Marking point detection method, device, system and electronic device

Abstract

The present application relates to a marking point detection method, device, system and electronic device, wherein the marking point detection method is applied to the marking point detection system, including: obtaining the scanning results for all the marking points and the preset detection angle of the marking points; based on the detection angle, obtaining the imaging features of the marking points in the scanning results, and calculating the detection index corresponding to each of the marking points according to the imaging features; obtaining the visual detection result of each of the marking points according to the detection index. Through this application, the problem of low accuracy of marking point use in the marking point application process is solved, and high-precision visual marking point detection is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of marker point detection, and in particular to a marker point detection method, device, system and electronic device. Background Art

[0002] Artificial markers are often used to locate, track, and splice targets. They are often used in the field of industrial measurement due to their good adaptability, flexibility, and high accuracy. However, in actual applications, factors such as environmental pollution, the quality of the markers themselves, and the placement of the markers make it likely that the markers will affect the accuracy of positioning, tracking, and splicing. In related technologies, the influencing factors of the above markers are often ignored, or customers are not reminded in time to replace and re-paste the markers, resulting in reduced positioning accuracy of the markers, affecting the final experimental results.

[0003] There is no effective solution yet for the problems of poor quality due to contamination or incomplete marking points during their application, as well as reduced accuracy due to other irregular uses. Summary of the invention

[0004] The embodiments of the present application provide a marking point detection method, apparatus, system and electronic device to at least solve the problem of low accuracy of marking point use in the marking point application process in the related art.

[0005] In a first aspect, an embodiment of the present application provides a marking point detection method, which is applied to a marking point detection system, and the method includes:

[0006] Obtaining scanning results for all the marking points and preset detection angles of the marking points;

[0007] Based on the detection angle, acquiring imaging features of the marking points in the scanning result, and calculating the detection index corresponding to each marking point according to the imaging features;

[0008] A visual detection result of each of the marking points is obtained according to the detection index.

[0009] In some embodiments, based on the detection angle, acquiring the imaging features of the marking points in the scanning result, and calculating the detection index corresponding to each of the marking points according to the imaging features; and obtaining the visual detection result of each of the marking points according to the detection index includes:

[0010] Based on the detection angle, obtaining a first imaging feature for characterizing the imaging quality corresponding to each of the marking points;

[0011] A first detection index for the imaging quality is calculated according to the first imaging feature, and the first detection index is processed to obtain the visual detection result.

[0012] In some embodiments, the first detection index for the imaging quality calculated according to the first imaging feature includes:

[0013] According to the first imaging feature, counting the pixel grayscale within each of the marking points;

[0014] Based on the pixel grayscale, a fitting plane for the marking point is obtained to calculate a fitting residual of the fitting plane, and a grayscale distribution value is determined according to the fitting residual; or, based on the pixel grayscale, a percentage of points within a preset interval is calculated, and the grayscale distribution value is determined according to the percentage of points;

[0015] The first detection index is obtained according to the grayscale distribution value.

[0016] In some embodiments, the first detection index for the imaging quality calculated according to the first imaging feature includes:

[0017] According to the first imaging feature, a sub-pixel edge corresponding to each of the marking points is acquired, and edge sharpness is calculated based on the sub-pixel edge;

[0018] The detection index is obtained according to the edge sharpness.

[0019] In some embodiments, based on the detection angle, acquiring the imaging features of the marking points in the scanning result, and calculating the detection index corresponding to each of the marking points according to the imaging features; and obtaining the visual detection result of each of the marking points according to the detection index includes:

[0020] Based on the detection angle, obtaining a second imaging feature for characterizing the positioning accuracy corresponding to each of the marking points;

[0021] According to the second imaging feature, a second detection index for the positioning accuracy is obtained based on a preset elimination strategy, and the second detection index is analyzed and processed to obtain the visual detection result.

[0022] In some embodiments, the analyzing and processing the second detection index to obtain the visual detection result includes:

[0023] When the processing result of the second detection indicator is that the second detection indicator is in an abnormal state, the visual detection result is obtained; wherein the visual detection result is used to remind the user to perform a detection operation on the mark point detection system.

[0024] In some embodiments, based on the detection angle, acquiring the imaging features of the marking points in the scanning result, and calculating the detection index corresponding to each of the marking points according to the imaging features; and obtaining the visual detection result of each of the marking points according to the detection index includes:

[0025] Based on the detection angle, obtaining a third imaging feature for characterizing the stitching accuracy corresponding to each of the marking points;

[0026] The stitching error of the marking point is calculated according to the third imaging feature, so as to obtain a third detection index for the stitching accuracy according to the stitching error, and the third detection index is analyzed and processed to obtain the visual detection result.

[0027] In some embodiments, obtaining a visual detection result of each of the marking points according to the detection index includes:

[0028] When the detection indicator indicates that the marking point is normal, generating a first visual detection result; wherein the first visual detection result is displayed with a first mark, and the first mark is used to indicate that the marking point is in a normal state;

[0029] When the detection indicator indicates that the marking point is abnormal, a second visual detection result is generated; wherein the second visual detection result is displayed with a second mark, and the second mark is used to indicate that the marking point is in an abnormal state and remind the user to perform maintenance operations on the marking point.

