A measurement method, system and medium based on depth camera-assisted positioning accuracy

Abstract

The present invention provides a method, system, and medium for measuring the accuracy of depth camera-assisted positioning. The method comprises: using a reference device to assist in the positioning of a calibration device; providing at least three feature points on the calibration device, and measuring the first pose information of the feature points in a real-space system; using a depth camera to obtain a calibration image of the feature points, and extracting the second pose information of the feature points in the calibration image; establishing a spatial mapping relationship between the real-space system and the depth camera imaging system based on the first pose information and the second pose information; using the depth camera to obtain a detection image of the feature points, and extracting the third pose information of the feature points in the detection image; and calculating the relative pose information of the calibration device and the reference device in real space based on the spatial mapping relationship and the third pose information. This measurement method and system can realize the automated measurement of the three-dimensional posture alignment accuracy of assisted positioning, thereby improving the work efficiency of three-dimensional alignment accuracy measurement.

Description

Technical Field

[0001] The present invention belongs to the field of measurement technology; specifically, it relates to a non-contact three-dimensional alignment accuracy automated measurement method and system; more specifically, it relates to a depth camera-assisted positioning accuracy measurement method, system and medium. Background Art

[0002] In the final assembly of modern large-scale, complex systems, exemplified by the automated loading of large boxes, it is necessary to measure the three-dimensional alignment accuracy of the box relative to a reference datum. Currently, the commonly used measurement method is theodolite-based stationing. This involves using a high-precision theodolite with a collimation function, such as Leica, to align the plane mirror and cubic mirror to be measured. The theodolites then intersect and use the theodolite's code disk values ​​to calculate the three-dimensional alignment accuracy of the box to be measured relative to the reference datum. However, since theodolite observations require human observation, measurement accuracy is limited by environmental factors such as theodolite placement distance and lighting, and automated measurement is not feasible.

[0003] This invention proposes calculating the spatial pose of the docking target relative to the depth camera using a pose calculation algorithm based on 3D point cloud matching, based on the target's 3D image and geometric features obtained by a depth camera. This method ultimately enables automated measurement of the 3D pose alignment accuracy of the docking target relative to the docking system. With the development of advanced manufacturing industries such as aerospace, shipbuilding, and large-scale precision optical systems, the demand for 3D pose alignment accuracy measurement during equipment installation is increasing, with increasingly higher precision requirements. This method, based on real-time automated measurement of 3D alignment accuracy using a depth camera, has broad application prospects and could promote the future development of large-scale, complex system integration manufacturing industries such as aerospace, shipbuilding, and other industries. Summary of the Invention

[0004] In response to the above defects or improvement needs of the prior art, the present invention provides a method, system and medium for measuring the accuracy of depth camera-assisted positioning. Among them, the present invention is used to assist in positioning at least one calibration device based on a reference device, and to measure in real time the accuracy of the calibration device when it moves to the corresponding target positioning area. The accuracy measurement system includes a depth camera, a posture calibration module and an accuracy measurement module. The above devices and modules are all set on the reference device. First, the depth camera is calibrated according to the position of the calibration device moving to the corresponding target positioning area to obtain the corresponding three-dimensional point cloud data. Then, through the posture calculation algorithm of matching the real-time detected image with the three-dimensional point cloud of the geometric features of the target to be aligned, the three-dimensional posture information of the calibration device relative to the depth camera imaging is calculated, and finally, the automated measurement of the three-dimensional posture alignment accuracy of the docking target relative to the reference device is realized.

[0005] To achieve the above objectives, according to a first aspect of the present invention, a method for measuring positioning accuracy based on depth camera assistance is provided, comprising:

[0006] A reference device and at least one calibration device are provided, and the reference device is used to assist in positioning the calibration device; at least three feature points are set on the calibration device, and the first pose information of the feature points in the actual space system is measured;

[0007] Arrange at least one depth camera on the surface of the reference device and close to one side of the calibration device so that each of the feature points is within the field of view of the depth camera; use the depth camera to obtain a calibration image of the feature point when the calibration device moves to the target positioning area, and extract second pose information of the feature point in the calibration image;

[0008] Establishing a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose information and the second pose information;

[0009] Using the depth camera to detect a detection image of the feature point when the calibration device moves to the target positioning area, and extracting third pose information of the feature point in the detection image;

[0010] The relative posture information of the calibration device and the reference device in the actual space is calculated according to the spatial mapping relationship and the third posture information.

