Local equipment updating method and system based on panoramic image and laser point cloud technology

Abstract

The invention provides a substation local equipment updating method and system based on a panoramic image and a laser point cloud technology. The method comprises the steps that laser point cloud data, panoramic image data and track data in the acquisition process of a changing device are acquired around the changing device by a circle; establishing a mapping relationship between the point cloud data and the panoramic image data; automatically acquiring a to-be-updated area of the equipment and performing point cloud registration; and replacing the changed equipment data according to the obtained to-be-updated area. The system part comprises a data acquisition module which is used for acquiring laser point cloud data, panoramic image data and track data in the acquisition process of a changing device around the changing device by a circle; the coordinate conversion module is used for establishing a mapping relation between the point cloud data and the panoramic image data; and the point cloud registration module is used for carrying out point cloud registration through the equipment nameplate information.

Description

Technical Field

[0001] The present invention belongs to the field of substation equipment updating, and in particular relates to a local equipment updating method and system based on panoramic imaging and laser point cloud technology. Background Art

[0002] In recent years, VR panoramic technology has been applied in power grids. Technicians use 360-degree panoramic technology to restore the primary and secondary equipment of the entire substation, as well as the layout of roads and buildings, to achieve remote inspections within the station. VR panoramic technology brings convenience and efficiency to work. By connecting various production data such as PMS ledgers, production data, and operation and maintenance data, multiple interactions between people, equipment, and the surrounding environment are carried out in a 720-degree all-round three-dimensional environment, which essentially improves the inspection efficiency. The panoramic platform can realize site jumps, display nameplate information, physical ID and other content, and display the real scene of the actual substation in 360° / 720° visual blind spots.

[0003] LiDAR technology LiDAR point cloud data has been used in power grids for many years. LiDAR point cloud data LiDAR can perform three-dimensional modeling quickly and with high precision. The generated point cloud can reflect the geometric shape of the substation and equipment location information. Functions such as distance measurement can be developed within the point cloud model, and aerial / ground data collection and application have been realized.

[0004] At present, when updating equipment in a substation, it is necessary to collect data from the entire station, and then solve, pre-process and identify the data before the data can be used for business applications. The existing methods for updating equipment in stations have the following technical defects:

[0005] (1) It is necessary to scan the entire site and repeatedly scan unchanged devices, resulting in data redundancy and resource occupation;

[0006] (2) It is necessary to solve, preprocess and identify the target of the whole station data, which takes a long time and the repeated work leads to the waste of human resources and hardware resources;

[0007] (3) The existing data update scheme only updates the laser point cloud data and does not involve the panoramic data.

[0008] The data obtained by scanning the same area twice will have different accuracy, resulting in different values ​​of the global coordinates of the point cloud. If they are directly replaced, the coordinates of the replaced device will be misaligned with the global coordinates of the substation. Summary of the invention

[0009] In order to solve the deficiencies in the prior art, the present invention provides a local device updating method and system based on panoramic imaging and laser point cloud technology.

[0010] The present invention adopts the following technical solution.

[0011] The present invention provides a local device update method based on panoramic imaging and laser point cloud technology, comprising:

[0012] Collect laser point cloud data, panoramic image data and trajectory data of the changed device during the collection process by circling the changed device;

[0013] Establish a mapping relationship between point cloud data and panoramic image data;

[0014] Automatically obtain the device area to be updated and perform point cloud registration;

[0015] Replace the changed device data based on the acquired area to be updated.

[0016] Preferably, the establishing of a mapping relationship between point cloud data and panoramic image data includes:

[0017] Convert the point cloud data in the WGS84 coordinate system to the local horizontal coordinate system, convert the object points in the local horizontal coordinate system to the inertial measurement unit IMU coordinate system, convert the IMU coordinate system to the panoramic spherical coordinate system, and obtain the corresponding RGB value of the spherical surface yesterday.

