CN115047974A - Virtual fitting interaction method and device for clothes - Google Patents
Virtual fitting interaction method and device for clothes Download PDFInfo
- Publication number
- CN115047974A CN115047974A CN202210698964.2A CN202210698964A CN115047974A CN 115047974 A CN115047974 A CN 115047974A CN 202210698964 A CN202210698964 A CN 202210698964A CN 115047974 A CN115047974 A CN 115047974A
- Authority
- CN
- China
- Prior art keywords
- clothes
- human body
- model
- parameters
- fitting
- 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
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/73—Querying
- G06F16/738—Presentation of query results
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/7867—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T13/00—Animation
- G06T13/20—3D [Three Dimensional] animation
- G06T13/40—3D [Three Dimensional] animation of characters, e.g. humans, animals or virtual beings
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/143—Sensing or illuminating at different wavelengths
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Human Computer Interaction (AREA)
- Library & Information Science (AREA)
- Computational Linguistics (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention provides a virtual fitting interaction method and a virtual fitting interaction device for clothes, wherein the method comprises the following steps: collecting human body images of a fitting object, wherein the human body images comprise visible light images and infrared images; inputting the visible light image and the infrared image into a human body parameter identification model obtained by pre-training, and identifying the human body parameters of the fitting object; acquiring an identifier of the clothes to be tried on, and selecting a clothes model of the clothes to be tried on, which is matched with the human body parameter size, from a database based on the identifier; and generating a display video of the fitting object wearing the clothes to be fitted based on the human body parameter size and the selected clothes model of the clothes to be fitted. By using the human body parameter identification method combining the visible light image and the infrared image, the influence of clothes originally worn by a fitting object on the actual parameters of the human body can be effectively avoided, and therefore more accurate human body parameter sizes can be obtained.
Description
Technical Field
The invention relates to the technical field of virtual fitting mirrors, in particular to a method and a device for interaction of clothes virtual fitting.
Background
In order to enable customers to quickly try on clothes with different clothes styles in a short time, virtual fitting glasses are put in various shopping malls and clothes stores, so that the customers can quickly find out the clothes and styles suitable for the customers. At present, a fitting system adopted by a virtual fitting mirror only obtains a visible light image of a fitting object, and then a clothing model is covered on a human body image through image processing.
Disclosure of Invention
Therefore, the invention provides a virtual fitting interaction method and a virtual fitting interaction device for clothes, aiming at solving the technical problem that the sizes of clothes and all parts of a human body are not matched because a fitting system in the prior art recognizes human body characteristics inaccurately.
According to a first aspect, an embodiment of the present invention provides a virtual fitting interaction method for a garment, including the following steps:
collecting human body images of a fitting object, wherein the human body images comprise visible light images and infrared images;
inputting the visible light image and the infrared image into a human body parameter identification model obtained by pre-training, and identifying the human body parameters of the fitting object;
acquiring an identifier of the clothes to be tried on, and selecting a clothes model of the clothes to be tried on, which is matched with the human body parameter size, from a database based on the identifier;
and generating a display video of the fitting object wearing the clothes to be fitted based on the human body parameter size and the selected clothes model of the clothes to be fitted.
Optionally, the selecting, from a database, a clothing model of the clothing to be tried, which is adapted to the human body parameter size, based on the identification, includes:
determining the type of the clothes model of the clothes to be tried on by using the identification;
acquiring size data in the human body parameters, and matching the size data with the size of the type of the clothes model;
and taking the matched clothes model as the clothes model of the selected clothes to be tried on.
Optionally, the generating a display video of the fitting subject wearing the to-be-fitted garment based on the human body parameter and the selected garment model of the to-be-fitted garment includes:
modeling the fitting object based on the human body parameter size to generate a virtual human body model of the fitting object;
fusing the selected clothes model of the clothes to be tried on with the virtual character model to obtain the virtual character model wearing the clothes model;
and controlling the virtual character model wearing the clothes model to make corresponding actions according to preset action types to form the display video.
Optionally, the body parameters further include skin color of the fitting object, and the method for virtual fitting interaction of clothing further includes: and selecting the color of the matched clothes to be tried on according to the skin color of the fitting object.
Optionally, the selecting the color of the fitting clothes according to the skin color of the fitting object includes:
and inquiring the color of the clothes to be tried, which is matched with the skin color of the fitting object, according to a pre-established skin color and clothes color matching table, and recommending the color to the fitting object.
Optionally, the human body parameters include visible light human body parameters and infrared human body parameters, the visible light human body parameters are the human body parameters of the fitting object identified according to the visible light image, and the infrared human body parameters are the human body parameters of the fitting object identified according to the infrared image.
Optionally, the acquiring size data of the human body parameter includes:
judging invalid parameters in the visible light human body parameters by using the infrared human body parameters;
and adjusting the invalid parameters into parameters corresponding to the infrared human body parameters.
Optionally, the method for virtual fitting interaction of clothing further includes:
and adjusting the visible light image part corresponding to the invalid parameter to the infrared human body parameter.
According to a second aspect, an embodiment of the present invention provides a virtual fitting interaction device for a garment, including:
the image acquisition module is used for acquiring a human body image of a fitting object, wherein the human body image comprises a visible light image and an infrared image;
the recognition module is used for inputting the visible light image and the infrared image into a human body parameter recognition model obtained by pre-training to recognize the human body parameters of the fitting object;
the selection module is used for acquiring the identification of the clothes to be tried on and selecting the clothes model of the clothes to be tried on, which is matched with the human body parameter size, from the database based on the identification;
and the display module is used for generating a display video of the clothes to be tried worn by the clothes fitting object based on the human body parameters and the selected clothes model of the clothes to be tried on by the user.
The technical scheme of the invention has the following advantages:
1. firstly, collecting a visible light human body image and an infrared human body image of a fitting object; secondly, inputting the visible light human body image and the infrared human body image into a human body parameter identification model obtained by pre-training, and identifying the human body parameters of the fitting object; selecting clothes to be tried on according to the clothes to be tried on and acquiring corresponding identification, and selecting a clothes model of the clothes to be tried on, which is matched with the human body parameter size, from a database based on the identification; finally, according to the action instruction, the fitting object completes the action and generates a display video of the fitting object wearing the clothes to be fitted. By using the human body parameter identification method combining the visible light image and the infrared image, the influence of clothes originally worn by a fitting object on the actual parameters of the human body can be effectively avoided, and therefore more accurate human body parameter sizes can be obtained. Meanwhile, a clothes model which is more adaptive to the fitting object can be selected based on the human body parameter size, the matching degree of the human body and the clothes model is higher in the generated display video, and the fitting object can be effectively and quickly helped to select clothes suitable for the person.
2. In the embodiment, the fitting object generates the virtual character model to be displayed in a three-dimensional mode, the virtual character model is fused with the selected clothes model, corresponding actions are made according to preset action types, and a display video is generated.
3. In the embodiment, the color of the clothes to be tried on, which is suitable for the fitting object, can be recommended according to the skin color of the fitting object, the fitting effect of the fitting object is improved, and the fitting object is further helped to select the clothes and style which are suitable for the fitting object.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flowchart of a specific example of a method for virtual fitting interaction of a garment in embodiment 1 of the present application;
FIG. 2 is a schematic view showing a specific example of a visible light image profile in embodiment 1 of the present application;
fig. 3 is a schematic view showing a specific example of an infrared image in embodiment 1 of the present application;
FIG. 4 is a diagram illustrating a specific example of the human body parameters before the human body parameters are not adjusted according to the visible light in embodiment 1 of the present application;
fig. 5 is a schematic diagram of a specific example of the visible light human body parameter with the upper body parameter adjusted in embodiment 1 of the present application;
fig. 6 is a schematic block diagram of a specific example of a virtual fitting interaction device for clothing in embodiment 2 of the present application.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; the two elements may be directly connected or indirectly connected through an intermediate medium, or may be communicated with each other inside the two elements, or may be wirelessly connected or wired connected. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The embodiment provides a virtual fitting interaction method for clothes, which can be executed by devices such as a portrait acquisition module and a server, acquires a human body image of a fitting object through the portrait acquisition module, processes the image and identifies human body parameters by using the devices such as the server, selects a clothes model of clothes to be fitted, which is matched with the human body parameter in size, from a database of the devices such as the server, and generates a display video of the clothes to be fitted, so as to realize the virtual fitting interaction for the clothes, as shown in fig. 1, the virtual fitting interaction method comprises the following steps:
step S101, collecting human body images of a fitting object, wherein the human body images comprise visible light images and infrared images.
The visible light image can show the whole human body shape of the fitting object, including the clothes worn by the fitting object, the human body shape outline can be better shown, the infrared image can directly show the outline of the human body according to the surface temperature of the human body, as shown in fig. 2, an L1 line in the image is a human body whole shape schematic diagram shot by the visible light image, as shown in fig. 3, the human body whole shape schematic diagram is a visible light image.
In this embodiment, the human body image of the fitting object can be simultaneously collected by using the visible light camera and the infrared camera which are arranged on the virtual fitting mirror.
And S102, inputting the visible light image and the infrared image into a human body parameter identification model obtained by pre-training, and identifying the human body parameters of the fitting object.
The human body parameter identification model can identify the overall contour parameters of the human body according to visible light images, and comprises the height, the shoulder circumference, the waist circumference, the chest circumference, the hip circumference, the neck circumference, the upper body length, the arm length, the leg length and the like of the human body, wherein the distance between the shoulder circumference, the waist circumference, the chest circumference, the hip circumference and the neck circumference is twice of the distance between one side and the other side of the human body, taking the shoulder circumference as an example, and the distance between the end points of the left shoulder and the right shoulder is twice of the distance between the end points of the left shoulder and the right shoulder. Meanwhile, the self-contour parameters of the human body are identified according to the infrared image, and the self-contour parameters of the human body are the same as the above.
The human parameter identification model is established by collecting visible light human body images and infrared human body images of people with different heights and body types at fixed positions, corresponding human body parameters of a detected person under the visible light human body images and the infrared human body images to the corresponding visible light human body images and the infrared human body images, wherein the visible light human body images, the corresponding human body parameters, the infrared human body images and the corresponding human body parameters are used as an input set and a training set, and when the visible light images and the infrared images obtained by shooting a fitting object are input into the human parameter identification model obtained by training, the human body parameters of the fitting object can be correspondingly output.
And S103, acquiring the identification of the clothes to be tried on, and selecting a clothes model of the clothes to be tried on, which is matched with the human body parameter size, from a database based on the identification.
In this embodiment, the database stores clothes of different styles and sizes, each of the clothes corresponds to a respective identifier, and the corresponding clothes style can be found according to the identifier, and each of the clothes styles also corresponds to a different size.
As described above, the visible light image shows the overall shape of the human body of the fitting object, and the infrared image directly shows the contour of the human body according to the surface temperature of the human body. If in winter, the fitting object usually wears bulkier down jackets, the virtual fitting mirror can not determine a clothes model suitable for the body parameters of the fitting object according to the visible light images or the infrared images. Because if the human body parameters corresponding to the visible light images are adopted, namely the visible light human body parameters in the embodiment, the problems that the size of the determined clothes model is larger and the determined clothes model is not matched with the real human body parameters of the fitting object occur, the display effect is poor, and the fitting object cannot select clothes and styles suitable for the fitting object; if the human body parameters corresponding to the infrared image, that is, the infrared human body parameters in this embodiment, are adopted, a problem that the determined clothes model is not matched with the visible light image corresponding to the current fitting object may occur, and if the clothes model is covered on the infrared image, the fitting object cannot judge whether the clothes model is suitable for itself according to a hairstyle, a skin color and the like.
Therefore, in this embodiment, before selecting the clothes model of the clothes to be tried, which is adapted to the human body parameter size, from the database according to the identifier, the human body parameter is optimized to obtain the human body parameter size.
Specifically, when the identified visible light human body parameters are completely the same as the infrared human body parameters, selecting the size of the clothes to be tried on corresponding to the current parameters; when the identified visible light human body parameters are the same as the infrared human body parameters, determining that the parameters of the part are effective parameters, judging whether the parameter difference value between the visible light human body parameters and the infrared human body parameters corresponding to the visible light human body parameters in the other part is within a preset difference value range, if so, determining that the corresponding visible light human body parameters are effective parameters, and selecting a corresponding clothes model of clothes to be tried on according to the parameters corresponding to the visible light image; if not, determining the corresponding visible light human body parameter as an invalid parameter, modifying the corresponding invalid parameter into the corresponding infrared human body parameter, and selecting the corresponding clothes model of the clothes to be tried according to the infrared human body parameter and part of the valid parameters.
For example, the following steps are carried out: taking the upper body as an example, the parameters of the upper body of the human body acquired according to the visible light image are as follows: 163cm of height of the human body, 82cm of shoulder circumference, 87cm of chest circumference and 82cm of waist circumference, wherein the parameters of the upper half of the human body, which are obtained according to the infrared image, are 163cm of height of the human body, 76cm of shoulder circumference, 81cm of chest circumference and 78cm of waist circumference, and if the preset difference range is more than or equal to 0 and less than or equal to 4cm, 163cm (no difference) of height of the human body and 82cm (4 cm difference) of waist circumference in the parameters of the upper half of the human body, which are obtained according to the visible image, are effective parameters, 82cm of shoulder circumference (6 cm difference) and 87cm of chest circumference (6 cm difference) are ineffective differences, and the infrared parameters corresponding to the ineffective differences of shoulder circumference and 87cm are modified, namely 76cm of shoulder circumference and 81cm of chest circumference. At the moment, the corresponding clothes model of the clothes to be tried on is selected according to the height 163cm, the shoulder circumference 76cm, the chest circumference 81cm and the waist circumference 82cm of the human body.
In addition, when the determined visible light human body parameter is an invalid parameter, the image processing is utilized to adjust the human body invalid parameter part corresponding to the visible light image to the infrared human body parameter corresponding to the human body invalid parameter part, which is to say, as the above example, the corresponding shoulder circumference and chest circumference part in the visible light image is adjusted from 82cm to 76cm, from 87cm to 81cm, so as to match with the selected corresponding clothes model of the clothes to be tried on. As shown in fig. 4 and 5, taking the upper body as an example, fig. 4 is a schematic diagram before the visible light human body parameters are adjusted, and fig. 5 is a schematic diagram after the visible light human body parameters are adjusted with the arm, waist and chest parameters.
In the embodiment, firstly, the fitting object selects the clothes to be fitted, secondly, the server selects the clothes model of the clothes to be fitted, which is matched with the optimized human body parameter size, from the database according to the self identification of the clothes to be fitted, and the clothes model can be a 3D clothes model.
And step S104, generating a display video of the fitting object wearing the clothes to be fitted based on the human body parameter size and the selected clothes model of the clothes to be fitted.
After the clothes model of the clothes to be tried on, which is matched with the optimized human body parameter size, is selected from the database, the clothes fitting object can perform action indication to complete clothes fitting display, including swinging arms up and down, rotating, shaking the body and the like, and finally a display video of the clothes to be tried on, which are worn by the clothes fitting object, can be generated.
In the embodiment, firstly, visible light human body images and infrared human body images of a fitting object are collected; secondly, inputting the visible light human body image and the infrared human body image into a human body parameter identification model obtained by pre-training, and identifying the human body parameters of the fitting object; selecting clothes to be tried on according to the clothes to be tried on and acquiring corresponding identification, and selecting a clothes model of the clothes to be tried on, which is matched with the human body parameter size, from a database based on the identification; finally, according to the action instruction, the fitting object completes the action and generates a display video of the fitting object wearing the clothes to be fitted. By using the human body parameter identification method combining the visible light image and the infrared image, the influence of clothes originally worn by a fitting object on the actual parameters of the human body can be effectively avoided, and therefore more accurate human body parameter sizes can be obtained. Meanwhile, a clothes model which is more adaptive to the fitting object can be selected based on the human body parameter size, the matching degree of the human body and the clothes model is higher in the generated display video, and the fitting object can be effectively and quickly helped to select clothes suitable for the person. Moreover, the clothes model suitable for the fitting object can be more really fitted by adopting the visible light image.
As an optional implementation manner, in an embodiment of the present invention, the selecting, from a database, a clothes model of the clothes to be tried, which is adapted to the human body parameter size, based on the identifier includes:
determining the type of the clothes model of the clothes to be tried on by using the identification;
acquiring size data in the human body parameters, and matching the size data with the size of the type of the clothes model;
and taking the matched clothes model as the clothes model of the selected clothes to be tried on.
Firstly, clothes to be tried on are selected by a clothes trying object, and secondly, the server selects a corresponding clothes model type of the clothes to be tried on from the database according to the self identification of the clothes to be tried on. Identifying corresponding visible light human body parameters and infrared human body parameters according to the obtained visible light images and infrared images, determining effective parameters and ineffective parameters according to a preset difference range, modifying the ineffective parameters into corresponding infrared human body parameters, taking the determined final effective parameters as size data in the human body parameters, matching the size data with the size of a clothes model type, and finally taking the matched clothes model as a selected clothes model of the clothes to be tried.
In the embodiment, the fitting object can select the favorite clothes model type and can also match the size of the proper clothes model type according to the size data, and the size data is matched with the size of the clothes model, so that the problem that the selected clothes model type is not matched with the size of the fitting object, and the phenomenon that the clothes model is obviously misplaced on a human body image is avoided.
As an optional implementation manner, in an embodiment of the present invention, the generating a display video of the fitting object wearing the fitting clothes based on the human body parameter and the selected clothes model of the clothes to be fitted includes:
modeling the fitting object based on the human body parameter size to generate a virtual human body model of the fitting object;
fusing the selected clothes model of the clothes to be tried on with the virtual character model to obtain the virtual character model wearing the clothes model;
and controlling the virtual character model wearing the clothes model to make corresponding actions according to preset action types to form the display video.
In this embodiment, the clothes model may be a 3D clothes model, in order to show the fitting degree of the clothes to be fitted and the fitting object in an all-round manner, the fitting object is modeled according to the human parameter size, a virtual character model of the three-dimensional fitting object is generated, and the virtual character model is fused with the clothes model determined by selection, so that the virtual character model of the clothes wearing model is presented. The fitting object only needs to control the virtual character model wearing the clothes model to make corresponding actions according to preset action types or action instructions, the actions comprise swinging arms up and down, rotating, shaking the body and the like, and a display video can be automatically formed. Through the demonstration video, the fitting object can see the adaptation degree of the clothes model and the fitting object can be seen in an all-round mode.
In the embodiment, the fitting object generates the virtual character model to be displayed in a three-dimensional mode, the virtual character model is fused with the selected clothes model, corresponding actions are made according to preset action types, and a display video is generated.
As an optional implementation manner, in an embodiment of the present invention, the human body parameter further includes a skin color of the fitting object, and the method for virtual fitting interaction of clothing further includes:
and selecting the color of the matched clothes to be tried on according to the skin color of the fitting object.
As an optional implementation manner, in an embodiment of the present invention, the selecting, according to the skin color of the fitting object, the color of the fitting clothes to be fitted includes:
and inquiring the color of the clothes to be tried, which is matched with the skin color of the fitting object, according to a pre-established skin color and clothes color matching table, and recommending the color to the fitting object.
In the embodiment, the color of the clothes to be tried on, which is suitable for the fitting object, can be recommended according to the skin color of the fitting object, the fitting effect of the fitting object is improved, and the fitting object is further helped to select the clothes and style which are suitable for the fitting object.
As an optional implementation manner, in the embodiment of the present invention, the human body parameters include a visible light human body parameter and an infrared human body parameter, the visible light human body parameter is a human body parameter of the fitting object identified according to a visible light image, and the infrared human body parameter is a human body parameter of the fitting object identified according to an infrared image.
The visible light human body parameters comprise the height, shoulder circumference, waist circumference, chest circumference, hip circumference, neck circumference, upper body length, arm length, leg length and the like of the human body, wherein the distance between one side of the human body and the other side of the human body is twice as long as the distance between the shoulder circumference, the chest circumference, the hip circumference and the neck circumference, taking the shoulder circumference as an example, the distance between the end points of the left shoulder and the right shoulder is twice as long as the distance between the end points of the left shoulder and the right shoulder, and the infrared human body parameters are the same as the above.
As an optional implementation manner, in an embodiment of the present invention, the acquiring size data in the human body parameter includes:
judging invalid parameters in the visible light human body parameters by using the infrared human body parameters;
and adjusting the invalid parameters into parameters corresponding to the infrared human body parameters.
As an optional implementation manner, in an embodiment of the present invention, the method for interacting a virtual fit of a garment further includes:
and adjusting the visible light image part corresponding to the invalid parameter to the infrared human body parameter.
Specifically, when the identified visible light human body parameters are completely the same as the infrared human body parameters, selecting the size of the clothes to be tried on corresponding to the current parameters; when the identified visible light human body parameters are the same as the infrared human body parameters, determining that the parameters of the part are effective parameters, judging whether the parameter difference value between the visible light human body parameters and the infrared human body parameters corresponding to the visible light human body parameters in the other part is within a preset difference value range, if so, determining that the corresponding visible light human body parameters are effective parameters, and selecting a corresponding clothes model of clothes to be tried to be worn according to the parameters corresponding to the visible light images; if not, determining the corresponding visible light human body parameter as an invalid parameter, modifying the corresponding invalid parameter into the corresponding infrared human body parameter, and selecting the corresponding clothes model of the clothes to be tried according to the infrared human body parameter and part of the valid parameters. In addition, when the determined visible light human body parameters are invalid parameters, the human body invalid parameter parts corresponding to the visible light images are adjusted to be corresponding infrared human body parameters by image processing.
The detailed description has been given above for the example and is not repeated herein.
Example 2
This embodiment provides a virtual fitting interaction device for clothing, which may be configured to execute the virtual fitting interaction method in embodiment 1, where the device may be disposed inside a server, a virtual fitting mirror, or other devices, and modules of the device cooperate with each other to implement virtual fitting interaction for clothing, as shown in fig. 6, the device includes:
the image acquisition module 201 is used for acquiring a human body image of a fitting object, wherein the human body image comprises a visible light image and an infrared image;
the recognition module 202 is configured to input the visible light image and the infrared image into a human body parameter recognition model obtained through pre-training, and recognize a human body parameter of the fitting object;
the selection module 203 is used for acquiring an identifier of the clothes to be tried on, and selecting a clothes model of the clothes to be tried on, which is matched with the human body parameter size, from a database based on the identifier;
and a display module 204, which is used for generating a display video of the fitting object wearing the clothes to be fitted based on the human body parameters and the selected clothes model of the clothes to be fitted.
In the embodiment, firstly, visible light human body images and infrared human body images of a fitting object are collected; secondly, inputting the visible light human body image and the infrared human body image into a human body parameter identification model obtained by pre-training, and identifying the human body parameters of the fitting object; selecting clothes to be tried on according to the clothes to be tried on and acquiring corresponding identification, and selecting a clothes model of the clothes to be tried on, which is matched with the human body parameter size, from a database based on the identification; finally, according to the action instruction, the fitting object completes the action and generates a display video of the fitting object wearing the clothes to be fitted. By using the human body parameter identification method combining the visible light image and the infrared image, the influence of clothes originally worn by a fitting object on the actual parameters of the human body can be effectively avoided, and therefore more accurate human body parameter sizes can be obtained. Meanwhile, a clothes model which is more adaptive to the fitting object can be selected based on the human body parameter size, the matching degree of the human body and the clothes model is higher in the generated display video, and the fitting object can be effectively and quickly helped to select clothes suitable for the person.
For the detailed description of the above device part, reference may be made to the above method embodiments, which are not described herein again.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (9)
1. A virtual fitting interaction method for clothes is characterized by comprising the following steps:
collecting human body images of a fitting object, wherein the human body images comprise visible light images and infrared images;
inputting the visible light image and the infrared image into a human body parameter identification model obtained by pre-training, and identifying the human body parameters of the fitting object;
acquiring an identifier of the clothes to be tried on, and selecting a clothes model of the clothes to be tried on, which is matched with the human body parameter size, from a database based on the identifier;
and generating a display video of the fitting object wearing the clothes to be fitted based on the human body parameter size and the selected clothes model of the clothes to be fitted.
2. The method for virtual fitting interaction of clothes according to claim 1, wherein the selecting a clothes model of the clothes to be fitted with the human body parameter size from a database based on the identification comprises:
determining the type of the clothes model of the clothes to be tried on by using the identification;
acquiring size data in the human body parameters, and matching the size data with the size of the type of the clothes model;
and taking the matched clothes model as the clothes model of the selected clothes to be tried on.
3. The method for virtual fitting interaction of clothes according to claim 1, wherein the generating of the display video of the fitting object wearing the clothes to be fitted based on the human body parameters and the selected clothes model of the clothes to be fitted comprises:
modeling the fitting object based on the human body parameter size to generate a virtual human body model of the fitting object;
fusing the selected clothes model of the clothes to be tried on with the virtual character model to obtain the virtual character model wearing the clothes model;
and controlling the virtual character model wearing the clothes model to make corresponding actions according to preset action types to form the display video.
4. The virtual fit interaction method for clothing according to claim 1, wherein the body parameters further include skin color of the fitting object, the virtual fit interaction method further comprising:
and selecting the color of the matched clothes to be tried on according to the skin color of the fitting object.
5. The method for virtual fitting interaction of clothes according to claim 4, wherein the selecting the adapted color of the clothes to be fitted according to the skin color of the fitting object comprises:
and inquiring the color of the clothes to be tried, which is matched with the skin color of the fitting object, according to a pre-established skin color and clothes color matching table, and recommending the color to the fitting object.
6. The virtual fitting interaction method for clothing according to claim 2, wherein the body parameters include visible light body parameters and infrared body parameters, the visible light body parameters are body parameters of the fitting object identified according to a visible light image, and the infrared body parameters are body parameters of the fitting object identified according to an infrared image.
7. The method for virtual fitting interaction of clothing according to claim 6, wherein the obtaining of the size data of the body parameters comprises:
judging invalid parameters in the visible light human body parameters by using the infrared human body parameters;
and adjusting the invalid parameters into parameters corresponding to the infrared human body parameters.
8. The method of claim 7, further comprising:
and adjusting the visible light image part corresponding to the invalid parameter to the infrared human body parameter.
9. A virtual fitting interaction device for a garment, comprising:
the image acquisition module is used for acquiring a human body image of a fitting object, wherein the human body image comprises a visible light image and an infrared image;
the recognition module is used for inputting the visible light image and the infrared image into a human body parameter recognition model obtained by pre-training to recognize the human body parameters of the fitting object;
the selection module is used for acquiring the identification of the clothes to be tried on and selecting the clothes model of the clothes to be tried on, which is matched with the human body parameter size, from the database based on the identification;
and the display module is used for generating a display video of the clothes to be tried worn by the clothes fitting object based on the human body parameters and the selected clothes model of the clothes to be tried on by the user.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210698964.2A CN115047974A (en) | 2022-06-20 | 2022-06-20 | Virtual fitting interaction method and device for clothes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210698964.2A CN115047974A (en) | 2022-06-20 | 2022-06-20 | Virtual fitting interaction method and device for clothes |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115047974A true CN115047974A (en) | 2022-09-13 |
Family
ID=83164087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210698964.2A Pending CN115047974A (en) | 2022-06-20 | 2022-06-20 | Virtual fitting interaction method and device for clothes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115047974A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115983952A (en) * | 2023-03-21 | 2023-04-18 | 江西服装学院 | Custom garment design recommendation system |
-
2022
- 2022-06-20 CN CN202210698964.2A patent/CN115047974A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115983952A (en) * | 2023-03-21 | 2023-04-18 | 江西服装学院 | Custom garment design recommendation system |
| CN115983952B (en) * | 2023-03-21 | 2023-12-08 | 江西服装学院 | Custom-made clothing design recommendation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109196516A (en) | Plant control unit and apparatus control method | |
| US20150248583A1 (en) | Image processing apparatus, image processing system, image processing method, and computer program product | |
| US20200380594A1 (en) | Virtual try-on system, virtual try-on method, computer program product, and information processing device | |
| CN107273846B (en) | Human body shape parameter determination method and device | |
| CN105308494B (en) | For determining the method for at least one value of the parameter of customization visional compensation equipment | |
| KR20200030471A (en) | Clothing registration device and clothing recommendation device, and online system including the same | |
| KR20170068741A (en) | Method and program for providing virtual fitting service | |
| CN109143581A (en) | A kind of head-mounted display apparatus and its eyeball tracking method | |
| CN104813340A (en) | System and method for deriving accurate body size measures from a sequence of 2d images | |
| EP2569744A2 (en) | Method for remotely determining clothes dimensions | |
| KR101720016B1 (en) | A clothing fitting system with a mirror display by using salient points and the method thereof | |
| WO2016158729A1 (en) | Makeup assistance system, measurement device, portable terminal device, and program | |
| CN115047974A (en) | Virtual fitting interaction method and device for clothes | |
| JP6109288B2 (en) | Information processing apparatus, information processing method, and program | |
| US20160071321A1 (en) | Image processing device, image processing system and storage medium | |
| KR102506352B1 (en) | Digital twin avatar provision system based on 3D anthropometric data for e-commerce | |
| CN109035259A (en) | A kind of three-dimensional multi-angle fitting device and fitting method | |
| KR20190127481A (en) | Method for Providing Augmented Clothing Service Based on Mobile Web | |
| KR102514515B1 (en) | A server and method for providing customized clothing by measuring the characteristics of a user's body part using a vision artificial intelligence, and a system and method therefor | |
| KR20190052830A (en) | Television for virtual fitting cloth based on augmented reality | |
| KR102117517B1 (en) | Method for Providing Augmented Wig Service | |
| KR20170131062A (en) | Apparatus and method for providing information corresponding somatotype | |
| KR101937327B1 (en) | Method for Providing Augmented Glasses Service | |
| CN111079597A (en) | Three-dimensional information detection method and electronic equipment | |
| CN106774517B (en) | Based on temprature control method, the apparatus and system virtually worn |
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 |