A method, system and electronic device for three-dimensional object detection

Abstract

The present application discloses a three-dimensional object detection method, system and electronic device, which obtain first point cloud data, the first point cloud data is obtained by scanning a first area of ​​a three-dimensional object to be detected by at least one first light source device, and obtain second point cloud data, the second point cloud data is obtained by scanning a second area of ​​the three-dimensional object to be detected by a second light source device, the first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than the scanning accuracy of the first light source device; a three-dimensional object scanning model is obtained based on the first point cloud data and the second point cloud data, the three-dimensional object scanning model is model-aligned with the three-dimensional object standard model, and the deviation of the three-dimensional object to be detected in at least one direction in the three-dimensional space direction is obtained based on the alignment result of the model alignment.

Description

Technical Field

[0001] This application relates to the field of three-dimensional object measurement, and particularly to a three-dimensional object detection method, system, and electronic device. Background Art

[0002] During the product production process, deformations often occur due to production process problems, such as notebook casings, which will reduce the refinement of the equipment assembled with the product.

[0003] Currently, to measure the deformation degree of a product, it is usually necessary to fix the product in a physical extrusion form through a jig and then measure it. During the physical extrusion process of the product, the probability of the product being bruised and scratched is increased. At the same time, for the measurement of multiple deformation degree parameters, multiple clamping operations are required, which further increases the probability of the product being scratched, seriously affecting the efficiency of the production line assembly. Summary of the Invention

[0004] In view of this, this application provides a three-dimensional object detection method, system, and electronic device, and its specific solutions are as follows:

[0005] A three-dimensional object detection method includes:

[0006] Obtain first point cloud data, where the first point cloud data is obtained by scanning a first region of the three-dimensional object to be detected through at least one first light source device;

[0007] Obtain second point cloud data, where the second point cloud data is obtained by scanning a second region of the three-dimensional object to be detected through a second light source device. The first region and the second region constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device;

[0008] Based on the first point cloud data and the second point cloud data, obtain a three-dimensional object scanning model, and perform model registration on the three-dimensional object scanning model and a three-dimensional object standard model;

[0009] Based on the registration result of the model registration, obtain the deviation of the three-dimensional object to be detected in at least one direction in the three-dimensional space direction.

[0010] Further, it further includes:

[0011] Control the at least one first light source device to move from the first end to the second end of the first region of the three-dimensional object to be detected at a determined first moving speed;

[0012] Control the second light source device to move from the first end to the second end of the second region of the three-dimensional object to be detected at a second moving speed;

[0013] Among them, the first moving speed is not higher than the second moving speed.

[0014] Further, determining the first moving speed includes:

[0015] Determine the first sub-region, the second sub-region, and the third sub-region of the first region of the three-dimensional object to be detected. Among them, the first sub-region is the region within the first preset range at the first end of the first region, the second sub-region is the region within the second preset range at the second end of the first region, and the third sub-region is the region within the first region except the first sub-region and the second sub-region;

[0016] Determine the first moving speed based on the correspondence between the signal radiation range of the at least one first light source device and the sub-regions of the first region.

[0017] Further, the determining the first moving speed based on the correspondence between the signal radiation range of the at least one first light source device and the sub-regions of the first region includes:

[0018] If it is determined that the signal radiation range of the at least one first light source device is in the first sub-region or the second sub-region of the first region, control the first light source device to move at a third moving speed;

[0019] If it is determined that the signal radiation range of the at least one first light source device is in the third sub-region, control the first light source device to move at a fourth moving speed;

[0020] Among them, the third moving speed is less than the fourth moving speed.

[0021] Further, the obtaining the deviation of the three-dimensional object to be detected in at least one direction in the three-dimensional space direction based on the registration result of the model registration includes:

[0022] Determine at least one specific region on the scanning surface of the scanned model of the three-dimensional object based on the registration result of the model registration; determine the height deviation between the at least one specific region and the region corresponding to the specific region on the standard model of the three-dimensional object;

[0023] Determine the projected size of the scanning surface of the scanned model of the three-dimensional object based on the registration result of the model registration; determine the size deviation between the projected size of the scanning surface of the scanned model of the three-dimensional object and the projected size of the specific surface corresponding to the scanning surface on the standard model of the three-dimensional object.

[0024] Further, based on the registration result of the model registration, at least one specific area on the scanning surface of the three-dimensional object scanning model is determined; determining the height deviation between the at least one specific area and the corresponding area of the three-dimensional object standard model at the specific area includes:

[0025] Determine a first specific point on the specific area of the three-dimensional object scanning model, where the first specific point is a point in the first point cloud data;

[0026] Based on the registration result of the model registration, determine a point on the three-dimensional object standard model that intersects with the normal direction of the first specific point, and determine the point on the three-dimensional object standard model that intersects with the normal direction of the first specific point as the second specific point;

[0027] Determine the distance between the first specific point and the second specific point, and determine the distance as the height deviation of the three-dimensional object to be detected.