[0018] Preferably, converting the point cloud data in the WGS84 coordinate system to the local horizontal coordinate system includes:

[0019] The coordinates of the object point (laser point cloud point) in the world coordinate system are (X, Y, Z) WGS84 , the position corresponding to the time when the photo was taken is (X, Y, Z) O , the panoramic photo is taken at the time corresponding to the geodetic coordinate longitude and latitude (B, L), then the object point in the world geodetic coordinate system is converted to the coordinates in the local horizontal coordinate system (X, Y, Z) Local The calculation formula is

[0020]

[0021]

[0022] Preferably, the converting of the local horizontal coordinate system object point to the inertial measurement unit IMU coordinate system comprises:

[0023] According to the attitude angle corresponding to the moment when the panoramic photo was taken, the roll angle, pitch angle, and yaw angle are (φ, ω, κ) respectively, and the coordinates in the local horizontal coordinate system are converted to the coordinates in the IMU coordinate system (X, Y, Z) IMU :

[0024]

[0025]

[0026]

[0027] Preferably, the automatically acquiring the device area to be updated includes:

[0028] Identify the nameplates on the substation equipment in the original data and the newly collected data, and obtain the label content on the nameplates;

[0029] Search the original data for devices with the same name in the newly collected data outside the trajectory data range;

[0030] Using the mapping relationship between point cloud data and panoramic image data, find the devices with the same name in the original data and the newly collected data respectively, and obtain the point cloud data corresponding to the devices with the same name through the mapping relationship between image and point cloud as the feature data of point cloud registration;

[0031] Perform point cloud registration to register the newly collected data with the original data, and update the trajectory data according to the registration results. The updated part of the trajectory is the area to be updated.

[0032] Preferably, the point cloud registration includes:

[0033] Find the corresponding sign in the original data through the recognized text in the newly collected data;

[0034] The position of the sign is obtained through the correspondence between the panoramic image and the point cloud, and the corner points of the sign are used as the registration feature points;

[0035] Select at least 4 groups of sign positions that are not in the same plane as the registration feature set;

[0036] The ICP algorithm is used to perform registration calculation on the registration feature set to obtain the registration coordinate transformation relationship.

[0037] Preferably, the replacing of the changed device data according to the acquired area to be updated includes:

[0038] Use coordinate transformation relationships to update the newly collected trajectory data, point cloud data, and panoramic image sign positions as a whole;

[0039] Using the updated trajectory data, point cloud data and panoramic image data within the trajectory range are selected from the original data;

[0040] Use the updated trajectory data to select point cloud data and panoramic data within the same range in the newly collected data;

[0041] Replace the data in the original data with the data selected from the newly collected data.

[0042] The present invention also provides a local equipment update system based on panoramic imaging and laser point cloud technology, which is used by the aforementioned substation local equipment update method based on panoramic imaging and laser point cloud technology, and includes:

[0043] A data acquisition module, used to collect laser point cloud data, panoramic image data and trajectory data of the changed device during a circle around the changed device;

[0044] Coordinate conversion module, used to establish the mapping relationship between point cloud data and panoramic image data;

[0045] The point cloud registration module is used to perform point cloud registration based on equipment nameplate information.

[0046] The present invention also provides a terminal, including a processor and a storage medium; the characteristics are:

[0047] The storage medium is used to store instructions;

[0048] The processor is configured to operate according to the instructions to execute the steps according to the aforementioned method.

[0049] The present invention also provides a computer-readable storage medium on which a computer program is stored, characterized in that the program implements the steps of the above method when executed by a processor.

