Feature extraction method for three-dimensional measurement, three-dimensional measurement method and tracking device

Abstract

The present application relates to a feature extraction method for three-dimensional measurement, a three-dimensional measurement method and a tracking device, wherein the feature extraction method for three-dimensional measurement includes: obtaining feature data in the historical frame tracking data obtained by tracking the device to be tracked; determining the region of interest in the current frame tracking data according to the position of the feature data in the historical frame tracking data; the historical frame is a data frame collected before the current frame and separated by a preset number of frames from the current frame; collecting the tracking data in the region of interest as target tracking data, and extracting the target feature data corresponding to the current frame tracking data from the target tracking data. It can extract feature extraction efficiency, improve the fluency of tracking data processing and tracking efficiency, and thus improve the accuracy of three-dimensional measurement.

Description

Technical Field

[0001] The present application relates to the field of three-dimensional measurement, and in particular to a feature extraction method, a three-dimensional measurement method and a tracking device for three-dimensional measurement. Background Art

[0002] Existing three-dimensional measurement systems usually measure the measurement object through measuring devices such as scanners and light pens. During this process, the measuring device is tracked based on the tracking device. After that, the computing device calculates the final three-dimensional measurement result of the measurement object based on the measurement data of the measuring device and the tracking data of the tracking device.

[0003] At present, in order to improve the tracking effect of tracking equipment on measuring equipment, tracking equipment begins to use high-resolution cameras to realize image acquisition of measuring equipment. Since the data processing module inside the tracking device cannot process the data collected by the high-resolution camera at a high frame rate, the tracking data processing is not smooth enough, the tracking efficiency is reduced, and the three-dimensional measurement accuracy is affected.

[0004] Currently, no effective solution has been proposed to address the problem of low three-dimensional measurement accuracy in related technologies. Summary of the invention

[0005] In this embodiment, a feature extraction method for three-dimensional measurement, a three-dimensional measurement method and a tracking device are provided to solve the problem of low three-dimensional measurement accuracy in related technologies.

[0006] In a first aspect, a feature extraction method for three-dimensional measurement is provided in this embodiment, comprising:

[0007] Acquire feature data in historical frame tracking data obtained by tracking the device to be tracked;

[0008] Determine the region of interest in the current frame tracking data according to the feature data position in the historical frame tracking data; the historical frame is a data frame collected before the current frame and separated from the current frame by a preset number of frames;

[0009] The tracking data in the region of interest is collected as target tracking data, and target feature data corresponding to the current frame tracking data is extracted from the target tracking data.

[0010] In some of the embodiments, determining the region of interest in the current frame tracking data according to the feature data position in the historical frame tracking data includes:

[0011] Determining a graphic region containing all the feature data according to the position distribution of each feature data in the historical frame tracking data;

[0012] According to the graphic area, a region of interest in the current frame tracking data is determined.

[0013] In some embodiments, if the current frame tracking data is the first frame tracking data, the method further includes:

[0014] According to the pre-calibrated feature data structure, the corresponding feature data is matched from the first frame tracking data as the target feature data.

[0015] In some embodiments, the method further comprises:

[0016] If the feature data of the device to be tracked exists in the current frame tracking data, the region of interest of the next frame tracking data is determined according to the position of the feature data in the current frame tracking data.

[0017] In some embodiments, if the feature data of the device to be tracked does not exist in the current frame tracking data, the method further includes:

[0018] The entire area of ​​the current frame tracking data is used as the feature data extraction area of ​​the next frame tracking data.

[0019] In some embodiments, the method further comprises:

[0020] The feature data extracted from each frame of the tracking data is transmitted to an associated computing device.

[0021] In a second aspect, a three-dimensional measurement method is provided in this embodiment, and the method includes:

[0022] Acquire measurement data obtained by performing three-dimensional measurement of the object to be tracked by the device to be tracked;

[0023] Acquire feature data obtained by the tracking device executing the feature extraction method described in the first aspect above;

[0024] A three-dimensional measurement result of the measured object is obtained according to the measurement data and the characteristic data.

[0025] In a third aspect, a tracking device is provided in this embodiment, including: an image sensor and a data processing module; wherein:

[0026] The image sensor is used to track the device to be tracked and obtain tracking data;

[0027] The data processing module is used to execute the feature extraction method of three-dimensional measurement described in the first aspect above.

[0028] In a fourth aspect, a three-dimensional measurement system is provided in this embodiment, comprising: a device to be tracked, a computing device, and the tracking device described in the third aspect;

[0029] The device to be tracked is used to perform three-dimensional measurement on the measurement object to obtain measurement data;

[0030] The tracking device is used to track the device to be tracked to obtain tracking data;

[0031] The computing device is used to execute the three-dimensional measurement method described in the second aspect above.

