Curved surface lap joint groove feature point extraction method and device

Abstract

The invention discloses a curved surface lap joint groove feature point extraction method and device. The method comprises the steps that a 3D contourgraph is used for scanning a lap joint groove to obtain lap joint groove contour depth data; performing multi-dimensional interpolation filtering on the lap groove contour depth data to remove noise contour data; an ROI region is set to segment and remove redundant data in the depth data of the section contour of the lap joint groove; processing data in the ROI region by using a PELT change point detection method, and extracting a plurality of groups of feature point sets to be selected; and screening the multiple groups of to-be-selected feature point sets by utilizing dynamic threshold optimization to obtain target feature points.

Description

Technical Field

[0001] The present application relates to the field of intelligent welding technology, and more specifically, to a method and device for extracting characteristic points of a curved surface lap groove. Background Art

[0002] Intelligent welding is developing rapidly and is commonly used in industrial applications requiring high strength and good sealing, such as automotive roof and body welding. Currently, most lap welds rely on robots pre-setting the welding trajectory. This method not only increases labor and time costs, but also greatly lacks flexibility and stability. Furthermore, many current methods for extracting groove features are based on the situation where the plate type is two parallel overlapping plates. If the plate is bent, the effect will be greatly reduced.

[0003] However, the lap weld of the roof is not the most common parallel overlap of two plates, but an overlap with an arc. However, most of the current positioning methods are based on the lap weld type of parallel overlapping plates, and the applicable types are limited. Summary of the Invention

[0004] In response to at least one defect or improvement need in the prior art, the present invention provides a method and device for extracting feature points of lap joint grooves on curved surfaces. A 3D line laser profiler is used to collect data, extract the height information of the groove cross-section profile, and then use a feature point extraction algorithm to calculate the groove feature information. This effectively solves the problem of extracting feature information of lap weld grooves of various types of plates, improves the adaptability to plates, and achieves the purpose of improving welding automation and intelligence.

[0005] To achieve the above-mentioned purpose, according to the first aspect of the present invention, a method for extracting feature points of a lap joint groove of a curved surface is provided, the method comprising: using a 3D profilometer to scan the lap joint groove to obtain lap joint groove profile depth data; performing multi-dimensional interpolation filtering on the lap joint groove profile depth data to remove noise profile data; setting ROI region segmentation to eliminate redundant data in the lap joint groove cross-sectional profile depth data; using the PELT change point detection method to process the data in the ROI region to extract multiple sets of candidate feature point sets; and using dynamic threshold optimization to screen the multiple sets of candidate feature point sets to obtain target feature points.

[0006] In an exemplary embodiment, the multi-dimensional interpolation filtering of the overlap groove profile depth data to remove noise profile data includes: obtaining the current profile data point, traversing the profile data points, and querying whether there is noise profile data; if noise profile data exists, forward interpolating the noise profile data in the Y dimension; if the current profile is the starting profile or the current profile and the previous round of profiles have noise points at the same position, linear interpolating the current noise profile data in the X and Z dimensions.

[0007] In an exemplary embodiment, the method of processing the data in the ROI region by using the PELT change point detection method to extract multiple sets of candidate feature points includes: performing mutation point statistics on the data by using the PELT change point detection method to obtain a set of mutation point positions (t0, t1, ..., t k+1 ); The minimum value of the total cost function is specifically, Where t0=0, t k+1 =n, n is the length of ROI area data, is the change point t i to t i+1 A piece of data, is the cost function, β is the penalty coefficient, and k is the number of change points.

[0008] In an exemplary embodiment, the use of dynamic threshold optimization to screen the multiple sets of candidate feature points to obtain target feature points includes: calculating the local slope set of each change point interval; determining the dynamic threshold by calculating the local slope baseline value and the local standard deviation; wherein the baseline value is the median of the local slopes of all change point intervals, and the local standard deviation is used to characterize the degree of fluctuation within the data of each change point interval.

[0009] In an exemplary embodiment, determining the dynamic threshold by calculating the reference value and the local standard deviation includes: the dynamic threshold is expressed as dynamic_threshold=base_slope-K*local_std, where dynamic_threshold is the dynamic threshold, base_slope is the reference value, local_std is the local standard deviation, and K is the sensitivity coefficient.

