A panoramic calibration system, method and device

Abstract

The present invention relates to a panoramic calibration system, method and device. The system includes: a calibration board, a control terminal and at least two point cloud acquisition devices. Each point cloud acquisition device in this application is fixedly arranged in different areas within the scene. During implementation, the control terminal calibrates the point cloud data of the spatial position of the calibration board collected by each point cloud acquisition device to establish a three-dimensional map within the scene. Since the calibration board serving as a calibration point in this application is inlaid with a reflector, the reflector can be clearly recognized by the point cloud acquisition device under any light conditions, thereby avoiding the interference of external factors such as light and shadow during the reconstruction of the three-dimensional map and improving the mapping restoration degree of the three-dimensional map.

Description

Technical Field

[0001] The present invention relates to the field of three-dimensional mapping, and particularly to a panoramic calibration system, method and device. Background Art

[0002] With the development of artificial intelligence technology, multiple scientific systems such as image processing, stereo vision, and pattern recognition all rely on the acquisition of three-dimensional information of target objects. The three-dimensional mapping technology based on point cloud has been widely applied in fields such as medical treatment, cultural relic protection, robot vision, automatic navigation, industrial product appearance design and production.

[0003] While machine learning brings opportunities to people, it also brings challenges. In the prior art, when performing three-dimensional map reconstruction based on the binocular vision principle (generally through a traditional RGB color camera), effective detection cannot be obtained due to changes in light, shadow, etc., resulting in a low reduction degree of the constructed three-dimensional map. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a panoramic calibration system, method and device to solve the problem that the reduction degree of the three-dimensional map is low due to external factors such as light and shadow during three-dimensional map reconstruction in the prior art.

[0005] According to the first aspect of the embodiment of the present invention, a panoramic calibration system is provided, including:

[0006] A calibration board, a control end and at least two point cloud acquisition devices;

[0007] Some areas of the calibration board are inlaid with reflector plates;

[0008] Each of the point cloud acquisition devices is fixedly arranged in different areas within the scene;

[0009] The control end is used to calibrate the point cloud data of the spatial position of the calibration board collected by each of the point cloud acquisition devices to establish a three-dimensional map within the scene.

[0010] Preferably, the system further includes: a vehicle to be navigated;

[0011] The control end is further used to provide navigation for the vehicle to be navigated according to the three-dimensional map.

[0012] Preferably, the calibration board is a black-and-white checkerboard calibration board, and the reflector plates are inlaid in the white checkerboard areas of the calibration board.

[0013] Preferably, the system further includes: a plurality of scene coordinate boards laid on the ground within the scene at a preset interval;

[0014] The scene coordinate board is inlaid with a reflector, and the reflector on the scene coordinate board is engraved with a number identifier bound to the scene coordinate board;

[0015] The control end is used to identify the number identifiers of the scene coordinate boards in the point cloud data to determine the numbers of the corresponding virtual scene coordinate boards in the three-dimensional map, and provide navigation for the vehicle to be navigated in the scene according to the numbers of the virtual scene coordinate boards.

[0016] Preferably, the system further includes: an identification board mounted on an object to be identified in the scene;

[0017] The identification board is inlaid with the reflector, and the reflector on the identification board is engraved with an identity information identifier bound to the object to be identified;

[0018] The control end is used to identify the identity information identifiers of the identification boards in the point cloud data to determine the identity information of the corresponding virtual objects in the three-dimensional map, and provide navigation for the vehicle to be navigated in the scene according to the identity information of the virtual objects.

[0019] According to the second aspect of the embodiments of the present invention, a panoramic calibration method is provided, including:

[0020] Obtain point cloud data in the scene; the point cloud data at least includes the point cloud data of a calibration board inlaid with a reflector;

[0021] Calibrate the point cloud data to establish a three-dimensional map in the scene.

[0022] Preferably, the obtaining of the point cloud data in the scene includes:

[0023] Collect the point cloud data of the area where the calibration board is located at different spatial positions in the scene through a plurality of point cloud acquisition devices.

