CN112184593A - Key point determination method, device, equipment and computer readable medium - Google Patents

Key point determination method, device, equipment and computer readable medium Download PDF

Info

Publication number
CN112184593A
CN112184593A CN202011096279.XA CN202011096279A CN112184593A CN 112184593 A CN112184593 A CN 112184593A CN 202011096279 A CN202011096279 A CN 202011096279A CN 112184593 A CN112184593 A CN 112184593A
Authority
CN
China
Prior art keywords
annotation image
alignment
image
key points
coordinates
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202011096279.XA
Other languages
Chinese (zh)
Inventor
邓启力
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Zitiao Network Technology Co Ltd
Original Assignee
Beijing Zitiao Network Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Zitiao Network Technology Co Ltd filed Critical Beijing Zitiao Network Technology Co Ltd
Priority to CN202011096279.XA priority Critical patent/CN112184593A/en
Publication of CN112184593A publication Critical patent/CN112184593A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/70—Denoising; Smoothing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20092—Interactive image processing based on input by user

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)

Abstract

The embodiment of the disclosure discloses a key point determination method, a key point determination device, electronic equipment and a computer readable medium. One embodiment of the method comprises: aligning a first annotation image marked with key points and a second annotation image marked with related key points with a template annotation image marked with related key points to obtain a first alignment annotation image and a second alignment annotation image; updating the key points in the first alignment annotation image to obtain an updated first alignment annotation image; and aligning the updated first alignment annotation image with the first annotation image to obtain a target annotation image. According to the embodiment, the key points in the original annotation image are smoothed after the original annotation image is aligned with the template annotation image, so that the influence of the displacement of the content displayed in the image on the key points in the smoothed aligned annotation image is reduced. The stability of the key points when the template annotation image is switched to the target annotation image is improved.