[0050] The beneficial effect of the present invention is that, compared with the prior art, the present invention uses laser point cloud technology and panoramic imaging technology to realize the automatic update of substation data when there is equipment update in the substation. At the same time, the ICP algorithm is introduced for point cloud registration, which solves the problem of low efficiency and resource waste caused by the need to scan the entire station equipment data twice when the equipment is updated in the prior art, and solves the problem that the data obtained by the two scans in the prior art will be different in accuracy, resulting in different values ​​of the global coordinates of the point cloud. If directly replaced, the replaced device coordinates and the global coordinates of the substation will be misaligned. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 Schematic diagram of the mapping relationship transformation process between the laser point cloud and the panoramic image in the present invention;

[0052] Figure 2 It is a schematic diagram of the transformation between the panoramic sphere and the panoramic image in the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical scheme and advantages of the present invention clearer, the technical scheme of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The embodiments described in this application are only part of the embodiments of the present invention, not all of them. Based on the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the scope of protection of the present invention.

[0054] Original data: laser point cloud data of the entire substation and corresponding panoramic image data;

[0055] Purpose: To replace the changed equipment data in the substation.

[0056] Embodiment 1 of the present invention provides a method for updating local equipment in a substation based on panoramic imaging and laser point cloud technology, comprising:

[0057] Step 1: Collect the laser point cloud data and panoramic image data of the changed device. This process is to go around the device once to obtain complete device data and save the trajectory data during the collection.

[0058] Step 2: Establish a mapping relationship between point cloud data and panoramic image data;

[0059] The initial coordinate system of the three-dimensional laser point cloud is the world geodetic coordinate system, and the panoramic image uses the image pixel coordinate system. In the process of establishing a mapping relationship between the laser point cloud and the panoramic image, multiple coordinate system transformations are required to convert to the same coordinate system. In order to quantitatively describe the camera imaging process, four reference coordinate systems are defined: the world coordinate system, the camera coordinate system, the image physical coordinate system, and the image pixel coordinate system.

[0060] World coordinate system: A user-defined three-dimensional world coordinate system introduced to describe the position of objects in the real world. The unit is m, and the commonly used standard is the WGS84 coordinate system.

[0061] The WGS-84 coordinate system (World Geodetic System-1984 Coordinate System) is a geocentric coordinate system adopted internationally. The origin of the coordinates is the center of mass of the earth. The Z axis of the geocentric rectangular coordinate system points to the direction of the agreed earth pole (CTP) defined by BIH (International Time Service) 1984.0, and the X axis points to the intersection of the zero meridian plane of BIH 1984.0 and the CTP equator. The Y axis is perpendicular to the Z axis and the X axis to form a right-handed coordinate system, which is called the 1984 World Geodetic Coordinate System.

[0062] Local horizontal coordinate system: A coordinate system established on the camera, defined to describe the position of an object from the camera's perspective, serving as an intermediate link between the world coordinate system and the image / pixel coordinate system. The unit is m.

[0063] IMU coordinate system: It is the local coordinate system of the inertial measurement unit (IMU), which is used to reflect the acceleration and angular velocity measured by the IMU itself.

[0064] Panoramic sphere coordinate system: The center of the panoramic sphere is the origin of the coordinate system O S , the Y axis points to the forward direction, the X axis points to the right side of the vehicle, and the Z axis is vertically upward. S -XYZ constitutes the panoramic sphere space coordinate system.

[0065] Image space coordinate system: It is introduced to describe the coordinates of the image points of an object on a digital image (photo). It is the coordinate system where the information we actually read from the camera is located. The unit is (number of pixels).

[0066] The mapping relationship between laser point cloud and panoramic image, the whole transformation process is as follows Figure 2 shown.

[0067] The conversion process is broken down into the following 4 steps.

[0068] 1) The point cloud in the WGS84 coordinate system is converted to the local horizontal coordinate system. The coordinates of the object point (laser point cloud point) in the world geodetic coordinate system are (X, Y, Z) WGS84 , the position corresponding to the time when the photo was taken is (X, Y, Z) O , the panoramic photo is taken at the time corresponding to the geodetic coordinate longitude and latitude (B, L), then the object point in the world geodetic coordinate system is converted to the coordinates of the local horizontal coordinate system [(X, Y, Z) Local The calculation formula of ] is

[0069]

[0070]