[0030] In some embodiments, obtaining scanning results for all the marking points includes:

[0031] Acquire at least two frames of image information containing the marking point, and determine the scanning result according to the image information; or acquire the scanning result in a real-time scanning process for the marking point.

[0032] In a second aspect, an embodiment of the present application provides a marking point detection device, the device comprising: an acquisition module, a detection module and a visualization module;

[0033] The acquisition module is used to acquire scanning results for all the marking points and preset detection angles of the marking points;

[0034] The detection module is used to obtain the imaging features of the marking points in the scanning result based on the detection angle, and calculate the detection index corresponding to each marking point according to the imaging features;

[0035] The visualization module is used to obtain a visualization detection result of each of the marking points according to the detection index.

[0036] In a third aspect, an embodiment of the present application provides a marking point detection system, wherein the system cabinet comprises: a terminal device, a transmission device, and a server device; wherein the terminal device is connected to the server device via the transmission device;

[0037] The terminal device is used to display the visual detection results;

[0038] The transmission device is used to transmit the visual detection result;

[0039] The server device is used to execute the marking point detection method as described in the first aspect above.

[0040] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the marking point detection method as described in the first aspect above is implemented.

[0041] Compared with the related art, the marking point detection method, device, system and electronic device provided in the embodiments of the present application obtain the scanning results for all the marking points and the preset detection angle of the marking points; based on the detection angle, the imaging features of the marking points in the scanning results are obtained, and the detection indicators corresponding to each of the marking points are calculated according to the imaging features; the visual detection results of each of the marking points are obtained according to the detection indicators, thereby solving the problem of low accuracy of marking point use in the marking point application process and realizing high-precision visual marking point detection.

[0042] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0044] Figure 1 is an application environment diagram of a marking point detection method according to an embodiment of the present application;

[0045] Figure 2 is a flow chart of a marking point detection method according to an embodiment of the present application;

[0046] Figure 3 is a flow chart of another marking point detection method according to an embodiment of the present application;

[0047] Figure 4A is a schematic diagram of grayscale distribution of a marking point according to an embodiment of the present application;

[0048] Figure 4B is a schematic diagram of grayscale three-dimensional display of a marking point according to an embodiment of the present application;

[0049] Figure 5A is a schematic diagram of a marking point edge according to an embodiment of the present application;

[0050] Figure 5B is a schematic diagram of another marking point edge according to an embodiment of the present application;

[0051] Figure 5C is a schematic diagram of the edge distribution of a marking point according to an embodiment of the present application;

[0052] Figure 6 is a flow chart of a marking point detection method according to a preferred embodiment of the present application;

[0053] Figure 7 is a flow chart of another marking point detection method according to a preferred embodiment of the present application;

[0054] Figure 8 is a structural block diagram of a marking point detection device according to an embodiment of the present application;

[0055] Fig. 9 is a structural block diagram of a marking point detection system according to an embodiment of the present application;

[0056] Fig.10 It is a structural diagram of the inside of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the contents disclosed in the present application, some changes such as design, manufacturing or production based on the technical contents disclosed in the present application are only conventional technical means, and should not be understood as insufficient contents disclosed in the present application.

[0058] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0059] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to greater than or equal to two. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The terms "first", "second", "third" and the like involved in the present application are merely used to distinguish similar objects and do not represent a specific ordering of the objects.

[0060] The marking point detection method provided in this application can be applied to Figure 1 In the application environment shown. Among them, the terminal device 102 communicates with the server device 104 through the network. The server device 104 obtains the scanning result of the mark point, and then obtains the imaging feature of the mark point in the scanning result according to the preset detection angle, calculates and obtains the detection index of each mark point according to the imaging feature, and finally sends the visual detection result obtained according to the detection index to the terminal device 102, and the terminal device 102 displays the visual detection result on the user interface. Among them, the terminal device 102 can be but not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices, and the server device 104 can be implemented by an independent server device or a server device cluster composed of multiple server devices.

[0061] This embodiment provides a marking point detection method. Figure 2 is a flow chart of a marking point detection method according to an embodiment of the present application. Figure 2 As shown, the process includes the following steps:

[0062] Step S210, obtaining scanning results for all the marking points and the preset detection angles of the marking points.

[0063] Among them, the above-mentioned marking points include circular marking points, square marking points, corner marking points or reflective marking points of different types and materials. The above-mentioned scanning results can be generated by the processor receiving the scanning data obtained by the scanning device scanning all the marking points, and performing point cloud processing and other analysis on the scanning data. The above-mentioned detection angle for the marking points can be set in advance by the user. The detection angle is used to instruct the processor to obtain the scanning results obtained from the corresponding angle detection. For example, the user can set the detection angle in advance to evaluate the sparsity of the marking points. In the subsequent detection steps, the processor can use the detection mechanism corresponding to the sparsity of the marking points to detect the sparsity of each marking point.

[0064] Step S220: Based on the detection angle, the imaging features of the marked points in the scanning result are obtained, and the detection index corresponding to each marked point is calculated according to the imaging features.