Description

Key point determination method, device, equipment and computer readable medium
Technical Field
The embodiment of the disclosure relates to the technical field of computers, in particular to a method, a device, equipment and a computer readable medium for determining key points.
Background
In a video processing tool, it is often necessary to first detect a target area in some video frames, in which target content is shown, and then process a video in the detected target area. For example, image material is added in the detected target area. In order to ensure the stability of the target area in the previous and subsequent frames of the video, the position parameters of the target area detected in the previous and subsequent frames are usually smoothed, and then the position of the target area in the subsequent frame is updated according to the smoothing result. The related technology directly smoothes the front frame and the rear frame, so that the smoothing result is influenced by the displacement of the target content in the front frame and the rear frame, the updated target area in the rear frame is inaccurate, and the video processing effect is poor.
Disclosure of Invention
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Some embodiments of the present disclosure propose a key point determination method, apparatus, device and computer readable medium to solve the technical problems mentioned in the background section above.
In a first aspect, some embodiments of the present disclosure provide a method for determining a keypoint, the method comprising: aligning a first annotation image marked with key points and a second annotation image marked with related key points with a template annotation image marked with related key points to obtain a first alignment annotation image and a second alignment annotation image; updating the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image to obtain an updated first alignment annotation image; and aligning the updated first alignment annotation image with the first annotation image to obtain a target annotation image.
In a second aspect, some embodiments of the present disclosure provide a keypoint determination apparatus, the apparatus comprising: the first alignment unit is configured to align a first annotation image marking the relevant key points and a second annotation image marking the relevant key points with the template annotation image marking the relevant key points to obtain a first alignment annotation image and a second alignment annotation image; an updating unit configured to update the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image, so as to obtain an updated first alignment annotation image; and a second alignment unit configured to align the updated first alignment annotation image with the first annotation image to obtain a target annotation image.
In a third aspect, some embodiments of the present disclosure provide an electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon, which when executed by one or more processors, cause the one or more processors to implement the method as described in any of the implementations of the first aspect.
In a fourth aspect, some embodiments of the disclosure provide a computer readable medium having a computer program stored thereon, where the program when executed by a processor implements a method as described in any of the implementations of the first aspect.
One of the above-described various embodiments of the present disclosure has the following advantageous effects: the key points in the original annotation image are smoothed after the original annotation image is aligned with the template annotation image, so that the influence of the displacement of the content displayed in the image on the key points in the smoothed aligned annotation image is reduced. The stability of the key points when the template annotation image is switched to the target annotation image is improved.
Drawings
The above and other features, advantages and aspects of various embodiments of the present disclosure will become more apparent by referring to the following detailed description when taken in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numbers refer to the same or similar elements. It should be understood that the drawings are schematic and that elements and elements are not necessarily drawn to scale.
FIG. 1 is a schematic diagram of one application scenario of the keypoint determination method of some embodiments of the present disclosure;
FIG. 2 is a flow diagram of some embodiments of a keypoint determination method according to the present disclosure;
FIG. 3 is a flow diagram of further embodiments of a keypoint determination method according to the present disclosure;
FIG. 4 is a schematic block diagram of some embodiments of a keypoint determination apparatus according to the present disclosure;
FIG. 5 is a schematic structural diagram of an electronic device suitable for use in implementing some embodiments of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure are shown in the drawings, it is to be understood that the disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the disclosure are for illustration purposes only and are not intended to limit the scope of the disclosure.
It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings. The embodiments and features of the embodiments in the present disclosure may be combined with each other without conflict.
It should be noted that the terms "first", "second", and the like in the present disclosure are only used for distinguishing different devices, modules or units, and are not used for limiting the order or interdependence relationship of the functions performed by the devices, modules or units.
It is noted that references to "a", "an", and "the" modifications in this disclosure are intended to be illustrative rather than limiting, and that those skilled in the art will recognize that "one or more" may be used unless the context clearly dictates otherwise.
The names of messages or information exchanged between devices in the embodiments of the present disclosure are for illustrative purposes only, and are not intended to limit the scope of the messages or information.
The present disclosure will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.
Fig. 1 shows a schematic diagram of one application scenario in which the keypoint determination method of some embodiments of the present disclosure may be applied.
In the application scenario shown in FIG. 1, first, the computing device 101 can align a first annotation image 102 annotating the relevant key points and a second annotation image 103 annotating the relevant key points with a template annotation image 104 annotating the relevant key points, resulting in a first aligned annotation image 105 and a second aligned annotation image 106. In the application scenario, each frame of image includes 12 key points distributed over the contour of the face and the contour of the mouth for identifying their positions. Then, the key points in the first alignment-labeled image 105 are updated based on the key points in the first alignment-labeled image 105 and the key points in the second alignment-labeled image 106, and an updated first alignment-labeled image 107 is obtained. Finally, the updated first alignment annotation image 107 is aligned with the first annotation image 102 to obtain the target annotation image 108.