[0071] 2) The local horizontal coordinate system object point is transferred to the inertial measurement unit (IMU) coordinate system. According to the attitude angle corresponding to the moment when the panoramic photo was taken [roll angle, pitch angle, yaw angle (φ, ω, κ)], the coordinates in the local horizontal coordinate system are converted to the coordinates in the IMU coordinate system (X, Y, Z) IMU :

[0072]

[0073]

[0074] 3) The IMU coordinate system is converted to the panoramic spherical coordinate system, and the collinear equation is used to solve the coordinates of the spherical points, such as Figure 2As shown. The spatial position relationship of the axes between each sensor has been strictly calibrated. The conversion from the IMU coordinate system to the panoramic spherical coordinate system mainly includes 6 parameters: 3 rotation angles (α, β, γ) and 3 translation amounts (ΔX, ΔY, ΔZ) C . Let the panoramic spherical coordinates be (X S , Y S , Z S ) S , the coordinates in the IMU coordinate system are (X, Y, Z) IMU , through translation and rotation, the coordinates of the laser point in the panoramic spherical coordinates are obtained, and then the collinearity equation is used to solve the corresponding spherical point coordinates. The collinearity condition equation in the spherical coordinate system is

[0075]

[0076]

[0077] Where R is the distance from the object point to the center of the sphere, and r is the radius of the custom panoramic sphere.

[0078] 4) Obtain the RGB value (color) corresponding to the spherical coordinates. At this point, the conversion between the laser point and the panoramic spherical point is completed. The panoramic image is usually collected in a plane form. In order to obtain the corresponding RGB value, the panoramic spherical point must be restored to the image space coordinate system, and the RGB value is obtained according to the pixel point coordinate system. The conversion is as follows: Figure 2 shown.

[0079] The transformation relationship between the panoramic sphere and the panoramic image is:

[0080]

[0081]

[0082] Where x p ,y p is the pixel coordinates corresponding to the panoramic image, and r is the radius of the custom panoramic sphere. The RGB value at the position can be obtained through the pixel coordinates.

[0083] Step 3: Automatically obtain the device area to be updated. The specific steps are as follows:

[0084] (1) Identify the nameplates on the substation equipment in the original data and the newly collected data, and obtain the label content (equipment name) on the nameplate;

[0085] The present invention uses a machine learning algorithm SVM classifier to analyze the texture features of the signboard, and then recognizes the text on the signboard to perform signboard recognition. Substation signs are mainly red characters on a white background, black characters on a white background, and phase names are yellow, red, and green as the background color, and the characters are white. First, most of the areas of interest in the panoramic image are roughly extracted through the color features of the signboard itself, and then the text in the panoramic image signboard is recognized by OCR technology.

[0086] (2) Search the original data for devices with the same name in the newly collected data outside the trajectory data range;

[0087] (3) Using the mapping relationship between point cloud data and panoramic image data, find the devices with the same name in the original data and the newly collected data, respectively, and obtain the point cloud data corresponding to the devices with the same name through the mapping relationship between the image and the point cloud as the feature data for point cloud registration;

[0088] (4) Point cloud registration: register the newly collected data with the original data, and update the trajectory data based on the registration results. The updated part of the trajectory is the area that needs to be updated.

[0089] Point cloud registration is essentially the coordinate transformation of point cloud data. In a three-dimensional point cloud data set, take any point in the set as Pi (x, y, z), and record the point obtained by coordinate transformation as P′i (x′, y′, z′). Record the rotation matrix R, translation matrix T, and transformation matrix H, then the three-dimensional space coordinate transformation equations are as follows:

[0090]

[0091]

[0092] Wherein: tx represents the offset of point P on the x-axis (the same applies to ty and tz); V represents the scale of the projection transformation in each coordinate direction; U refers to the scale factor of the overall point cloud. Since the point cloud data generated by laser scanning will not produce singular deformation, V is the zero vector and U = 1; α represents the clockwise rotation angle of the point around the x-axis (the same applies to β and θ).