[0011] Furthermore, the relative posture information of the calibration device and the reference device in the real space includes: an offset angle of the calibration device relative to the reference device in the three-dimensional direction of the real space system.

[0012] Furthermore, establishing a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose information and the second pose information includes:

[0013] Establishing a first three-dimensional coordinate system in the actual space, and extracting the first pose coordinates (x01, y01, z01), (x02, y02, z02) ..., (x0n, y0n, z0n) of the feature points P1, P2, ..., Pn in the first coordinate system;

[0014] establishing a three-dimensional second coordinate system in the calibration image, calibrating the second coordinate system so as to be parallel to the first coordinate system, and obtaining the calibrated second coordinate system;

[0015] Extracting the second pose coordinates (x11, y11, z11), (x12, y12, z12) ..., (x1n, y1n, z1n) of the feature points P1, P2, ..., Pn in the second coordinate system after calibration;

[0016] Establishing a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose coordinates and the second pose coordinates;

[0017] Wherein, n is a positive integer, and n≥3.

[0018] Furthermore, extracting the third pose information of the feature point in the detection image includes:

[0019] Based on the calibrated second coordinate system, the third pose coordinates (x21, y21, z21), (x22, y22, z22) ..., (x2n, y2n, z2n) of the feature points P1, P2, ..., Pn in the detection image are extracted.

[0020] Furthermore, the calculating the relative pose information of the calibration device and the reference device in the actual space according to the spatial mapping relationship and the third pose information includes:

[0021] Match the coordinates of the third pose coordinates (x21, y21, z21), (x22, y22, z22) ..., (x2n, y2n, z2n) with the coordinates corresponding to the feature points P1, P2, ..., Pn in the second pose coordinates (x11, y11, z11), (x12, y12, z12) ..., (x1n, y1n, z1n);

[0022] The rotation parameters [α, β, γ] of the third pose coordinates relative to the second pose coordinates around the coordinate axis are obtained based on a coordinate transformation algorithm.

[0023] According to a second aspect of the present invention, a system for measuring positioning accuracy based on depth camera assistance is provided, comprising:

[0024] A reference device and at least one calibration device, wherein the calibration device is provided with at least three characteristic points;

[0025] At least one depth camera, disposed on the surface of the reference device and close to one side of the calibration device, for acquiring a calibration image and a detection image of the feature points when the calibration device moves to the target positioning area; wherein each of the feature points is within the field of view of the depth camera;

[0026] A pose calibration module is configured to measure a first pose information of the feature point in the actual space system, extract a second pose information of the feature point in the calibration image, and establish a spatial mapping relationship between the actual space system and the depth camera imaging system based on the first pose information and the second pose information;

[0027] The accuracy measurement module is used to extract the third posture information of the feature point in the detection image, and calculate the relative posture information of the calibration device and the reference device in the actual space based on the spatial mapping relationship and the third posture information.

[0028] Furthermore, the relative posture information of the calibration device and the reference device in the real space includes: an offset angle of the calibration device relative to the reference device in the three-dimensional direction of the real space system.

[0029] Furthermore, the posture calibration module includes:

[0030] A first extraction unit is configured to establish a three-dimensional first coordinate system in the actual space and extract the first pose coordinates (x01, y01, z01), (x02, y02, z02) ..., (x0n, y0n, z0n) of the feature points P1, P2, ..., Pn in the first coordinate system;

[0031] A second extraction unit is configured to establish a three-dimensional second coordinate system in the calibration image, calibrate the second coordinate system so that it is parallel to the first coordinate system, and obtain the calibrated second coordinate system; and extract the second pose coordinates (x11, y11, z11), (x12, y12, z12) ..., (x1n, y1n, z1n) of the feature points P1, P2, ..., Pn in the calibrated second coordinate system;

[0032] a calibration and matching unit, configured to establish a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose coordinates and the second pose coordinates;

[0033] Wherein, n is a positive integer, and n≥3.

[0034] Furthermore, the accuracy measurement module includes:

[0035] A third extraction unit is used to extract third pose coordinates (x21, y21, z21), (x22, y22, z22) ..., (x2n, y2n, z2n) of the feature points P1, P2, ..., Pn in the detection image based on the calibrated second coordinate system;

[0036] a detection and matching unit, configured to perform one-to-one matching between the coordinates of the third pose (x21, y21, z21), (x22, y22, z22) ..., (x2n, y2n, z2n) and the coordinates corresponding to the feature points P1, P2, ..., Pn in the second pose coordinates (x11, y11, z11), (x12, y12, z12) ..., (x1n, y1n, z1n);

[0037] The accuracy measurement unit is used to obtain the rotation parameters [α, β, γ] of the third posture coordinate relative to the second posture coordinate around the coordinate axis based on a coordinate transformation algorithm.