The computing device 101 may be hardware or software. When the computing device is hardware, it may be implemented as a distributed cluster composed of a plurality of servers or electronic devices, or may be implemented as a single server or a single electronic device. When the computing device is embodied as software, it may be implemented as multiple pieces of software or software modules, for example, to provide distributed services, or as a single piece of software or software module. And is not particularly limited herein.
It should be understood that the number of computing devices 101 in FIG. 1 is merely illustrative. There may be any number of computing devices 101, as desired for implementation.
With continued reference to fig. 2, a flow 200 of some embodiments of a keypoint determination method according to the present disclosure is shown. The key point determining method comprises the following steps:
step 201, aligning the first annotation image marked with the key point and the second annotation image marked with the key point with the template annotation image marked with the key point to obtain a first alignment annotation image and a second alignment annotation image.
In some embodiments, there are the same number of key points in the first annotation image, the second annotation image, and the template annotation image. And each keypoint in an image has a unique number.
In some embodiments, the first annotation image can be obtained by inputting the first image into a pre-trained keypoint prediction network, for example, by the execution subject of the keypoint determination method. And, the second labeled image may also adopt the same method, which is not described herein again.
In some embodiments, the execution agent may use an image alignment network to perform this step. Taking as an example the alignment of the first annotation image annotating the relevant key points with the template annotation image annotating the relevant key points, the above-mentioned image alignment network may be a generation countermeasure network. On this basis, the execution body may input the first annotation image and the template annotation image to the generator in the generation countermeasure network to obtain a deformation matrix. And applying the deformation matrix to the coordinates of each pixel point in the first annotation image, namely determining the result of the inner product of the coordinates of the pixel points and the deformation matrix as the coordinates of the pixel points in the first alignment annotation image to obtain the first alignment annotation image.
The training of the generation countermeasure network may be to use the to-be-aligned annotation image of the sample and the template annotation image of the sample as the input of a generator in the generation countermeasure network, and the generator outputs the aligned sample annotation image. The discriminator inputs the sample template annotation image and the aligned sample annotation image, and outputs the similarity between the aligned sample annotation image and the sample template annotation image. And setting a loss function and executing a gradient descent algorithm to enable the output of the discriminator in the generation countermeasure network to be higher than a preset threshold value.
In some optional implementations of some embodiments, the executing subject may further determine a first number of pairs of reference points in the first annotation image and the template annotation image first. The reference points may be selected randomly or according to a preset number. Then, a coordinate transformation matrix is determined based on the first number of pairs of reference points. This step can be done using an interface provided in the image processing tool. For example, the findHomography (point1, point2) interface in the OpenCV (open Computer Vision) tool. In this embodiment, the parameters point1 and point2 in the function are the first number of reference points in the first annotation image and the first number of reference points in the template annotation image, respectively. And finally, applying the coordinate transformation matrix to the coordinates of each pixel point in the first annotation image to obtain the first alignment annotation image.
Step 202, updating the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image to obtain an updated first alignment annotation image.
In some embodiments, the executing entity may determine a midpoint of a connecting line between the key point in the first alignment annotation image and the key point in the second alignment annotation image projected on the same plane as each other as the key point in the updated first alignment annotation image.
In some optional implementation manners of some embodiments, the executing entity may further perform numerical calculation on the coordinates of each keypoint in the first alignment annotation image, the coordinates of a corresponding keypoint in the second alignment annotation image, and a preset smoothing coefficient to obtain a corresponding smooth keypoint coordinate. And then, updating the key points in the first alignment image into pixel points at the smooth key point coordinates to obtain an updated first alignment annotation image.
By way of example, with (x)1，y1) The coordinate of a key point in the first alignment mark image is expressed by (x)2，y2) Indicating the (x) in the second alignment mark image1，y1) The coordinates of the corresponding key points are represented by S as the smoothing coefficient. The corresponding smoothed keypoint coordinate may be (((1-S) × x)1+S*x2)，((1-S)*y1+S*y2)). But also (((1-exp ((| x))1-x2|/S)3))*x1+exp((|x1-x2|/S)3))*x2)，((1-exp((|y1-y2|/S)3))*y1+exp((|y1-y2|/S)3)*y2)). Wherein, the corresponding relation is determined by the number of the key point.
Step 203, aligning the updated first aligned annotation image with the first annotation image to obtain a target annotation image.
In some embodiments, the executing entity may apply an inverse matrix of the deformation matrix to the coordinates of each pixel point in the first alignment marking image. And aligning the first alignment annotation image with the first annotation image to obtain the target annotation image.
In some optional implementation manners of some embodiments, the executing body may further apply an inverse matrix of the coordinate transformation matrix to the coordinates of each pixel point in the first alignment annotation image, so that the first alignment annotation image is aligned with the first annotation image, and the target annotation image is obtained.
According to the method provided by some embodiments of the present disclosure, the original annotation image is aligned with the template annotation image, and then the key points in the original annotation image are smoothed, so that the influence of the displacement of the content displayed in the image on the key points in the smoothed aligned annotation image is reduced. The stability of the key points when the template annotation image is switched to the target annotation image is improved.
With further reference to FIG. 3, a flow 300 of further embodiments of a keypoint determination method is shown. The process 300 of the keypoint determination method includes the following steps:
step 301, aligning the first annotation image marked with the key point and the second annotation image marked with the key point with the template annotation image marked with the key point to obtain a first alignment annotation image and a second alignment annotation image.
In some embodiments, the specific implementation of step 301 and the technical effect thereof may refer to step 201 in the embodiment corresponding to fig. 2, and are not described herein again.