[0065] Among them, the above-mentioned imaging features refer to the image grayscale, clarity or edge features in the scanning results of each mark point. Specifically, the imaging features corresponding to the above-mentioned detection angle are obtained, and the detection index of each mark point is calculated using the imaging features; for example, if the detection angle is the imaging quality assessment of the mark point, then the image grayscale distribution and other features corresponding to the imaging quality assessment are obtained, and the image grayscale distribution and other features are used as the imaging features, and the detection index of each mark point is calculated according to the image grayscale distribution; or, if the detection angle is the positioning accuracy assessment of the mark point, then the image fitting and other features corresponding to the positioning accuracy assessment are obtained, and the image fitting and other features are used as the imaging features, and the detection index of each mark point is calculated according to the image fitting degree; or, if the detection angle is the sparse degree assessment of the mark point, then the mark point splicing accuracy and other features corresponding to the sparse degree assessment of the mark point are obtained, and the mark point splicing accuracy and other features are used as the imaging features, and the detection index is calculated according to the mark point splicing accuracy. It is understandable that in this embodiment, a detection angle can be selected and the detection index of each marking point can be obtained based on the detection angle, or the detection index can be obtained by selecting multiple detection angles for comprehensive evaluation and analysis, which will not be repeated here.

[0066] Step S230, obtaining a visual detection result of each of the marking points according to the detection index.

[0067] Specifically, after the processor calculates the detection index, it can evaluate the corresponding marking point according to each detection index and generate a visual detection result of each marking point; the processor can send the visual detection result to the terminal device, and the terminal device displays it. It should be supplemented that the visual detection result can also be generated in the following way: the evaluation result of each marking point obtained by the processor according to each detection index is sent to the terminal device, and the terminal device generates the visual detection result according to the evaluation result and displays it. Since all the marking points scanned above will be displayed in real time on the application software of the terminal device, the visual detection result corresponding to each marking point can also be displayed in real time with different colors, shapes or texts; for example, if a certain detection index indicates that the corresponding marking point is contaminated, the generated visual detection result is a red mark, and the terminal device will display the marking point in red.

[0068] Through the above steps S210 to S230, based on the preset detection angle, the visual detection result for each marker point is calculated in turn according to the scanning results of all the marker points, so that the usage of each marker point is obtained by diagnosing the imaging characteristics of each marker point on the camera device, and feedback and reminders are given to the user in an appropriate visual form, avoiding low scanning accuracy or splicing errors caused by marker point defects in the process of using marker points for three-dimensional scanning, solving the problem of low accuracy of marker point use in the marker point application process, and realizing a high-precision visual marker point detection method.

[0069] In some embodiments, a marker detection method is provided. Figure 3 is a flow chart of another marking point detection method according to an embodiment of the present application. Figure 3 As shown, the process includes the following steps:

[0070] Step S310: Based on the detection angle, a first imaging feature for characterizing the imaging quality corresponding to each of the marking points is obtained.

[0071] It should be noted that the above detection angle in this embodiment is used to indicate the detection of each mark point from the perspective of imaging quality. At this time, the first imaging feature corresponding to the imaging quality may include image grayscale distribution features or image edge features.

[0072] Step S320: Calculate a first detection index for the imaging quality according to the first imaging feature, and process the first detection index to obtain the visual detection result.

[0073] Among them, the above-mentioned first detection index for the imaging quality calculated according to the first imaging feature also includes the following steps: according to the first imaging feature, counting the pixel grayscale in each of the marked points; based on the pixel grayscale, obtaining the fitting plane for the marked point to calculate the fitting residual of the fitting plane, and determining the grayscale distribution value according to the fitting residual; or, based on the pixel grayscale, calculating the proportion of points in a preset interval, and determining the grayscale distribution value according to the proportion of points; obtaining the first detection index according to the grayscale distribution value.

[0074] It should be noted that since the positioning structures of most positioning algorithms are at the sub-pixel level, they are related to the image grayscale distribution of the positioning target. Figure 4A is a schematic diagram of grayscale distribution of a marking point according to an embodiment of the present application, Figure 4B is a schematic diagram of grayscale three-dimensional display of a marking point according to an embodiment of the present application, such as Figure 4A and 4B As shown, the grayscale distribution of the marking point is uneven; Figure 4B The X-axis and Y-axis coordinates in the marking point are used to represent the pixels in the X-axis direction and the Y-axis direction of the scanned image of the marking point, respectively, and the Z-axis represents the grayscale value of the corresponding pixel; for a marking point, it has the same material composition, and theoretically should have a relatively consistent imaging grayscale distribution, and good grayscale uniformity is the guarantee of positioning accuracy; therefore, in this embodiment, the above-mentioned first imaging feature is used as the image grayscale distribution. Then the above-mentioned processor counts the pixel grayscale in each marking point according to the first imaging feature of the image grayscale distribution adopted. Specifically, taking the circular marking point as an example, the center of the circular marking point can be used as a stable positioning center, and sub-pixel extraction is first performed along the edge of the marking point, and then an ellipse fitting is performed based on the sub-pixel to obtain the ellipse equation; according to the positioned ellipse equation, the pixel grayscale in the circle corresponding to the center marking point is selected, and a fitting plane is obtained by fitting; the residual of the pixel grayscale fitting plane is obtained, and the grayscale distribution value is calculated, and finally the grayscale distribution value is used as the first detection indicator for judging the grayscale uniformity of the marking point imaging. Alternatively, after obtaining the above-mentioned pixel grayscale according to the above-mentioned elliptical equation statistics, the proportion of the number of points within a preset interval can also be calculated to obtain the above-mentioned grayscale distribution value; the preset interval can be set in advance by the user. Taking the preset interval set using the 3σ principle as an example, the proportion of the number of points within the 3σ principle to the total number is calculated, and the proportion value is then used as the first detection indicator of the imaging grayscale uniformity.