[0032] Compared with the related art, the present embodiment provides a feature extraction method, a three-dimensional measurement method and a tracking device for three-dimensional measurement. The feature extraction method for three-dimensional measurement obtains feature data in the historical frame tracking data obtained by tracking the device to be tracked; determines the region of interest in the current frame tracking data according to the position of the feature data in the historical frame tracking data; the historical frame is a data frame collected before the current frame and separated by a preset number of frames from the current frame; collects the tracking data in the region of interest as target tracking data, and outputs the target tracking data. It can only transmit the local area where the feature data is located for feature extraction, thereby improving the feature extraction efficiency, improving the fluency of tracking data processing and tracking efficiency, and thus improving the accuracy of three-dimensional measurement.

[0033] 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

[0034] 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:

[0035] Figure 1 is a hardware structure block diagram of a terminal of the feature extraction method for three-dimensional measurement of this embodiment;

[0036] Figure 2 is a flow chart of the feature extraction method for three-dimensional measurement of this embodiment;

[0037] Figure 3 is a flow chart of a feature extraction method for three-dimensional measurement of some embodiments;

[0038] Figure 4 is a flow chart of the three-dimensional measurement method of this embodiment;

[0039] Figure 5 is a schematic diagram of the structure of the tracking device of this embodiment;

[0040] Figure 6 Schematic diagram of the structure of the three-dimensional measurement system of this embodiment. DETAILED DESCRIPTION

[0041] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0042] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (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 directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0043] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 FIG. 4 is a hardware structure diagram of a terminal of the feature extraction method for three-dimensional measurement of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1More or fewer components as shown, or with Figure 1 Different configurations shown.

[0044] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the feature extraction method of three-dimensional measurement in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0045] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0046] In this embodiment, a feature extraction method for three-dimensional measurement is provided. Figure 2 is a flow chart of the feature extraction method for three-dimensional measurement of this embodiment. Figure 2 As shown, the process includes the following steps:

[0047] Step S210 , acquiring feature data in historical frame tracking data obtained by tracking the device to be tracked.

[0048] Specifically, in a tracking-type three-dimensional measurement scenario, a tracking device and a measuring device are included, and marking points can be set on the surface of the measuring device. Among them, the tracking device is used to track the position and posture of the measuring device in real time; the measuring device is used to capture the surface information of the object to be measured. The device to be tracked can be a measuring device tracked by the tracked device in a tracking-type three-dimensional scanning scenario. Exemplarily, the device to be tracked can be a scanner, a light pen, etc. The historical frame tracking data can be the tracking data obtained by the tracking device tracking the device to be tracked. The tracking data can specifically be the image data collected by the left camera and the right camera of the tracking device, which contain the marking points set on the surface of the device to be tracked. That is, the above-mentioned feature data can be the marking point data set on the surface of the device to be tracked identified from the tracking data.

[0049] Step S220, determining the region of interest in the current frame tracking data according to the feature data position in the historical frame tracking data; the historical frame is a data frame collected before the current frame and separated from the current frame by a preset number of frames.

[0050] In this step, considering that when the camera frame rate increases, the distance that the device to be tracked moves in adjacent frames at a higher frame rate is relatively small, therefore, reflected in the tracking data of adjacent frames, the positions of the feature data corresponding to the tracking data of adjacent frames are relatively close. Based on this, the range of the feature data in the current frame tracking data can be determined by the position of the feature data in the historical frame tracking data, thereby obtaining the region of interest.

[0051] Among them, the region of interest in the current frame tracking data can be determined by the position of the feature data in the previous frame, the previous two frames, or a historical frame separated by other preset frames adjacent to the current frame. The region of interest in the current frame tracking data can also be jointly determined by statistically analyzing the positions of the feature data in multiple consecutive frames of historical frame tracking data. The specific number of frames between the historical frame tracking data and the current frame tracking data can be determined by factors such as the speed of movement of the device to be tracked and the frame rate of the image collected by the tracking device in the actual application scenario. In particular, in order to improve the accuracy of the extracted feature data, the previous frame tracking data of the current frame tracking data can be selected as the historical frame tracking data for determining the region of interest.

[0052] Next, take the light pen as an example to explain that after the tracking device collects the current frame tracking data for the light pen, the region of interest in the current frame tracking data is set according to the position of the mark point set on the surface of the light pen in the previous frame tracking data for the light pen, that is, the position of the feature data. The region of interest in the current frame tracking data is set according to the position of the feature data in the historical frame tracking data, and then the region of interest is used as the range for searching the feature data.