And 302, performing numerical calculation on the coordinates of each key point in the first alignment annotation image, the coordinates of the corresponding key point in the second alignment annotation image and a preset smoothing coefficient to obtain the coordinates of the corresponding smooth key point.
By way of example, one may use (x)1，y1) The coordinate of a key point in the first alignment mark image is expressed by (x)2，y2) Indicating the (x) in the second alignment mark image1，y1) The coordinates of the corresponding key points are represented by S as the smoothing coefficient. The corresponding smoothed keypoint coordinate may be (((1-S) × x)1+S*x2)，((1-S)*y1+S*y2)). Wherein, the corresponding relation is determined by the number of the key point.
As yet another example, the smooth keypoint coordinates described above may also be (((1-exp ((| x)1-x2|/S)3))*x1+exp((|x1-x2|/S)3))*x2)，((1-exp((|y1-y2|/S)3))*y1+exp((|y1-y2|/S)3)*y2))。
Step 303, updating the key points in the first alignment annotation image to the pixel points at the smooth key point coordinates, so as to obtain an updated first alignment annotation image.
Step 304, aligning the updated first aligned annotation image with the first annotation image to obtain a target annotation image.
In some embodiments, the specific implementation of step 304 and the technical effect thereof may refer to step 203 in the embodiment corresponding to fig. 2, which is not described herein again.
As can be seen from fig. 3, compared with the description of some embodiments corresponding to fig. 2, in the process 300 of the keypoint determination method in some embodiments corresponding to fig. 3, the coordinates of each keypoint in the first alignment annotation image, the coordinates of the corresponding keypoint in the second alignment annotation image, and a preset smoothing coefficient are numerically calculated to obtain the coordinates of the corresponding smooth keypoint, so that the smoothing degree of the keypoint in the first alignment annotation image can be flexibly adjusted according to actual needs.
With further reference to fig. 4, as an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a keypoint determination apparatus, which correspond to those of the method embodiments shown in fig. 2, and which may be applied in various electronic devices in particular.
As shown in fig. 4, the keypoint determination apparatus 400 of some embodiments comprises: a first alignment unit 401, an update unit 402, and a second alignment unit 403. The first alignment unit 401 is configured to align a first annotation image for labeling a relevant key point and a second annotation image for labeling a relevant key point with a template annotation image for labeling a relevant key point, so as to obtain a first alignment annotation image and a second alignment annotation image; an updating unit 402, configured to update the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image, so as to obtain an updated first alignment annotation image; a second alignment unit 403, configured to align the updated first alignment annotation image with the first annotation image to obtain a target annotation image.
In an optional implementation of some embodiments, the updating unit 402 is further configured to: carrying out numerical calculation on the coordinates of each key point in the first alignment annotation image, the coordinates of the corresponding key point in the second alignment annotation image and a preset smoothing coefficient to obtain the coordinates of the corresponding smooth key point; and updating the key points in the first alignment annotation image into pixel points at the smooth key point coordinates to obtain an updated first alignment annotation image.
In an optional implementation of some embodiments, the first alignment unit 401 is further configured to: determining a first number of reference points in the first annotation image and the template annotation image; determining a coordinate transformation matrix based on the first number of pairs of reference points; and applying the coordinate transformation matrix to the coordinates of each pixel point in the first annotation image to obtain the first alignment annotation image.
In an optional implementation of some embodiments, the second alignment unit 402 is further configured to: and applying the inverse matrix of the coordinate conversion matrix to the coordinates of each pixel point in the updated first alignment annotation image to obtain the target annotation image.
It will be understood that the elements described in the apparatus 400 correspond to various steps in the method described with reference to fig. 2. Thus, the operations, features and resulting advantages described above with respect to the method are also applicable to the apparatus 400 and the units included therein, and will not be described herein again.
Referring now to fig. 5, a schematic diagram of an electronic device (e.g., the server or terminal device of fig. 1) 500 suitable for use in implementing some embodiments of the present disclosure is shown. The electronic device in some embodiments of the present disclosure may include, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (personal digital assistant), a PAD (tablet computer), a PMP (portable multimedia player), a vehicle-mounted terminal (e.g., a car navigation terminal), and the like, and a stationary terminal such as a digital TV, a desktop computer, and the like. The electronic device shown in fig. 5 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.
As shown in fig. 5, electronic device 500 may include a processing means (e.g., central processing unit, graphics processor, etc.) 501 that may perform various appropriate actions and processes in accordance with a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage means 508 into a Random Access Memory (RAM) 503. In the RAM503, various programs and data necessary for the operation of the electronic apparatus 500 are also stored. The processing device 501, the ROM 502, and the RAM503 are connected to each other through a bus 504. An input/output (I/O) interface 505 is also connected to bus 504.
Generally, the following devices may be connected to the I/O interface 505: input devices 506 including, for example, a touch screen, touch pad, keyboard, mouse, camera, microphone, accelerometer, gyroscope, etc.; output devices 507 including, for example, a Liquid Crystal Display (LCD), speakers, vibrators, and the like; storage devices 508 including, for example, magnetic tape, hard disk, etc.; and a communication device 509. The communication means 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. While fig. 5 illustrates an electronic device 500 having various means, it is to be understood that not all illustrated means are required to be implemented or provided. More or fewer devices may alternatively be implemented or provided. Each block shown in fig. 5 may represent one device or may represent multiple devices as desired.
In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flow diagrams may be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In some such embodiments, the computer program may be downloaded and installed from a network via the communication means 509, or installed from the storage means 508, or installed from the ROM 502. The computer program, when executed by the processing device 501, performs the above-described functions defined in the methods of some embodiments of the present disclosure.
