Key point marking method and related equipment

By selecting matching targets on an image and using key points from a template image for annotation, the inefficiency of existing technologies is solved, achieving more efficient key point annotation.

CN112633305BActive Publication Date: 2024-11-19SHENZHEN INTELLIFUSION TECHNOLOGIES CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN201910906487.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2019-09-24
Publication Date
2024-11-19
Estimated Expiration
2039-09-24

AI Technical Summary

Technical Problem

The existing key point annotation method is inefficient, requiring annotators to annotate each point individually, which is time-consuming.

Method used

By selecting a first image and a first template image, matching targets are selected and labeled according to key points in the template image, reducing manual intervention.

Benefits of technology

It improves the efficiency of key point annotation and reduces the time cost of manual intervention.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN112633305B_ABST
    Figure CN112633305B_ABST
Patent Text Reader

Abstract

The present application discloses a key point labeling method, which is applied to electronic devices, and the method includes: selecting a first image including N first targets, where N is a positive integer; selecting a first template image, where the first template image includes K first key points, where K is a positive integer; selecting one of the N first targets on the first image, where the type of the one of the first targets matches the type of the first template image; and labeling the one of the first targets with key points according to the K first key points. The efficiency of key point labeling can be improved by using the embodiments of the present application.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a key point marking method and related equipment. Background Art

[0002] Key point annotation is the process of annotators finding key points in an image according to the requirements of algorithm personnel, and recording and storing their coordinates to train AI models with image feature recognition capabilities. The key point annotation methods currently used are mainly sequential annotation and index annotation. Both of these methods require annotators to annotate key points one by one, which is inefficient. Summary of the invention

[0003] The embodiments of the present application provide a key point labeling method and related devices for improving the efficiency of key point labeling.

[0004] In a first aspect, an embodiment of the present application provides a key point labeling method, which is applied to an electronic device, and the method includes:

[0005] Selecting a first image including N first targets, where N is a positive integer;

[0006] Selecting a first template image, where the first template image includes K first key points of the second target, where K is a positive integer;

[0007] Selecting one of the N first objects on the first image, wherein a type of the one of the first objects matches a type of the second object;

[0008] Key point marking is performed on one of the first targets according to the K first key points.

[0009] In a second aspect, an embodiment of the present application provides a key point marking device, which is applied to an electronic device, and the device includes:

[0010] A first selection unit, configured to select a first image including N first objects, where N is a positive integer;

[0011] A second selection unit is used to select a first template image, where the first template image includes K first key points of the second target, where K is a positive integer;

[0012] a frame selection unit, configured to frame one of the N first objects on the first image, wherein a type of the one of the first objects matches a type of the second object;

[0013] A labeling unit is used to label one of the first targets with key points according to the K first key points.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, comprising a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the steps in the method described in the first aspect of the embodiment of the present application.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps described in the method described in the first aspect of the embodiment of the present application.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute part or all of the steps described in the method described in the first aspect of the embodiment of the present application.

[0017] It can be seen that in the embodiment of the present application, the first image and the first template image are first selected, and then one of the first targets is framed on the first image according to the first template image, and finally, key points of one of the first targets are marked according to multiple first key points in the key point template, which can reduce the time required for manual participation in key point marking and improve the efficiency of key point marking.

[0018] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative work.

[0020] Figure 1 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0021] Figure 2 It is a flowchart of a key point marking method provided in an embodiment of the present application;

[0022] Figure 3 It is a flowchart of another key point marking method provided in an embodiment of the present application;

[0023] Figure 4A schematic diagram of the structure of an electronic device provided in an embodiment of the present application;

[0024] Figure 5 A schematic structural diagram of a first target tracking device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0026] The following are detailed descriptions of each.

[0027] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present application and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0028] Reference to "embodiments" herein 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 skilled in the art that the embodiments described herein may be combined with other embodiments.

[0029] Below, some terms in this application are explained to facilitate understanding by those skilled in the art.

[0030] Electronic devices may include various handheld devices, vehicle-mounted devices, wearable devices, computing devices or other processing devices connected to a wireless modem with wireless communication functions, as well as various forms of user equipment (UE), mobile stations (MS), terminal devices, etc.

[0031] like Figure 1 As shown, Figure 11 is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device includes a processor, a memory, a display screen, a random access memory (RAM), and a camera. The memory, the display screen, the RAM, and the camera are all connected to the processor.

[0032] Furthermore, the electronic device also includes a signal communication interface, a signal processor, a speaker, a microphone and a sensor. The signal processor, the speaker, the microphone and the sensor are all connected to the processor, and the communication interface is connected to the signal processor.

[0033] The display screen may be a liquid crystal display (LCD), an organic or inorganic light-emitting diode (OLED), an active matrix organic light-emitting diode panel (AMOLED), etc.

[0034] The camera may be a common camera or an infrared camera, which is not limited here. The camera may be a front camera or a rear camera, which is not limited here.

[0035] Among them, the sensor includes at least one of the following: a light sensor, a gyroscope, an infrared proximity sensor, a fingerprint sensor, a pressure sensor, and the like. Among them, the light sensor, also known as an ambient light sensor, is used to detect the brightness of ambient light. The light sensor may include a photosensitive element and an analog-to-digital converter. Among them, the photosensitive element is used to convert the collected light signal into an electrical signal, and the analog-to-digital converter is used to convert the above electrical signal into a digital signal. Optionally, the light sensor may also include a signal amplifier, which may amplify the electrical signal converted by the photosensitive element and output it to the analog-to-digital converter. The above-mentioned photosensitive element may include at least one of a photodiode, a phototransistor, a photoresistor, and a silicon photocell.

[0036] Among them, the processor is the control center of the electronic device, which uses various interfaces and lines to connect the various parts of the entire electronic device, and performs various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory, and calling data stored in the memory, thereby monitoring the electronic device as a whole.

[0037] The processor may integrate an application processor and a modem processor, wherein the application processor mainly processes an operating system, a user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the modem processor may not be integrated into the processor.

[0038] The memory is used to store software programs and / or modules, and the processor executes various functional applications and data processing of the electronic device by running the software programs and / or modules stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, a software program required for at least one function, etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0039] The following is a detailed description of the embodiments of the present application.

[0040] like Figure 2 As shown, an embodiment of the present application provides a key point marking method, which is applied to the above electronic device and specifically includes the following steps:

[0041] Step 201: Select a first image including N first targets, where N is a positive integer;

[0042] If the first image is a face image, the first target may include eyes, nose, ears, mouth, etc. If the first image is a human body image, the first target may include hands, palms, legs, soles, head, etc.

[0043] Optionally, the selecting includes N first images of the first targets, including: displaying an image selection interface, the image selection interface displaying multiple images; and when a first selection operation on the image selection interface is detected, selecting the first image selected by the first selection operation.

[0044] For example, assuming that three images, such as image 1, image 2 and image 3, are displayed on the image selection interface, if the user selects image 1 by using a mouse or manually touching the touch screen, the first image is image 1.

[0045] Optionally, the method further includes: the electronic device determining that a resolution of the first image is greater than or equal to a first threshold.

[0046] Optionally, the method further includes: if the resolution of the first image is less than a first threshold, the electronic device processes the first image, and the resolution of the processed first image is greater than or equal to the first threshold. The first threshold may be 230 pixels / foot, 250 pixels / foot, 300 pixels / foot, 330 pixels / foot, or other values.

[0047] Step 202: Select a first template image, where the first template image includes K first key points of the second target, where K is a positive integer.

[0048] If the first image is a face image, the first template image may include, for example, an eye template image, a nose template image, an ear template image, a mouth template image, etc. If the first image is a human body image, the first template image may include, for example, a hand template image, a palm template image, a leg template image, a sole template image, a head template image, etc.

[0049] The second targets corresponding to different first template images are different. The number of first key points corresponding to different first template images can be the same or different, which is not limited here. The height or width of different first template images can be the same or different, which is not limited here.

[0050] The K first key points are used to represent points at different positions of the second target in the first template image. For example, if the second target is an eye, the K first key points are used to represent different points of the eye contour. For another example, if the second target is a mouth, the K first key points are used to represent different points of the mouth contour.

[0051] Optionally, the selecting the first template image includes: displaying a template selection interface, the template selection interface displaying a plurality of template images; and when a second selection operation on the template selection interface is detected, selecting the first template image selected by the human selection operation.

[0052] For example, assuming that three template images are displayed on the template selection interface, such as template image a1, template image a2 and template image a3, and the user selects template image a1 by using a mouse or manually touching the touch screen, the first template image is template image a1.

[0053] Step 203: Select one of the N first targets on the first image, wherein the type of the one of the first targets matches the type of the second target.

[0054] The type of the first target matches the type of the second target, that is, the types of the two targets are the same. For example, if the second target is an eye, then the first target is also an eye. For another example, if the second target is a mouth, then the first target is also a mouth.

[0055] Optionally, selecting one of the N first targets on the first image includes: displaying a selection interface, the selection interface displaying the first image, a selection option and a pointer; when a selection operation for the selection option is detected, switching the function of the pointer to selection; when a selection operation of the pointer on the first image is detected, selecting one of the first targets selected by the selection operation.

[0056] Optionally, selecting one of the N first targets on the first image includes: parsing the first image to obtain types of the N first targets; determining one of the first targets that matches the type of the second target; and selecting one of the first targets.

[0057] Step 204: perform key point labeling on one of the first targets according to the K first key points.

[0058] In one embodiment of the present application, the K first key points correspond to K first positions, and each first position is used to represent the position of the first key point corresponding to it in the first template image; and the key point marking of one of the first targets according to the K first key points includes:

[0059] K second positions are determined according to the K first positions, the K second positions correspond to K second key points, one of the first targets includes the K second key points, the K first positions correspond one-to-one to the K second positions, and each second position is used to indicate the position of the corresponding second key point in the first image; the K second key points are labeled according to the K second positions.

[0060] Among them, the K first key points correspond one-to-one to the K first positions, and the K second positions correspond one-to-one to the K second key points.

[0061] In an implementation of the present application, one of the first targets is selected by a first frame, and determining K second positions according to the K first positions includes:

[0062] Selecting M first positions from the K first positions, where M is greater than or equal to 4;

[0063] Based on the size information of the first template image, the size information of the first frame, and the M first positions, respectively determine M second positions corresponding to the M first positions;

[0064] Based on the M first positions, the M second positions and the W first positions, the W second positions corresponding to the W first positions are respectively determined, the W first positions and the M first positions constitute the K first positions, and the W second positions and the M second positions constitute the K second positions.

[0065] Among them, the M first positions correspond one-to-one to the M second positions, and the W first positions correspond one-to-one to the W second positions.

[0066] Among them, the M first positions include a first position X1, a first position X2, a first position X3 and a first position X4, the horizontal coordinate value corresponding to X1 is smaller than the horizontal coordinate value corresponding to the first position other than X1 among the K first positions, the horizontal coordinate value corresponding to X2 is larger than the horizontal coordinate value corresponding to the first position other than X2 among the K first positions, the vertical coordinate value corresponding to X3 is smaller than the vertical coordinate value corresponding to the first position other than X3 among the K first positions, and the vertical coordinate value corresponding to X4 is larger than the vertical coordinate value corresponding to the first position other than X4 among the K first positions.

[0067] Among them, the M second positions include a second position Y1, a second position Y2, a second position Y3 and a second position Y4, the horizontal coordinate value corresponding to Y1 is smaller than the horizontal coordinate value corresponding to the second position among the K second positions except Y1, and the horizontal coordinate value corresponding to Y2 is larger than the horizontal coordinate value corresponding to the second position among the K second positions except Y2; the vertical coordinate value corresponding to Y3 is smaller than the vertical coordinate value corresponding to the second position among the K second positions except Y3, and the vertical coordinate value corresponding to Y4 is larger than the vertical coordinate value corresponding to the second position among the K second positions except Y4.

[0068] Specifically, based on the first formula, the size information of the first template image, the size information of the first frame and the M first positions, the M second positions corresponding to the M first positions are respectively determined.

[0069] The size information of the first template image includes a first height of the first template image and a first width of the first template image, and the size information of the first frame includes a second height of the first frame and a second width of the first frame.

[0070] Among them, the first formula is: (A1 / A2)=(B1 / B2); when determining the horizontal coordinate value of the second position, the A1 and the A2 in the first formula are both widths, the B1 and the B2 are both horizontal coordinate values, the images associated with the A1 and the B1 are the same, and the images associated with the A2 and the B2 are the same; when determining the vertical coordinate value of the second position, the A1 and the A2 in the first formula are both heights, the B1 and the B2 are both vertical coordinate values, the images associated with the A1 and the B1 are the same, and the images associated with the A2 and the B2 are the same.

[0071] For example, assuming that the first height is 100px, the first width is 80px, the second height is 90px, the second width is 80px, and the coordinates of a first position are (50px, 40px), then according to the first formula, the first height, the second height and the vertical coordinate value corresponding to the first position, it can be calculated that the vertical coordinate value of the second position corresponding to the first position is 40px, and according to the first formula, the first width, the second width and the horizontal coordinate value of 50px corresponding to the first position, it can be calculated that the horizontal coordinate value of the second position corresponding to the first position is 45px, thereby determining that the coordinates of the second position corresponding to the first position are (45px, 40px).

[0072] Specifically, based on the second formula, the M first positions, the M second positions and the W first positions, the W second positions corresponding to the W first positions are respectively determined.

[0073] Among them, the second formula is: q=min2+(p-min1)*(max2-min2) / (max1-min1). When determining the horizontal coordinate value of the second position, min1 in the second formula is the minimum horizontal coordinate value, max1 is the maximum horizontal coordinate value, q is the horizontal coordinate value corresponding to the second position, and p is the horizontal coordinate value corresponding to one of the first positions; when determining the vertical coordinate value of the second position, min1 in the second formula is the minimum vertical coordinate value, max1 is the maximum vertical coordinate value, q is the vertical coordinate value corresponding to the second position, and p is the vertical coordinate value corresponding to one of the first positions.

[0074] For example, assuming that there are 5 key points in the first template image, the corresponding first positions are (20px, 30px), (40px, 32px), (30px, 50px), (25px, 20px) and (46px, 35px), among which the minimum horizontal coordinate value corresponding to the first position (20px, 30px) is 20px, the minimum vertical coordinate value corresponding to the first position (25px, 20px) is 20px, the maximum horizontal coordinate value corresponding to the first position (46px, 35px) is 46px, and the maximum vertical coordinate value corresponding to the first position (30px, 50px) is 50px. There are 5 key points in the first target area, and the second positions corresponding to 4 of them are (10px, 15px), (15px, 25px), (12px, 10px) and (23px, 17px), among which, the second position (10px, 15px) corresponds to the minimum horizontal coordinate value of 10px, the second position (12px, 10px) is associated with the minimum vertical coordinate value of 10px, the second position (23px, 17px) is associated with the maximum horizontal coordinate value of 23px, and the second position (15px, 25px) is associated with the maximum vertical coordinate value of 25px. Therefore, the minimum horizontal coordinate value corresponding to the first position, the minimum horizontal coordinate value corresponding to the second position, and the maximum horizontal coordinate value corresponding to the first position are obtained. Coordinate value, the maximum horizontal coordinate value corresponding to the second position and the horizontal coordinate value 40px corresponding to the first position (40px, 32px), it can be determined that the horizontal coordinate value corresponding to the second coordinate corresponding to the first position (40px, 32px) is 20px; through the minimum vertical coordinate value corresponding to the first position, the minimum vertical coordinate value corresponding to the second position, through the maximum vertical coordinate value corresponding to the first position, the maximum vertical coordinate value corresponding to the second position and the vertical coordinate value 32px corresponding to the first position (40px, 32px), it can be determined that the horizontal coordinate value corresponding to the second coordinate corresponding to the first position (40px, 32px) is 16px, and finally the second position corresponding to the first position (40px, 32px) is determined to be (20, 16).

[0075] It can be seen that in the embodiment of the present application, the first image and the first template image are first selected, and then one of the first targets is framed on the first image according to the first template image, and finally, key points of one of the first targets are marked according to multiple first key points in the key point template, which can reduce the time required for manual participation in key point marking and improve the efficiency of key point marking.

[0076] In one embodiment of the present application, one of the first targets is selected using a first frame, and after the K second key points are marked according to the K second positions, the method further includes:

[0077] adjusting the size and / or position of the first frame, so that the adjusted first frame selects one of the first targets;

[0078] Determine, based on the adjusted size and / or position of the first frame, K third positions corresponding to the K second key points;

[0079] The K second key points are labeled according to the K third positions.

[0080] The size of the first frame may be adjusted by adjusting the second height and / or the second width of the first frame, and the second height and / or the second width may be increased or decreased.

[0081] The position of the first frame may be adjusted by moving it to the left, to the upper right, to the lower left, or downward relative to the position in the first image.

[0082] The K third positions are determined by the K first positions, and the determination method is the same as the method of determining the K second positions by the K first positions.

[0083] Optionally, for any first template image, the size and / or position of the first frame may be adjusted.

[0084] Optionally, for a complex first template image, if the number of first key points is greater than or equal to a first numerical value, the K third positions corresponding to the K second key points can be determined by adjusting the size and / or position of the first frame, and the first numerical value is a constant (which may be different in different situations).

[0085] It can be seen that in the embodiment of the present application, by adjusting the size and / or position of the first frame to mark the second key point, the accuracy of marking the second key point can be improved.

[0086] In one embodiment of the present application, after marking the K second key points according to the K first key points, the method further includes:

[0087] Adjusting the positions of the K second key points to obtain K fourth positions;

[0088] The K second key points are labeled according to the K fourth positions.

[0089] Among them, the positions of the K second key points are adjusted by adjusting the horizontal coordinate value and / or the vertical coordinate value corresponding to the position of at least one of the K second key points, and the horizontal coordinate value and / or the vertical coordinate value can be increased or decreased.

[0090] Optionally, for a simple first template image, if the number of the first key points is less than the first value, the K fourth positions may be determined by adjusting the positions of the second key points.

[0091] It can be seen that in the embodiment of the present application, by adjusting the position of the second key point to mark the second key point, the time required for marking can be reduced and the efficiency of marking the second key point can be improved.

[0092] With the Figure 2 For details on the embodiments shown in the drawings, please refer to Figure 3 , Figure 3 : is a flow chart of another key point marking method provided in an embodiment of the present application, which is applied to the above electronic device and specifically includes the following steps:

[0093] Step 301: Select a first image including N first objects.

[0094] Step 302: Select a first template image, where the first template image includes K first key points of the second target.

[0095] Step 303: Use a first frame to select one of the N first targets on the first image.

[0096] Step 304: Select M first positions from the K first positions, where M is greater than or equal to 4.

[0097] Step 305: Based on the size information of the first template image, the size information of the first frame and the M first positions, respectively determine M second positions corresponding to the M first positions.

[0098] Step 306: Based on the M first positions, the M second positions and the W first positions, respectively determine the W second positions corresponding to the W first positions, the W first positions and the M first positions constitute the K first positions, and the W second positions and the M second positions constitute the K second positions.

[0099] Step 307: label the K second key points according to the K second positions. After executing step 307, step 308 or step 311 may be executed.

[0100] Step 308: Adjust the size and / or position of the first frame, and the adjusted first frame selects one of the first targets. After executing step 308, execute steps 309 to 310.

[0101] Step 309: Determine K third positions corresponding to the K second key points based on the adjusted size and / or position of the first frame.

[0102] Step 310: Label the K second key points according to the K third positions.

[0103] Step 311: Adjust the positions of the K second key points to obtain K fourth positions.

[0104] Step 312: label the K second key points according to the K fourth positions.

[0105] It should be noted that the specific implementation process of this embodiment can refer to the specific implementation process described in the above method embodiment, which will not be described here.