[0038] According to a third aspect of the present invention, a computer-readable medium is provided, which stores a computer program executed by an electronic device. When the computer program is run on the electronic device, the electronic device executes the method described above.

[0039] In general, the above technical solutions conceived by the present invention have the following beneficial effects compared with the prior art:

[0040] The present invention provides a measurement method, system and medium based on depth camera-assisted positioning accuracy. The measurement method and measurement system can realize the automated measurement of the three-dimensional posture alignment accuracy of assisted positioning, the measurement accuracy can reach angular grading, and the measurement efficiency can reach 100 times per minute. The method can effectively solve the problems of operator fatigue in observing the results, large human subjective errors, and inability to automatically measure in real time during the measurement of the three-dimensional posture alignment accuracy of a reference device relative to a calibration device, thereby improving the work efficiency of three-dimensional alignment accuracy measurement, thereby providing a simple, real-time, automated and accurate three-dimensional alignment accuracy automatic measurement method and system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of a method for measuring depth camera-assisted positioning accuracy is provided according to the present invention. DETAILED DESCRIPTION

[0042] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0043] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

[0044] It should be noted that the symbol "·" in the function equation involved in the present invention is an operation symbol representing the multiplication of two constants or vectors, and the symbol " / " is an operation symbol representing the division of two constants or vectors. All function equations in the present invention follow the mathematical rules of addition, subtraction, multiplication and division.

[0045] It should be noted that the terms "first" and "second" as used herein are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understood that the terms "first" and "second" may interchangeably represent a specific order or precedence, where permitted. It should be understood that the objects distinguished by "first" and "second" may be interchangeable, where appropriate, such that the embodiments of the present invention described herein may be implemented in an order other than that described or illustrated herein.

[0046] According to a specific embodiment of the present invention, Figure 1 A method for measuring positioning accuracy based on depth camera assistance is provided, comprising:

[0047] S1: providing a reference device and at least one calibration device, and using the reference device to assist in positioning the calibration device; the calibration device is provided with at least three feature points P1, P2, ..., Pn, and measuring the first pose information of the feature points in the actual space system;

[0048] S2: placing at least one depth camera on the surface of the reference device and close to one side of the calibration device so that each of the feature points is within the field of view of the depth camera; using the depth camera to obtain a calibration image of the feature point when the calibration device moves to the target positioning area, and extracting second pose information of the feature point in the calibration image;

[0049] S3: Establishing a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose information and the second pose information;

[0050] S4: using the depth camera to detect a detection image of the feature point when the calibration device moves to the target positioning area, and extracting third pose information of the feature point in the detection image;

[0051] S5: Calculate relative pose information of the calibration device and the reference device in the actual space according to the spatial mapping relationship and the third pose information.

[0052] Specifically, in step S1, at least three feature points P1, P2, ..., Pn are set on the calibration device, where n is at least 3, but in actual applications n is 100 or even 100,000. The more feature points are selected, the more accurate the measurement accuracy of the method.

[0053] Specifically, in step S2, a depth camera is used to collect a calibration image, and it is ensured that each of the feature points is within the field of view of the depth camera. The depth camera is an active visual sensor that emits near-infrared (NIR) light from a light-emitting diode (LED). It can be used in dark environments and its operation will be affected by external light sources. It can simultaneously output the depth, amplitude and grayscale information of the measured target. It is a relatively new and convenient three-dimensional imaging device. For example, the depth camera in the present invention can adopt PMD@Camcube3.0 produced by PMD, and its main performance indicators are: (2) frame rate: 50fps; (5) effective pixels: 200×200; (6) working distance: 10m; (4) distance resolution: 3mm@4m.

[0054] Specifically, in step S3, establishing a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose information and the second pose information includes:

[0055] S31: Establish a first three-dimensional coordinate system in the actual space, and extract the first pose coordinates (x01, y01, z01), (x02, y02, z02) ..., (x0n, y0n, z0n) of the feature points P1, P2, ..., Pn in the first coordinate system;

[0056] S32: establishing a three-dimensional second coordinate system in the calibration image, calibrating the second coordinate system to make it parallel to the first coordinate system, and obtaining the calibrated second coordinate system;

[0057] S33: Extracting the second pose coordinates (x11, y11, z11), (x12, y12, z12) ..., (x1n, y1n, z1n) of the feature points P1, P2, ..., Pn in the second coordinate system after calibration;

[0058] S34: Establishing a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose coordinates and the second pose coordinates;

[0059] Wherein, n is a positive integer, and n≥3.