[0010] In an exemplary embodiment, the method further includes: if the lap groove type is left lap, the change point interval in which the local slope is less than the dynamic threshold is confirmed as the target change point interval, and the target feature point is extracted from the target change point interval; if the lap groove type is right lap, the change point interval in which the local slope is greater than the dynamic threshold is confirmed as the target change point interval, and the target feature point is extracted from the target change point interval.

[0011] According to the second aspect of the present invention, a device for extracting feature points of a curved surface lap groove is also provided, which includes: an acquisition unit for scanning the lap groove using a 3D profiler to obtain lap groove profile depth data; a filtering unit for performing multi-dimensional interpolation filtering on the lap groove profile depth data to remove noise profile data; a segmentation unit for setting ROI area segmentation to eliminate redundant data in the lap groove cross-sectional profile depth data; an extraction unit for processing data in the ROI area using the PELT change point detection method to extract multiple groups of candidate feature point sets; and a screening unit for screening the multiple groups of candidate feature point sets using dynamic threshold optimization to obtain target feature points.

[0012] According to a third aspect of the present invention, a computer-readable storage medium is provided, in which a computer program is stored, wherein the computer program is configured to execute the above-mentioned method for extracting characteristic points of lap grooves of curved surfaces when running.

[0013] According to a fourth aspect of the present invention, an electronic device is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for extracting feature points of a lap groove of a curved surface through the computer program.

[0014] In general, the above technical solutions conceived by the present invention can achieve the following beneficial effects compared with the prior art:

[0015] (1) The present invention provides a method for extracting feature points of lap joint grooves on curved surfaces. By using a 3D profilometer to collect the cross-sectional height information of the lap weld, and then based on noise filtering and ROI area screening, a PELT+ dynamic threshold optimization method is further proposed for groove feature point extraction. This method can effectively solve the problem of extracting feature information of lap weld grooves of various types of plates, thereby enhancing the adaptability to plates, making welding technology more automated and intelligent, saving manpower and time costs to a certain extent, simplifying the production process and improving welding production efficiency. The use of multi-dimensional interpolation methods and ROI areas effectively solves the problem of environmental and workpiece factors causing scanning data to generate noise data, and at the same time solves the problem of computational time and memory overhead caused by data redundancy in analysis.

[0016] (2) The present invention combines the PELT method and proposes a cost function based on mean mutation. In the complex trend of feature point changes, it can effectively and accurately extract multiple sets of candidate feature point sets, and has good recognition capabilities for both flat plates and curved plates. Then, dynamic threshold optimization is used to accurately locate the target point set, i.e., the groove position, from the candidate feature point set, which greatly improves the accuracy and flexibility of groove positioning and expands the application scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 A schematic flow chart of an optional method for extracting feature points of a curved surface lap groove provided in an embodiment of the present application;

[0019] Figure 2 A schematic diagram of an optional lap groove cross-section profile depth information provided in an embodiment of the present application;

[0020] Figure 3 An optional overlap groove cross-section profile noise data diagram provided in an embodiment of the present application;

[0021] Figure 4 A schematic diagram of an optional ROI area of ​​lap groove cross-section profile depth information provided in an embodiment of the present application;

[0022] Figure 5 A schematic diagram of a set of change points found by an optional PELT change point algorithm provided in an embodiment of the present application;

[0023] Figure 6 A schematic diagram of an optional local slope and dynamic threshold of a candidate change point interval provided in an embodiment of the present application;

[0024] Figure 7 A schematic diagram of an optional lap groove feature extraction result provided in an embodiment of the present application;

[0025] Figure 8 A schematic structural diagram of an optional device for extracting characteristic points of a curved surface lap groove provided in an embodiment of the present application;

[0026] Figure 9 A schematic structural diagram of an optional electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.

[0028] The terms "first," "second," "third," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements, but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0029] According to one aspect of the embodiment of the present application, a method for extracting feature points of a curved surface lap groove is provided. Figure 1 The method for extracting feature points of a curved surface lap groove provided in an embodiment of the present application is described.