[0093] The ICP algorithm, or the iterative closest point registration algorithm, is a classic algorithm for precise point cloud registration. The ICP algorithm is essentially an optimal matching algorithm based on least squares. It repeatedly searches for corresponding points and optimal coordinate transformations between two point clouds until a certain convergence condition is met and the iteration is terminated. The purpose of this algorithm is to find the transformation matrices R and T between the original point cloud and the target point cloud so that the two point clouds meet the optimal matching under a certain metric. The basic idea of ​​the algorithm is: first assume an initial pose (position and attitude) estimate, select a certain number of points from the point set obtained from a scan from one perspective, and then find the point set with the closest distance to these points from the point set obtained from the scan from another perspective. Through the optimal coordinate transformation, the distance between the corresponding points is minimized, and it is calculated iteratively until the objective function value composed of the residual sum of squares remains unchanged.

[0094] The panoramic and point cloud data in the present invention are in geographic coordinate systems. The coordinates of the two collected data do not involve large numerical differences, only a deviation of about 1 cm in the XY direction and a deviation of about 3 cm in the Z direction. Therefore, coarse alignment is not involved. The present invention directly uses the ICP algorithm for fine alignment.

[0095] The main process of this solution for registration through sign information is as follows:

[0096] (1) Find the corresponding sign in the original data through the recognized text in the newly collected data;

[0097] (2) Obtain the position of the sign through the correspondence between the panoramic image and the point cloud, and use the corner points of the sign as the registration feature points;

[0098] (3) Select at least four groups of sign positions that are not in the same plane as the registration feature set;

[0099] (4) Use the ICP algorithm to perform registration calculations on the registration feature set to obtain the registration coordinate transformation relationship.

[0100] Step 4: Replace the changed device data according to the acquired area to be updated.

[0101] (1) Use coordinate transformation relationships to update the newly collected trajectory data, point cloud data, and panoramic image sign positions as a whole;

[0102] (2) Using the updated trajectory data, point cloud data and panoramic image data within the trajectory range are selected from the original data;

[0103] (3) Use the updated trajectory data to select point cloud data and panoramic data within the same range of the newly collected data;

[0104] (4) The data selected from the newly collected data is used to replace the data in the original data. At this point, the local device data is automatically updated.

[0105] The local equipment updating method of substation based on panoramic image and laser point cloud technology includes changing equipment acquisition (including panoramic and laser point cloud), fusing panoramic image and point cloud data, identifying signs of data outside the track, obtaining label content and corresponding three-dimensional position, finding the label and position of the panoramic image in the original three-dimensional data; using label data for registration, and replacing the data in the track path after registration.

[0106] Use the coordinate transformation relationship to update the newly collected trajectory data, solved point cloud data, and panoramic image sign position as a whole. Use the updated trajectory data to select the point cloud data and panoramic image data within the maximum trajectory range in the original data, and use the trajectory data to select the point cloud data and panoramic data within the same range in the newly collected data; use the data selected from the newly collected data to replace the data in the original data. At this point, the local device data is automatically updated.

[0107] The beneficial effect of the present invention is that, compared with the prior art, the present invention uses laser point cloud technology and panoramic imaging technology to realize the automatic update of substation data when there is equipment update in the substation. At the same time, the ICP algorithm is introduced for point cloud registration, which solves the problem of low efficiency and resource waste caused by the need to scan the entire station equipment data twice when the equipment is updated in the prior art, and solves the problem that the data obtained by the two scans in the prior art will be different in accuracy, resulting in different values ​​of the global coordinates of the point cloud. If directly replaced, the replaced device coordinates and the global coordinates of the substation will be misaligned.

[0108] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0109] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0110] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0111] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0112] 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 above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A local device update method based on panoramic imaging and laser point cloud technology, comprising: Collect laser point cloud data, panoramic image data and trajectory data of the changed device during the collection process by circling the changed device; Establish a mapping relationship between point cloud data and panoramic image data; Automatically obtain the device area to be updated and perform point cloud registration; Replace the changed device data based on the acquired area to be updated.