[0024] Preferably, the calibrating of the point cloud data to establish a three-dimensional map in the scene includes:

[0025] Take the point cloud data collected by any point cloud acquisition device as reference data, and take the point cloud data collected by other point cloud acquisition devices as data to be fused;

[0026] Take the calibration board as a calibration point, generate a reference transformation matrix between the reference data coordinate system and the data-to-be-fused coordinate system, and also generate a world transformation matrix between the reference data coordinate system and the world coordinate system in the scene;

[0027] According to the reference transformation matrix, fuse the data to be fused with the reference data to obtain fused data;

[0028] According to the world transformation matrix, convert the coordinate values of each point in the fused data into the coordinate values in the world coordinate system within the scene;

[0029] According to the obtained coordinate values of each point in the world coordinate system within the scene, establish a three-dimensional map within the scene.

[0030] Preferably, the step of fusing the data to be fused with the reference data according to the reference transformation matrix includes:

[0031] Compare the reference data with the data to be fused to determine the missing point cloud data in the reference data;

[0032] According to the reference transformation matrix, convert the coordinate values of the missing point cloud data in the coordinate system of the data to be fused where the missing point cloud data is located into the coordinate values in the reference data coordinate system.

[0033] Preferably, the method further includes:

[0034] Identify the point cloud data identifier in the world coordinate system within the scene; the point cloud data identifier includes: the number identifier of the scene coordinate board and the identity information identifier of the object to be identified;

[0035] Determine the number of the virtual scene coordinate board and the identity information of the virtual object used to construct the three-dimensional map according to the point cloud data identifier;

[0036] When constructing the three-dimensional map, assign the corresponding number to the virtual scene coordinate board and assign the corresponding identity information to the virtual object.

[0037] Preferably, the method further includes:

[0038] Group and store the coordinate values of the virtual scene coordinate board and the virtual object in the world coordinate system within the scene.

[0039] Preferably, the method further includes: providing navigation for the vehicle to be navigated within the scene according to the three-dimensional map.

[0040] According to the third aspect of the embodiments of the present invention, there is provided a panoramic calibration device, including:

[0041] An acquisition module, configured to acquire point cloud data within the scene; the point cloud data at least includes the point cloud data of a calibration board inlaid with a reflector;

[0042] A map building module, configured to calibrate the point cloud data to establish a three-dimensional map within the scene.

[0043] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: The panoramic calibration system in this application includes a calibration board, a control terminal, and at least two point cloud acquisition devices. Each point cloud acquisition device in this application is fixedly arranged in different areas within the scene. During implementation, the control terminal calibrates the point cloud data of the spatial position of the calibration board collected by each point cloud acquisition device to establish a three-dimensional map of the scene. Since the calibration board serving as the calibration point in this application is inlaid with a reflector, the reflector can be clearly recognized by the point cloud acquisition device under any lighting conditions, thereby avoiding interference from external factors such as light and shadow during the reconstruction of the three-dimensional map and improving the mapping reduction degree of the three-dimensional map.

[0044] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and cannot limit the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present invention and, together with the specification, are used to explain the principles of the present invention.

[0046] Figure 1 is a schematic structural diagram of a panoramic calibration system shown according to an exemplary embodiment;

[0047] Figure 2 is a schematic diagram of a calibration board in a panoramic calibration system shown according to an exemplary embodiment;

[0048] Figure 3 is a schematic structural diagram of a panoramic calibration system shown according to another exemplary embodiment;

[0049] Figure 4 is a flowchart of a panoramic calibration method shown according to an exemplary embodiment;

[0050] Figure 5 is a flowchart of a panoramic calibration method shown according to another exemplary embodiment;

[0051] Figure 6 is a schematic structural diagram of a panoramic calibration device system shown according to an exemplary embodiment.

[0052] Reference numerals: calibration board - 1; control terminal - 2; point cloud acquisition device - 3; vehicle to be navigated - 4; scene coordinate board - 5; object to be recognized - 6; acquisition module - 201; mapping module - 202. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present invention as detailed in the appended claims.

[0054] Embodiment 1

[0055] Figure 1 is a schematic structural diagram of a panoramic calibration system shown according to an exemplary embodiment, as Figure 1 shown, the system includes:

[0056] a calibration board, a control terminal, and at least two point cloud acquisition devices;

[0057] Reflective plates are inlaid in a partial area of the calibration board;

[0058] Each point cloud acquisition device is fixedly arranged in different areas within the scene;

[0059] The control terminal is used to calibrate the point cloud data of the area where the calibration board is located collected by each point cloud acquisition device to establish a three-dimensional map within the scene.

[0060] It should be noted that the technical solution provided in this embodiment is applicable to the process of three-dimensional map reconstruction based on point clouds, and the three-dimensional map reconstruction is widely used in fields such as medical treatment, cultural relic protection, robot vision, automatic navigation, industrial product appearance design and production.

