensional point cloud features

    CN112669385A

  • Multi-solid-state-laser-radar external parameter calibration method based on SIFT-SHOT characteristics

    CN113470090A

  • Method and system for measuring deflection angle and speed of gantry crane based on laser radar

    CN115784015A

  • Substation equipment identification method and device based on combination of SHOT feature and ESF feature

    CN116110040A

  • Bulk cargo ship image point cloud fusion scanning segmentation method

    CN117252895A