It should be noted that the computer readable medium described in some embodiments of the present disclosure may be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In some embodiments of the disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In some embodiments of the present disclosure, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
In some embodiments, the clients, servers may communicate using any currently known or future developed network Protocol, such as HTTP (HyperText Transfer Protocol), and may interconnect with any form or medium of digital data communication (e.g., a communications network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), the Internet (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed network.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: aligning a first annotation image marked with key points and a second annotation image marked with related key points with a template annotation image marked with related key points to obtain a first alignment annotation image and a second alignment annotation image; updating the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image to obtain an updated first alignment annotation image; and aligning the updated first alignment annotation image with the first annotation image to obtain a target annotation image.
Computer program code for carrying out operations for embodiments of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in some embodiments of the present disclosure may be implemented by software, and may also be implemented by hardware. The described units may also be provided in a processor, and may be described as: a processor includes a first alignment unit, an update unit, and a second alignment unit. Where the names of these units do not in some cases constitute a limitation on the unit itself, for example, an update unit may also be described as a "unit that updates a keypoint".
The functions described herein above may be performed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), systems on a chip (SOCs), Complex Programmable Logic Devices (CPLDs), and the like.
According to one or more embodiments of the present disclosure, there is provided a keypoint determination method including: aligning a first annotation image marked with key points and a second annotation image marked with related key points with a template annotation image marked with related key points to obtain a first alignment annotation image and a second alignment annotation image; updating the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image to obtain an updated first alignment annotation image; and aligning the updated first alignment annotation image with the first annotation image to obtain a target annotation image.
According to one or more embodiments of the present disclosure, updating the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image to obtain an updated first alignment annotation image includes: carrying out numerical calculation on the coordinates of each key point in the first alignment annotation image, the coordinates of the corresponding key point in the second alignment annotation image and a preset smoothing coefficient to obtain the coordinates of the corresponding smooth key point; and updating the key points in the first alignment annotation image into pixel points at the smooth key point coordinates to obtain an updated first alignment annotation image.
According to one or more embodiments of the present disclosure, aligning a first annotation image marked with a key point with a template annotation image marked with a relevant key point to obtain a first aligned annotation image, includes: determining a first number of reference points in the first annotation image and the template annotation image; determining a coordinate transformation matrix based on the first number of pairs of reference points; and applying the coordinate transformation matrix to the coordinates of each pixel point in the first annotation image to obtain the first alignment annotation image.
According to one or more embodiments of the present disclosure, aligning the updated first alignment annotation image with the first annotation image to obtain a target annotation image includes: and applying the inverse matrix of the coordinate conversion matrix to the coordinates of each pixel point in the updated first alignment annotation image to obtain the target annotation image.
According to one or more embodiments of the present disclosure, there is provided a keypoint determination apparatus including: the first alignment unit is configured to align a first annotation image marking the relevant key points and a second annotation image marking the relevant key points with the template annotation image marking the relevant key points to obtain a first alignment annotation image and a second alignment annotation image; an updating unit configured to update the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image, so as to obtain an updated first alignment annotation image; and a second alignment unit configured to align the updated first alignment annotation image with the first annotation image to obtain a target annotation image.
According to one or more embodiments of the present disclosure, the update unit is further configured to: carrying out numerical calculation on the coordinates of each key point in the first alignment annotation image, the coordinates of the corresponding key point in the second alignment annotation image and a preset smoothing coefficient to obtain the coordinates of the corresponding smooth key point; and updating the key points in the first alignment annotation image into pixel points at the smooth key point coordinates to obtain an updated first alignment annotation image.
According to one or more embodiments of the present disclosure, the first alignment unit is further configured to: determining a first number of reference points in the first annotation image and the template annotation image; determining a coordinate transformation matrix based on the first number of pairs of reference points; and applying the coordinate transformation matrix to the coordinates of each pixel point in the first annotation image to obtain the first alignment annotation image.
According to one or more embodiments of the present disclosure, the second alignment unit is further configured to: and applying the inverse matrix of the coordinate conversion matrix to the coordinates of each pixel point in the updated first alignment annotation image to obtain the target annotation image.
According to one or more embodiments of the present disclosure, there is provided an electronic device including: one or more processors; a storage device having one or more programs stored thereon which, when executed by one or more processors, cause the one or more processors to implement a method as in any above.
According to one or more embodiments of the present disclosure, a computer-readable medium is provided, on which a computer program is stored, wherein the program, when executed by a processor, implements the method as any one of the above.
The foregoing description is only exemplary of the preferred embodiments of the disclosure and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention in the embodiments of the present disclosure is not limited to the specific combination of the above-mentioned features, but also encompasses other embodiments in which any combination of the above-mentioned features or their equivalents is made without departing from the inventive concept as defined above. For example, the above features and (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure are mutually replaced to form the technical solution.