[0028] Further, the determining the first specific point on the three-dimensional object scanning model includes:

[0029] Determine a point on the specific area of the three-dimensional object to be detected whose degree of deformation is greater than that of other points, and determine the point on the specific area whose degree of deformation is greater than that of other points as the first specific point.

[0030] Further, it further includes:

[0031] Based on the deviations of the three-dimensional object to be detected in each direction in the unclamped state, compensation data is determined to compensate for the deviations of the three-dimensional object to be detected in the clamped state.

[0032] An electronic device includes:

[0033] At least one first light source device for scanning a first area of the three-dimensional object to be detected to obtain first point cloud data;

[0034] A second light source device for scanning a second area of the three-dimensional object to be detected to obtain second point cloud data, where the first area and the second area form a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device;

[0035] A processor for obtaining a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, performing model registration on the three-dimensional object scanning model and the three-dimensional object standard model, and obtaining the deviation of the three-dimensional object to be detected in at least one direction in the three-dimensional space based on the registration result of the model registration.

[0036] A three-dimensional object detection system includes:

[0037] A first acquisition unit, configured to acquire first point cloud data, where the first point cloud data is acquired by scanning a first area of a three-dimensional object to be detected through at least one first light source device;

[0038] A second acquisition unit, configured to acquire second point cloud data, where the second point cloud data is acquired by scanning a second area of the three-dimensional object to be detected through a second light source device, and the first area and the second area form a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device;

[0039] A registration unit, configured to obtain a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, and perform model registration on the three-dimensional object scanning model and a three-dimensional object standard model;

[0040] A deviation acquisition unit, configured to obtain at least one deviation in the three-dimensional space direction of the three-dimensional object to be detected based on the registration result of the model registration.

[0041] As can be seen from the above technical solution, the three-dimensional object detection method, system, and electronic device disclosed in this application acquire first point cloud data, where the first point cloud data is acquired by scanning a first area of a three-dimensional object to be detected through at least one first light source device, acquire second point cloud data, where the second point cloud data is acquired by scanning a second area of the three-dimensional object to be detected through a second light source device, the first area and the second area form a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device; obtain a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, perform model registration on the three-dimensional object scanning model and a three-dimensional object standard model, and obtain at least one deviation in the three-dimensional space direction of the three-dimensional object to be detected based on the registration result of the model registration. In this solution, different areas of the three-dimensional object to be detected are scanned by light source devices with different accuracies to obtain point cloud data, and then registered with the standard model, so as to realize the determination of the deviation of the three-dimensional object to be detected. During the whole process, there is no need to clamp the three-dimensional object to be detected, avoiding the situation of bruising caused by clamping the three-dimensional object during the deviation determination process; moreover, the deviation of data in multiple different directions can be realized through one scan, improving the data detection efficiency and ensuring the production line assembly efficiency. Description of the Drawings

[0042] To more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0043] Figure 1 Flow chart of a three-dimensional object detection method disclosed in an embodiment of the present application;

[0044] Figure 2 Schematic diagram of the positions of the first region and the second region in a scanning plane disclosed in an embodiment of the present application;

[0045] Figure 3 Schematic diagram of the positions of the first region and the second region in a scanning plane disclosed in an embodiment of the present application;

[0046] Figure 4 Flow chart of a three-dimensional object detection method disclosed in an embodiment of the present application;

[0047] Figure 5 Schematic diagram of the correspondence between the scanning range of a first light source device and the first region disclosed in an embodiment of the present application;

[0048] Figure 6 Schematic diagram of the structure of a scanning plane disclosed in an embodiment of the present application;

[0049] Figure 7 Flow chart of a three-dimensional object detection method disclosed in an embodiment of the present application;

[0050] Figure 8 Schematic diagram of the projection sizes of a scanning plane and a specific plane disclosed in an embodiment of the present application;

[0051] Figure 9 Schematic diagram of the height deviation between a scanning plane and a specific plane disclosed in an embodiment of the present application;

[0052] Figure 10 Schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application;

[0053] Figure 11 Schematic diagram of the structure of a three-dimensional object detection system disclosed in an embodiment of the present application. Detailed implementation manners

[0054] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0055] The present application discloses a three-dimensional object detection method, and its flowchart is as Figure 1 shown, including:

[0056] Step S11, obtaining first point cloud data, where the first point cloud data is obtained by scanning a first area of the three-dimensional object to be detected through at least one first light source device;

[0057] Step S12, obtaining second point cloud data, where the second point cloud data is obtained by scanning a second area of the three-dimensional object to be detected through a second light source device. The first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device;

[0058] Step S13, obtaining a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, and performing model registration on the three-dimensional object scanning model and the three-dimensional object standard model;

[0059] Step S14, obtaining the deviation of the three-dimensional object to be detected in at least one direction in the three-dimensional space direction based on the registration result of the model registration.

[0060] During the product production process, deformation may occur. In order to measure its degree of deformation, a jig is usually used to squeeze the product into a state matching the standard model for measurement, which increases the probability of scratching the product during the squeezing process.