[0075] Alternatively, the above-mentioned calculation of the first detection index for the imaging quality based on the first imaging feature also includes the following steps: according to the first imaging feature, obtaining the sub-pixel edge corresponding to each marking point, and calculating the edge sharpness based on the sub-pixel edge; obtaining the detection index based on the edge sharpness.

[0076] It should be noted that the edge sharpness of the marking point is also related to the positioning accuracy of the marking point and can reflect the imaging quality of the device. Figure 5A is a schematic diagram of a marking point edge according to an embodiment of the present application, Figure 5B is a schematic diagram of another marking point edge according to an embodiment of the present application, such as Figure 5A and 5B As shown, Figure 5A If the image edge is blurred in the scanning result of the marker point in the image, the marker point is not a clear marker point in terms of physical characteristics, reflecting the low imaging quality; Figure 5B The image edge in the scanning result of another marking point in the image is clear, which can reflect that the imaging quality is relatively high. Therefore, in this embodiment, the above-mentioned first imaging feature is adopted as the image edge feature. Then the above-mentioned processor counts the edge sharpness corresponding to each marking point according to the adopted first imaging feature of the image edge feature. Specifically, the processor obtains the sub-pixel edge in each marking point respectively, samples the edge gradient direction with the sub-pixel edge as the center, and calculates the edge sharpness. The sampling method can be SFR algorithm, etc.; then the distribution of the edge sharpness of the marking point is counted, where, Figure 5C is a schematic diagram of a marking point edge distribution according to an embodiment of the present application, such as Figure 5C As shown, the horizontal axis of the schematic diagram represents the pixel coordinates of the edge of the image, and the vertical axis represents the grayscale value of the corresponding pixel, and the grayscale value ranges from 0 to 255; finally, the clarity of the entire marking point is judged based on the statistical results, and the statistical results are used as the above-mentioned first detection indicator.

[0077] It is understandable that in this embodiment, the user can pre-select any first imaging feature in the above-mentioned image grayscale distribution or image edge feature, and the above-mentioned processor can calculate the corresponding first detection index based on the selected first imaging feature; or, the above-mentioned processor can also calculate the image grayscale distribution and image edge feature to obtain a comprehensive analysis result of the first detection index, thereby effectively improving the accuracy of the mark point detection. After the processor obtains the first detection index corresponding to the imaging quality, it can generate a corresponding visual detection result. For example, when the physical reflective properties of the mark point itself do not meet the standard due to some stains or damage, the processor obtains that the first detection index corresponding to the mark point is abnormal, and then generates a corresponding visual detection result to remind the user to replace the mark point or indicate that the mark point is abnormal.

[0078] Through the above steps S310 to S320, the corresponding first detection index is calculated from the perspective of imaging quality detection, so that it is possible to timely detect whether there are stains or damaged incomplete marking points, avoiding the problem of low scanning accuracy due to defects in marking points, which is conducive to improving the accuracy of marking point detection.

[0079] In some embodiments, the above-mentioned imaging features of the mark point in the scanning result are obtained based on the detection angle, and the detection index corresponding to each mark point is calculated according to the imaging features; obtaining the visual detection result of each mark point according to the detection index also includes the following steps: based on the detection angle, a second imaging feature is obtained for characterizing the positioning accuracy corresponding to each mark point; based on the second imaging feature, a second detection index for the positioning accuracy is obtained based on a preset elimination strategy, and the second detection index is analyzed and processed to obtain the visual detection result.

[0080] Among them, the above-mentioned detection angle in this embodiment is used to indicate the detection of each marked point from the perspective of positioning accuracy. At this time, the second imaging feature corresponding to the positioning accuracy may include image fitting features, etc. The above-mentioned preset rejection strategy refers to a method for removing abnormal edge points set in advance by the user; the preset rejection strategy can be: by randomly dividing the features, establishing a random forest, and considering the points that can be divided after a small number of divisions as abnormal points; or, clustering the features, and in the clustering process, the points that are far away from the center cluster are considered to be abnormal points. Specifically, taking the above-mentioned marking point as a circular marking point as an example, the center of the marking point can be used as a stable positioning center; first, along the edge of the marking point, use the canny operator or other edge operators to preliminarily extract the edge of the marking point to obtain the pixel-level positioning of the edge, and then obtain the sub-pixel level positioning of the edge according to the parabola interpolation method to extract the sub-pixel; perform ellipse fitting based on the sub-pixel to obtain the ellipse equation; then preliminarily fit and remove abnormal edge points based on the preset removal strategy, where the preset removal strategy can be: use the distance from the point participating in the fitting to the ellipse as the basis for judging the quality of the fitting, for example, for the extracted n edge points, first perform ellipse fitting on all of them, and then calculate the distance from the point participating in the fitting to the ellipse according to the residual of the fitting or the distance from the point participating in the fitting to the ellipse. The residual is removed according to the 3σ principle, the edge is fitted again and the steps of the preset removal strategy are repeated; finally, the residual of the fitted ellipse equation is calculated, and the recorded removed abnormal noise points are used to evaluate the proportion of abnormal edge points to evaluate the number of abnormal edge points, and then the above-mentioned second detection index is obtained. For example, if a total of 25 points of a certain marking point are initially fitted, and 5 points are finally removed as abnormal noise, then the proportion of points involved in the fitting is 20 / 25, and the second detection index can be considered normal; if 15 points are removed as abnormal points, the proportion of points involved in the fitting is 10 / 25. At this time, this proportion is low, and it can be considered that the marking point does not meet the standard and the second detection index is abnormal.