Claims (10)

1. A method of keypoint determination, comprising:
aligning a first annotation image marked with key points and a second annotation image marked with related key points with a template annotation image marked with related key points to obtain a first alignment annotation image and a second alignment annotation image;
updating the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image to obtain an updated first alignment annotation image;
and aligning the updated first alignment annotation image with the first annotation image to obtain a target annotation image.
2. The method of claim 1, wherein updating the keypoints in the first registered annotation image based on the keypoints in the first registered annotation image and the keypoints in the second registered annotation image to obtain an updated first registered annotation image comprises:
carrying out numerical calculation on the coordinates of each key point in the first alignment annotation image, the coordinates of the corresponding key point in the second alignment annotation image and a preset smoothing coefficient to obtain the coordinates of the corresponding smooth key point;
and updating the key points in the first alignment annotation image into pixel points at the smooth key point coordinates to obtain an updated first alignment annotation image.
3. The method of claim 1, wherein said aligning a first annotated image with keypoints and a template annotated image with related keypoints to obtain a first aligned annotated image comprises:
determining a first number of pairs of reference points in the first annotation image and the template annotation image;
determining a coordinate transformation matrix based on the first number of pairs of reference points;
and applying the coordinate transformation matrix to the coordinates of each pixel point in the first annotation image to obtain the first alignment annotation image.
4. The method of claim 3, wherein said aligning said updated first aligned annotation image with said first annotation image to obtain a target annotation image comprises:
and applying an inverse matrix of the coordinate conversion matrix to the coordinates of each pixel point in the updated first alignment annotation image to obtain the target annotation image.
5. A keypoint determination apparatus comprising:
the first alignment unit is configured to align a first annotation image marking the relevant key points and a second annotation image marking the relevant key points with the template annotation image marking the relevant key points to obtain a first alignment annotation image and a second alignment annotation image;
an updating unit, configured to update the key points in the first alignment annotation image based on the key points in the first alignment annotation image and the key points in the second alignment annotation image, to obtain an updated first alignment annotation image;
a second alignment unit configured to align the updated first aligned annotation image with the first annotation image to obtain a target annotation image.
6. The apparatus of claim 5, wherein the update unit is further configured to:
carrying out numerical calculation on the coordinates of each key point in the first alignment annotation image, the coordinates of the corresponding key point in the second alignment annotation image and a preset smoothing coefficient to obtain the coordinates of the corresponding smooth key point;
and updating the key points in the first alignment annotation image into pixel points at the smooth key point coordinates to obtain an updated first alignment annotation image.
7. The apparatus of claim 5, wherein the first alignment unit is further configured to:
determining a first number of pairs of reference points in the first annotation image and the template annotation image;
determining a coordinate transformation matrix based on the first number of pairs of reference points;
and applying a coordinate transformation matrix to the coordinates of each pixel point in the first annotation image to obtain the first alignment annotation image.
8. The apparatus of claim 7, wherein the second alignment unit is further configured to:
and applying an inverse matrix of the coordinate conversion matrix to the coordinates of each pixel point in the updated first alignment annotation image to obtain the target annotation image.
9. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-4.
10. A computer-readable medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method of any one of claims 1-4.
CN202011096279.XA 2020-10-14 2020-10-14 Key point determination method, device, equipment and computer readable medium Pending CN112184593A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011096279.XA CN112184593A (en) 2020-10-14 2020-10-14 Key point determination method, device, equipment and computer readable medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011096279.XA CN112184593A (en) 2020-10-14 2020-10-14 Key point determination method, device, equipment and computer readable medium