[0030] Figure 1 FIG. 1 is a flow chart of an optional method for extracting characteristic points of a surface lap groove provided in an embodiment of the present application, such as Figure 1 As shown, the process of the method may include the following steps:

[0031] S102, scanning the overlapping groove using a 3D profilometer to obtain overlapping groove profile depth data;

[0032] S104, performing multi-dimensional interpolation filtering on the overlap groove profile depth data to remove noise profile data;

[0033] S106, setting ROI region segmentation to eliminate redundant data in the overlapping groove section profile depth data;

[0034] S108, using the PELT change point detection method to process the data in the ROI area and extract multiple sets of candidate feature points;

[0035] S110 , screening the multiple groups of candidate feature point sets using dynamic threshold optimization to obtain target feature points.

[0036] The present application provides a method for extracting feature points of a curved surface lap groove, which can be applied to intelligent welding scenarios, such as automobile roof and body welding.

[0037] Optionally, in the case of curved plates or overlapping plates with curvatures, to extract the characteristic information of the curved lap groove, a robot-driven 3D profilometer is used to scan the lap groove to collect data, extract the groove cross-sectional profile height information, and perform multi-dimensional interpolation filtering on the extracted cross-sectional depth profile to process data noise. Then, based on Region of Interest (ROI) segmentation, redundant data is eliminated and key areas are concentrated to improve analysis efficiency. The characteristic point extraction algorithm of the present invention is then used to calculate the groove characteristic information.

[0038] The robot drives the 3D profiler to scan the overlap groove point cloud data. Due to the large amount of point cloud data, the processing calculation will generate a large memory overhead, which greatly affects the efficiency and has the problem of high computational complexity. Therefore, during the scanning process, each frame of data scanned by the 3D profiler is scanned by the robot. Figure 2 As shown, the overlap groove profile depth information is generated.

[0039] Through the above steps S102 to S110, the lap groove profile depth data is obtained by scanning the lap groove with a 3D profilometer; the lap groove profile depth data is subjected to multi-dimensional interpolation filtering to remove noise profile data; ROI region segmentation is set to eliminate redundant data in the lap groove cross-sectional profile depth data; the data in the ROI region is processed using the pruned exact linear time change point detection method (Pruned Exact Linear Time, PELT) to extract multiple sets of candidate feature point sets; the multiple sets of candidate feature point sets are screened using dynamic threshold optimization to obtain target feature points, which effectively solves the problem of extracting feature information of lap weld grooves of various types of plates, improves the adaptability to plates, and achieves the purpose of improving welding automation and intelligence.

[0040] In an exemplary embodiment, performing multi-dimensional interpolation filtering on the overlap groove profile depth data to remove noise profile data includes:

[0041] S11, obtaining a current contour data point, traversing the contour data points, and querying whether there is noise contour data;

[0042] S12, if noise profile data exists, forward interpolating the noise profile data in the Y dimension;

[0043] S13: If the current contour is the starting contour or the current contour and the previous contour have noise points at the same position, perform linear interpolation in the X and Z dimensions on the current noise contour data.

[0044] In the embodiment of the present application, filtering is performed based on the acquired profile depth information data in order to reduce the influence of noise data on the groove feature point extraction process, such as Figure 3 As shown in Figure 3, this is the noise data encountered by the 3D profiler during the scanning process.

[0045] Exemplarily, when performing multi-dimensional interpolation, the current contour data point is first obtained, the contour data point is traversed, and it is checked whether there is noise data (ie, the Z value is less than a set value).

[0046] If there is noise data, first perform forward interpolation of the noise contour in the Y dimension, specifically recording the current noise contour data points (X0, Z0), (X1, Z1), ..., (X m ,Z m ), and obtain the data point (X0, Z0), (X1, Z1), ..., (X n ,Z n ), if the Z value of the position corresponding to the previous contour data point is not a noise point, then this value is assigned to the Z value of the current X position noise data point.

[0047] If the current contour is the starting contour (i.e., there is no previous contour) or the current contour and the previous contour have noise points at the same position, then the current noise contour is linearly interpolated in the X and Z dimensions, and the current noise contour data points (X0, Z0), (X1, Z1), ..., (X m ,Z m ), traverse these noise data points, for example (X i ,Z i ), obtain the forward and backward non-noise data points corresponding to each noise data point (X i-1 ,Z i-1 ) and (X i+1 ,Z i+1 ), then the current noise data point Z i for:

[0048]

[0049] The above steps are repeated during the extraction of contour feature information to complete the filtering of noise contours during the extraction process.