[0061] It should be noted that the control terminal in this embodiment can be connected to each point cloud acquisition device through wired communication or wireless communication for data and control signal transmission.

[0062] It can be understood that the reason for using at least two point cloud acquisition devices in this embodiment is to prevent the acquisition area of a single point cloud acquisition device from being insufficient to cover all objects within the scene. Preferably, in this embodiment, the number of point cloud acquisition devices to be arranged can be determined according to the size of the scene, and the acquisition areas of multiple point cloud acquisition devices can be superimposed to cover the entire scene.

[0063] It should be noted that traditional calibration boards are generally black-and-white checkerboard calibration boards. In this embodiment, the traditional calibration board is improved. As Figure 2 shown, reflective plates are inlaid in the white checkerboard areas of the calibration board in this embodiment. The calibration board is used for calibration between each point cloud acquisition device.

[0064] It can be understood that each point cloud acquisition device is fixedly arranged in different areas within the scene to acquire the point cloud data of the area where the calibration board is located from different angles.

[0065] It should be noted that when the spatial position of the calibration board changes within the scene, the control terminal also controls each point cloud acquisition device to re-acquire the point cloud data of the area where the calibration board is located.

[0066] It can be understood that in this embodiment, the point cloud data of the area where the calibration board is located at different spatial positions within the scene is acquired, that is, the point cloud data of the calibration board at different spatial positions and different angles within the scene is acquired through multiple point cloud acquisition devices. For example, if the calibration board is subjected to 30 spatial position transformations within the scene, 30 sets of point cloud data of the calibration board at different spatial positions can be obtained. Each set of point cloud data includes the point cloud data of the calibration board at different angles acquired by each point cloud acquisition device. The technical solution provided in this embodiment can reduce the noise and angular influence during point cloud data calibration.

[0067] In specific practice, the point cloud acquisition device can be, but is not limited to, a depth camera. Compared with the RGB camera used in the traditional three-dimensional map reconstruction process, the depth camera can clearly photograph the reflector in the absence of light.

[0068] It can be understood that the calibration board inlaid with reflectors and the scene coordinate board in this embodiment can be clearly recognized by the point cloud acquisition device under any light conditions, thus avoiding the interference of external factors such as light and shadow during three-dimensional map reconstruction and improving the mapping reduction degree of the three-dimensional map.

[0069] Embodiment 2

[0070] A panoramic map calibration system in an exemplary embodiment further includes: a vehicle to be navigated;

[0071] The control terminal is further configured to provide navigation for the vehicle to be navigated according to the three-dimensional map.

[0072] It should be noted that the control terminal in this embodiment can be wirelessly communicatively connected to the vehicle to be navigated for data and control signal transmission.

[0073] The three-dimensional map reconstruction technology based on point cloud has been widely applied in the field of autonomous navigation. Since the mapping reduction degree of the three-dimensional map in the prior art is relatively low when affected by external factors such as light and shadow, the existing autonomous navigation system is also equipped with a variety of sensors to assist in correcting the navigation route of the vehicle to be navigated on the basis of the three-dimensional map. The complexity and computational amount of processing the data of a variety of sensors have relatively high requirements for the processor, resulting in an increase in the cost of the processor, and the installation of a variety of sensors is also relatively high.

[0074] It can be understood that in this embodiment, a depth camera is used as a point cloud acquisition device to complete the acquisition of point cloud data, and then the point cloud data is calibrated to establish a three-dimensional map in the scene. Moreover, when performing three-dimensional map reconstruction in this embodiment, external factors such as light and shadow can be avoided, and the mapping reduction degree of the three-dimensional map is relatively high. There is no need to additionally configure a variety of sensors to assist in correcting the navigation route of the vehicle to be navigated, the requirements for building the hardware structure are reduced, and the total cost is also reduced.

[0075] Embodiment III

[0076] Figure 3 It is a schematic structural diagram of a panoramic calibration system shown according to another exemplary embodiment. Refer to Figure 3 and this system further includes:

[0077] A plurality of scene coordinate plates laid on the ground in the scene at a preset interval;

[0078] Reflective plates are inlaid on the scene coordinate plates, and number identification marks bound to the scene coordinate plates are engraved on the reflective plates of the scene coordinate plates;

[0079] The control end is used to identify the number identification marks of each scene coordinate plate in the point cloud data to determine the numbers of the corresponding virtual scene coordinate plates in the three-dimensional map, and provide navigation for the vehicle to be navigated in the scene according to the numbers of the virtual scene coordinate plates.