[0061] To avoid this problem, in this solution, point cloud data is obtained through a light source device, so as to obtain the model of the product, and then compared with the standard model to determine the deviation. The deviation of the product can be determined without going through the physical squeezing process, the operation is simple, and the situation of scratching the product is avoided.

[0062] Specifically, a first area of the three-dimensional object to be detected is scanned through at least one first light source device to obtain first point cloud data, and a second area of the three-dimensional object to be detected is scanned through a second light source device to obtain second point cloud data.

[0063] The first region and the second region constitute a surface of the three-dimensional object to be detected, i.e., the detection surface. When the first point cloud data and the second point cloud data are combined, a scanning surface of the three-dimensional object to be detected can be obtained. This scanning surface corresponds to the detection surface and is a perfect match. For example, if the back shell of a mobile phone is scanned by the first light source device and the second light source device, then the first region and the second region together form the back shell, and the scanning surface obtained by combining the first point cloud data and the second point cloud data is the scanning surface obtained by scanning the back shell of the mobile phone.

[0064] In addition, the scanning accuracy of the second light source device is lower than that of the first light source device. The first region is scanned by the first light source device with a higher scanning accuracy, and the second region is scanned by the second light source device with a lower scanning accuracy.

[0065] At this time, the first region can be the edge region of the detection surface, and the second region can be the middle region of the detection surface. Since, in the detection surface of the three-dimensional model to be detected, the edge part of the detection surface is usually deformed during the production process, while the middle region of the detection surface is not easily deformed. Therefore, for the edge region that is easily deformed, the first light source device with a higher scanning accuracy is used, and for the middle region that is not easily deformed, the second light source device with a lower scanning accuracy is used.

[0066] Take Figure 2 as an example for illustration. The second region is located in the middle part of the detection surface, and the first region is located in the edge part of the detection surface, including: the first region 21 and the second region 22. When the first region is located in the edge part of the detection surface, there can be 4 first light source devices, which are respectively used to detect the first regions of the four sides around the second region.

[0067] Or, that is, only the region that is easily deformed during the production process is determined as the first region. If only two opposite surfaces in the edge region of the detection surface are the arc-shaped and easily deformed regions, then the first region is a part of the edge region of the detection surface, and all other regions on the detection surface except the first region are the second region. As Figure 3 shown, including: the first region 31 and the second region 32. When the first region is located in a part of the edge region of the detection surface, there can be 2 first light source devices, which are respectively used to detect the first regions on both sides of the second region.

[0068] After the first region is scanned by the first light source device to obtain the first point cloud data, and the second region is scanned by the second light source device to obtain the second point cloud data, a three-dimensional object scanning model can be obtained based on the first point cloud data and the second point cloud data.

[0069] Both the first point cloud data and the second point cloud data are composed of the coordinates of multiple points. By combining the coordinates of multiple points in the first point cloud data and the coordinates of multiple points in the second point cloud data, a model of the three-dimensional object scanned by the first light source device and the second light source device can be constructed, that is, the scanned model of the three-dimensional object to be detected.

[0070] The standard model of a three-dimensional object, that is, when producing the three-dimensional object to be detected, the original model template based on which the three-dimensional object is produced. When producing based on this standard original model template, errors may occur during the production process, and the scanned models of the produced three-dimensional objects may be different. Comparing two possibly different models, that is, performing model registration on the scanned model of the three-dimensional object and the standard model of the three-dimensional object, and then comparing after registration, can determine the deviation between the scanned model of the three-dimensional object and the standard model of the three-dimensional object relative to the standard model of the three-dimensional object, thereby determining the deformation degree of the scanned model of the produced three-dimensional model.

[0071] In this solution, light source devices with different precisions are used to scan different regions of the three-dimensional object to be detected respectively, thereby obtaining point cloud data and registering it with the standard model, so as to realize the determination of the deviation of the three-dimensional object to be detected. During the whole process, there is no need to clamp the three-dimensional object to be detected, avoiding the situation of bruising caused by clamping the three-dimensional object during the process of determining the deviation.

[0072] This embodiment discloses a method for detecting a three-dimensional object, and its flowchart is as Figure 4 shown, including:

[0073] Step S41: Control at least one light source device to move from the first end to the second end of the first region of the three-dimensional object to be detected at a determined first moving speed, and obtain the first point cloud data through scanning during the moving process;

[0074] Step S42: Control the second light source device to move from the first end to the second end of the second region of the three-dimensional object to be detected at a second moving speed, and obtain the first point cloud data through scanning during the moving process. The first region and the second region constitute a surface of the three-dimensional object to be detected. The scanning precision of the second light source device is lower than that of the first light source device, and the first moving speed is not higher than the second moving speed;

[0075] Step S43: Obtain the scanned model of the three-dimensional object based on the first point cloud data and the second point cloud data, and perform model registration on the scanned model of the three-dimensional object and the standard model of the three-dimensional object;

[0076] Step S44: Obtain the deviation of the three-dimensional object to be detected in at least one direction in the three-dimensional space direction based on the registration result of the model registration.