[0053] Step S230 , collecting tracking data in the region of interest as target tracking data, and extracting target feature data corresponding to the current frame tracking data from the target tracking data.

[0054] That is, after determining the region of interest in the current frame tracking data, only the tracking data in the region of interest is sampled as target tracking data, and feature data representing the surface marker points of the device to be tracked is extracted from the target tracking data.

[0055] Taking the light pen as an example, the specific extraction process is explained: the position of the marker point on the surface of the light pen can be calibrated before leaving the factory. After that, the 3D coordinates of the marker point are calculated by using the 2D graphics captured by the left and right cameras of the tracking device in the historical frame tracking data. By matching with the position of the pre-calibrated marker point, the marker points that do not belong to the light pen can be filtered out, and then the position of the marker point in the historical frame tracking data can be determined; then, the region of interest in the current frame tracking data can be determined based on it.

[0056] By sampling only the tracking data in the region of interest, the search range for the feature data of the current frame is reduced, and the size of the tracking data to be transmitted is reduced. Since the bus bandwidth of the internal image sensor of the tracking device output to the field programmable gate array (FPGA) of the tracking device is fixed, if the region of interest is set, the image sensor only outputs the data in the given region of interest to the FPGA for feature data extraction, then the amount of data transmitted will be smaller, and the number of frames transmitted from the image sensor to the FPGA per unit time will increase when the bandwidth remains unchanged, and the transmission frame rate can be improved. Therefore, under the condition that the bandwidth remains unchanged, more frames of feature data can be transmitted to the FPGA of the tracking device through the image sensor of the tracking device, thereby improving the frame rate of the feature data cutout, and further improving the smoothness of the light pen; in addition, in the light pen use scenario, for a measurement of the object to be measured by the device to be tracked, more tracked feature data can be transmitted to the lower device, so that the light pen posture can be determined based on more frames of feature data, and the accuracy of the posture calculation to be tracked can be improved, so the accuracy of the final measurement result can also be improved.

[0057] Through the above steps S210 to S230, the feature data in the historical frame tracking data obtained by tracking the device to be tracked is obtained; according to the position of the feature data in the historical frame tracking data, the region of interest in the current frame tracking data is determined; the historical frame is a data frame collected before the current frame and separated by a preset number of frames from the current frame; the tracking data in the region of interest is collected as the target tracking data, and the target feature data corresponding to the current frame tracking data is extracted from the target tracking data. It can improve the efficiency of feature extraction, improve the fluency of tracking data processing and tracking efficiency, thereby improving the accuracy of three-dimensional measurement.

[0058] In one embodiment, determining the region of interest in the current frame tracking data according to the feature data position in the historical frame tracking data may specifically include:

[0059] According to the position distribution of each feature data in the historical frame tracking data, a graphic area containing all feature data is determined; according to the graphic area, an area of ​​interest in the current frame tracking data is determined.

[0060] Among them, the graphic area can be the minimum rectangle that can frame all feature data in the historical frame tracking data, or other geometric figures, determined based on the feature data identified in the historical frame tracking data. On the basis of the graphic area, a number of pixels are expanded outward to form a region of interest. For example, in the previous frame tracking data, based on the position distribution of each marker point, the minimum rectangle that can frame all marker points is determined, and the minimum rectangle is expanded outward by a number of pixels from the top, bottom, left and right directions to form the region of interest of the current frame tracking data. Alternatively, the positions of all marker points in the previous frame tracking data are determined as the graphic area, and the adjacent rows of all marker points are determined as the region of interest.

[0061] By determining the graphic area containing all feature data according to the position distribution of each feature data in the historical frame tracking data, and then determining the region of interest, the accuracy of the region of interest division can be improved.

[0062] Additionally, in one embodiment, if the current frame tracking data is the first frame tracking data, the feature extraction method may further include:

[0063] According to the pre-calibrated feature data structure, the corresponding feature data is matched from the first frame tracking data as the target feature data.

[0064] Specifically, the feature data structure of the device to be tracked can be calibrated in advance. After the tracking data is first acquired, the corresponding feature data is matched from the first frame tracking data according to the calibrated feature data structure in advance, thereby determining the position of the feature data in the first frame tracking data.

[0065] Additionally, in one embodiment, the feature extraction method may further include:

[0066] If the feature data of the device to be tracked exists in the current frame tracking data, the region of interest of the next frame tracking data is determined according to the position of the feature data in the current frame tracking data.

[0067] After determining the region of interest, in order to improve the recognition accuracy of the feature data, it is necessary to determine whether there is feature data of the device to be tracked in the region of interest. Specifically, according to the feature data structure of the feature data of the device to be tracked that has been pre-calibrated, matching can be performed in the region of interest to determine whether there is feature data of the device to be tracked. If there is, the corresponding feature data is extracted as the target feature data corresponding to the current frame tracking data. In this way, the accuracy of feature data recognition can be improved and misrecognition of feature data can be avoided.

[0068] In addition, after completing the extraction of feature data in the current frame tracking data, the area of ​​interest of the next frame tracking data can be determined based on the position of the feature data in the current frame tracking data, so as to determine the corresponding feature data from the area of ​​interest of the next frame tracking data until the tracking device completes tracking of the device to be tracked.

[0069] Additionally, in one embodiment, if the feature data of the device to be tracked does not exist in the current frame tracking data, the feature extraction method may further include:

[0070] The entire area of ​​the current frame tracking data is used as the feature data extraction area of ​​the next frame tracking data. That is, if no feature data is extracted from the current frame tracking data, the entire area of ​​the current frame tracking data is used as the feature data extraction area of ​​the next frame tracking data.

[0071] In addition, in one embodiment, the feature extraction method may further include: transmitting the feature data extracted from each frame of tracking data to an associated computing device. The associated computing device may be a lower device that is communicatively connected to the tracking device. The tracking device transmits the extracted feature data to the computing device, and the computing device calculates the posture of the device to be tracked based on the feature data, and then determines the three-dimensional measurement result of the measured object based on the posture of the device to be tracked and the measurement data collected by the device to be tracked.

[0072] Figure 3 is a flow chart of a feature extraction method for three-dimensional measurement in some embodiments, such as Figure 3 As shown, the feature extraction method of the three-dimensional measurement may include:

[0073] Step S301, start the feature extraction function of the device to be tracked.

[0074] Step S302: Acquire current frame tracking data obtained by tracking the device to be tracked.

[0075] Step S303, traverse the current frame tracking data to determine whether there is feature data in the current frame tracking data; if so, execute step S304; otherwise, execute step S305.

[0076] Step S304, according to the position of the feature data in the current frame tracking data, determine the region of interest to be set in the next frame tracking data; wherein, determine the minimum rectangle that can contain all the feature data in the current frame tracking data, expand the minimum region by n pixels from the x-axis and m pixels from the y-axis, and obtain the region of interest corresponding to the next frame tracking data. The x-axis and y-axis correspond to the horizontal and vertical length directions of the minimum rectangle, and n and m are both positive integers.

[0077] Step S305, cancel setting of the next frame region of interest.

[0078] This embodiment also provides a three-dimensional measurement method. Figure 4 is a flow chart of the three-dimensional measurement method of this embodiment. Figure 4 As shown, the process includes the following steps:

[0079] Step S401, obtaining measurement data obtained by performing three-dimensional measurement on the object to be tracked by the device to be tracked. The device to be tracked may be any device that can perform three-dimensional measurement on the object to be tracked, such as a three-dimensional scanner or a light pen. During the three-dimensional measurement process, the device to be tracked collects measurement data on the object to be tracked while moving, so as to obtain measurement data that characterizes the three-dimensional spatial features of the surface of the object to be tracked.

[0080] Step S402, obtaining feature data obtained by the tracking device executing the feature extraction method provided in the above embodiment. During the process of the device to be tracked performing three-dimensional measurement, the tracking device continuously tracks the device to be tracked, and dynamically sets the position of the region of interest in each frame of tracking data by executing the feature extraction method provided in the above embodiment, thereby realizing the extraction of feature data in the region of interest.

[0081] Step S403, obtaining a three-dimensional measurement result of the measured object according to the measurement data and the feature data. The tracking device transmits the feature data extracted from each frame to the associated computing device. The device to be tracked transmits the collected measurement data to the associated computing device. The computing device calculates the posture of the device to be tracked according to the feature data of multiple frames, and calculates the three-dimensional measurement result of the measured object in combination with the measurement data provided by the device to be tracked. For example, when the device to be tracked is a light pen, the computing device obtains the dot data obtained by the light pen when dotting the measured object, and combines the dot data of the light pen at different positions on the measured object in combination with the light pen posture obtained based on the feature data, to obtain the overall dot result of the measured object, thereby obtaining the final three-dimensional measurement result. When the device to be tracked is a scanner, the computing device obtains the scan data obtained by the scanner when scanning the measured object at different positions, and combines the scan data corresponding to different positions in combination with the scanner posture obtained based on the feature data, thereby obtaining the overall scan data of the measured object, thereby obtaining the final three-dimensional measurement result.

[0082] Through the above steps S401 to S403, the feature extraction efficiency can be improved, the fluency of tracking data processing and the tracking efficiency can be improved, thereby improving the accuracy of three-dimensional measurement.

[0083] In this embodiment, a tracking device is also provided. Figure 5 FIG. 5 is a schematic diagram of the structure of the tracking device 50 of this embodiment. Figure 5 As shown, the tracking device 50 includes: an image sensor 52 and a data processing module 54; wherein:

[0084] The image sensor 52 is used to track the device to be tracked and obtain tracking data; the data processing module 54 is used to execute the feature extraction method of three-dimensional measurement provided in any of the above embodiments. In particular, in some of the embodiments, the data processing module 54 can be a built-in FPGA of the tracking device 50.

[0085] In addition, a three-dimensional measurement system is also provided in this embodiment. Figure 6 is a schematic diagram of the structure of the three-dimensional measurement system 60 of this embodiment, as shown in Figure 6 As shown, the three-dimensional measurement system 60 includes: a device to be tracked 62, a computing device 64, and the tracking device 50 provided in the above embodiment;

[0086] The device to be tracked 62 is used to perform three-dimensional measurement on the measured object to obtain measurement data; the tracking device 50 is used to track the device to be tracked to obtain tracking data; and the computing device 64 is used to execute the three-dimensional measurement method provided in the above embodiment.

[0087] 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 will not be repeated in this embodiment.

[0088] In addition, in combination with the feature extraction method for three-dimensional measurement provided in the above embodiments, a storage medium may be provided in this embodiment to implement the feature extraction method for three-dimensional measurement. The storage medium stores a computer program; when the computer program is executed by a processor, any feature extraction method for three-dimensional measurement in the above embodiments is implemented.

[0089] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0090] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0091] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0092] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0093] 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 patent protection. 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 scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A feature extraction method for three-dimensional measurement, characterized in that: include: Acquire feature data in historical frame tracking data obtained by tracking the device to be tracked; Determine the region of interest in the current frame tracking data according to the feature data position in the historical frame tracking data; the historical frame is a data frame collected before the current frame and separated from the current frame by a preset number of frames; The tracking data in the region of interest is collected as target tracking data, and target feature data corresponding to the current frame tracking data is extracted from the target tracking data.

2. The feature extraction method according to claim 1, characterized in that: Determining the region of interest in the current frame tracking data according to the feature data position in the historical frame tracking data includes: Determining a graphic region containing all the feature data according to the position distribution of each feature data in the historical frame tracking data; According to the graphic area, a region of interest in the current frame tracking data is determined.

3. The feature extraction method according to claim 1, characterized in that: If the current frame tracking data is the first frame tracking data, the method further includes: According to the pre-calibrated feature data structure, the corresponding feature data is matched from the first frame tracking data as the target feature data.

4. The feature extraction method according to claim 1, characterized in that: The method further comprises If the feature data of the device to be tracked exists in the current frame tracking data, the region of interest of the next frame tracking data is determined according to the position of the feature data in the current frame tracking data.

5. The feature extraction method according to claim 4, characterized in that: If the feature data of the device to be tracked does not exist in the current frame tracking data, the method further includes: The entire area of ​​the current frame tracking data is used as the feature data extraction area of ​​the next frame tracking data.

6. The feature extraction method according to any one of claims 1 to 5, characterized in that: The method further comprises: The feature data extracted from each frame of the tracking data is transmitted to an associated computing device.

7. A three-dimensional measurement method, characterized in that: The method comprises: Acquire measurement data obtained by performing three-dimensional measurement of the object to be tracked by the device to be tracked; Acquire feature data obtained by executing the feature extraction method according to any one of claims 1 to 6 by the tracking device; A three-dimensional measurement result of the measured object is obtained according to the measurement data and the characteristic data.

8. A tracking device, characterized in that: include: Image sensor and data processing module; wherein: The image sensor is used to track the device to be tracked and obtain tracking data; The data processing module is used to execute the feature extraction method for three-dimensional measurement according to any one of claims 1 to 6.

9. A three-dimensional measurement system, characterized in that: include: A device to be tracked, a computing device, and the tracking device according to claim 8; The device to be tracked is used to perform three-dimensional measurement on the measurement object to obtain measurement data; The tracking device is used to track the device to be tracked to obtain tracking data; The computing device is used to execute the three-dimensional measurement method described in claim 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the feature extraction method for three-dimensional measurement according to any one of claims 1 to 6 are implemented.

Images