[0060] More specifically, in steps S31 and S33, the pose information of feature points P1, P2, ..., Pn can be extracted using a related image processing device. For example, the related image processing device can be a Kintex-7 and TMS320C6678 visual image processing system for the Camera Link interface, developed by the Information Recognition and System Control Research Center of the Institute of Microelectronics, Chinese Academy of Sciences. This product consists of two core modules: an FPGA module and a DSP module, and is primarily targeted at the field of embedded miniaturized visual imaging. The DSP uses TI's latest generation Keystone multi-core C66x series TMS320C6678, which has 10G processing power; the FPGA uses Xilinx's Kintex-7 (K7) series XC7K325T-2FFG900I, which has 326080 logic units and can be used for intelligent image processing and analysis such as defect detection, size measurement, color sorting, moving target detection and tracking, and character recognition.

[0061] More specifically, in steps S32 and S34, the principle of a 3D point cloud matching algorithm is used to solve the relative spatial pose of multiple markers. The target coordinate system O0-X0Y0Z0 is established by multiple known geometric feature points P1, P2, ..., Pn (n ≥ 3) on the calibration device. In order to make this coordinate system parallel to the depth camera coordinate system O1-X1Y1Z1 after the rotation transformation, the rotation transformation process is represented by the rotation parameters of the reference device coordinate system around the coordinate axis.

[0062] Specifically, in step S4, extracting the third pose information of the feature point in the detection image includes:

[0063] S41: Based on the calibrated second coordinate system, extract the third pose coordinates (x21, y21, z21), (x22, y22, z22)..., (x2n, y2n, z2n) of the feature points P1, P2, ..., Pn in the detection image.

[0064] More specifically, the method of extracting feature point data in step S41 is the same as that in steps S31 and S33.

[0065] Specifically, in step S5, the relative posture information of the calibration device and the reference device in the real space includes: an offset angle of the calibration device relative to the reference device in the three-dimensional direction of the real space system.

[0066] More specifically, calculating the relative pose information of the calibration device and the reference device in the actual space according to the spatial mapping relationship and the third pose information includes:

[0067] S51: Match the coordinates of the third pose coordinates (x21, y21, z21), (x22, y22, z22) ..., (x2n, y2n, z2n) with the coordinates corresponding to the feature points P1, P2, ..., Pn in the second pose coordinates (x11, y11, z11), (x12, y12, z12) ..., (x1n, y1n, z1n);

[0068] S52: Obtaining rotation parameters [α, β, γ] of the third posture coordinates relative to the second posture coordinates around the coordinate axis based on a coordinate transformation algorithm.

[0069] More specifically, in step S51 and step S52, the three-dimensional point cloud data of the calibration device measured by the depth camera is matched with the calibration data of the feature points in the calibration image of the feature points measured by the depth camera when the calibration device moves to the target positioning area, and the coordinates of each feature point in the depth camera coordinate system O1-X1Y1Z1 are obtained. Then, through the coordinate transformation, the value of the rotation parameter [α, β, γ] can be obtained, which is the three-dimensional alignment accuracy of the device to be calibrated relative to the reference device.

[0070] According to another specific embodiment of the present invention, a system for measuring positioning accuracy based on depth camera assistance is provided, comprising:

[0071] A reference device and at least one calibration device, wherein the calibration device is provided with at least three characteristic points;

[0072] At least one depth camera, disposed on the surface of the reference device and close to one side of the calibration device, for acquiring a calibration image and a detection image of the feature points when the calibration device moves to the target positioning area; wherein each of the feature points is within the field of view of the depth camera;

[0073] A pose calibration module is configured to measure a first pose information of the feature point in the actual space system, extract a second pose information of the feature point in the calibration image, and establish a spatial mapping relationship between the actual space system and the depth camera imaging system based on the first pose information and the second pose information;

[0074] The accuracy measurement module is used to extract the third posture information of the feature point in the detection image, and calculate the relative posture information of the calibration device and the reference device in the actual space based on the spatial mapping relationship and the third posture information.