[0077] When the first light source device scans the first area of the three-dimensional object to be detected, the scanning range of the first light source device is smaller than the first area. Therefore, when scanning the first area through the first light source device, it is necessary to control the first light source device to move along the direction of the first area. Similarly, when the second light source device scans the second area of the three-dimensional object to be detected, it also needs to move along the direction of the second area.

[0078] Specifically, regardless of the shapes of the first area and the second area, they can be expressed in the first direction and the second direction that are perpendicular to each other. For example, the scanning range of the first light source device can cover the side of the first area in the first direction, as Figure 5 shown, including: the first area 51, the scanning range 52 of the first light source device, the first direction D1, and the second direction D2. Among them, if the scanning range of the first light source device can cover the side of the first area in the first direction, then the first light source device needs to move along the first area in the second direction so that as the first light source device moves, the first light source device can scan the entire first area to facilitate determining the first point cloud data of the first area.

[0079] Among them, the first direction is the direction along the first end of the first area, and the second direction is the moving direction from the first end of the first area to the second end of the first area.

[0080] Similarly, if the scanning range of the second light source device can cover the side of the second area in the first direction, then the second light source device needs to move along the second area in the second direction so that as the second light source device moves, the second light source device can scan the entire second area to facilitate determining the second point cloud data of the second area; in addition, the second light source device can also be such that its scanning range can cover the side of the second area in the second direction, and the second light source device moves along the second area in the first direction so that as the second light source device moves, the second light source device can scan the entire second area to facilitate determining the second point cloud data of the second area.

[0081] That is, the first light source device and the second light source device can move in the same direction or in different directions, which is not specifically limited here.

[0082] When the first light source device and the second light source device move in the same direction, the first light source device and the second light source device can move synchronously, that is, the first light source device and the second light source device maintain the same speed and move from one end of the three-dimensional model to be detected to the other end at the same time. At this time, the first light source device and the second light source device can be fixed on the same bracket, and as the bracket moves, the first light source device and the second light source device move synchronously;

[0083] Of course, when the first light source device and the second light source device move in the same direction, they do not move synchronously. Since the first area scanned by the first light source device is more likely to be deformed, the first light source device moves at a slower speed. The second area scanned by the second light source device is less likely to be deformed, so the second light source device moves at a slower speed, that is, the first moving speed is less than the second moving speed.

[0084] Furthermore, before the first light source device scans the first area, it is necessary to first determine the moving speed of the first light source device when scanning the first area, that is, to determine the first moving speed.

[0085] Specifically, determining the first moving speed can be: determining the first sub-area, the second sub-area and the third sub-area of the first area of the three-dimensional object to be detected, where the first sub-area is the area within the first preset range at the first end of the first area, the second sub-area is the area within the second preset range at the second end of the first area, and the third sub-area is the area in the first area except the first sub-area and the second sub-area; determining the first moving speed based on the correspondence between the signal radiation range of at least one first light source device and the sub-areas of the first area.

[0086] In the three-dimensional object to be detected, there are areas that are prone to deformation and areas that are not prone to deformation during production, that is, the first area and the second area. In the first area that is prone to deformation, there are also sub-areas with a higher degree of deformation and sub-areas with a lower degree of deformation. For sub-areas with different degrees of deformation in the first area, different moving speeds are also used, and the scanning accuracy will not change.

[0087] For sub-areas with a higher degree of deformation, the moving speed is slower, so that the data volume of the point cloud obtained by scanning is larger; for sub-areas with a lower degree of deformation, the moving speed is faster, so that the data volume of the point cloud obtained by scanning is smaller.

[0088] For three-dimensional objects such as the back shell of a mobile phone or the back shell or front cover of a laptop computer, the areas with a higher degree of deformation in the first area are generally the four corners of the rectangular scanning surface, as Figure 6 shown, is a schematic diagram of the object to be detected, including: the first area 61 and the second area 62, the first area 61 includes: the first sub-area 611, the second sub-area 612 and the third sub-area 613.

[0089] The first sub-region is the region within the first preset range at the first end of the first region, the second sub-region is the region within the second preset range at the second end of the first region, and the third sub-region is the region in the first region excluding the first sub-region and the second sub-region. Among them, the first preset range and the second preset range can be the same or different. If the structures of the first end and the second end of the first region are the same, the first preset range and the second preset range can be the same; if the structures of the first end and the second end of the first region are different, the first preset range and the second preset range can be different. Of course, they can also be the same.

[0090] Since the first sub-region and the second sub-region are located at the corner positions of the three-dimensional object to be detected, it is more likely that there are points with the largest degree of deformation in the first sub-region and the second sub-region. Therefore, when the first light source device scans the first sub-region and the second sub-region, a slower speed is adopted. When the first light source device scans the third sub-region, a relatively slower speed can be adopted.

[0091] Specifically, if it is determined that the signal radiation range of at least one light source device is in the first sub-region or the second sub-region of the first region, control the first light source device to move at a third moving speed; if it is determined that the signal radiation range of at least one first light source device is in the third sub-region, control the first light source device to move at a fourth moving speed.