2. According to claim 1, a local device update method based on panoramic imaging and laser point cloud technology is characterized in that: The establishment of a mapping relationship between point cloud data and panoramic image data includes: Convert the point cloud data in the WGS84 coordinate system to the local horizontal coordinate system, convert the object points in the local horizontal coordinate system to the inertial measurement unit IMU coordinate system, convert the IMU coordinate system to the panoramic spherical coordinate system, and obtain the RGB value corresponding to the spherical surface yesterday.

3. The local device update method based on panoramic imaging and laser point cloud technology according to claim 2 is characterized in that: The conversion of the point cloud data in the WGS84 coordinate system to the local horizontal coordinate system includes: The coordinates of the object point (laser point cloud point) in the world coordinate system are (X, Y, Z) WGS84 , the position corresponding to the time when the photo was taken is (X, Y, Z) O , the panoramic photo is taken at the time corresponding to the geodetic coordinate longitude and latitude (B, L), then the object point in the world geodetic coordinate system is converted to the coordinates in the local horizontal coordinate system (X, Y, Z) Local The calculation formula is 4. The local device update method based on panoramic imaging and laser point cloud technology according to claim 3 is characterized in that: The method of converting the local horizontal coordinate system object point to the inertial measurement unit IMU coordinate system includes: According to the attitude angle corresponding to the moment when the panoramic photo was taken, the roll angle, pitch angle, and yaw angle are (φ, ω, κ) respectively, and the coordinates in the local horizontal coordinate system are converted to the coordinates in the IMU coordinate system (X, Y, Z) IMU :

5. The local device update method based on panoramic imaging and laser point cloud technology according to claim 4 is characterized in that: The automatically obtaining the device area to be updated includes: Identify the nameplates on the substation equipment in the original data and the newly collected data, and obtain the label content on the nameplates; Search the original data for devices with the same name in the newly collected data outside the trajectory data range; Using the mapping relationship between point cloud data and panoramic image data, find the devices with the same name in the original data and the newly collected data respectively, and obtain the point cloud data corresponding to the devices with the same name through the mapping relationship between image and point cloud as the feature data of point cloud registration; Perform point cloud registration to register the newly collected data with the original data, and update the trajectory data according to the registration result. The part of the range within the updated trajectory is the area to be updated.

6. The local device update method based on panoramic imaging and laser point cloud technology according to claim 5, characterized in that: The point cloud registration comprises: Find the corresponding sign in the original data through the recognized text in the newly collected data; The position of the sign is obtained through the correspondence between the panoramic image and the point cloud, and the corner points of the sign are used as registration feature points; Select at least 4 groups of sign positions that are not in the same plane as the registration feature set; The ICP algorithm is used to perform registration calculation on the registration feature set to obtain the registration coordinate transformation relationship.

7. The local device update method based on panoramic imaging and laser point cloud technology according to claim 6 is characterized in that: The replacing of the changed device data according to the acquired area to be updated includes: Use coordinate transformation relationships to update the newly collected trajectory data, point cloud data, and panoramic image sign positions as a whole; Using the updated trajectory data, point cloud data and panoramic image data within the trajectory range are selected from the original data; Use the updated trajectory data to select point cloud data and panoramic data within the same range in the newly collected data; Replace the data in the original data with the data selected from the newly collected data.

8. A local equipment update system based on panoramic imaging and laser point cloud technology, the system being the system used in the local equipment update method for substations based on panoramic imaging and laser point cloud technology as claimed in any one of claims 1 to 7, comprising: A data acquisition module, used to collect laser point cloud data, panoramic image data and trajectory data of the changed device during a circle around the changed device; Coordinate conversion module, used to establish the mapping relationship between point cloud data and panoramic image data; The point cloud registration module is used to perform point cloud registration based on equipment nameplate information.

9. A terminal comprising a processor and a storage medium; characterized in that: The storage medium is used to store instructions; The processor is configured to operate according to the instructions to execute the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images