[0081] After obtaining the above-mentioned second detection index, a visual detection result can be obtained according to the second detection index; for example, if the second detection index is normal, it means that the corresponding mark point is in a normal state at this time, and a visual detection result corresponding to the normal state can be generated; if the second detection index is abnormal, it means that the corresponding mark point is in an abnormal state at this time, and a visual detection result corresponding to the abnormal state can be generated. It can be understood that the second detection index can also be comprehensively analyzed with the above-mentioned first detection index to obtain the visual detection result; for example, if the second detection index corresponding to a certain mark point is normal, and the first detection index of the same mark point is abnormal, it means that the positioning accuracy of the mark point is good but the imaging quality is poor, and a visual detection result can be generated to prompt the user to change the mark point; if the second detection index is abnormal and the first detection index is normal, it means that the imaging quality of the mark point is good but the positioning accuracy is poor, and a visual detection result can be generated to prompt the mark point to be contaminated; and when the first detection index and the second detection index are both normal, a visual result of the mark point being in a normal state is generated. Therefore, in this embodiment, each indicator is presented to the user separately or comprehensively, which can remind the user to perform appropriate operations in time, thereby improving the safety and accuracy of the mark point application.

[0082] Through the above embodiment, the corresponding second detection index is calculated from the detection angle of positioning accuracy, so that it is possible to timely detect whether there are marking points with poor positioning accuracy, avoiding the problem of low scanning accuracy caused by the equipment not being calibrated for a long time or the equipment having abnormalities, which is conducive to further improving the accuracy of marking point detection.

[0083] In some embodiments, the above-mentioned analysis and processing for the second detection index to obtain the visual detection result also includes the following steps: when the processing result for the second detection index is that the second detection index is in an abnormal state, the visual detection result is obtained; wherein the visual detection result is used to remind the user to perform the detection operation for the mark point detection system. Specifically, when it is detected that the current range of the second detection index does not belong to the corresponding normal index range, it means that the second detection index is in an abnormal state, that is, the positioning accuracy of the mark point corresponding to the second detection index is poor, and there may be a problem that the device has not been calibrated for a long time or the device is abnormal, so a visual detection result can be generated to remind the user to perform the detection operation for the mark point detection system. It should be noted that at this time, the visual detection result can be represented by reminder information or color, for example, the words "Please check the device!" are displayed below the corresponding mark point on the application software of the above-mentioned terminal device, or the mark point is displayed in orange, which will not be repeated here. Through the above embodiments, a method for timely reminding the user to check the scanning device when the second detection index is abnormal is realized, avoiding the problem of low equipment operation efficiency caused by scanning device failure, thereby improving the safety and efficiency of the use of the scanning device.

[0084] In some of the embodiments, the above-mentioned imaging features of the marked point in the scanning result are obtained based on the detection angle, and the detection indicators corresponding to each of the marked points are calculated according to the imaging features; obtaining the visual detection result of each of the marked points according to the detection indicators also includes the following steps: based on the detection angle, a third imaging feature is obtained for characterizing the stitching accuracy corresponding to each of the marked points; the stitching error of the marked point is calculated according to the third imaging feature, so as to obtain a third detection indicator for the stitching accuracy according to the stitching error, and the third detection indicator is analyzed and processed to obtain the visual detection result.

[0085] Among them, the above-mentioned detection angle in this embodiment is used to indicate the detection of each marking point from the perspective of stitching accuracy. At this time, the third imaging feature corresponding to the stitching accuracy may include a stitching error feature or a positioning error feature, etc. Specifically, the above-mentioned processor first pre-scans all marking points, and records the stitching accuracy of each marking point, and uses the stitching accuracy as the above-mentioned third detection index to generate a visual detection result to prompt the points with poor accuracy, so that the user can be reminded in time when the stitching error of the stitching of two marking points is large. Or for circular marking points, pre-scan and reconstruct all marking points, search around each marking point with a certain radius, the more points that fall into the radius, the more robust the marking point is; and the fewer points that fall into the radius, the less robust the marking point is. At this time, a visual detection result can be generated to prompt the user to add marking points around the marking point, so that the user can be reminded in time when the error of the circular marking point identification and positioning circle is large.

[0086] In some embodiments, the above step S230 further includes the following steps:

[0087] Step S231, when the detection indicator indicates that the marked point is normal, generate a first visual detection result; wherein the first visual detection result is displayed with a first mark, and the first mark is used to indicate that the marked point is in a normal state.

[0088] Step S232, when the detection indicator indicates that the mark point is abnormal, generate a second visual detection result; wherein the second visual detection result is displayed with a second mark, and the second mark is used to indicate that the mark point is in an abnormal state and remind the user to perform maintenance operations on the mark point.