[0092] That is, the first moving speed includes: the third moving speed and the fourth moving speed, and the third moving speed is less than the fourth moving speed. Since the first moving speed is not greater than the second moving speed, neither the third moving speed nor the fourth moving speed is greater than the second moving speed.

[0093] Specifically, if the first light source device and the second light source device move synchronously, the moving speed of the first light source device and the moving speed of the second light source device always remain the same. Then, when the first light source device scans the first sub-region or the second sub-region, the moving speed of the first light source device is the third moving speed, and the moving speed of the second light source device is the third moving speed; when the first light source device scans the third sub-region, the moving speed of the first light source device is the fourth moving speed, and the moving speed of the second light source device is the fourth moving speed.

[0094] That is, as long as the first light source device and the second light source device move synchronously, no matter what the first moving speed is, the second moving speed is the same as the first moving speed, and the second light source device changes with the change of the moving speed of the first light source device.

[0095] In addition, if the first light source device and the second light source device do not move synchronously and their moving speeds are different, the first moving speed is always less than the second moving speed. Whether the first moving speed is the third moving speed or the fourth moving speed, the second moving speed does not need to change;

[0096] Alternatively, the second region is also divided into a first sub-region, a second sub-region, and a third sub-region. Specifically, the region within a first preset range at the first end of the second region is determined as the first sub-region of the second region, the region within a second preset range at the second end of the second region is determined as the second sub-region of the second region, and the other regions of the second region except the first sub-region and the second sub-region are determined as the third sub-region of the second region.

[0097] When scanning the second region with the second light source device, the scanning range of the second light source device can be set to a fifth moving speed when it is in the first sub-region and the second sub-region, and a sixth moving speed when it is in the third sub-region. That is, the second moving speed includes the fifth moving speed and the sixth moving speed, and the fifth moving speed is not greater than the sixth moving speed. Since the first sub-region and the second sub-region of the second region are more prone to deformation than the third sub-region, a lower moving speed is adopted in the first sub-region and the second sub-region of the second region to obtain more data and improve the scanning accuracy.

[0098] It should be noted that whether the second moving speed is the fifth moving speed or the sixth moving speed, its magnitude is not greater than the first moving speed. Only when the first light source device and the second light source device move synchronously, the fifth moving speed is equal to the third moving speed, and the sixth moving speed is equal to the fourth moving speed. However, the third moving speed is less than the fourth moving speed; when the first light source device and the second light source device do not move synchronously, usually the moving speed of the first light source device is necessarily less than that of the second light source device. For example, the third moving speed is less than the fourth moving speed, and at the same time, the third moving speed is less than the fifth moving speed and the third moving speed is less than the sixth moving speed. At this time, the fifth moving speed and the sixth moving speed can be the same or different, the fourth moving speed can be greater than the fifth moving speed and the sixth moving speed, or the fourth moving speed can be equal to the fifth moving speed, and the sixth moving speed is necessarily not greater than the fifth moving speed. Of course, there can also be other situations, which are not specifically limited here.

[0099] In this solution, the first area of the three-dimensional object to be detected is scanned at a first moving speed, and the second area of the three-dimensional object to be detected is scanned at a second moving speed. Moreover, the first moving speed is not higher than the second moving speed, that is, the first area is scanned at a slower speed and with higher precision, while the second area is scanned at a faster speed and with lower precision. This makes the scanning density of the first area where deformation is likely to occur high, improving the measurement accuracy, and the scanning density of the second area where deformation is not likely to occur low, reducing the data processing volume and ensuring the normal operation of the production line. That is, the scanning method based on the above configuration takes into account the data processing ability while ensuring the scanning accuracy of the three-dimensional object scanning model constructed from the first point cloud data and the second point cloud data.

[0100] This embodiment discloses a three-dimensional object detection method, and its flowchart is as Figure 7 shown, including:

[0101] Step S71: Obtain first point cloud data, where the first point cloud data is obtained by scanning the first area of the three-dimensional object to be detected through at least one first light source device;

[0102] Step S72: Obtain second point cloud data, where the second point cloud data is obtained by scanning the second area of the three-dimensional object to be detected through a second light source device. The first area and the second area form a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device;

[0103] Step S73: Obtain a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, and perform model registration on the three-dimensional object scanning model and the three-dimensional object standard model;

[0104] Step S74: Determine at least one specific area on the scanning surface of the three-dimensional object scanning model based on the registration result of the model registration, and determine the height deviation between the at least one specific area and the corresponding area on the three-dimensional object standard model;

[0105] Step S75: Determine the projected size of the scanning surface of the three-dimensional object scanning model based on the registration result of the model registration, and determine the size deviation between the projected size of the scanning surface of the three-dimensional object scanning model and the projected size of the specific surface corresponding to the scanning surface on the three-dimensional object standard model.

[0106] Performing model registration on the three-dimensional object scanning model and the three-dimensional object standard model. Only after model registration can the parts that do not completely overlap in the two models be compared, and this part is the part with deviation. And the three-dimensional object standard model is the original standard model, and the three-dimensional object is produced based on this standard model. Therefore, the part with deviation must be the three-dimensional object scanning model. The part with deviation in the three-dimensional object scanning model is determined as the specific area on the scanning surface.

[0107] The deviation of the scanning surface of the three-dimensional object scanning model from the specific surface of the three-dimensional object standard model may not be only in one place, but may be in multiple places. If there are multiple places, then there are multiple specific areas on the scanning surface.

[0108] To determine the deviation of the specific area of the scanning surface of the three-dimensional object scanning model, it is necessary to determine not only the height deviation but also the size deviation. Among them, the height deviation is: the height deviation between the corresponding areas of the specific area on the scanning surface of the three-dimensional object scanning model and the specific surface of the three-dimensional object standard model; and the size deviation is: the deviation between the projected size of the scanning surface of the three-dimensional object scanning model and the projected size of the specific surface on the three-dimensional object standard model.

[0109] In this solution, the determination of multiple deviation data can be achieved by scanning the three-dimensional object to be detected once. There is no need for clamping during the whole process, and there will be no situation of bumping or scratching. Nor will it necessarily involve the situation of increasing the probability of bumping and scratching caused by multiple clamping. The determination of multiple deviation data can be achieved by one scan, which improves the efficiency of production line assembly.

[0110] Specifically, for the determination of the size deviation, when determining the projected size, it is necessary to determine the projected size based on the registration standard of model registration. Different registration standards will result in different projected sizes. For example: registering with the X-axis and Y-axis of the three-dimensional object standard model, registering with the plane where the point (0,0) is located as the registration standard, and registering with the plane where the point (0,10) is located as the registration standard, the obtained projected sizes will surely be different.

[0111] As Figure 8 shown, it includes: the scanning surface and the specific surface. The projected size of the scanning surface is L1, and the projected size of the specific surface is L2. Then the deviation between the projected size of the scanning surface of the three-dimensional object scanning model and the projected size of the specific surface on the three-dimensional object standard model is L1 - L2.

[0112] Furthermore, to determine the height deviation, it can be: determining the first specific point on the specific area of the three-dimensional object scanning model, where the first specific point is a point in the first point cloud data; determining the point on the three-dimensional object standard model that intersects with the normal direction of the first specific point based on the registration result of model registration, and determining the point on the three-dimensional object standard model that intersects with the normal direction of the first specific point as the second specific point; determining the distance between the first specific point and the second specific point, and determining this distance as the height deviation of the three-dimensional object to be detected.

[0113] Determine the specific area where the scanned model of the three-dimensional object deviates from the standard model of the three-dimensional object. Select a point from the specific area and determine it as the first specific point. Since the scanned model of the three-dimensional object is composed of the first point cloud data and the second point cloud data, the selected first specific point must be one of the point cloud data. And because the first area of the three-dimensional object has a deviation or usually has a large deviation value in the first area, it can be determined that the first specific point is a point in the first point cloud data. Of course, the first specific point can also be a point in the second point cloud data.

[0114] After selecting the first specific point on the scanned model of the three-dimensional object, it is necessary to select the second specific point corresponding to the first specific point on the standard model of the three-dimensional object. The selection of the second specific point is based on the normal direction of the first specific point on the scanned model of the three-dimensional object, that is, select the point on the normal direction of the first specific point and located on the standard model of the three-dimensional object. As Figure 9 shown, including: the scanned model K1 of the three-dimensional object, the standard model K2 of the three-dimensional object. Select the first specific point Pt on the scanning surface of the scanned model K1 of the three-dimensional object, perform plane fitting on the first specific point to determine the normal direction m1 of the first specific point, and determine the point where the line on the normal direction m1 of the first specific point intersects the standard model K2 of the three-dimensional object as the second specific point Ps. That is, the second specific point Ps is the point corresponding to the first specific point Pt on the standard model of the three-dimensional object.

[0115] After determining the first specific point and the second specific point corresponding to the first specific point, only need to calculate the distance between the first specific point and the second specific point to determine the height deviation between the scanned model of the three-dimensional object and the standard model of the three-dimensional object.

[0116] Specifically, the first specific point selected on the scanned model of the three-dimensional object can be the point with the largest deformation degree on the determined three-dimensional object to be detected, that is, the point with the largest deviation of the scanned model of the three-dimensional object relative to the standard model of the three-dimensional object. Select the point with the largest deviation as the first specific point for calculating the height deviation to ensure the detection accuracy and the compensation accuracy after detecting the deviation.

[0117] Specifically, after detecting the deviation, it is also necessary to compensate for the deviation to overcome the influence caused by the deviation.

[0118] Among them, the deviation of the three-dimensional object to be detected is detected in a state of being free of clamping. That is, the scanned model of the three-dimensional object simulated by the point cloud data obtained by the first light source device and the second light source device is scanned in a state of not being clamped. And it can be compared with the standard model of the three-dimensional object in a state of not requiring clamping, so as to obtain the height deviation and size deviation of the three-dimensional object to be detected, that is, detected in a state of being free of clamping.

[0119] The compensation data is for compensating the three-dimensional object to be detected. When the three-dimensional object to be detected is assembled with other products, the three-dimensional object to be detected needs to be clamped. Therefore, it is necessary to use the compensation data to make the three-dimensional object to be detected match the size and height of the standard model in the clamped state, so as to meet the assembly requirements with other products.

[0120] In this solution, the scanned model of the three-dimensional object and the standard model of the three-dimensional object are registered to determine the height deviation and size deviation of the scanned model of the three-dimensional object relative to the standard model of the three-dimensional object, so as to facilitate the compensation of the height deviation and size deviation; moreover, multiple deviation parameters of the scanned model of the three-dimensional object can be determined by one scan, which improves the acquisition efficiency of the deviation parameters and ensures the assembly efficiency of the production line.

[0121] This embodiment discloses an electronic device, and its structural schematic diagram is as Figure 10 shown, including:

[0122] At least one first light source device 101, a second light source device 102 and a processor 103.

[0123] Among them, at least one first light source device 101 is used to scan the first area of the three-dimensional object to be detected to obtain first point cloud data;

[0124] The second light source device 102 is used to scan the second area of the three-dimensional object to be detected to obtain second point cloud data. The first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device;

[0125] The processor 103 is used to obtain the scanned model of the three-dimensional object based on the first point cloud data and the second point cloud data, register the scanned model of the three-dimensional object with the standard model of the three-dimensional object, and obtain the deviation in at least one direction in the three-dimensional space direction of the three-dimensional object to be detected based on the registration result of the model registration.

[0126] The processor is also used to implement the steps of the above three-dimensional object detection method.

[0127] The electronic device disclosed in this embodiment is implemented based on the three-dimensional object detection method disclosed in the above embodiment, and will not be elaborated here.

[0128] The electronic device disclosed in this embodiment obtains first point cloud data, which is obtained by scanning a first area of a three-dimensional object to be detected through at least one first light source device, obtains second point cloud data, which is obtained by scanning a second area of the three-dimensional object to be detected through a second light source device, where the first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device; a three-dimensional object scanning model is obtained based on the first point cloud data and the second point cloud data, the three-dimensional object scanning model is registered with a three-dimensional object standard model, and at least one deviation in the three-dimensional space direction of the three-dimensional object to be detected is obtained based on the registration result of the model registration. In this solution, different areas of the three-dimensional object to be detected are scanned by light source devices with different accuracies to obtain point cloud data, and then registered with the standard model, so as to determine the deviation of the three-dimensional object to be detected. During the whole process, it is not necessary to clamp the three-dimensional object to be detected, avoiding the situation of being damaged due to clamping the three-dimensional object during the deviation determination process; moreover, the deviation of data in multiple different directions can be realized through one scan, improving the data detection efficiency and ensuring the production line assembly efficiency.

[0129] This embodiment discloses a three-dimensional object detection system, and its structural schematic diagram is as Figure 11 shown, including:

[0130] A first acquisition unit 111, a second acquisition unit 112, a registration unit 113, and a deviation acquisition unit 114.

[0131] Specifically, the first acquisition unit 111 is used to acquire first point cloud data, where the first point cloud data is obtained by scanning a first area of a three-dimensional object to be detected through at least one first light source device;

[0132] The second acquisition unit 112 is used to acquire second point cloud data, which is obtained by scanning a second area of the three-dimensional object to be detected through a second light source device, where the first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device;

[0133] The registration unit 113 is used to obtain a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, and register the three-dimensional object scanning model with a three-dimensional object standard model;

[0134] The deviation acquisition unit 114 is used to obtain at least one deviation in the three-dimensional space direction of the three-dimensional object to be detected based on the registration result of the model registration.

[0135] The three-dimensional object detection system disclosed in this embodiment is implemented based on the three-dimensional object detection method disclosed in the above embodiment, and will not be elaborated here.

[0136] The three-dimensional object detection system disclosed in this embodiment obtains first point cloud data, which is obtained by scanning a first area of the three-dimensional object to be detected through at least one first light source device, and obtains second point cloud data, which is obtained by scanning a second area of the three-dimensional object to be detected through a second light source device. The first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device. A three-dimensional object scanning model is obtained based on the first point cloud data and the second point cloud data, the three-dimensional object scanning model is registered with a three-dimensional object standard model, and at least one deviation in the three-dimensional space direction of the three-dimensional object to be detected is obtained based on the registration result of the model registration. In this solution, different areas of the three-dimensional object to be detected are scanned by light source devices with different accuracies to obtain point cloud data, which is then registered with the standard model, so as to determine the deviation of the three-dimensional object to be detected. During the whole process, there is no need to clamp the three-dimensional object to be detected, avoiding the situation of being bruised caused by clamping the three-dimensional object during the deviation determination process. Moreover, the deviation of data in multiple different directions can be achieved through one scan, improving the data detection efficiency and ensuring the production line assembly efficiency.

[0137] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and reference can be made to the description in the method part for related parts.

[0138] Those skilled in the art can further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0139] The steps of the method or algorithm described in combination with the embodiments disclosed in this article can be directly implemented by hardware, a software module executed by a processor, or a combination of the two. The software module can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, register, hard disk, removable disk, CD-ROM, or any other form of storage medium well-known in the technical field.