[0080] It should be noted that in this embodiment, the traditional scene coordinate plate is also improved. On the basis of the traditional scene coordinate plate, reflective plates are also inlaid on the scene coordinate plate.

[0081] It can be understood that, for example, when there are 4 scene coordinate plates, number identification marks bound to the scene coordinate plates are respectively engraved on the reflective plates of each scene coordinate plate, such as 1, 2, 3, 4. The control end determines the numbers of the corresponding virtual scene coordinate plates in the three-dimensional map according to the number identification marks of each scene coordinate plate in the point cloud data, so as to guide the vehicle to be navigated to move forward in sequence according to the positions of the 1, 2, 3, 4 scene coordinate plates.

[0082] It can be understood that each scene coordinate plate is laid in the scene at a preset interval (such as 1 m), which can not only facilitate the navigation work of the control end, but also reduce the arrangement quantity of the scene coordinate plates and reduce the cost.

[0083] It should be noted that the panoramic calibration system further includes: an identification plate mounted on an object to be identified in the scene;

[0084] Reflective plates are inlaid on the identification plate, and identity information identification marks bound to the object to be identified are engraved on the reflective plates of the identification plate;

[0085] The control terminal is used to identify the identity information identifiers of each identification board in the point cloud data to determine the identity information of the corresponding virtual objects in the three-dimensional map, and provide navigation for the vehicle to be navigated in the scene according to the identity information of each virtual object.

[0086] It should be noted that the identity information identifier can be a two-dimensional code encapsulating the code and name of the object to be identified.

[0087] It can be understood that the control terminal determines the identity information of the corresponding virtual objects in the three-dimensional map according to the identity information identifiers of each identification board in the point cloud data, so as to guide the vehicle to be navigated to avoid or move forward towards the virtual object for interaction.

[0088] Embodiment 4

[0089] Figure 4 is a flowchart of a panoramic calibration method shown according to an exemplary embodiment, as Figure 4 shown, the method includes:

[0090] Step S1, obtain the point cloud data in the scene; the point cloud data at least includes the point cloud data of the calibration board inlaid with a reflector.

[0091] Step S2, calibrate the point cloud data to establish a three-dimensional map in the scene.

[0092] It should be noted that the technical solution provided in this embodiment is applicable to the process of three-dimensional map reconstruction based on point cloud, and the three-dimensional map reconstruction is widely used in fields such as medical treatment, cultural relic protection, robot vision, automatic navigation, industrial product appearance design and production.

[0093] It can be understood that the technical solution provided in this embodiment obtains the point cloud data in the scene and calibrates the point cloud data to establish a three-dimensional map in the scene. Since the point cloud data at least includes the point cloud data of the calibration board inlaid with a reflector, and the reflector has higher and clearer recognition in any light condition, therefore, the technical solution provided in this embodiment can avoid the interference of external factors such as light and shadow during three-dimensional map reconstruction, and improve the mapping reduction degree of the three-dimensional map.

[0094] It should be noted that obtaining the point cloud data in the scene includes:

[0095] Collect the point cloud data of the area where the calibration board is located at different spatial positions in the scene through multiple point cloud acquisition devices.

[0096] It can be understood that in this embodiment, point cloud data of the area where the calibration board is located at different spatial positions in the scene is collected by multiple point cloud acquisition devices. That is, point cloud data of the calibration board at different spatial positions and different angles in the scene is collected by multiple point cloud acquisition devices. For example, if the calibration board is subjected to 30 spatial position transformations in the scene, 30 sets of point cloud data of the calibration board at different spatial positions can be obtained. Each set of point cloud data includes point cloud data of the calibration board at different angles collected by each point cloud acquisition device. The technical solution provided in this embodiment can reduce the noise and angular influence during point cloud data calibration.