[0089] In the above steps S231 to S232, the above first mark and the second mark can be set to different colors, shapes or information to prompt the user to pay attention; the first mark and the second mark can be freely adjusted according to actual needs. For example, the first mark is set to green, and the second mark is set to red. When the above detection index indicates that the corresponding mark point is normal, the above processor or directly generates a green mark point on the above terminal device, and displays it on the application interface of the terminal device, and when the detection index indicates that the mark point is abnormal, a red mark point is generated; or, the first mark is set to a dot, and the second mark is set to a triangle. When the detection index indicates that the corresponding mark point is normal, a dot can be displayed below this mark point on the application interface, and when the detection index indicates that the mark point is abnormal, a triangle is displayed below this mark point. In addition, the second mark can also be set to voice, reminder message or light display, etc., as long as it can be used to remind the user of abnormal status, it will not be repeated here.

[0090] Through the above steps S231 to S232, the marking points can be displayed with different signs for normal and abnormal marking points, so that users can obtain abnormal information of the marking points in real time, avoid large positioning, tracking and splicing accuracy errors caused by untimely replacement of marking points, and realize rapid positioning of marking point failure problems.

[0091] In some embodiments, the above-mentioned acquisition of scanning results for all the marking points also includes the following steps: obtaining at least two frames of image information containing the marking points, and determining the scanning results based on the image information; or, obtaining the scanning results in the real-time scanning process for the marking points. Specifically, the execution order of the above-mentioned marking point detection method can be a pre-scan followed by an overall evaluation, or real-time feedback of the detection results during the scanning process. It should be supplemented that, during the scanning and real-time stitching process, if it is detected that the stitching accuracy of some marking points is lower than the preset accuracy set by the user, the visual detection results can be displayed in real time on the application software of the above-mentioned terminal device when the point cloud is not displayed, thereby enabling real-time feedback to the user.

[0092] The embodiments of the present invention are described in detail below in combination with actual application scenarios, taking a method for detecting a marking point by first pre-scanning and then evaluating the marking point as an example. Figure 6 is a flow chart of a marking point detection method according to a preferred embodiment of the present application. Figure 6 As shown, the process includes the following steps:

[0093] Step S601 , scanning all the marking points on the target object in a marking point scanning mode, scanning n frames in total; n is a positive integer greater than 1.

[0094] Step S602, real-time recording of each marker point detection, including: real-time recording of each marker point positioning accuracy evaluation, real-time recording of each marker point imaging quality evaluation, real-time recording of each marker point splicing accuracy, and real-time recording of each marker point sparse degree evaluation.

[0095] Step S603, processing the detection index of each marking point and providing the detection result.

[0096] Step S604: Generate a visual marker point detection result based on the above detection result.

[0097] Take the marker point detection method that provides real-time feedback of detection results during scanning as an example. Figure 7 is a flow chart of another marking point detection method according to a preferred embodiment of the present application. Figure 7 As shown, the process includes the following steps:

[0098] Step S701, start real-time scanning.

[0099] Step S702, real-time recording of each marker point detection, including: real-time recording of each marker point positioning accuracy evaluation, real-time recording of each marker point imaging quality evaluation, and real-time recording of each marker point splicing accuracy.

[0100] Step S703, processing the detection index of each marking point and providing the detection result.

[0101] Step S704, obtaining visual detection results in real time.

[0102] Step S705: When the scan is finished, the detection result of each marked point is given.

[0103] Step S706: Generate a visual marker point detection result based on the above detection result.

[0104] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0105] This embodiment also provides a marking point detection device, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the terms "module", "unit", "subunit", etc. can be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0106] Figure 8 is a structural block diagram of a marking point detection device according to an embodiment of the present application, such as Figure 8 As shown, the device includes: an acquisition module 82, a detection module 84 and a visualization module 86. The acquisition module 82 is used to acquire the scanning results for all the marking points and the preset detection angle of the marking points; the detection module 84 is used to acquire the imaging features of the marking points in the scanning results based on the detection angle, and calculate the detection index corresponding to each marking point according to the imaging features; the visualization module 86 is used to obtain the visual detection result of each marking point according to the detection index.

[0107] Through the above embodiment, the above visualization module 86 calculates the visualization detection result for each marker point in sequence based on the scanning results of all marker points based on the preset detection angle, thereby diagnosing the imaging characteristics of each marker point on the camera device to obtain the usage of each marker point, and provides feedback and reminders to the user in an appropriate visualization form, thereby avoiding low scanning accuracy or splicing errors caused by marker point defects in the process of using marker points for three-dimensional scanning, solving the problem of low accuracy of marker point use in the marker point application process, and realizing a high-precision visualization marker point detection device.

[0108] In some embodiments, the detection module 84 is further used to obtain a first imaging feature for characterizing the imaging quality corresponding to each marking point based on the detection angle; the detection module 84 calculates a first detection index for the imaging quality based on the first imaging feature; and the visualization module 86 is further used to process the first detection index to obtain the visualization detection result.