[0050] In an exemplary embodiment, the method of processing data within the ROI region using the PELT change point detection method to extract multiple sets of candidate feature point sets includes:

[0051] S21, use the PELT change point detection method to perform mutation point statistics on the data, and obtain a set of mutation point positions (t0, t1, ..., t k+1 );

[0052] S22, the minimum value of the total cost function is specifically, Where t0=0, t k+1 =n, n is the length of ROI area data, is the change point t i to t i+1 A piece of data, is the cost function, β is the penalty coefficient, and k is the number of change points.

[0053] For example, after filtering and denoising the original contour data, since the groove information of the overall contour depth occupies a small amount of data, a region of interest of appropriate size is set to facilitate positioning of the groove position, thereby reducing the interference introduced by irrelevant areas and reducing the accuracy of target analysis. At the same time, it also reduces the problems of computational time and memory overhead caused by the increase of irrelevant areas, such as Figure 4 As shown in the figure, the inner interval outline defined by the two red dotted lines is the ROI area.

[0054] Furthermore, PELT is used to perform mutation point statistics on the data. There is a set of mutation point positions t0, t1, ..., t k+1 , divide the X direction into k+1 segments so that the total cost function is minimized:

[0055]

[0056] The above t0=0, t k+1 =n (n is the length of ROI area data) is a fixed boundary; is the change point t i to t i+1 A piece of data, is the cost function, and β is the penalty coefficient.

[0057] For example, Figure 5 As shown in FIG, the PELT algorithm is used to screen out the set of candidate feature points (change points) as (t1, t2, ..., t7).

[0058] For the complex trend data in the ROI area, the PELT change point detection method is used to find multiple sets of candidate feature points. Optionally, the model is initialized first, that is, the cost function is defined Since the data trend around the feature point is flat → suddenly drop → flat, the mean mutation is selected as the cost function, which is defined as in, Secondly, the penalty coefficient β is used to control the sparsity of the number of change points k. This parameter is used to balance the number of change points to avoid overfitting and underfitting.

[0059] In an exemplary embodiment, the screening of the plurality of candidate feature point sets using dynamic threshold optimization to obtain target feature points includes:

[0060] S31, calculating the local slope set of each change point interval;

[0061] S32, determining a dynamic threshold by calculating a local slope reference value and a local standard deviation; wherein the reference value is the median of the local slopes of all change point intervals, and the local standard deviation is used to characterize the degree of fluctuation within each change point interval data.

[0062] In an embodiment of the present application, in order to extract the final feature point from the set of candidate feature points (t1, t2, ..., t7), dynamic threshold optimization can be used to screen the change points, filter out false change points, and screen out the final result, while also ensuring that the global fixed threshold cannot adapt to the fluctuation characteristics of different intervals.

[0063] In an optional example, first, the local slope set of each change point interval is calculated Secondly, the benchmark and local standard deviation are calculated to determine the dynamic threshold. It should be noted that the benchmark value is the median of the local slopes of all change point intervals, and the local standard deviation is used to obtain the degree of fluctuation within the data of each change point interval.

[0064] In an exemplary embodiment, determining the dynamic threshold by calculating the reference value and the local standard deviation includes:

[0065] S41, the dynamic threshold is expressed as dynamic_threshold=base_slope-K*local_std,

[0066] Among them, dynamic_threshold is the dynamic threshold, base_slope is the base value, local_std is the local standard deviation, and K is the sensitivity coefficient.

[0067] It should be noted that the sensitivity coefficient is usually 1.5 to 3.0, and the larger the value, the stricter the threshold.

[0068] In an exemplary embodiment, the method further comprises:

[0069] S51, if the lap joint type is left lap, identifying the change point interval in which the local slope is less than the dynamic threshold as a target change point interval, and extracting the target feature point from the target change point interval;

[0070] S52: If the overlapping groove type is right overlapping, the change point interval in which the local slope is greater than the dynamic threshold is determined as a target change point interval, and the target feature point is extracted from the target change point interval.

[0071] In this embodiment of the present application, the conditions for determining whether it is a final change point interval are:

[0072] If the overlap groove type is left overlap (the overlapped part is on the left side of the operator): the final change point interval

[0073] If the overlap groove type is right overlap (the overlapped part is on the left side of the operator): the final change point interval

[0074] For example, Figure 6 As shown, if the lap groove type described in the above steps is the left lap groove type, the final local slope is selected based on the final change point interval conditions. The conditions are met, so the change point interval is (t3:t4), that is, the final feature points (change points) are t3 and t4. Figure 7 As shown, the final result is the change point interval composed of H and L, and H and L are the final extracted feature points (i.e., the feature points of the overlap groove).

[0075] Through this embodiment, the target point set, that is, the groove position, is accurately located from the set of feature points to be selected, which greatly improves the accuracy and flexibility of groove positioning and expands the application scenarios.

[0076] According to another aspect of the embodiments of the present application, a feature point extraction device for implementing the above-mentioned method for extracting feature points of a lap joint groove of a curved surface is also provided. Figure 8 is a schematic structural diagram of an optional device for extracting characteristic points of a curved surface lap groove according to an embodiment of the present application, such as Figure 8 As shown, the device may include:

[0077] An acquiring unit 802 is configured to scan the overlap groove using a 3D profilometer to acquire the overlap groove profile depth data;

[0078] The filtering unit 804 is used to perform multi-dimensional interpolation filtering on the overlap groove profile depth data to remove noise profile data;

[0079] The segmentation unit 806 is used to set ROI area segmentation to eliminate redundant data in the overlap groove section profile depth data;

[0080] An extraction unit 808 is used to process the data in the ROI region using the PELT change point detection method to extract multiple sets of candidate feature points;

[0081] The screening unit 810 is configured to screen the plurality of candidate feature point sets using dynamic threshold optimization to obtain target feature points.

[0082] It should be noted that the acquisition unit 802 in this embodiment can be used to execute the above-mentioned step S102, the filtering unit 804 in this embodiment can be used to execute the above-mentioned step S104, the segmentation unit 806 in this embodiment can be used to execute the above-mentioned step S106, the extraction unit 808 in this embodiment can be used to execute the above-mentioned step S108, and the screening unit 810 in this embodiment can be used to execute the above-mentioned step S110.

[0083] Through the above module, the lap groove profile depth data is obtained by scanning the lap groove with a 3D profilometer; the lap groove profile depth data is subjected to multi-dimensional interpolation filtering to remove noise profile data; ROI region segmentation is set to eliminate redundant data in the lap groove section profile depth data; the data in the ROI region is processed using the PELT change point detection method to extract multiple sets of candidate feature point sets; the multiple sets of candidate feature point sets are screened using dynamic threshold optimization to obtain target feature points, which effectively solves the problem of extracting feature information of lap weld grooves of various types of plates, improves the adaptability to plates, and achieves the purpose of improving welding automation and intelligence.

[0084] In an exemplary embodiment, the filtering unit includes: a first acquisition module, used to obtain the current contour data point, traverse the contour data point, and query whether there is noise contour data; a first interpolation module, used to perform forward interpolation of the noise contour data in the Y dimension if there is noise contour data; a second interpolation module, used to perform linear interpolation of the current noise contour data in the X and Z dimensions if the current contour is the starting contour or the current contour and the previous round of contours have noise points at the same position.

[0085] In one exemplary embodiment, the extraction unit includes: a change point detection module for performing mutation point statistics on the data using the PELT change point detection method to obtain a set of mutation point positions (t0, t1, ..., t k+1 ); The minimum value of the total cost function is specifically, Where t0=0, t k+1 =n, n is the length of ROI area data, is the change point t i to t i+1 A piece of data, is the cost function, β is the penalty coefficient, and k is the number of change points.

[0086] In an exemplary embodiment, the screening unit includes: a calculation module for calculating the local slope set of each change point interval; a determination module for determining the dynamic threshold by calculating the local slope baseline value and the local standard deviation; wherein the baseline value is the median of the local slopes of all change point intervals, and the local standard deviation is used to characterize the degree of fluctuation within the data of each change point interval.

[0087] In an exemplary embodiment, the determination module includes: a dynamic threshold submodule, and the dynamic threshold is expressed as dynamic_threshold=base_slope-K*local_std, where dynamic_threshold is the dynamic threshold, base_slope is the reference value, local_std is the local standard deviation, and K is the sensitivity coefficient.

[0088] In an exemplary embodiment, the device also includes: a first determination unit, which is used to confirm the change point interval in which the local slope is less than the dynamic threshold as a target change point interval if the lap groove type is a left lap, and extract the target feature point from the target change point interval; a second confirmation unit, which is used to confirm the change point interval in which the local slope is greater than the dynamic threshold as a target change point interval if the lap groove type is a right lap, and extract the target feature point from the target change point interval.

[0089] It should be noted here that the examples and scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the contents disclosed in the above embodiments. It should be noted that the above modules as part of the device can run in a hardware environment, can be implemented by software, and can also be implemented by hardware, where the hardware environment includes a network environment.

[0090] According to another aspect of the embodiments of the present application, a storage medium is further provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the above-mentioned methods for extracting feature points of a curved surface lap groove in the embodiments of the present application.

[0091] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the following steps:

[0092] S1, using a 3D profilometer to scan the lap groove to obtain the profile depth data of the lap groove;

[0093] S2, performing multi-dimensional interpolation filtering on the overlap groove profile depth data to remove noise profile data;

[0094] S3, setting ROI region segmentation to eliminate redundant data in the overlapping groove section profile depth data;

[0095] S4, using the PELT change point detection method to process the data in the ROI area and extract multiple sets of candidate feature points;

[0096] S5, screening the multiple groups of candidate feature point sets using dynamic threshold optimization to obtain target feature points.

[0097] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, which will not be described in detail in this embodiment.

[0098] Among them, computer-readable storage media may include, but are not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives and magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0099] According to another aspect of the embodiments of the present application, an electronic device for implementing the above-mentioned method for extracting feature points of lap grooves of curved surfaces is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0100] Figure 9 is a schematic structural diagram of an optional electronic device according to an embodiment of the present application, such as Figure 9 As shown, it includes a processor 902, a communication interface 904, a memory 906 and a communication bus 908, wherein the processor 902, the communication interface 904, and the memory 906 communicate with each other via the communication bus 908, wherein,

[0101] Memory 906, for storing computer programs;

[0102] The processor 902 is configured to execute the computer program stored in the memory 906 to implement the following steps:

[0103] S1, using a 3D profilometer to scan the lap groove to obtain the profile depth data of the lap groove;

[0104] S2, performing multi-dimensional interpolation filtering on the overlap groove profile depth data to remove noise profile data;

[0105] S3, setting ROI region segmentation to eliminate redundant data in the overlapping groove section profile depth data;

[0106] S4, using the PELT change point detection method to process the data in the ROI area and extract multiple sets of candidate feature points;

[0107] S5, screening the multiple groups of candidate feature point sets using dynamic threshold optimization to obtain target feature points.

[0108] Optionally, the communication bus may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The communication bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 9 The communication interface is used for communication between the electronic device and other devices.

[0109] The memory may include RAM, or may include non-volatile memory, such as at least one disk memory. Alternatively, the memory may also be at least one storage device located away from the aforementioned processor.

[0110] As an example, the memory 906 may include, but is not limited to, the acquisition unit 802, filtering unit 804, segmentation unit 806, extraction unit 808, and screening unit 810 in the device for extracting feature points of overlapping grooves on curved surfaces. Furthermore, the memory 906 may also include, but is not limited to, other module units in the device for extracting feature points of overlapping grooves on curved surfaces, which will not be described in detail in this example.

[0111] The above-mentioned processor can be a general-purpose processor, which can include but is not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; it can also be DSP (Digital Signal Processing), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0112] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments, and this embodiment will not be described in detail here.

[0113] It should be noted that for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by this application.

[0114] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of the device or unit can be electrical or other forms.

[0116] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0117] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0118] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0119] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0120] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the specification and practicing the disclosure herein, those skilled in the art will easily think of the implementation scheme of the present disclosure. This application is intended to cover any variation, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary technical means in the art that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

[0121] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above 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.

[0122] It will be easily understood by those skilled in the art that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for extracting characteristic points of a surface lap groove, characterized in that: include: Use a 3D profilometer to scan the overlap groove to obtain the overlap groove profile depth data; Performing multi-dimensional interpolation filtering on the overlap groove profile depth data to remove noise profile data; Setting ROI area segmentation to eliminate redundant data in the overlapping groove section profile depth data; The PELT change point detection method is used to process the data in the ROI area and extract multiple sets of candidate feature points; The multiple groups of candidate feature point sets are screened using dynamic threshold optimization to obtain target feature points.

2. The method for extracting characteristic points of a curved surface lap groove according to claim 1, wherein: The performing of multi-dimensional interpolation filtering on the overlap groove profile depth data to remove noise profile data comprises: Obtain the current contour data point, traverse the contour data points, and query whether there is noise contour data; If there is noise profile data, forward interpolation is performed on the noise profile data in the Y dimension; If the current contour is the starting contour or the current contour and the previous contour have noise points at the same position, perform linear interpolation in the X and Z dimensions on the current noise contour data.

3. The method for extracting characteristic points of a curved surface lap groove according to claim 1, wherein: The PELT change point detection method is used to process the data in the ROI area and extract multiple sets of feature points to be selected, including: The PELT change point detection method is used to perform mutation point statistics on the data and obtain a set of mutation point positions (t0, t1, ..., t k+1 ); The minimum value of the total cost function is specifically, Where t0=0, t k+1 =n, n is the length of ROI area data, is the change point t i to t i+1 A piece of data, is the cost function, β is the penalty coefficient, and k is the number of change points.

4. The method for extracting characteristic points of a curved surface lap groove according to claim 1, wherein: The method of using dynamic threshold optimization to screen the multiple sets of candidate feature points to obtain target feature points includes: Calculate the local slope set of each change point interval; The dynamic threshold is determined by calculating the local slope reference value and the local standard deviation; wherein the reference value is the median of the local slopes of all change point intervals, and the local standard deviation is used to characterize the degree of fluctuation within each change point interval data.

5. The method for extracting characteristic points of a curved surface lap groove according to claim 4, wherein: Determining the dynamic threshold by calculating the reference value and the local standard deviation includes: The dynamic threshold is expressed as dynamic_threshold=base_slope-K*local_std, wherein dynamic_threshold is the dynamic threshold, base_slope is the reference value, local_std is the local standard deviation, and K is the sensitivity coefficient.

6. The method for extracting characteristic points of a curved surface lap groove according to claim 4, wherein: The method further comprises: If the lap joint type is left lap, identifying the change point interval in which the local slope is less than the dynamic threshold as a target change point interval, and extracting the target feature point from the target change point interval; If the lap groove type is right lap, the change point interval in which the local slope is greater than the dynamic threshold is determined as a target change point interval, and the target feature point is extracted from the target change point interval.

7. A device for extracting characteristic points of a curved surface lap groove, characterized in that: include: An acquisition unit is used for scanning the overlap groove using a 3D profiler to acquire the overlap groove profile depth data; A filtering unit, configured to perform multi-dimensional interpolation filtering on the overlap groove profile depth data to remove noise profile data; A segmentation unit, used for setting ROI area segmentation to eliminate redundant data in the overlap groove section profile depth data; An extraction unit is used to process the data in the ROI area using the PELT change point detection method to extract multiple sets of feature points to be selected; The screening unit is used to screen the multiple groups of candidate feature point sets using dynamic threshold optimization to obtain target feature points.

8. The device for extracting characteristic points of a curved surface lap groove according to claim 7, wherein: The filtering unit comprises: A first acquisition module is used to acquire current contour data points, traverse the contour data points, and query whether there is noise contour data; A first interpolation module is configured to perform forward interpolation in the Y dimension on the noise profile data if noise profile data exists; The second interpolation module is used to perform linear interpolation in the X and Z dimensions on the current noise contour data if the current contour is the starting contour or the current contour and the previous contour have noise points at the same position.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method according to any one of claims 1 to 6 when executed.

10. 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 execute the method according to any one of claims 1 to 6 through the computer program.

Images