[0140] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A three-dimensional object detection method, including: obtaining first point cloud data, where the first point cloud data is obtained by scanning a first area of a three-dimensional object to be detected through at least one first light source device; obtaining second point cloud data, where the second point cloud data is obtained by scanning a second area of the three-dimensional object to be detected through a second light source device, where the first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device; obtaining a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, and performing model registration on the three-dimensional object scanning model and a three-dimensional object standard model; obtaining deviations of the three-dimensional object to be detected in at least one direction in the three-dimensional space direction based on the registration result of the model registration.

2. The method according to claim 1, wherein, further including: controlling the at least one first light source device to move from a first end to a second end of the first area of the three-dimensional object to be detected at a determined first moving speed; controlling the second light source device to move from a first end to a second end of the second area of the three-dimensional object to be detected at a second moving speed; wherein the first moving speed is not higher than the second moving speed.

3. The method according to claim 2, wherein, determining the first moving speed includes: determining a first sub-area, a second sub-area, and a third sub-area of the first area of the three-dimensional object to be detected, where the first sub-area is an area within a first preset range at the first end of the first area, the second sub-area is an area within a second preset range at the second end of the first area, and the third sub-area is an area within the first area excluding the first sub-area and the second sub-area; determining the first moving speed based on the correspondence between the signal radiation range of the at least one first light source device and the sub-areas of the first area.

4. The method according to claim 3, wherein, the determining the first moving speed based on the correspondence between the signal radiation range of the at least one first light source device and the sub-areas of the first area includes: if it is determined that the signal radiation range of the at least one first light source device is in the first sub-area or the second sub-area of the first area, controlling the first light source device to move at a third moving speed; if it is determined that the signal radiation range of the at least one first light source device is in the third sub-area, controlling the first light source device to move at a fourth moving speed; wherein the third moving speed is less than the fourth moving speed.

5. The method according to claim 1, wherein, the obtaining deviations of the three-dimensional object to be detected in at least one direction in the three-dimensional space direction based on the registration result of the model registration includes: determining at least one specific area on the scanning surface of the three-dimensional object scanning model based on the registration result of the model registration; determining the height deviation between the at least one specific area and the area corresponding to the specific area of the three-dimensional object standard model. Determine the projected size of the scanning surface of the three-dimensional object scanning model based on the registration result of the model registration; determine the dimensional deviation between the projected size of the scanning surface of the three-dimensional object scanning model and the projected size of the specific surface corresponding to the scanning surface on the three-dimensional object standard model.

6. The method according to claim 5, wherein, determine at least one specific area on the scanning surface of the three-dimensional object scanning model based on the registration result of the model registration; determine the height deviation between the at least one specific area and the area corresponding to the specific area on the three-dimensional object standard model, including: determine a first specific point on the specific area of the three-dimensional object scanning model, and the first specific point is a point in the first point cloud data; based on the registration result of the model registration, determine the point on the three-dimensional object standard model that intersects with the normal direction of the first specific point, and determine the point on the three-dimensional object standard model that intersects with the normal direction of the first specific point as the second specific point; determine the distance between the first specific point and the second specific point, and determine the distance as the height deviation of the three-dimensional object to be detected.

7. The method according to claim 6, wherein, the determination of the first specific point on the three-dimensional object scanning model includes: determine the point on the specific area of the three-dimensional object to be detected with a deformation degree greater than that of other points, and determine the point on the specific area with a deformation degree greater than that of other points as the first specific point.

8. The method according to claim 1, wherein, further includes: determine compensation data based on the deviations of the three-dimensional object to be detected in each direction in the unclamped state to compensate for the deviations of the three-dimensional object to be detected in the clamped state.

9. An electronic device, including: at least one first light source device for scanning a first area of a three-dimensional object to be detected to obtain first point cloud data; a second light source device for scanning a second area of the three-dimensional object to be detected to obtain second point cloud data, where the first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device; a processor for obtaining a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, performing model registration on the three-dimensional object scanning model and a three-dimensional object standard model, and obtaining the deviation of the three-dimensional object to be detected in at least one direction in the three-dimensional space based on the registration result of the model registration.

10. A three-dimensional object detection system, including: a first obtaining unit for obtaining first point cloud data, where the first point cloud data is obtained by scanning a first area of a three-dimensional object to be detected by at least one first light source device; a second obtaining unit for obtaining second point cloud data, where the second point cloud data is obtained by scanning a second area of the three-dimensional object to be detected by a second light source device, where the first area and the second area constitute a surface of the three-dimensional object to be detected, and the scanning accuracy of the second light source device is lower than that of the first light source device; A registration unit, configured to obtain a three-dimensional object scanning model based on the first point cloud data and the second point cloud data, and perform model registration on the three-dimensional object scanning model and a three-dimensional object standard model; A deviation obtaining unit, configured to obtain deviations of the three-dimensional object to be detected in at least one direction in the three-dimensional space direction based on the registration result of the model registration.

Images