[0109] In some embodiments, the detection module 84 is also used to count the pixel grayscale within each marking point based on the first imaging feature; the detection module 84 obtains the fitting plane for the marking point based on the pixel grayscale to calculate the fitting residual of the fitting plane, and determines the grayscale distribution value based on the fitting residual; or, the detection module 84 calculates the proportion of points in a preset interval based on the pixel grayscale, and determines the grayscale distribution value based on the proportion of points; the detection module obtains the first detection indicator based on the grayscale distribution value.

[0110] In some embodiments, the detection module 84 is further used to obtain the sub-pixel edge corresponding to each marking point according to the first imaging feature, and calculate the edge sharpness based on the sub-pixel edge; the detection module 84 obtains the detection index according to the edge sharpness.

[0111] In some embodiments, the detection module 84 is also used to obtain a second imaging feature for characterizing the positioning accuracy corresponding to each marking point based on the detection angle; the detection module 84 obtains a second detection index for the positioning accuracy based on a preset elimination strategy according to the second imaging feature, and analyzes and processes the second detection index to obtain the visual detection result.

[0112] In some of the embodiments, the visualization module 86 is also used to obtain the visual detection result when the processing result of the second detection indicator is that the second detection indicator is in an abnormal state; wherein the visual detection result is used to remind the user to perform detection operations on the mark point detection system.

[0113] In some of the embodiments, the detection module 84 is further used to obtain a third imaging feature for characterizing the stitching accuracy corresponding to each marking point based on the detection angle; the detection module 84 calculates the stitching error of the marking point according to the third imaging feature to obtain a third detection index for the stitching accuracy based on the stitching error; the visualization module 86 is further used to analyze and process the third detection index to obtain the visualization detection result.

[0114] In some embodiments, the above-mentioned visualization module 86 is also used to generate a first visualization detection result when the detection indicator indicates that the mark point is normal; wherein the first visualization detection result is displayed with a first mark, and the first mark is used to indicate that the mark point is in a normal state; the visualization module 86 generates a second visualization detection result when the detection indicator indicates that the mark point is abnormal; wherein the second visualization detection result is displayed with a second mark, and the second mark is used to indicate that the mark point is in an abnormal state, and remind the user to perform maintenance operations on the mark point.

[0115] In some embodiments, the acquisition module 82 is further used to acquire at least two frames of image information containing the marking point, and determine the scanning result based on the image information; or, the acquisition module 82 acquires the scanning result during a real-time scanning process for the marking point.

[0116] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0117] This embodiment also provides a marking point detection system. Fig. 9 is a structural block diagram of a marking point detection system according to an embodiment of the present application, such as Fig. 9 As shown, the generation system includes: a terminal device 102, a transmission device 92 and a server device 104; wherein the terminal device 102 is connected to the server device via the transmission device 92; the terminal device 102 is used to display the visual detection result; and the transmission device 92 is used to transmit the visual detection result. The server device 104 is used to obtain the scanning results for all the marking points and the preset detection angle of the marking point; based on the detection angle, the server device 104 obtains the imaging features of the marking point in the scanning result, and calculates the detection index corresponding to each marking point according to the imaging features. The server device 104 obtains the visual detection result of each marking point according to the detection index, and sends the visual result to the terminal device through the transmission device; or, the server device 104 can also send the detection index to the terminal device through the transmission device, and the terminal device directly generates the visual result for display.

[0118] Through the above embodiment, the above server device 104 calculates the visual detection results for each marker point in sequence based on the preset detection angle and the scanning results of all the marker points, so as to diagnose the imaging characteristics of each marker point on the camera device to obtain the usage of each marker point, and provide feedback and reminders to the user in an appropriate visual form, thereby avoiding low scanning accuracy or splicing errors caused by marker point defects in the process of using marker points for three-dimensional scanning, solving the problem of low accuracy of marker point use in the marker point application process, and realizing a high-precision visual marker point detection system.

[0119] In some embodiments, a computer device is provided, which may be a server device. Fig.10 is a structural diagram of the inside of a computer device according to an embodiment of the present application, such as Fig.10 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store detection indicators. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a marking point detection method is implemented.

[0120] Those skilled in the art will understand that Fig.10 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0121] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0122] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0123] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0124] S1, obtaining scanning results for all the marking points and the preset detection angles of the marking points.

[0125] S2, based on the detection angle, obtaining the imaging features of the marked points in the scanning result, and calculating the detection index corresponding to each marked point according to the imaging features.

[0126] S3, obtaining a visual detection result of each marked point according to the detection index.

[0127] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0128] In addition, in combination with the marking point detection method in the above embodiment, the embodiment of the present application can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by a processor, any marking point detection method in the above embodiment is implemented.

[0129] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0130] Those skilled in the art should understand that the technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0131] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A marking point detection method, characterized in that: A marker point detection system applied to three-dimensional scanning, the method comprising: Obtaining scanning results for all the marking points and the preset detection angles of the marking points; the scanning results are obtained by the processor receiving scanning data obtained by scanning all the marking points by the scanning device, and performing point cloud processing and analysis on the scanning data; Based on the detection angle, the imaging features of the marking points in the scanning result are obtained, and the detection index corresponding to each marking point is calculated according to the imaging features; the detection angle includes the imaging quality evaluation, the positioning accuracy evaluation and the marking point sparsity evaluation of the marking points; the imaging features include the image grayscale distribution features corresponding to the imaging quality evaluation, the image fitting features corresponding to the positioning accuracy evaluation, and the marking point splicing accuracy features corresponding to the marking point sparsity evaluation; The visual detection result of each of the marking points is obtained according to the detection index; the visual detection result corresponding to each marking point is displayed in real time using different colors, shapes or texts.

2. The marking point detection method according to claim 1, characterized in that: Based on the detection angle, imaging features of the marking points in the scanning result are acquired, and detection indicators corresponding to each marking point are calculated according to the imaging features; Obtaining a visual detection result of each of the marking points according to the detection index includes: Based on the detection angle, obtaining a first imaging feature for characterizing the imaging quality corresponding to each of the marking points; A first detection index for the imaging quality is calculated according to the first imaging feature, and the first detection index is processed to obtain the visual detection result.

3. The marking point detection method according to claim 2, characterized in that: The first detection index for the imaging quality calculated according to the first imaging feature comprises: According to the first imaging feature, counting the pixel grayscale within each of the marking points; Based on the pixel grayscale, a fitting plane for the marking point is obtained to calculate a fitting residual of the fitting plane, and a grayscale distribution value is determined according to the fitting residual; or, based on the pixel grayscale, a percentage of points within a preset interval is calculated, and the grayscale distribution value is determined according to the percentage of points; The first detection index is obtained according to the grayscale distribution value.

4. The marking point detection method according to claim 2, characterized in that: The first detection index for the imaging quality calculated according to the first imaging feature comprises: According to the first imaging feature, a sub-pixel edge corresponding to each of the marking points is acquired, and edge sharpness is calculated based on the sub-pixel edge; The detection index is obtained according to the edge sharpness.

5. The marking point detection method according to claim 1, characterized in that: Based on the detection angle, imaging features of the marking points in the scanning result are acquired, and detection indicators corresponding to each marking point are calculated according to the imaging features; Obtaining a visual detection result of each of the marking points according to the detection index includes: Based on the detection angle, obtaining a second imaging feature for characterizing the positioning accuracy corresponding to each of the marking points; According to the second imaging feature, a second detection index for the positioning accuracy is obtained based on a preset elimination strategy, and the second detection index is analyzed and processed to obtain the visual detection result.

6. The marking point detection method according to claim 5, characterized in that: The analyzing and processing the second detection index to obtain the visual detection result includes: When the processing result of the second detection indicator is that the second detection indicator is in an abnormal state, the visual detection result is obtained; wherein the visual detection result is used to remind the user to perform a detection operation on the mark point detection system.

7. The marking point detection method according to claim 1, characterized in that: Based on the detection angle, imaging features of the marking points in the scanning result are acquired, and detection indicators corresponding to each marking point are calculated according to the imaging features; Obtaining a visual detection result of each of the marking points according to the detection index includes: Based on the detection angle, obtaining a third imaging feature for characterizing the stitching accuracy corresponding to each of the marking points; The stitching error of the marking point is calculated according to the third imaging feature, so as to obtain a third detection index for the stitching accuracy according to the stitching error, and the third detection index is analyzed and processed to obtain the visual detection result.

8. The marking point detection method according to claim 1, characterized in that: Obtaining a visual detection result of each of the marking points according to the detection index includes: When the detection indicator indicates that the marking point is normal, generating a first visual detection result; wherein the first visual detection result is displayed with a first mark, and the first mark is used to indicate that the marking point is in a normal state; When the detection indicator indicates that the marking point is abnormal, a second visual detection result is generated; wherein the second visual detection result is displayed with a second mark, and the second mark is used to indicate that the marking point is in an abnormal state and remind the user to perform maintenance operations on the marking point.

9. The marking point detection method according to any one of claims 1 to 8, characterized in that: The obtaining of scanning results for all the marking points comprises: Acquire at least two frames of image information containing the marking point, and determine the scanning result according to the image information; or acquire the scanning result in a real-time scanning process for the marking point.

10. A marking point detection device, characterized in that: The device comprises: an acquisition module, a detection module and a visualization module; The acquisition module is used to acquire the scanning results for all the marking points and the preset detection angles of the marking points; the scanning results are generated by the processor receiving the scanning data obtained by the scanning device scanning all the marking points, and performing point cloud processing and analysis on the scanning data; The detection module is used to obtain the imaging features of the marking points in the scanning result based on the detection angle, and calculate the detection index corresponding to each marking point according to the imaging features; the detection angle includes the imaging quality evaluation, positioning accuracy evaluation and marking point sparsity evaluation of the marking points; the imaging features include the image grayscale distribution features corresponding to the imaging quality evaluation, the image fitting features corresponding to the positioning accuracy evaluation, and the marking point splicing accuracy features corresponding to the marking point sparsity evaluation; The visualization module is used to obtain the visualization detection result of each of the marking points according to the detection index; the visualization detection result corresponding to each marking point is displayed in real time using different colors, shapes or texts.

11. A marking point detection system, characterized in that: The system comprises: a terminal device, a transmission device and a server device; wherein the terminal device is connected to the server device via the transmission device; The terminal device is used to display the visual detection results; The transmission device is used to transmit the visual detection result; The server device is used to execute the marking point detection method according to any one of claims 1 to 9.

12. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the marking point detection method according to any one of claims 1 to 9.

Images