Publications (1)

Publication Number Publication Date
CN112184593A true CN112184593A (en) 2021-01-05

Family

ID=73950891

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011096279.XA Pending CN112184593A (en) 2020-10-14 2020-10-14 Key point determination method, device, equipment and computer readable medium

Country Status (1)

Country Link
CN (1) CN112184593A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663361A (en) * 2012-04-01 2012-09-12 北京工业大学 Face image reversible geometric normalization method facing overall characteristics analysis
JP2014027405A (en) * 2012-07-25 2014-02-06 Nippon Hoso Kyokai <Nhk> Frame interpolation apparatus and program
CN107920257A (en) * 2017-12-01 2018-04-17 北京奇虎科技有限公司 Video Key point real-time processing method, device and computing device
CN108027878A (en) * 2015-09-21 2018-05-11 三菱电机株式会社 Method for face alignment
CN109978063A (en) * 2019-03-28 2019-07-05 厦门美图之家科技有限公司 A method of generating the alignment model of target object
CN110264431A (en) * 2019-06-29 2019-09-20 北京字节跳动网络技术有限公司 Video beautification method, device and electronic equipment
US20200068185A1 (en) * 2018-08-24 2020-02-27 Samsung Electronics Co., Ltd. Rectifying a sequence of stereo images
CN110856014A (en) * 2019-11-05 2020-02-28 北京奇艺世纪科技有限公司 Moving image generation method, moving image generation device, electronic device, and storage medium
CN111488774A (en) * 2019-01-29 2020-08-04 北京搜狗科技发展有限公司 Image processing method and device for image processing