[0097] Refer to Figure 5 , and calibrate the point cloud data to establish a three-dimensional map in the scene, including:

[0098] Step S21: Use the point cloud data collected by any one point cloud acquisition device as the reference data, and use the point cloud data collected by other point cloud acquisition devices as the data to be fused;

[0099] Step S22: Use the calibration board as the calibration point to generate the reference transformation matrix between the reference data coordinate system and the data-to-be-fused coordinate system, and also generate the world transformation matrix between the reference data coordinate system and the world coordinate system in the scene;

[0100] Step S23: According to the reference transformation matrix, fuse the data to be fused with the reference data to obtain the fused data;

[0101] Step S24: According to the world transformation matrix, convert the coordinate values of each point in the fused data into the coordinate values in the world coordinate system in the scene;

[0102] Step S25: Establish a three-dimensional map in the scene according to the coordinate values of each point obtained in the world coordinate system in the scene.

[0103] It can be understood that since the point cloud data collected by each point cloud acquisition device contains the point cloud data of the calibration board, in this embodiment, the calibration board is used as the calibration point to determine the coordinate values of the calibration board in the reference data coordinate system and the data-to-be-fused coordinate system. According to the coordinate values of the calibration board in each coordinate system, the reference transformation matrix between the reference data coordinate system and the data-to-be-fused coordinate system is generated. Specifically, the point cloud acquisition device that collects the reference data is used as the reference device, and a reference transformation matrix is generated between each other point cloud acquisition device and the reference device. The number of reference transformation matrices varies with the number of other point cloud acquisition devices.

[0104] It can be understood that in this embodiment, the reference device is used as the origin of the world coordinate system in the scene to establish the world coordinate system in the scene. According to the coordinate values of the calibration board in the reference data coordinate system and the coordinate values in the world coordinate system in the scene, the world transformation matrix between the reference data coordinate system and the world coordinate system in the scene is generated.

[0105] It should be noted that, according to the reference transformation matrix, fusing the data to be fused with the reference data includes:

[0106] Comparing the reference data with the data to be fused to determine the missing point cloud data in the reference data;

[0107] According to the reference transformation matrix, converting the coordinate values of the missing point cloud data in the coordinate system of the data to be fused where the missing point cloud data is located into the coordinate values of the reference data coordinate system.

[0108] It should be noted that it is difficult to collect the point cloud data of all objects in the scene with only one point cloud acquisition device. Therefore, in this embodiment, the point cloud data in the scene is collected based on multiple point cloud acquisition devices at the same time, so that the acquisition areas of multiple point cloud acquisition devices can be superimposed to cover the entire scene. In this way, the point cloud data collected by other point cloud acquisition devices can be used to supplement the reference data. First, it is necessary to compare the reference data with the data to be fused to determine the missing point cloud data in the reference data. For example, there is no point cloud data of the No. 1 scene coordinate board in the reference data, while the point cloud data collected by the No. 2 point cloud acquisition device contains the point cloud data of the No. 1 scene coordinate board. At this time, according to the reference transformation matrix between the reference device and the No. 2 point cloud acquisition device, the coordinate values of the No. 1 scene coordinate board in the coordinate system of the data to be fused corresponding to the No. 2 point cloud acquisition device can be converted into the coordinate values of the reference data coordinate system.

[0109] It should be noted that the panoramic calibration method further includes:

[0110] Identifying the point cloud data identifier in the world coordinate system in the scene; the point cloud data identifier includes: the number identifier of the scene coordinate board and the identity information identifier of the object to be identified;

[0111] Determining the number of the virtual scene coordinate board and the identity information of the virtual object used to construct the three-dimensional map according to the point cloud data identifier;

[0112] When constructing the three-dimensional map, assigning the corresponding number to the virtual scene coordinate board and the corresponding identity information to the virtual object.

[0113] It can be understood that when the technical solution in this embodiment is applied to the navigation field, it can guide the vehicle to be navigated to move forward in the order of the numbers of the virtual scene coordinate boards; it can also guide the vehicle to be navigated to avoid the virtual object or move forward towards the virtual object for interaction according to the identity information of the virtual object.

[0114] It should be noted that the panoramic calibration method further includes:

[0115] Group and store the coordinate values of numbered virtual objects and virtual objects with identity information in the world coordinate system within the scene.

[0116] It can be understood that by grouping and storing the coordinate values of numbered virtual objects and virtual objects with identity information in the world coordinate system within the scene, it facilitates subsequent data analysis and traceability.

[0117] It should be noted that the panoramic calibration method further includes: providing navigation for the vehicle to be navigated within the scene according to the 3D map. That is, the technical solution provided in this embodiment can be applied to the field of automatic navigation.

[0118] Embodiment 5

[0119] Figure 6 is a schematic structural diagram of a panoramic calibration device shown according to an exemplary embodiment, as Figure 6 shown, the device includes:

[0120] An acquisition module 201, configured to acquire point cloud data within the scene; the point cloud data at least includes the point cloud data of a calibration board inlaid with a reflector.

[0121] A mapping module 202, configured to calibrate the point cloud data to establish a 3D map within the scene.

[0122] It should be noted that the technical solution provided in this embodiment is applicable to the process of 3D map reconstruction based on point clouds, and the 3D map reconstruction is widely used in fields such as medical treatment, cultural relic protection, robot vision, automatic navigation, industrial product appearance design and production.

[0123] It should be noted that the acquisition module 201 is specifically configured to acquire the point cloud data of the area where the calibration board is located at different spatial positions within the scene through multiple point cloud acquisition devices.

[0124] It should be noted that the mapping module 202 is specifically configured to use the point cloud data acquired by any one point cloud acquisition device as the reference data, and the point cloud data acquired by other point cloud acquisition devices as the data to be fused; use the calibration board as the calibration point to generate the reference transformation matrix between the reference data coordinate system and the data to be fused coordinate system, and also generate the world transformation matrix between the reference data coordinate system and the world coordinate system within the scene; according to the reference transformation matrix, fuse the data to be fused with the reference data to obtain the fused data; according to the world transformation matrix, convert the coordinate values of each point in the fused data into the coordinate values in the world coordinate system within the scene; according to the obtained coordinate values of each point in the world coordinate system within the scene, establish a 3D map within the scene.

[0125] It should be noted that the panoramic calibration device further includes:

[0126] An identification module for identifying the point cloud data identifiers in the world coordinate system within a scene; the point cloud data identifiers include: the number identifier of the scene coordinate board and the identity information identifier of the object to be identified; determining the number of the virtual scene coordinate board and the identity information of the virtual object used for constructing the three-dimensional map according to the point cloud data identifiers.

[0127] It should be noted that the mapping module 202 is also used to assign corresponding numbers to the virtual scene coordinate boards and corresponding identity information to the virtual objects when constructing the three-dimensional map.

[0128] It should be noted that the panoramic image calibration device further includes:

[0129] A storage module for storing the coordinate values of the virtual scene coordinate board and the virtual object in the world coordinate system within the scene in groups;

[0130] A navigation module for providing navigation for the vehicle to be navigated within the scene according to the three-dimensional map.

[0131] It can be understood that the same or similar parts in the above embodiments can be referred to each other, and the content not detailed in some embodiments can be referred to the same or similar content in other embodiments.

[0132] It should be noted that in the description of the present invention, terms such as "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise stated, the meaning of "a plurality of" refers to at least two.

[0133] Any process or method description in the flowchart or described in other ways herein can be understood as representing a module, segment, or part of code including one or more executable instructions for implementing a specific logical function or process, and the scope of the preferred embodiments of the present invention includes additional implementations, where the functions can be executed in a manner that is not shown or discussed, including in a substantially simultaneous manner or in a reverse order according to the involved functions, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0134] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following well-known technologies in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0135] Those of ordinary skill in the art can understand that all or part of the steps carried out in implementing the above-described embodiment methods can be completed by instructing relevant hardware through a program. 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.

[0136] In addition, each functional unit in various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software functional module. When the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0137] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, or the like.

[0138] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0139] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A panoramic icon calibration system, characterized in that, Including: A calibration board, a control terminal, and at least two point cloud acquisition devices; Reflective plates are inlaid in part of the area of the calibration board; Each of the point cloud acquisition devices is fixedly arranged in different areas within the scene; The control terminal is used to calibrate the point cloud data of the spatial position of the calibration board collected by each of the point cloud acquisition devices to establish a three-dimensional map within the scene; It further includes: A vehicle to be navigated; The control terminal is further used to provide navigation for the vehicle to be navigated according to the three-dimensional map; It further includes: An identification board mounted on an object to be identified within the scene; Reflective plates are inlaid on the identification board, and identity information identifiers bound to the object to be identified are engraved on the reflective plates of the identification board; The control terminal is used to identify the identity information identifiers of each identification board in the point cloud data to determine the identity information of the corresponding virtual objects in the three-dimensional map, and provide navigation for the vehicle to be navigated within the scene according to the identity information of each virtual object.

2. The system according to claim 1, characterized in that, The calibration board is a black-and-white checkerboard calibration board, and reflective plates are inlaid in the white checkerboard areas of the calibration board.

3. The system according to claim 1, characterized in that, It further includes: Multiple scene coordinate boards laid on the ground within the scene at a preset interval; Reflective plates are inlaid on the scene coordinate boards, and number identifiers bound to the scene coordinate boards are engraved on the reflective plates of the scene coordinate boards; The control terminal is used to identify the number identifiers of each scene coordinate board in the point cloud data to determine the numbers of the corresponding virtual scene coordinate boards in the three-dimensional map, and provide navigation for the vehicle to be navigated within the scene according to the numbers of each virtual scene coordinate board.

4. A panoramic icon calibration method, characterized in that, Including: Obtaining point cloud data within the scene through a point cloud acquisition device; at least the point cloud data of the calibration board with reflective plates inlaid and the point cloud data of the identification board with reflective plates inlaid are included in the point cloud data; Calibrating the point cloud data to establish a three-dimensional map within the scene; Identifying the identity information identifiers of each identification board in the point cloud data to determine the identity information of the corresponding virtual objects in the three-dimensional map, and providing navigation for the vehicle to be navigated within the scene according to the identity information of each virtual object; Wherein, each of the point cloud acquisition devices is fixedly arranged in different areas within the scene; The identification board is mounted on an object to be identified within the scene; reflective plates are inlaid on the identification board, and identity information identifiers bound to the object to be identified are engraved on the reflective plates of the identification board.

5. The method according to claim 4, characterized in that, The obtaining of the point cloud data within the scene includes: Collecting the point cloud data of the area where the calibration board is located at different spatial positions within the scene through multiple point cloud acquisition devices.

6. The method according to claim 5, characterized in that, The calibrating of the point cloud data to establish a three-dimensional map within the scene includes: Taking the point cloud data collected by any one point cloud acquisition device as reference data, and taking the point cloud data collected by other point cloud acquisition devices as data to be fused; Taking the calibration board as a calibration point, generating a reference transformation matrix between the reference data coordinate system and the data-to-be-fused coordinate system, and also generating a world transformation matrix between the reference data coordinate system and the world coordinate system within the scene; Fusing the data to be fused with the reference data according to the reference transformation matrix to obtain the fused data; Convert the coordinate values of each point in the fused data into the coordinate values in the world coordinate system within the scene according to the described world transformation matrix; Establish a three-dimensional map within the scene according to the coordinate values of each point in the world coordinate system within the obtained scene.

7. The method according to claim 6, characterized in that, The fusing the data to be fused with the reference data according to the reference transformation matrix includes: Compare the reference data with the data to be fused to determine the missing point cloud data in the reference data; Convert the coordinate values of the missing point cloud data in the coordinate system of the data to be fused where the missing point cloud data is located into the coordinate values in the reference data coordinate system according to the reference transformation matrix.

8. The method according to claim 6, characterized in that, The method further includes: Identify the point cloud data identifier in the world coordinate system within the scene; the point cloud data identifier includes: the number identifier of the scene coordinate board and the identity information identifier of the object to be recognized; Determine the number of the virtual scene coordinate board and the identity information of the virtual object used to construct the three-dimensional map according to the point cloud data identifier; When constructing the three-dimensional map, assign the corresponding number to the virtual scene coordinate board and assign the corresponding identity information to the virtual object.

9. According to the method described in claim 8, characterized in that, The method further includes: Group and store the coordinate values of the virtual scene coordinate board and the virtual object in the world coordinate system within the scene.

10. According to the method described in any one of claims 5 to 8, characterized in that, The method further includes: providing navigation for the vehicle to be navigated within the scene according to the three-dimensional map.

11. A panoramic calibration device, characterized in that, including: An acquisition module for acquiring point cloud data within the scene; the point cloud data at least includes the point cloud data of the calibration board inlaid with a reflector and the point cloud data of the identification board inlaid with a reflector; A mapping module for calibrating the point cloud data to establish a three-dimensional map within the scene; The panoramic icon calibration device identifies the identity information identifier of each identification board in the point cloud data to determine the identity information of each corresponding virtual object in the three-dimensional map, and provides navigation for the vehicle to be navigated within the scene according to the identity information of each virtual object; Among them, each point cloud acquisition device is fixedly arranged in different areas within the scene; The identification board is mounted on the object to be recognized within the scene; a reflector is inlaid on the identification board, and the identity information identifier bound to the object to be recognized is engraved on the reflector of the identification board.

Images