[0106] With the above Figure 2 and Figure 3 For details on the embodiments shown in the drawings, please refer to Figure 4 , Figure 4 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. As shown in the figure, the electronic device includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the program includes instructions for executing the following steps:

[0107] Selecting a first image including N first targets, where N is a positive integer;

[0108] Selecting a first template image, where the first template image includes K first key points of the second target, where K is a positive integer;

[0109] Selecting one of the N first objects on the first image, wherein a type of the one of the first objects matches a type of the second object;

[0110] Key point marking is performed on one of the first targets according to the K first key points.

[0111] In an implementation of the present application, in terms of corresponding K first positions according to the K first key points, each of the first positions being used to represent the position of the first key point corresponding thereto in the first template image; and in terms of labeling the key points of one of the first targets according to the K first key points, the above program is specifically used to execute the following steps:

[0112] Determine K second positions according to the K first positions, the K second positions correspond to K second key points, one of the first targets includes the K second key points, the K first positions correspond to the K second positions one by one, and each second position is used to represent the position of the corresponding second key point in the first image;

[0113] The K second key points are labeled according to the K second positions.

[0114] In an implementation of the present application, in terms of using the first frame to select one of the first targets, and determining the K second positions according to the K first positions, the above program is specifically used to execute the following step instructions:

[0115] Selecting M first positions from the K first positions, where M is greater than or equal to 4;

[0116] Based on the size information of the first template image, the size information of the first frame, and the M first positions, respectively determine M second positions corresponding to the M first positions;

[0117] Based on the M first positions, the M second positions and the W first positions, the W second positions corresponding to the W first positions are respectively determined, the W first positions and the M first positions constitute the K first positions, and the W second positions and the M second positions constitute the K second positions.

[0118] In one implementation of the present application, the M first positions include a first position X1, a first position X2, a first position X3 and a first position X4, the horizontal coordinate value corresponding to X1 is smaller than the horizontal coordinate value corresponding to the first position other than X1 among the K first positions, the horizontal coordinate value corresponding to X2 is larger than the horizontal coordinate value corresponding to the first position other than X2 among the K first positions, the vertical coordinate value corresponding to X3 is smaller than the vertical coordinate value corresponding to the first position other than X3 among the K first positions, and the vertical coordinate value corresponding to X4 is larger than the vertical coordinate value corresponding to the first position other than X4 among the K first positions. In one implementation of the present application, the M second positions include a second position Y1, a second position Y2, a second position Y3 and a second position Y4, the horizontal coordinate value corresponding to Y1 is smaller than the horizontal coordinate value corresponding to the second position other than Y1 among the K second positions, and the horizontal coordinate value corresponding to Y2 is larger than the horizontal coordinate value corresponding to the second position other than Y2 among the K second positions; the vertical coordinate value corresponding to Y3 is smaller than the vertical coordinate value corresponding to the second position other than Y3 among the K second positions, and the vertical coordinate value corresponding to Y4 is larger than the vertical coordinate value corresponding to the second position other than Y4 among the K second positions.

[0119] In an implementation of the present application, after the K second key points are marked according to the K second positions, the above program is specifically used to execute the following step instructions:

[0120] Determine, based on the adjusted size and / or position of the first frame, K third positions corresponding to the K second key points;

[0121] The K second key points are labeled according to the K third positions.

[0122] In an implementation of the present application, after the K second key points are marked according to the K second positions, the above program is further used to execute the following step instructions:

[0123] Adjusting the positions of the K second key points to obtain K fourth positions;

[0124] The K second key points are labeled according to the K fourth positions.

[0125] It should be noted that the specific implementation process of this embodiment can refer to the specific implementation process described in the above method embodiment, which will not be described here.

[0126] See also Figure 5 , Figure 5 A key point marking device provided in an embodiment of the present application is applied to an electronic device, and the device includes:

[0127] A first selection unit 501 is used to select a first image including N first objects, where N is a positive integer;

[0128] A second selection unit 502 is used to select a first template image, where the first template image includes K first key points of the second target, where K is a positive integer;

[0129] A frame selection unit 503 is used to frame one of the N first objects on the first image, wherein a type of the one of the first objects matches a type of the second object;

[0130] The labeling unit 504 is configured to label one of the first objects with key points according to the K first key points.

[0131] In an implementation of the application, when marking the K second key points according to the K first key points, the marking unit 504 is specifically used to:

[0132] Determine K second positions according to the K first positions, the K second positions correspond to K second key points, one of the first targets includes the K second key points, the K first positions correspond to the K second positions one by one, and each second position is used to represent the position of the corresponding second key point in the first image;

[0133] The K second key points are labeled according to the K second positions.

[0134] In an implementation of the application, one of the first targets is selected using a first frame, and K second positions are determined according to the K first positions. The marking unit 504 is specifically used to:

[0135] Selecting M first positions from the K first positions, where M is greater than or equal to 4;

[0136] Based on the size information of the first template image, the size information of the first frame, and the M first positions, respectively determine M second positions corresponding to the M first positions;

[0137] Based on the M first positions, the M second positions and the W first positions, the W second positions corresponding to the W first positions are respectively determined, the W first positions and the M first positions constitute the K first positions, and the W second positions and the M second positions constitute the K second positions.

[0138] In one implementation of the application, the M first positions include a first position X1, a first position X2, a first position X3 and a first position X4, the horizontal coordinate value corresponding to X1 is smaller than the horizontal coordinate value corresponding to the first position other than X1 among the K first positions, the horizontal coordinate value corresponding to X2 is larger than the horizontal coordinate value corresponding to the first position other than X2 among the K first positions, the vertical coordinate value corresponding to X3 is smaller than the vertical coordinate value corresponding to the first position other than X3 among the K first positions, and the vertical coordinate value corresponding to X4 is larger than the vertical coordinate value corresponding to the first position other than X4 among the K first positions.

[0139] In one implementation of the application, the M second positions include a second position Y1, a second position Y2, a second position Y3 and a second position Y4, the horizontal coordinate value corresponding to Y1 is smaller than the horizontal coordinate value corresponding to the second position among the K second positions except Y1, and the horizontal coordinate value corresponding to Y2 is larger than the horizontal coordinate value corresponding to the second position among the K second positions except Y2; the vertical coordinate value corresponding to Y3 is smaller than the vertical coordinate value corresponding to the second position among the K second positions except Y3, and the vertical coordinate value corresponding to Y4 is larger than the vertical coordinate value corresponding to the second position among the K second positions except Y4.

[0140] In an implementation of the application, after marking the K second key points according to the K first key points, the frame selection unit 503 is specifically used to:

[0141] adjusting the size and / or position of the first frame, so that the adjusted first frame selects one of the first targets;

[0142] In an implementation of the application, after the K second key points are labeled according to the K first key points, the labeling unit 504 is specifically used to:

[0143] Determine, based on the adjusted size and / or position of the first frame, K third positions corresponding to the K second key points;

[0144] The K second key points are labeled according to the K third positions.

[0145] In an implementation of the application, after marking the K second key points according to the K first key points, the frame selection unit 503 is specifically used to:

[0146] Adjusting the positions of the K second key points to obtain K fourth positions;

[0147] The K second key points are labeled according to the K fourth positions.

[0148] It should be noted that the first selection unit 501, the second selection unit 502, the frame selection unit 503 and the marking unit 504 can be implemented by a processor.

[0149] An embodiment of the present application also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute some or all of the steps described for the electronic device in the above method embodiment.

[0150] The present application also provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps described for the electronic device in the above method. The computer program product may be a software installation package.

[0151] The steps of the method or algorithm described in the embodiment of the present application can be implemented in a hardware manner, or can be implemented by a processor executing software instructions. The software instructions can be composed of corresponding software modules, and the software modules can be stored in a random access memory (Random Access Memory, RAM), a flash memory, a read-only memory (Read Only Memory, ROM), an erasable programmable read-only memory (Erasable Programmable ROM, EPROM), an electrically erasable programmable read-only memory (Electrically EPROM, EEPROM), a register, a hard disk, a mobile hard disk, a read-only compact disk (CD-ROM) or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an ASIC. In addition, the ASIC can be located in an access network device, a first target network device, or a core network device. Of course, the processor and the storage medium can also be present in an access network device, a first target network device, or a core network device as discrete components.

[0152] Those skilled in the art should be aware that in one or more of the above examples, the functions described in the embodiments of the present application can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiments of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrations. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0153] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of the embodiments of the present application. It should be understood that the above description is only the specific implementation method of the embodiments of the present application and is not intended to limit the protection scope of the embodiments of the present application. Any modifications, equivalent substitutions, improvements, etc. made on the basis of the technical solutions of the embodiments of the present application should be included in the protection scope of the embodiments of the present application.

Claims

1. A key point labeling method, It is characterized in that Applied to electronic equipment, the method comprises: Selecting a first image including N first targets, where N is a positive integer; Selecting a first template image, the first template image corresponds to a second target, the first template image includes K first key points of the second target, K is a positive integer, the K first key points correspond to K first positions, and each first position is used to represent the position of the first key point corresponding to it in the first template image; Selecting one of the N first objects on the first image, wherein a type of the one of the first objects matches a type of the second object; Marking one of the first targets with key points according to the K first key points, including: determining K second positions according to the K first positions, the K second positions corresponding to the K second key points, one of the first targets including the K second key points, the K first positions corresponding to the K second positions one by one, each second position being used to indicate a position of the corresponding second key point in the first image; marking the K second key points according to the K second positions; One of the first targets is selected by the first frame, and determining K second positions based on the K first positions includes: selecting M first positions from the K first positions, where M is greater than or equal to 4; based on size information of the first template image, size information of the first frame and the M first positions, respectively determining M second positions corresponding to the M first positions; based on the M first positions, the M second positions and W first positions, respectively determining W second positions corresponding to the W first positions, the W first positions and the M first positions constitute the K first positions, and the W second positions and the M second positions constitute the K second positions.

2. The method according to claim 1, It is characterized in that After marking the K second key points according to the K second positions, the method further includes: adjusting the size and / or position of the first frame, so that the adjusted first frame selects one of the first targets; Determine, based on the adjusted size and / or position of the first frame, K third positions corresponding to the K second key points; The K second key points are labeled according to the K third positions.

3. The method according to claim 1, It is characterized in that After marking the K second key points according to the K second positions, the method further includes: Adjusting the positions of the K second key points to obtain K fourth positions; The K second key points are labeled according to the K fourth positions.

4. A key point marking device, It is characterized in that Applied to electronic equipment, the device comprises: A first selection unit, configured to select a first image including N first objects, where N is a positive integer; A second selection unit is used to select a first template image, where the first template image corresponds to a second target, the first template image includes K first key points of the second target, where K is a positive integer, the K first key points correspond to K first positions, and each first position is used to indicate a position of the first key point corresponding to it in the first template image; a frame selection unit, configured to frame one of the N first objects on the first image, wherein a type of the one of the first objects matches a type of the second object; A labeling unit, configured to label one of the first targets with key points according to the K first key points, comprising: determining K second positions according to the K first positions, the K second positions corresponding to the K second key points, the one of the first targets including the K second key points, the K first positions corresponding to the K second positions one by one, each of the second positions being used to indicate a position of the corresponding second key point in the first image; labeling the K second key points according to the K second positions; One of the first targets is selected by the first frame, and in determining K second positions based on the K first positions, the labeling unit is specifically used to: select M first positions from the K first positions, and M is greater than or equal to 4; based on size information of the first template image, size information of the first frame and the M first positions, respectively determine M second positions corresponding to the M first positions; based on the M first positions, the M second positions and W first positions, respectively determine W second positions corresponding to the W first positions, the W first positions and the M first positions constitute the K first positions, and the W second positions and the M second positions constitute the K second positions.

5. An electronic device, It is characterized in that The electronic device includes a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the programs include instructions for executing the steps in the method as described in any one of claims 1-3.

6. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores a computer program, wherein the computer program is processed to execute the method according to any one of claims 1 to 3.