[0075] Specifically, the relative posture information of the calibration device and the reference device in the real space includes: an offset angle of the calibration device relative to the reference device in the three-dimensional direction of the real space system.

[0076] More specifically, the depth camera is an active visual sensor that emits near-infrared (NIR) light from a light-emitting diode (LED). It can be used in dark environments and its operation is affected by external light sources. It can simultaneously output the depth, amplitude, and grayscale information of the target being measured. It is a relatively new and convenient three-dimensional imaging device. For example, the depth camera in the present invention can use PMD@Camcube3.0 produced by PMD, whose main performance indicators are: (2) frame rate: 50fps; (5) effective pixels: 200×200; (6) working distance: 10m; (4) distance resolution: 3mm@4m.

[0077] Specifically, the posture calibration module includes:

[0078] A first extraction unit is configured to establish a three-dimensional first coordinate system in the actual space and extract the first pose coordinates (x01, y01, z01), (x02, y02, z02) ..., (x0n, y0n, z0n) of the feature points P1, P2, ..., Pn in the first coordinate system;

[0079] A second extraction unit is configured to establish a three-dimensional second coordinate system in the calibration image, calibrate the second coordinate system so that it is parallel to the first coordinate system, and obtain the calibrated second coordinate system; and extract the second pose coordinates (x11, y11, z11), (x12, y12, z12) ..., (x1n, y1n, z1n) of the feature points P1, P2, ..., Pn in the calibrated second coordinate system;

[0080] a calibration and matching unit, configured to establish a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose coordinates and the second pose coordinates;

[0081] Wherein, n is a positive integer, and n≥3.

[0082] Specifically, the accuracy measurement module includes:

[0083] A third extraction unit is used to extract third pose coordinates (x21, y21, z21), (x22, y22, z22) ..., (x2n, y2n, z2n) of the feature points P1, P2, ..., Pn in the detection image based on the calibrated second coordinate system;

[0084] a detection and matching unit, configured to perform one-to-one matching between the coordinates of the third pose (x21, y21, z21), (x22, y22, z22) ..., (x2n, y2n, z2n) and the coordinates corresponding to the feature points P1, P2, ..., Pn in the second pose coordinates (x11, y11, z11), (x12, y12, z12) ..., (x1n, y1n, z1n);

[0085] The accuracy measurement unit is used to obtain the rotation parameters [α, β, γ] of the third posture coordinate relative to the second posture coordinate around the coordinate axis based on a coordinate transformation algorithm.

[0086] More specifically, the first, second, and third extraction units can utilize relevant image processing devices. For example, the relevant image processing devices can utilize the Camera Link interface-oriented Kintex-7 and TMS320C6678 visual image processing system from the Information Recognition and System Control Research Center of the Institute of Microelectronics, Chinese Academy of Sciences. This product consists of two core modules—an FPGA module and a DSP module—and is primarily targeted at the embedded miniaturized visual imaging field. The DSP utilizes TI's latest generation Keystone multi-core C66x series TMS320C6678, which offers 10G processing power. The FPGA utilizes Xilinx's Kintex-7 (K7) series XC7K325T-2FFG900I, which features 326,080 logic units and can be used for intelligent image processing and analysis, such as defect detection, size measurement, color sorting, moving target detection and tracking, and character recognition.

[0087] In this embodiment, the provided technical solution of the measurement system based on depth camera assisted positioning accuracy is the same as the above-mentioned measurement method based on depth camera assisted positioning accuracy, and other specific technical solutions are not repeated here.

[0088] According to another specific embodiment of the present invention, a computer-readable medium is provided, which stores a computer program executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the method described above.

[0089] It should be understood that any process or method description in the method, structure diagram or otherwise described herein of the present invention may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and that the scope of the embodiments of the present invention includes additional implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0090] It should be understood that various parts of the present invention can be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0091] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0092] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing module, or each unit may exist physically separately, or two or more units may be integrated into a single module. The aforementioned integrated modules may be implemented in the form of hardware or in the form of software functional modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

[0093] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0094] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are illustrative and are not to be construed as limiting the present invention. Those skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments without departing from the principles and intent of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for measuring positioning accuracy based on depth camera assistance, characterized in that: include: Providing a reference device and at least one calibration device, and using the reference device to assist in positioning the calibration device; The calibration device is provided with at least three feature points, and measures the first pose information of the feature points in the actual space system; Arrange at least one depth camera on the surface of the reference device and close to one side of the calibration device so that each of the feature points is within the field of view of the depth camera; use the depth camera to obtain a calibration image of the feature point when the calibration device moves to the target positioning area, and extract second pose information of the feature point in the calibration image; Establishing a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose information and the second pose information, including: establishing a first coordinate system in the actual space, extracting the first pose coordinates of the feature point in the first coordinate system; establishing a second coordinate system in the calibration image, calibrating the second coordinate system so that it is parallel to the first coordinate system, and obtaining the calibrated second coordinate system; extracting the second pose coordinates of the feature point in the calibrated second coordinate system; establishing a spatial mapping relationship between the actual space system and the depth camera imaging system according to the first pose coordinates and the second pose coordinates; calibrating the second coordinate system as a rotation transformation process, and expressing it with the rotation parameters of the reference device coordinate system around the coordinate axis; Using the depth camera to detect a detection image of the feature point when the calibration device moves to the target positioning area, and extracting third pose information of the feature point in the detection image; The relative posture information of the calibration device and the reference device in the actual space is calculated according to the spatial mapping relationship and the third posture information.

2. The method for measuring positioning accuracy based on depth camera assistance according to claim 1, characterized in that: The relative posture information of the calibration device and the reference device in the real space includes: an offset angle of the calibration device relative to the reference device in the three-dimensional direction of the real space system.

3. The method for measuring positioning accuracy based on depth camera assistance according to claim 1, characterized in that: The extracting third pose information of the feature point in the detection image includes: The third pose coordinates of the feature point in the detection image are extracted based on the calibrated second coordinate system.

4. The method for measuring positioning accuracy based on depth camera assistance according to claim 3, characterized in that: The calculating the relative pose information of the calibration device and the reference device in the actual space according to the spatial mapping relationship and the third pose information includes: Match the third pose coordinates with the coordinates corresponding to the feature points in the second pose coordinates one by one; A rotation parameter of the third posture coordinate relative to the second posture coordinate around the coordinate axis is obtained based on a coordinate transformation algorithm.

5. A depth camera-assisted positioning accuracy measurement system, characterized in that: include: a reference device and at least one calibration device, wherein the calibration device is provided with at least three characteristic points; At least one depth camera, disposed on the surface of the reference device and close to one side of the calibration device, for acquiring a calibration image and a detection image of the feature points when the calibration device moves to the target positioning area; wherein each of the feature points is within the field of view of the depth camera; a pose calibration module for measuring the first pose information of the feature point in the actual space system, extracting the second pose information of the feature point in the calibration image, and establishing a spatial mapping relationship between the actual space system and the depth camera imaging system based on the first pose information and the second pose information; wherein the pose calibration module includes: a first extraction unit for establishing a three-dimensional first coordinate system in the actual space and extracting the first pose coordinates of the feature point in the first coordinate system; a second extraction unit for establishing a three-dimensional second coordinate system in the calibration image, calibrating the second coordinate system so that it is parallel to the first coordinate system, and obtaining the calibrated second coordinate system; and extracting the second pose coordinates of the feature point in the calibrated second coordinate system; a calibration matching unit for establishing a spatial mapping relationship between the actual space system and the depth camera imaging system based on the first pose coordinates and the second pose coordinates; calibrating the second coordinate system is a rotation transformation process, which is represented by the rotation parameters of the reference device coordinate system around the coordinate axis; The accuracy measurement module is used to extract the third posture information of the feature point in the detection image, and calculate the relative posture information of the calibration device and the reference device in the actual space based on the spatial mapping relationship and the third posture information.

6. The depth camera-assisted positioning accuracy measurement system according to claim 5, characterized in that: The relative posture information of the calibration device and the reference device in the real space includes: an offset angle of the calibration device relative to the reference device in the three-dimensional direction of the real space system.

7. The depth camera-assisted positioning accuracy measurement system according to claim 5, characterized in that: The accuracy measurement module includes: A third extraction unit is used to extract the third pose coordinates of the feature point in the detection image based on the calibrated second coordinate system; a detection and matching unit, configured to perform one-to-one matching between the third pose coordinates and the coordinates corresponding to the feature points in the second pose coordinates; The accuracy measurement unit is used to obtain the rotation parameters of the third posture coordinates relative to the second posture coordinates around the coordinate axis based on a coordinate transformation algorithm.

8. A computer-readable medium, characterized in that It stores a computer program executed by an electronic device, and when the computer program runs on the electronic device, the electronic device executes the method according to any one of claims 1 to 4.

Images