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102663361A (en) * 2012-04-01 2012-09-12 北京工业大学 Face image reversible geometric normalization method facing overall characteristics analysis
JP2014027405A (en) * 2012-07-25 2014-02-06 Nippon Hoso Kyokai <Nhk> Frame interpolation apparatus and program
CN108027878A (en) * 2015-09-21 2018-05-11 三菱电机株式会社 Method for face alignment
CN107920257A (en) * 2017-12-01 2018-04-17 北京奇虎科技有限公司 Video Key point real-time processing method, device and computing device
US20200068185A1 (en) * 2018-08-24 2020-02-27 Samsung Electronics Co., Ltd. Rectifying a sequence of stereo images
CN111488774A (en) * 2019-01-29 2020-08-04 北京搜狗科技发展有限公司 Image processing method and device for image processing
CN109978063A (en) * 2019-03-28 2019-07-05 厦门美图之家科技有限公司 A method of generating the alignment model of target object
CN110264431A (en) * 2019-06-29 2019-09-20 北京字节跳动网络技术有限公司 Video beautification method, device and electronic equipment
CN110856014A (en) * 2019-11-05 2020-02-28 北京奇艺世纪科技有限公司 Moving image generation method, moving image generation device, electronic device, and storage medium

Non-Patent Citations (4)

* Cited by examiner, † Cited by third party
Title
JAVIER SÁNCHEZ等: "Comparison of Motion Smoothing Strategies for Video Stabilization using Parametric Models", 《IMAGE PROCESSING ON LINE》, no. 7, 26 November 2017 (2017-11-26), pages 309 *
SWAMI SANKARANARAYANAN等: "Generate to Adapt: Aligning Domains Using Generative Adversarial Networks", 《PROCEEDINGS OF THE IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)》, 22 June 2018 (2018-06-22), pages 8503 - 8512, XP033473774, DOI: 10.1109/CVPR.2018.00887 *
吴洁: "基于学习的高分辨率大场景视频图像增强技术", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》, no. 2019, 15 July 2019 (2019-07-15), pages 138 - 1126 *
唐心宇等: "人体姿态估计及在康复训练情景交互中的应用", 《仪器仪表学报》, vol. 39, no. 11, 15 November 2018 (2018-11-15), pages 195 - 203 *

Similar Documents

Publication Publication Date Title
CN110532981B (en) Human body key point extraction method and device, readable storage medium and equipment
CN111784712B (en) Image processing method, device, equipment and computer readable medium
CN110288625B (en) Method and apparatus for processing image
CN111459364B (en) Icon updating method and device and electronic equipment
CN114964296B (en) Vehicle driving path planning method, device, equipment and computer readable medium
CN111368519A (en) Method, device, equipment and storage medium for editing online table
CN112257582A (en) Foot posture determination method, device, equipment and computer readable medium
CN111915532B (en) Image tracking method and device, electronic equipment and computer readable medium
CN112380883B (en) Model training method, machine translation method, device, equipment and storage medium
CN113191257A (en) Order of strokes detection method and device and electronic equipment
CN111756953A (en) Video processing method, device, equipment and computer readable medium
CN111461965A (en) Picture processing method and device, electronic equipment and computer readable medium
CN111338827A (en) Method and device for pasting table data and electronic equipment
CN114723640B (en) Obstacle information generation method and device, electronic equipment and computer readable medium
CN112764629B (en) Augmented reality interface display method, device, equipment and computer readable medium
CN110209851B (en) Model training method and device, electronic equipment and storage medium
CN112184593A (en) Key point determination method, device, equipment and computer readable medium
CN112418233B (en) Image processing method and device, readable medium and electronic equipment
CN111680754B (en) Image classification method, device, electronic equipment and computer readable storage medium
CN114637400A (en) Visual content updating method, head-mounted display device assembly and computer readable medium
CN110070479B (en) Method and device for positioning image deformation dragging point
CN114399627A (en) Image annotation method and device, electronic equipment and computer readable medium
CN113778078A (en) Positioning information generation method and device, electronic equipment and computer readable medium
CN112233207A (en) Image processing method, device, equipment and computer readable medium
CN112346630B (en) State determination method, device, equipment and computer readable medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination