WO2022262508A1 - 基于增强现实的智能试穿方法、系统、终端及介质 - Google Patents

基于增强现实的智能试穿方法、系统、终端及介质 Download PDF

Info

Publication number
WO2022262508A1
WO2022262508A1 PCT/CN2022/093344 CN2022093344W WO2022262508A1 WO 2022262508 A1 WO2022262508 A1 WO 2022262508A1 CN 2022093344 W CN2022093344 W CN 2022093344W WO 2022262508 A1 WO2022262508 A1 WO 2022262508A1
Authority
WO
WIPO (PCT)
Prior art keywords
try
user
image
data
product
Prior art date
Application number
PCT/CN2022/093344
Other languages
English (en)
French (fr)
Inventor
盛铭睿
盛征
Original Assignee
盛铭睿
盛征
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 盛铭睿, 盛征 filed Critical 盛铭睿
Publication of WO2022262508A1 publication Critical patent/WO2022262508A1/zh

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
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/06—Buying, selling or leasing transactions
    • G06Q30/0601—Electronic shopping [e-shopping]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects

Definitions

  • the present application relates to the field of virtual try-on technology, in particular to an augmented reality-based intelligent try-on method, system, terminal and medium.
  • the purpose of this application is to provide a smart try-on method, system, terminal and medium based on augmented reality to solve the technical problem that online shopping cannot be tried on in time in the prior art.
  • the first aspect of the present application provides an intelligent try-on method based on augmented reality, including: obtaining product feature data of the try-on product, and generating a corresponding virtual product image based on it; obtaining try-on A real mirror image of the user; combining the virtual product image of the try-on commodity with the real mirror image of the try-on user to generate and display a corresponding try-on effect image and/or dynamic image.
  • the method further includes: acquiring elasticity data of the product to be tried on; adjusting the try-on effect image according to the elasticity data when the try-on user changes the try-on posture , and emit the corresponding simulation sound of the fitting scene.
  • the method further includes: obtaining and displaying the total number of times the try-on product is tried on in the area where the try-on user is located within a preset period of time , for analysis of the item's popularity and/or chance of hitting a shirt.
  • the method further includes: in an offline state, acquiring the product feature data of the try-on product from an external storage device through a communication interface, and storing the virtual product image of the try-on product Combined with the real mirror image of the user trying on, generate and display a trying-on effect image.
  • the facial feature data at least includes acquiring and saving the body shape feature data of the try-on user based on the real mirror image of the try-on user; according to the stored body shape feature data Generate body shape change trend information, and send corresponding warning information to the try-on user when one or more reminder feature data exceeds a preset threshold; the warning information includes body management warning information and/or product size adjustment warning information.
  • the method further includes: constructing an adapted virtual environment effect according to the product characteristic data of the try-on product; wherein, the construction dimension of the virtual environment effect includes at least : weather dimension and/or space place type dimension and/or light and shade dimension; combine the virtual product image of the try-on product, the real image of the try-on user and the virtual environment effect to generate and display the virtual environment Try on effect image.
  • the method further includes: constructing a virtual environment effect according to the characteristics of the try-on product for the try-on user to verify the characteristics of the try-on product.
  • the second aspect of the present application provides an intelligent try-on system based on augmented reality, including: an image acquisition device, which is used to acquire image data of the try-on user and extract facial feature data; body shape data The collection device is used to obtain the body shape characteristic data of the try-on user; the smart try-on mirror is connected to the image collection device and the body shape data collection device through communication; to generate a corresponding virtual product image; obtain a real mirror image of the try-on user; combine the virtual product image of the try-on product with the real mirror image of the try-on user to generate and display a corresponding try-on effect image and/or motion picture.
  • the body shape data acquisition device includes any one or a combination of the following modules: weight data acquisition module, height data acquisition module, bust data acquisition module, waist circumference data acquisition module , hip circumference data acquisition module, shoulder width data acquisition module, leg length data acquisition module, neck length data acquisition module, arm span data acquisition module, head circumference data acquisition module, leg circumference data acquisition module, arm circumference data acquisition module, hand Body size data acquisition module and foot size data acquisition module.
  • the smart try-on mirror includes: an AR display mirror, a computing processor, a graphics processor, a memory, a communicator, an interface component, and an input device.
  • the third aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the smart try-on based on augmented reality is realized. method.
  • the fourth aspect of the present application provides an electronic terminal, including: a processor and a memory; the memory is used to store computer programs, and the processor is used to execute the computer programs stored in the memory , so that the terminal executes the augmented reality-based intelligent try-on method.
  • the augmented reality-based intelligent try-on method, system, terminal and medium of the present application have the following beneficial effects: the technical solution of the present invention is convenient for users to obtain corresponding virtual
  • the try-on effect image is the most convenient and intuitive way to feel the wearing effect of the product, which not only saves the tediousness of offline try-on, but also reduces the logistics pressure caused by the return.
  • the present invention also provides the function of offline try-on, which avoids various disputes and greatly improves user experience.
  • Fig. 1 is a schematic structural diagram of an augmented reality-based smart try-on system in an embodiment of the present application.
  • Fig. 2 is a schematic flowchart of an augmented reality-based intelligent try-on method in an embodiment of the present application.
  • FIG. 3 is a schematic structural diagram of an electronic terminal in an embodiment of the present application.
  • the present invention provides a smart try-on mirror based on augmented reality.
  • a certain number of image acquisition devices and body data acquisition devices are equipped around the smart try-on mirror.
  • the image acquisition device For collecting the image data of the try-on user, the body shape data collection device is used to collect the body data of the try-on user; the smart try-on mirror obtains the body data of the try-on user through the image collection device and the body data collection device Image data and extract face feature data and body data, combined with product feature data (such as color feature data, size feature data, shape feature data, etc.)
  • product feature data such as color feature data, size feature data, shape feature data, etc.
  • FIG. 1 a schematic structural diagram of an augmented reality-based intelligent try-on system in an embodiment of the present invention is shown.
  • the intelligent try-on system of the present embodiment comprises: an intelligent try-on mirror 11, an image acquisition device 12 and a body shape data acquisition device 13, and the intelligent try-on mirror establishes a communication connection with the image acquisition device 12 and the body shape data acquisition device 13 for Image data and body data of a user who is trying on the clothes are received.
  • the smart try-on mirror 11 is used to obtain commodity feature data of the try-on commodity, and generate a corresponding virtual commodity image accordingly; obtain a real mirror image of the try-on user; The image is combined with the real mirror image of the user trying on, to generate and display a corresponding trying-on effect image.
  • the smart try-on system forms the final try-on effect image based on the real image of the user.
  • the smart try-on mirror of the present invention shows The real mirror image of the user will change the mirror image and the final try-on effect image accordingly with the user's activities.
  • the existing system cannot perceive it in time, and can only be sensed by updating the data after the user actively inputs, but the technical solution of the present invention can sense the user's body shape change in time through the user image.
  • the smart try-on mirror 11 includes components such as an AR display mirror, a computing processor, a graphics processor, a memory, a communicator, an interface component, and an input device.
  • the AR display mirror is used to display the virtual try-on effect of the product and the try-on user.
  • the calculation processor includes but not limited to ARM (Advanced RISC Machines) controller, FPGA (Field Programmable Gate Array) controller, SoC (System on Chip) controller, DSP (Digital Signal Processing) controller, or MCU (Micorcontroller Unit) controller, etc.
  • the graphics processing unit (Graphics Processing Unit) is a kind of microprocessor specialized in image computing work on personal computers, workstations, game consoles and some mobile devices (such as tablet computers or smart phones, etc.), and is used to convert all computer systems into It converts and drives the required display information, and provides line scanning signals to the display to control the correct display of the display. It is an important component for connecting the display and the motherboard of the personal computer.
  • the memory may include a random access memory (Random Access Memory, RAM for short), and may also include a non-volatile memory (non-volatile memory).
  • the interface components include but not limited to USB interface, RS-232 interface, SATA interface, keyboard interface or mouse interface and so on.
  • the input devices include, but are not limited to, a mouse, a keyboard, and the like.
  • the image acquisition device 12 may be a camera module, and the camera module includes a camera device, a storage device and a processing device.
  • the camera device includes, but is not limited to: a camera, a video camera, a camera module integrated with an optical system or a CCD chip, a camera module integrated with an optical system and a CMOS chip, and the like.
  • the image acquisition device acquires the image data of the try-on user and the relative position data between the user and the smart try-on mirror, and the relative position data is used to reflect the degree to which the user deviates from the try-on mirror, so as to better The virtual item image is matched to the user's real mirror image.
  • the smart try-on mirror 11 can acquire the image of the try-on user from the image acquisition device and extract corresponding facial feature data therefrom. For example, after the image is acquired, use image recognition algorithms (such as image segmentation algorithm, image classification algorithm, object detection algorithm, etc.) Data, hairstyle data, hair color data, facial feature data and other facial feature data.
  • image recognition algorithms such as image segmentation algorithm, image classification algorithm, object detection algorithm, etc.
  • the body shape data collection device 13 includes but is not limited to: weight data collection module, height data collection module, bust data collection module, waist data collection module, hip data collection module, shoulder width data collection module, leg Length data acquisition module, neck length data acquisition module, arm span data acquisition module, head circumference data acquisition module, leg circumference data acquisition module, arm circumference data acquisition module, hand size data acquisition module, foot size data acquisition module, etc.
  • a laser body 3D scanner can be used to scan a user for a try-on to obtain the following data of the user: height data, weight data, chest circumference data, waist circumference data, hip circumference data, shoulder width data, leg length data, neck length data Data, arm span data, head circumference data, leg circumference data, arm circumference data, hand size data, foot size data, etc.
  • various measuring instruments with data interaction functions can also be used, such as body weight measuring instruments, height measuring instruments, waist circumference measuring instruments, etc. to measure corresponding data and then send them to the smart try-on mirror.
  • the product feature data acquired by the smart try-on mirror 11 includes but is not limited to size data, color data, style data, texture data, softness data, weight data, material data, etc.; the try-on product can be Apparel, coats, shoes, accessories, glasses, etc.
  • the way for the smart try-on mirror 11 to obtain the product feature data of the product can be any one or more of the following combinations:
  • the smart try-on mirror 11 is connected to the Internet through a wireless communication module, and is connected to a shopping APP (such as Taobao, Tmall, Jingdong, Pinduoduo, etc.) through the Internet to obtain the product to be tried on, and extract the product Characteristic data to match the user's physical data.
  • a shopping APP such as Taobao, Tmall, Jingdong, Pinduoduo, etc.
  • the smart try-on mirror 11 can establish a communication connection (such as via bluetooth or infrared) with some smart terminal devices (such as mobile phones, pad computers or smart watches, etc.), and obtain the information of the product to be tried on from the smart terminal device. Commodity characteristic data.
  • the mobile phone transmits the product feature data of the product to the smart fitting mirror through Bluetooth.
  • the smart try-on mirror 11 can also obtain the product characteristic data of the product to be tried in an offline state, that is, connect an external storage device through the communication interface, and import the data of the product to be tried on from the storage device.
  • Commodity characteristic data For example, the smart try-on mirror 11 can be set to only acquire product feature data from devices such as USB devices or mobile storage, so as to match the user's body data. In this case, complete offline operation can be realized to avoid leakage of personal privacy data.
  • the smart try-on mirror 11 can also be equipped with human-computer interaction components (such as touch screen, keyboard, etc.), for the try-on user to manually input the product feature data of the product to realize personal DIY design. Size and color, style and color of clothing, shoe size and style, etc.
  • the smart try-on mirror 11 also acquires elastic data of the product to be tried on, and adjusts the virtual image according to the elastic data and emits a scene simulation sound when the user changes the try-on posture.
  • the user usually squats down to feel the elasticity of the trousers when trying on the trousers, or fastens the buttons on the try-on clothes to feel the elasticity of the clothes. Therefore, in this embodiment, according to the elasticity data of the clothes to simulate these feelings, such as when the user squats down, the pants will be tight, the clothes will be tight when the buttons are fastened, and in extreme cases, it will simulate the sound of the pants collapsing, etc., which can improve the user experience.
  • the smart try-on mirror 11 uses AR technology to generate and display a try-on effect AR image on the mirror based on the image data and body data of the try-on user and the product feature data of the product to be tried on.
  • AR technology is an augmented reality technology, a technology that ingeniously integrates virtual information with the real world, and promotes the integration of real world information and virtual world information content. That is, the smart try-on mirror 11 first displays the real mirror image of the user trying on the mirror, and then generates an AR image after the user puts on the product according to the product feature data of the product to be tried on, and displays the AR image on the mirror. In this way, the most intuitive feeling can be given to the user, not only can know whether the product fits through the mirror image on the mirror, but also know how the upper body effect of the product is.
  • the technical solution of the present invention is to construct the final try-on effect image based on the real image of the try-on user. It can be more directly displayed in the mirror, thereby bringing a better user experience.
  • the smart try-on mirror acquires data on product feature modification and/or evaluation data performed by the user on the current try-on effect in response to user operations through human-computer interaction.
  • the product feature modification data mainly refers to some modifications made by the user because the current try-on effect is not satisfactory, such as adjusting the size of the product, changing the color of the product, changing the product, and so on.
  • the smart try-on mirror obtains product feature modification data and/or evaluation data, it adjusts the product accordingly and adjusts the display effect according to these data; it can also feed these data back to the corresponding merchant and inform the merchant to provide more suitable products , or provide users with DIY services according to their needs.
  • the smart try-on mirror obtains the total number of times that the product to be tried is tried on in the user's area and within a preset period of time, and displays it on the mirror for analysis of the product's popularity and/or The probability of hitting a shirt. For example, when a user tries on a certain T-shirt, the smart try-on mirror can display on the mirror based on big data that the T-shirt has been tried by other users in city A and city B where the user is located in the past month. After wearing it 100 times, the user can determine that this T-shirt is very popular after seeing the data, and can also avoid buying this T-shirt based on the data to avoid collisions.
  • the smart try-on mirror is also based on the real image of the try-on user, acquires and saves the body shape characteristic data of the try-on user; generates body shape change trend information according to the saved body shape characteristic data, and When one or more reminding feature data exceeds a preset threshold, corresponding warning information is sent to the try-on user; the warning information includes body management warning information and/or commodity size adjustment warning information.
  • the smart fitting mirror can save the user's body shape characteristic data and the corresponding time stamp every time he looks in the mirror or tries on a product.
  • the saved user body shape characteristic data includes But not limited to waist circumference data, arm circumference data, hip circumference data, leg circumference data, height data, weight data, etc.; then, the trend curve of its body shape characteristic data can be displayed to the user on a regular basis, or in a certain item or a certain item of the user.
  • a body management warning message will be issued to the user, such as "Your waistline has increased too fast in the past three months, please pay attention to increasing exercise.”
  • it is also necessary to send a warning message to the user to adjust the size of the product such as "Your height has increased by 5 cm, please pay attention to adjusting the size of the pants”.
  • the smart try-on mirror constructs an adapted virtual environment effect according to the product feature data of the try-on product; wherein, the construction dimensions of the virtual environment effect include at least: weather dimension and/or space location Type dimension and/or light and shade dimension; combine the virtual product image of the try-on product, the real image of the try-on user and the virtual environment effect to generate and display the try-on effect image in the virtual environment.
  • the weather dimension refers to simulated weather conditions, such as sunny days, rainy days, windy days, nights, etc.
  • the space place type dimension refers to simulated space places, such as stadiums, cinemas, gyms, playgrounds, libraries, offices, and bus lights
  • the light and shade dimension refers to indoor lighting intensity conditions, indoor lighting light types, and outdoor lighting intensity conditions.
  • the selection of the weather dimension and/or the space type dimension and/or the light and shade dimension are all adjusted according to the characteristics of the product, for example: if the user chooses to buy a suit, the space can be adjusted when trying on The type of place is simulated as an office, dinner party, or walking on the red carpet; if the user buys sports pants, the type of space and place can be simulated as a gym or a playground when trying them on; if the user buys sunglasses, they can The weather is simulated as a sunny day; there are many simulated scenarios, so I won't go into details here.
  • the smart try-on mirror constructs a virtual environment effect according to the characteristics of the try-on product for the try-on user to verify the characteristics of the try-on product. For example, construct a virtual environment effect based on the material of the product to be tried on, and simulate whether the clothes will get wet after being exposed to water, the degree of wrinkling, the degree of fit, etc. Users can verify the waterproofness of the purchased product through such simulation effects.
  • FIG. 2 shows a schematic flowchart of an augmented reality-based intelligent try-on method in an embodiment of the present invention, including steps S21-S23. It should be understood that the smart try-on method provided in this embodiment is applied to the smart try-on mirror in the above-mentioned smart try-on system.
  • Step S21 Obtain commodity feature data of the try-on commodity, and generate a corresponding virtual commodity image accordingly.
  • the product feature data of the try-on product includes but not limited to size data, color data, style data, texture data, softness data, weight data, material data, and the like.
  • the try-on items may be clothing, hats, shoes, accessories, glasses, and the like.
  • Step S22 Obtain the real image of the user who is trying on the clothes.
  • Step S23 Combining the virtual product image of the try-on product with the real image of the try-on user to generate and display a corresponding try-on effect image.
  • AR technology is used to generate and display a try-on effect AR image on the mirror.
  • AR technology is an augmented reality technology, a technology that ingeniously integrates virtual information with the real world, and promotes the integration of real world information and virtual world information content. That is, the smart try-on mirror 11 first displays the real mirror image of the user trying on the mirror, and then generates an AR image after the user puts on the product according to the product feature data of the product to be tried on, and displays the AR image on the mirror. In this way, the most intuitive feeling can be given to the user, not only can know whether the product fits through the mirror image on the mirror, but also know how the upper body effect of the product is.
  • the method further includes acquiring elasticity data of the try-on product, adjusting the try-on effect image according to the elasticity data when the try-on user changes the try-on posture, and issuing a corresponding try-on scene simulation sound.
  • the user usually squats down to feel the elasticity of the trousers when trying on the trousers, or fastens the buttons on the try-on clothes to feel the elasticity of the clothes. Therefore, in this embodiment, according to the elasticity data of the clothes to simulate these feelings, such as when the user squats down, the pants will be tight, the clothes will be tight when the buttons are fastened, and in extreme cases, it will simulate the sound of the pants collapsing, etc., which can improve the user experience.
  • the method further includes adjusting the product accordingly and adjusting the display effect according to the data after obtaining the product feature modification data and/or evaluation data; it is also possible to feed back these data to the corresponding merchant, and inform the merchant to provide More suitable products, or provide users with DIY services according to their needs.
  • the method further includes obtaining and displaying the total number of times the try-on product is tried on within a preset period of time in the area where the try-on user is located, for analysis of the popularity of the product and/or Or the probability of hitting a shirt. For example, when a user tries on a certain T-shirt, the smart try-on mirror can display on the mirror based on big data that the T-shirt has been tried by other users in city A and city B where the user is located in the past month. After wearing it 100 times, the user can determine that this T-shirt is very popular after seeing the data, and can also avoid buying this T-shirt based on the data to avoid collisions.
  • the method further includes acquiring and saving the body shape feature data of the try-on user based on the real image of the try-on user; generating body shape change trend information according to the saved body shape feature data, and When a plurality of reminding feature data exceeds a preset threshold, corresponding warning information is sent to the try-on user; the warning information includes body management warning information and/or product size adjustment warning information.
  • the method further includes that after the user uses the smart try-on mirror for a period of time, the smart try-on mirror can save the user's body shape feature data and the corresponding time stamp each time he looks in the mirror or tries on a product, and saves
  • the user's body shape characteristic data includes but not limited to waist circumference data, arm circumference data, hip circumference data, leg circumference data, height data, weight data, etc.; then, the change trend curve of the body shape characteristic data can be displayed to the user on a regular basis, or in the user
  • the body management warning message such as "Your waistline has increased too fast in the past three months, please pay attention to increasing exercise."
  • it is also necessary to send a warning message to the user to adjust the size of the product such as "Your height has increased by 5 cm, please pay attention to adjusting the size of the pants”.
  • the method further includes constructing an adapted virtual environment effect according to the product feature data of the try-on product; wherein, the construction dimensions of the virtual environment effect include at least: weather dimension and/or space type Dimensions and/or light and shade dimensions; combine the virtual product image of the try-on product, the real mirror image of the try-on user and the virtual environment effect to generate and display a try-on effect image in the virtual environment.
  • the weather dimension refers to simulated weather conditions, such as sunny days, rainy days, windy days, nights, etc.
  • the space place type dimension refers to simulated space places, such as stadiums, cinemas, gyms, playgrounds, libraries, offices, and bus lights
  • the light and shade dimension refers to indoor lighting intensity conditions, indoor lighting light types, and outdoor lighting intensity conditions.
  • the selection of the weather dimension and/or the space type dimension and/or the light and shade dimension are all adjusted according to the characteristics of the product, for example: if the user chooses to buy a suit, the space can be adjusted when trying on The type of place is simulated as an office, dinner party, or walking on the red carpet; if the user buys sports pants, the type of space and place can be simulated as a gym or a playground when trying them on; if the user buys sunglasses, they can The weather is simulated as a sunny day; there are many simulated scenarios, so I won't go into details here.
  • the method further includes constructing a virtual environment effect according to the characteristics of the try-on product for the try-on user to verify the characteristics of the try-on product. For example, construct a virtual environment effect based on the material of the product to be tried on, and simulate whether the clothes will get wet after being exposed to water, the degree of wrinkling, the degree of fit, etc. Users can verify the waterproofness of the purchased product through such simulation effects.
  • This embodiment provides a schematic structural diagram of an electronic terminal.
  • the electronic terminal provided by this example includes: a processor 31, a memory 32, and a communicator 33; the memory 32 is connected to the processor 31 and the communicator 33 through a system bus and completes mutual communication, and the memory 32 is used to store computer programs and communicate
  • the device 33 is used to communicate with other devices, and the processor 31 is used to run a computer program, so that the electronic terminal executes the above steps of the smart try-on method based on augmented reality.
  • the system bus mentioned above may be a Peripheral Component Interconnect (PCI for short) bus or an Extended Industry Standard Architecture (EISA for short) bus or the like.
  • PCI Peripheral Component Interconnect
  • EISA Extended Industry Standard Architecture
  • the system bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
  • the communication interface is used to realize the communication between the database access device and other devices (such as client, read-write library and read-only library).
  • the memory may include random access memory (Random Access Memory, RAM for short), and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
  • the above-mentioned processor can be a general-purpose processor, including a central processing unit (Central Processing Unit, referred to as CPU), a network processor (Network Processor, referred to as NP), etc.; it can also be a digital signal processor (Digital Signal Processing, referred to as DSP) , Application Specific Integrated Circuit (ASIC for short), Field Programmable Gate Array (Field-Programmable Gate Array, FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • CPU Central Processing Unit
  • NP Network Processor
  • DSP Digital Signal Processing
  • ASIC Application Specific Integrated Circuit
  • FPGA Field-Programmable Gate Array
  • the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the intelligent try-on method based on augmented reality is realized.
  • the aforementioned computer program can be stored in a computer-readable storage medium.
  • the program executes the steps including the above-mentioned method embodiments; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other various media that can store program codes.
  • the computer-readable storage medium may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, flash memory, USB flash drive, removable hard disk, or any other medium that can be used to store desired program code in the form of instructions or data structures and can be accessed by a computer. Also, any connection is properly termed a computer-readable medium.
  • the instruction is sent from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair wire, digital subscriber line (DSL), or wireless technology such as infrared, radio, and microwave
  • coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave
  • computer readable and writable storage media and data storage media do not include connections, carrier waves, signals, or other transitory media, but are intended to be directed to non-transitory, tangible storage media.
  • Disk and disc includes compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disc, and blu-ray disc, where disks usually reproduce data magnetically, while discs reproduce data optically with lasers. copy data.
  • this application provides a smart try-on method, system, terminal and medium based on augmented reality.
  • the technical solution of the present invention is convenient for users to obtain corresponding virtual try-on effect images according to commodity feature data when shopping online. , the most convenient and intuitive way to feel the wearing effect of the product, which not only eliminates the tediousness of offline try-on, but also eases the logistics pressure caused by returns.
  • the present invention also provides the function of offline try-on, which avoids various disputes and greatly improves user experience. Therefore, the present application effectively overcomes various shortcomings in the prior art and has high industrial application value.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Finance (AREA)
  • General Engineering & Computer Science (AREA)
  • Economics (AREA)
  • General Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • Development Economics (AREA)
  • Human Computer Interaction (AREA)
  • Computer Graphics (AREA)
  • Geometry (AREA)
  • Software Systems (AREA)
  • Processing Or Creating Images (AREA)

Abstract

本申请提供基于增强现实的智能试穿方法、系统、终端及介质，其获取试穿商品的商品特征数据，据以生成对应的虚拟商品图像；获取试穿用户的真实镜像；将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示对应的试穿效果图像。本发明的技术方案便于使用者在线上购物时，根据商品特征数据便可获得相应的虚拟试穿效果图像，最方便且直观地感受到商品的穿戴效果，不仅免去线下试穿的繁琐，也缓解了因退货造成的物流压力。另外，考虑到使用者隐私问题，本发明也提供离线试穿的功能，避免产生各种纠纷，用户体验大大提升。

Description

基于增强现实的智能试穿方法、系统、终端及介质 技术领域
本申请涉及虚拟试穿技术领域，特别是涉及基于增强现实的智能试穿方法、系统、终端及介质。
背景技术
随着互联网的普及，人们的购物方式也在发生着巨变，现在已经很少有人会前往实体店铺购物。网购虽然方便，但也有其自身的缺陷，例如购买服饰时不能试穿，消费者只能先将服饰买回试穿后才能验证该服饰是否合适，所以经常出现退货的情况，这不仅影响了购物体验，容易引起商家和客户之间的矛盾，也大大增加了物流压力。
发明内容
鉴于以上所述现有技术的缺点，本申请的目的在于提供基于增强现实的智能试穿方法、系统、终端及介质，用于解决现有技术中线上购物无法及时试穿的技术问题。
为实现上述目的及其他相关目的，本申请的第一方面提供一种基于增强现实的智能试穿方法，包括：获取试穿商品的商品特征数据，据以生成对应的虚拟商品图像；获取试穿用户的真实镜像；将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示对应的试穿效果图像和/或动态影像。
于本申请的第一方面的一些实施例中，所述方法还包括：获取试穿商品的弹性数据；在所述试穿用户改变试穿姿态时根据所述弹性数据调整所述试穿效果图像，并发出相应的试穿场景模拟声音。
于本申请的第一方面的一些实施例中，所述方法还包括：获取所述并显示一预设时段内，在所述试穿用户所在区域内所述试穿商品被试穿的总次数，供分析该商品的受欢迎程度和/或撞衫概率。
于本申请的第一方面的一些实施例中，所述方法还包括：在离线状态下，通过通信接口从外部存储设备获取试穿商品的商品特征数据，将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示试穿效果图像。
于本申请的第一方面的一些实施例中，所述脸型特征数据至少包括基于所述试穿用户的真实镜像，获取并保存所述试穿用户的体型特征数据；根据所保存的体型特征数据生成体型变化趋势信息，并在一或多个提醒特征数据超过预设阈值时向所述试穿用户发出相应的警示 信息；所述警示信息包括身材管理警示信息和/或调整商品尺寸警示信息。
于本申请的第一方面的一些实施例中，所述方法还包括：根据所述试穿商品的商品特征数据，构建适配的虚拟环境效果；其中，所述虚拟环境效果的构建维度至少包括：天气维度和/或空间场所类型维度和/或光线明暗维度；将所述试穿商品的虚拟商品图像、所述试穿用户的真实镜像及虚拟环境效果相结合，生成并显示虚拟环境下的试穿效果图像。
于本申请的第一方面的一些实施例中，所述方法还包括：按照所述试穿商品的特性来构建虚拟环境效果，供试穿用户验证该试穿商品的特性。
为实现上述目的及其他相关目的，本申请的第二方面提供一种基于增强现实的智能试穿系统，包括：图像采集装置，用于获取试穿用户的图像数据并提取脸型特征数据；体型数据采集装置，用于获取所述试穿用户的体型特征数据；智能试穿镜，通信连接所述图像采集装置和体型数据采集装置；所述智能试穿镜获取试穿商品的商品特征数据，据以生成对应的虚拟商品图像；获取试穿用户的真实镜像；将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示对应的试穿效果图像和/或动态影像。
于本申请的第二方面的一些实施例中，所述体型数据采集装置包括如下任一种或多种模块的组合：体重数据采集模块、身高数据采集模块、胸围数据采集模块、腰围数据采集模块、臀围数据采集模块、肩宽数据采集模块、腿长数据采集模块、颈长数据采集模块、臂展数据采集模块、头围数据采集模块、腿围数据采集模块、臂围数据采集模块、手部尺寸数据采集模块及脚部尺寸数据采集模块。
于本申请的第二方面的一些实施例中，所述智能试穿镜包括：AR显示镜面、计算处理器、图形处理器、存储器、通信器、接口组件、输入设备。
为实现上述目的及其他相关目的，本申请的第三方面提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现所述基于增强现实的智能试穿方法。
为实现上述目的及其他相关目的，本申请的第四方面提供一种电子终端，包括：处理器及存储器；所述存储器用于存储计算机程序，所述处理器用于执行所述存储器存储的计算机程序，以使所述终端执行所述基于增强现实的智能试穿方法。
如上所述，本申请的基于增强现实的智能试穿方法、系统、终端及介质，具有以下有益效果：本发明的技术方案便于使用者在线上购物时，根据商品特征数据便可获得相应的虚拟试穿效果图像，最方便且直观地感受到商品的穿戴效果，不仅免去线下试穿的繁琐，也减缓了因退货造成的物流压力。另外，考虑到使用者隐私问题，本发明也提供离线试穿的功能， 避免产生各种纠纷，用户体验大大提升。
附图说明
图1显示为本申请一实施例中基于增强现实的智能试穿系统的结构示意图。
图2显示为本申请一实施例中基于增强现实的智能试穿方法的流程示意图。
图3显示为本申请一实施例中电子终端的结构示意图。
具体实施方式
以下通过特定的具体实例说明本申请的实施方式，本领域技术人员可由本说明书所揭露的内容轻易地了解本申请的其他优点与功效。本申请还可以通过另外不同的具体实施方式加以实施或应用，本说明书中的各项细节也可以基于不同观点与应用，在没有背离本申请的精神下进行各种修饰或改变。需说明的是，在不冲突的情况下，以下实施例及实施例中的特征可以相互组合。
需要说明的是，在下述描述中，参考附图，附图描述了本申请的若干实施例。应当理解，还可使用其他实施例，并且可以在不背离本申请的精神和范围的情况下进行机械组成、结构、电气以及操作上的改变。下面的详细描述不应该被认为是限制性的，并且本申请的实施例的范围仅由公布的专利的权利要求书所限定。这里使用的术语仅是为了描述特定实施例，而并非旨在限制本申请。空间相关的术语，例如“上”、“下”、“左”、“右”、“下面”、“下方”、“下部”、“上方”、“上部”等，可在文中使用以便于说明图中所示的一个元件或特征与另一元件或特征的关系。
在本申请中，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”、“固定”、“固持”等术语应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。对于本领域的普通技术人员而言，可以根据具体情况理解上述术语在本申请中的具体含义。
再者，如同在本文中所使用的，单数形式“一”、“一个”和“该”旨在也包括复数形式，除非上下文中有相反的指示。本发明的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”“第四”等(如果存在)是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外，术语“包含”、“包括”表明存在所述的特征、操作、元件、组件、项目、种类、和/或组，但不排除一个或多个其他特 征、操作、元件、组件、项目、种类、和/或组的存在、出现或添加。应当进一步理解，此处使用的术语“或”和“和/或”被解释为包括性的，或意味着任一个或任何组合。因此，“A、B或C”或者“A、B和/或C”意味着“以下任一个：A；B；C；A和B；A和C；B和C；A、B和C”。仅当元件、功能或操作的组合在某些方式下内在地互相排斥时，才会出现该定义的例外。
为了解决上述背景技术中的问题，本发明提供一种基于增强现实的智能试穿镜，所述智能试穿镜的四周配备有一定数量的图像采集装置和身材数据采集装置，所述图像采集装置用于采集试穿用户的图像数据，所述体型数据采集装置用于采集所述试穿用户的身体数据；所述智能试穿镜通过所述图像采集装置和身材数据采集装置获取试穿用户的图像数据并提取脸型特征数据和身体数据，并结合被选中试穿商品的商品特征数据(如颜色特征数据、尺寸特征数据、造型特征数据等)，将最终形成的虚拟试穿效果通过AR技术显示在智能试穿镜上，试穿用户免于实体试衣，通过网络即可直观感受到商品与自身的匹配效果。
为了使本发明的目的、技术方案及优点更加清楚明白，通过下述实施例并结合附图，对本发明实施例中的技术方案的进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定发明。
实施例一：
如图1所示，展示了本发明一实施例中基于增强现实的智能试穿系统的结构示意图。本实施例的智能试穿系统包括：智能试穿镜11、图像采集装置12和体型数据采集装置13，所述智能试穿镜与图像采集装置12和体型数据采集装置13建立通信连接，用以接收试穿用户的图像数据和身体数据。
在本实施例中，所述智能试穿镜11用于获取试穿商品的商品特征数据，据以生成对应的虚拟商品图像；获取试穿用户的真实镜像；将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示对应的试穿效果图像。
需说明的是，本发明提供的智能试穿系统，是基于用户的真实镜像后形成最终的试穿效果图像的，这与现有的一些需要用户主动上传数据的技术方案相比，一是更加方便，二是很好地保护了用户隐私。另外，由于试穿商品是一个动态的过程，而用户主动上传的数据是静态的，它不会随着用户在试穿过程中走动而相应改变形态，而本发明的智能试穿镜展现的是用户的真实镜像，会随着用户活动而相应改变镜像及最终的试穿效果图像。再者，当用户身型发生变化时，现有的系统无法及时感知，只能通过用户主动输入后更新数据才能感知到，而本发明的技术方案可通过用户镜像及时感知到用户身型变化。
在一些示例中，所述智能试穿镜11包括AR显示镜面、计算处理器、图形处理器、存储器、通信器、接口组件、输入设备等部件。其中，所述AR显示镜面用于显示商品与试穿用户的虚拟试穿效果。所述计算处理器包括但不限于ARM(Advanced RISC Machines)控制器、FPGA(Field Programmable Gate Array)控制器、SoC(System on Chip)控制器、DSP(Digital Signal Processing)控制器、或者MCU(Micorcontroller Unit)控制器等。所述图形处理器(Graphics Processing Unit)是一种专门在个人电脑、工作站、游戏机和一些移动设备(如平板电脑或智能手机等)上图像运算工作的微处理器，用于将计算机系统所需的显示信息进行转换驱动，并向显示器提供行扫描信号，控制显示器的正确显示，是连接显示器和个人电脑主板的重要元件。所述存储器可能包含随机存取存储器(Random Access Memory，简称RAM)，也可能还包括非易失性存储器(non-volatile memory)。所述接口组件包括但不限于USB接口、RS-232接口、SATA接口、键盘接口或鼠标接口等。所述输入设备包括但不限于鼠标、键盘等。
在一些示例中，所述图像采集装置12可以为摄像模组，所述摄像模组包括摄像装置、存储装置和处理装置。所述摄像装置包括但不限于：照相机、视频摄像机、集成有光学系统或CCD芯片的摄像模块、集成有光学系统和CMOS芯片的摄像模块等。所述图像采集装置获取试穿用户的图像数据及该用户与智能试穿镜之间的相对位置数据，所述相对位置数据用于反映该用户偏离试穿镜的程度，从而能够更好地将虚拟商品图像匹配于用户的真实镜像。
进一步地，智能试穿镜11可从图像采集装置获取所述试穿用户的图像并从中提取出相应的脸型特征数据。举例来说，在获取到图像后，利用图像识别算法(如图像分割算法、图像分类算法、目标检测算法等)对图像进行处理，并从中提取出用户的脸型特征数据，例如试穿用户的肤色数据、发型数据、发色数据、五官特征数据等脸型特征数据。
在一些示例中，所述体型数据采集装置13包括但不限于：体重数据采集模块、身高数据采集模块、胸围数据采集模块、腰围数据采集模块、臀围数据采集模块、肩宽数据采集模块、腿长数据采集模块、颈长数据采集模块、臂展数据采集模块、头围数据采集模块、腿围数据采集模块、臂围数据采集模块、手部尺寸数据采集模块、脚部尺寸数据采集模块等。举例来说，可使用激光人体三维扫描仪来扫描试穿用户，得到该用户的如下数据：身高数据、体重数据、胸围数据、腰围数据、臀围数据、肩宽数据、腿长数据、颈长数据、臂展数据、头围数据、腿围数据、臂围数据、手部尺寸数据、脚部尺寸数据等。再例如，还可使用各种带有数据交互功能的测量仪，如体重测量仪、身高测量仪、腰围测量仪等分别测得对应数据后传送给智能试穿镜。
在一些示例中，智能试穿镜11获取到的商品特征数据包括但不限于尺寸数据、颜色数据、款式数据、质地数据、柔软度数据、重量数据、材质数据等；所述试穿商品可以是服饰、衣帽、鞋履、配饰、眼镜等。智能试穿镜11获取商品的商品特征数据的方式可选取如下任意一种或多种的组合：
方式1：所述智能试穿镜11通过无线通信模块连至互联网，通过互联网连接至购物APP(如淘宝、天猫、京东、拼多多等)获取到待试穿商品，并提取出商品的商品特征数据，以匹配使用者的身体数据。
方式2：所述智能试穿镜11可与一些智能终端设备(如手机、pad电脑或者智能手表等设备)建立通信连接(如通过蓝牙或红外等)，从智能终端设备获取待试穿商品的商品特征数据。例如，手机通过蓝牙传送商品的商品特征数据到智能试穿镜。
方式3：考虑到保护使用者隐私，所述智能试穿镜11也可在离线状态下获取待试穿商品的商品特征数据，即通过通信接口外接存储设备，从存储设备导入待试穿商品的商品特征数据。举例来说，智能试穿镜11可设置为仅从USB设备或移动存储器等设备获取商品的商品特征数据，以匹配使用者的身体数据。在这种情况下，可实现完全离线操作，避免个人隐私数据泄露。
方式4：所述智能试穿镜11也可设置人机交互部件(如触摸屏、键盘等)，供试穿用户手动输入商品的商品特征数据，以实现个人DIY设计，例如，可手动输入服饰的尺寸和颜色，衣帽的款式和颜色，鞋履的尺码和样式等。
在一些示例中，所述智能试穿镜11还获取试穿商品的弹性数据，并在试穿用户改变试穿姿态时根据所述弹性数据调整虚拟图像并发出场景模拟的声音。具体而言，用户在试穿裤子时通常还会下蹲来感受裤子的弹性，或者在试穿衣服上将纽扣扣紧来感受衣服的弹性，因此在本实施例中，可根据衣服的弹性数据来模拟这些感受，如当用户下蹲时裤子会绷紧，扣紧纽扣时衣服会绷紧，极端情况下还会模拟裤子崩坏而发出的声音等等，由此可提升用户体验。
在另一些示例中，所述智能试穿镜11基于试穿用户的图像数据和身体数据以及待试穿商品的商品特征数据，利用AR技术生成并于镜面中显示试穿效果AR图像。应理解的是，AR技术(Augmented Reality)是增强现实技术，是将虚拟信息与真实世界巧妙融合的技术，促使真实世界信息和虚拟世界信息内容之间综合在一起。即智能试穿镜11先将试穿用户的真实镜像显示于镜面中，再根据待试穿商品的商品特征数据生成用户穿上商品之后的AR图像，将AR图像展示于镜面中。这样，可以给使用者最直观的感受，不仅可以通过镜子上的镜像了解到这件商品是否合身，也能获悉这件商品的上身效果如何。
需说明的是，与现有的VR技术模拟虚拟图像所不同的是，本发明的技术方案是基于试穿用户的真实镜像来构建最终的试穿效果图像，这种方案更真实，试穿效果能够更直接地展示于镜面中，进而带来更好的用户体验。
在一些示例中，所述智能试穿镜通过人机交互方式，响应于用户操作而获取用户对当前试穿效果进行的商品特征修改数据和/或评价数据。其中，所述商品特征修改数据主要是指用户对当前试穿效果不够满意而做出的一些修改，例如调整商品尺码、更换商品颜色、更换商品等等。进一步的，智能试穿镜获取到商品特征修改数据和/或评价数据后，根据这些数据来相应调整商品并调整展示效果；还可以将这些数据反馈给对应的商家，告知商家提供更合适的商品，或者根据用户需求为用户提供DIY服务。
在一些示例中，所述智能试穿镜获取用户所在区域及预设时段内所述待试穿商品被试穿的总次数，并显示于镜面中，供分析该商品的受欢迎程度和/或撞衫概率。举例来说，用户在试穿某件T恤时，智能试穿镜可基于大数据并在镜面上显示，过去的一个月内该T恤被用户所在的A城市B城区内的其他用户总共试穿过100次，用户看到这些数据后可以确定这件T恤很受欢迎，另外也可以根据这些数据避免购买这件T恤以防撞衫。
在一些示例中，所述智能试穿镜还基于所述试穿用户的真实镜像，获取并保存所述试穿用户的体型特征数据；根据所保存的体型特征数据生成体型变化趋势信息，并在一或多个提醒特征数据超过预设阈值时向所述试穿用户发出相应的警示信息；所述警示信息包括身材管理警示信息和/或调整商品尺寸警示信息。
举例来说，在用户使用智能试穿镜一段时间后，每次照镜子或者试穿商品时，智能试穿镜都可以保存用户的体型特征数据及对应的时间戳，保存的用户体型特征数据包括但不限于腰围数据、臂围数据、臀围数据、腿围数据、身高数据、体重数据等；随后，可定期向用户展示其体型特征数据的变化趋势曲线，或者在用户的某一项或某几项体型特征超过预设阈值时向用户发出身材管理警示信息，如“您的腰围在最近三个月增大过快，请注意增加运动”。另外，当体型特征发生变化的同时，也需要向用户发出调整商品尺寸的警示信息，如“您的身高增长了5公分，请注意调节裤子尺寸”。
在一些示例中，所述智能试穿镜根据所述试穿商品的商品特征数据，构建适配的虚拟环境效果；其中，所述虚拟环境效果的构建维度至少包括：天气维度和/或空间场所类型维度和/或光线明暗维度；将所述试穿商品的虚拟商品图像、所述试穿用户的真实镜像及虚拟环境效果相结合，生成并显示虚拟环境下的试穿效果图像。
其中，天气维度是指模拟天气情况，如晴天、雨天、刮风天、夜晚等；空间场所类型维 度是指模拟空间场所，如球场、电影院、健身房、操场、图书馆、办公室、公交车灯；光线明暗维度指室内照明光强度条件、室内照明光种类、室外光照强度条件等。应理解的是，天气维度和/或空间场所类型维度和/或光线明暗维度的选择都是根据商品的特性来调整的，例如：若用户选择选购西装，那么在试穿时就可以将空间场所类型模拟为办公室、晚宴或者走红毯等场景；若用户选购运动裤，那么在试穿时就可以将空间场所类型模拟为健身房或操场；若用户选购太阳镜，那么在试戴时就可以将天气模拟为大晴天；因模拟场景众多，此处不再一一赘述。
在一些示例中，所述智能试穿镜按照所述试穿商品的特性来构建虚拟环境效果，供试穿用户验证该试穿商品的特性。例如，按照试穿商品的材质来构建虚拟环境效果，模拟出衣服遇水后是否被打湿、褶皱程度、贴身程度等，用户通过这类模拟效果可以验证所购商品的防水性。
实施例二：
如图2所示，展示了本发明一实施例中基于增强现实的智能试穿方法的流程示意图，包括步骤S21～S23。应理解的是，本实施例提供的智能试穿方法应用于上文智能试穿系统中的智能试穿镜。
步骤S21：获取试穿商品的商品特征数据，据以生成对应的虚拟商品图像。
在一些示例中，所述试穿商品的商品特征数据包括但不限于尺寸数据、颜色数据、款式数据、质地数据、柔软度数据、重量数据、材质数据等。所述试穿商品可以是服饰、衣帽、鞋履、配饰、眼镜等。
步骤S22：获取试穿用户的真实镜像。
步骤S23：将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示对应的试穿效果图像。
具体而言，基于试穿用户的图像数据和身体数据以及待试穿商品的商品特征数据，利用AR技术生成并于镜面中显示试穿效果AR图像。应理解的是，AR技术(Augmented Reality)是增强现实技术，是将虚拟信息与真实世界巧妙融合的技术，促使真实世界信息和虚拟世界信息内容之间综合在一起。即智能试穿镜11先将试穿用户的真实镜像显示于镜面中，再根据待试穿商品的商品特征数据生成用户穿上商品之后的AR图像，将AR图像展示于镜面中。这样，可以给使用者最直观的感受，不仅可以通过镜子上的镜像了解到这件商品是否合身，也能获悉这件商品的上身效果如何。
在一些示例中，所述方法还包括获取试穿商品的弹性数据，在所述试穿用户改变试穿姿 态时根据所述弹性数据调整所述试穿效果图像，并发出相应的试穿场景模拟声音。具体而言，用户在试穿裤子时通常还会下蹲来感受裤子的弹性，或者在试穿衣服上将纽扣扣紧来感受衣服的弹性，因此在本实施例中，可根据衣服的弹性数据来模拟这些感受，如当用户下蹲时裤子会绷紧，扣紧纽扣时衣服会绷紧，极端情况下还会模拟裤子崩坏而发出的声音等等，由此可提升用户体验。
在一些示例中，所述方法还包括在获取到商品特征修改数据和/或评价数据后，根据这些数据来相应调整商品并调整展示效果；还可以将这些数据反馈给对应的商家，告知商家提供更合适的商品，或者根据用户需求为用户提供DIY服务。
在一些示例中，所述方法还包括获取并显示一预设时段内，在所述试穿用户所在区域内所述试穿商品被试穿的总次数，供分析该商品的受欢迎程度和/或撞衫概率。举例来说，用户在试穿某件T恤时，智能试穿镜可基于大数据并在镜面上显示，过去的一个月内该T恤被用户所在的A城市B城区内的其他用户总共试穿过100次，用户看到这些数据后可以确定这件T恤很受欢迎，另外也可以根据这些数据避免购买这件T恤以防撞衫。
在一些示例中，所述方法还包括基于所述试穿用户的真实镜像，获取并保存所述试穿用户的体型特征数据；根据所保存的体型特征数据生成体型变化趋势信息，并在一或多个提醒特征数据超过预设阈值时向所述试穿用户发出相应的警示信息；所述警示信息包括身材管理警示信息和/或调整商品尺寸警示信息。
在一些示例中，所述方法还包括在用户使用智能试穿镜一段时间后，每次照镜子或者试穿商品时，智能试穿镜都可以保存用户的体型特征数据及对应的时间戳，保存的用户体型特征数据包括但不限于腰围数据、臂围数据、臀围数据、腿围数据、身高数据、体重数据等；随后，可定期向用户展示其体型特征数据的变化趋势曲线，或者在用户的某一项或某几项体型特征超过预设阈值时向用户发出身材管理警示信息，如“您的腰围在最近三个月增大过快，请注意增加运动”。另外，当体型特征发生变化的同时，也需要向用户发出调整商品尺寸的警示信息，如“您的身高增长了5公分，请注意调节裤子尺寸”。
在一些示例中，所述方法还包括根据所述试穿商品的商品特征数据，构建适配的虚拟环境效果；其中，所述虚拟环境效果的构建维度至少包括：天气维度和/或空间场所类型维度和/或光线明暗维度；将所述试穿商品的虚拟商品图像、所述试穿用户的真实镜像及虚拟环境效果相结合，生成并显示虚拟环境下的试穿效果图像。
其中，天气维度是指模拟天气情况，如晴天、雨天、刮风天、夜晚等；空间场所类型维度是指模拟空间场所，如球场、电影院、健身房、操场、图书馆、办公室、公交车灯；光线 明暗维度指室内照明光强度条件、室内照明光种类、室外光照强度条件等。应理解的是，天气维度和/或空间场所类型维度和/或光线明暗维度的选择都是根据商品的特性来调整的，例如：若用户选择选购西装，那么在试穿时就可以将空间场所类型模拟为办公室、晚宴或者走红毯等场景；若用户选购运动裤，那么在试穿时就可以将空间场所类型模拟为健身房或操场；若用户选购太阳镜，那么在试戴时就可以将天气模拟为大晴天；因模拟场景众多，此处不再一一赘述。
在一些示例中，所述方法还包括按照所述试穿商品的特性来构建虚拟环境效果，供试穿用户验证该试穿商品的特性。例如，按照试穿商品的材质来构建虚拟环境效果，模拟出衣服遇水后是否被打湿、褶皱程度、贴身程度等，用户通过这类模拟效果可以验证所购商品的防水性。
实施例三：
本实施例提供一种电子终端的结构示意图。本实例提供的电子终端，包括：处理器31、存储器32、通信器33；存储器32通过系统总线与处理器31和通信器33连接并完成相互间的通信，存储器32用于存储计算机程序，通信器33用于和其他设备进行通信，处理器31用于运行计算机程序，使电子终端执行如上基于增强现实的智能试穿方法的各个步骤。
上述提到的系统总线可以是外设部件互连标准(Peripheral Component Interconnect，简称PCI)总线或扩展工业标准结构(Extended Industry Standard Architecture，简称EISA)总线等。该系统总线可以分为地址总线、数据总线、控制总线等。为便于表示，图中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。通信接口用于实现数据库访问装置与其他设备(例如客户端、读写库和只读库)之间的通信。存储器可能包含随机存取存储器(Random Access Memory，简称RAM)，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。
上述的处理器可以是通用处理器，包括中央处理器(Central Processing Unit，简称CPU)、网络处理器(Network Processor，简称NP)等；还可以是数字信号处理器(Digital Signal Processing，简称DSP)、专用集成电路(Application Specific Integrated Circuit，简称ASIC)、现场可编程门阵列(Field－Programmable Gate Array，简称FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。
实施例四：
本发明还提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现所述基于增强现实的智能试穿方法。
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过计算机程序相关的硬件来完成。前述的计算机程序可以存储于一计算机可读存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
于本申请提供的实施例中，所述计算机可读写存储介质可以包括只读存储器、随机存取存储器、EEPROM、CD-ROM或其它光盘存储装置、磁盘存储装置或其它磁存储设备、闪存、U盘、移动硬盘、或者能够用于存储具有指令或数据结构形式的期望的程序代码并能够由计算机进行存取的任何其它介质。另外，任何连接都可以适当地称为计算机可读介质。例如，如果指令是使用同轴电缆、光纤光缆、双绞线、数字订户线(DSL)或者诸如红外线、无线电和微波之类的无线技术，从网站、服务器或其它远程源发送的，则所述同轴电缆、光纤光缆、双绞线、DSL或者诸如红外线、无线电和微波之类的无线技术包括在所述介质的定义中。然而，应当理解的是，计算机可读写存储介质和数据存储介质不包括连接、载波、信号或者其它暂时性介质，而是旨在针对于非暂时性、有形的存储介质。如申请中所使用的磁盘和光盘包括压缩光盘(CD)、激光光盘、光盘、数字多功能光盘(DVD)、软盘和蓝光光盘，其中，磁盘通常磁性地复制数据，而光盘则用激光来光学地复制数据。
综上所述，本申请提供基于增强现实的智能试穿方法、系统、终端及介质，本发明的技术方案便于使用者在线上购物时，根据商品特征数据便可获得相应的虚拟试穿效果图像，最方便且直观地感受到商品的穿戴效果，不仅免去线下试穿的繁琐，也缓解了因退货造成的物流压力。另外，考虑到使用者隐私问题，本发明也提供离线试穿的功能，避免产生各种纠纷，用户体验大大提升。所以，本申请有效克服了现有技术中的种种缺点而具高度产业利用价值。
上述实施例仅例示性说明本申请的原理及其功效，而非用于限制本申请。任何熟悉此技术的人士皆可在不违背本申请的精神及范畴下，对上述实施例进行修饰或改变。因此，举凡所属技术领域中具有通常知识者在未脱离本申请所揭示的精神与技术思想下所完成的一切等效修饰或改变，仍应由本申请的权利要求所涵盖。

Claims (12)

  1. 一种基于增强现实的智能试穿方法，其特征在于，包括：
    获取试穿商品的商品特征数据，据以生成对应的虚拟商品图像；
    获取试穿用户的真实镜像；
    将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示对应的试穿效果图像和/或动态影像。
  2. 根据权利要求1所述基于增强现实的智能试穿方法，其特征在于，所述方法还包括：
    获取试穿商品的弹性数据；
    在所述试穿用户改变试穿姿态时根据所述弹性数据调整所述试穿效果图像，并发出相应的试穿场景模拟声音。
  3. 根据权利要求1所述基于增强现实的智能试穿方法，其特征在于，所述方法还包括：
    获取所述并显示一预设时段内，在所述试穿用户所在区域内所述试穿商品被试穿的总次数，供分析该商品的受欢迎程度和/或撞衫概率。
  4. 根据权利要求1所述基于增强现实的智能试穿方法，其特征在于，所述方法还包括：在离线状态下，通过通信接口从外部存储设备获取试穿商品的商品特征数据，将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示试穿效果图像。
  5. 根据权利要求1所述基于增强现实的智能试穿方法，其特征在于，所述方法还包括：
    基于所述试穿用户的真实镜像，获取并保存所述试穿用户的体型特征数据；
    根据所保存的体型特征数据生成体型变化趋势信息，并在一或多个提醒特征数据超过预设阈值时向所述试穿用户发出相应的警示信息；所述警示信息包括身材管理警示信息和/或调整商品尺寸警示信息。
  6. 根据权利要求1所述基于增强现实的智能试穿方法，其特征在于，所述方法还包括：
    根据所述试穿商品的商品特征数据，构建适配的虚拟环境效果；其中，所述虚拟环境效果的构建维度至少包括：天气维度和/或空间场所类型维度和/或光线明暗维度；
    将所述试穿商品的虚拟商品图像、所述试穿用户的真实镜像及虚拟环境效果相结合，生成并显示虚拟环境下的试穿效果图像。
  7. 根据权利要求6所述基于增强现实的智能试穿方法，其特征在于，所述方法还包括：按照所述试穿商品的特性来构建虚拟环境效果，供试穿用户验证该试穿商品的特性。
  8. 一种基于增强现实的智能试穿系统，其特征在于，包括：
    图像采集装置，用于获取试穿用户的图像数据并提取脸型特征数据；
    体型数据采集装置，用于获取所述试穿用户的体型特征数据；
    智能试穿镜，通信连接所述图像采集装置和体型数据采集装置；所述智能试穿镜获取试穿商品的商品特征数据，据以生成对应的虚拟商品图像；获取试穿用户的真实镜像；将所述试穿商品的虚拟商品图像与所述试穿用户的真实镜像相结合，生成并显示对应的试穿效果图像和/或动态影像。
  9. 根据权利要求8述基于增强现实的智能试穿系统，其特征在于，所述体型数据采集装置包括如下任一种或多种模块的组合：体重数据采集模块、身高数据采集模块、胸围数据采集模块、腰围数据采集模块、臀围数据采集模块、肩宽数据采集模块、腿长数据采集模块、颈长数据采集模块、臂展数据采集模块、头围数据采集模块、腿围数据采集模块、臂围数据采集模块、手部尺寸数据采集模块及脚部尺寸数据采集模块。
  10. 根据权利要求8述基于增强现实的智能试穿系统，其特征在于，所述智能试穿镜包括：AR显示镜面、计算处理器、图形处理器、存储器、通信器、接口组件、输入设备。
  11. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被处理器执行时实现权利要求1至7中任一项所述基于增强现实的智能试穿方法。
  12. 一种电子终端，其特征在于，包括：处理器及存储器；
    所述存储器用于存储计算机程序；
    所述处理器用于执行所述存储器存储的计算机程序，以使所述终端执行权利要求1至7中任一项所述基于增强现实的智能试穿方法。
PCT/CN2022/093344 2021-06-15 2022-05-17 基于增强现实的智能试穿方法、系统、终端及介质 WO2022262508A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110660974.2A CN113282177A (zh) 2021-06-15 2021-06-15 基于增强现实的智能试穿方法、系统、终端及介质
CN202110660974.2 2021-06-15

Publications (1)

Publication Number Publication Date
WO2022262508A1 true WO2022262508A1 (zh) 2022-12-22

Family

ID=77284473

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/093344 WO2022262508A1 (zh) 2021-06-15 2022-05-17 基于增强现实的智能试穿方法、系统、终端及介质

Country Status (2)

Country Link
CN (1) CN113282177A (zh)
WO (1) WO2022262508A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113282177A (zh) * 2021-06-15 2021-08-20 盛铭睿 基于增强现实的智能试穿方法、系统、终端及介质
CN115147193B (zh) * 2022-09-02 2022-12-27 深圳前海鹏影数字软件运营有限公司 商品的采购推荐方法、装置、商品的电子采购终端及介质

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102930447A (zh) * 2012-10-22 2013-02-13 广州新节奏数码科技有限公司 一种虚拟穿戴的实现方法及设备
CN104820930A (zh) * 2015-05-19 2015-08-05 北京五悦信息科技有限公司 一种智能试衣系统及其虚拟试衣方法
US20170148089A1 (en) * 2015-11-25 2017-05-25 Yuri Murzin Live Dressing Room
CN107346561A (zh) * 2017-06-13 2017-11-14 深圳市吉亚鲁电子有限公司 一种基于ar技术的3d试衣系统
CN107451896A (zh) * 2017-08-09 2017-12-08 陕西科技大学 家庭智能试衣镜系统
CN109003168A (zh) * 2018-08-16 2018-12-14 深圳Tcl数字技术有限公司 虚拟试衣方法、智能电视以及计算机可读存储介质
CN109978640A (zh) * 2017-12-27 2019-07-05 广东欧珀移动通信有限公司 服饰试穿方法、装置、存储介质及移动终端
CN113282177A (zh) * 2021-06-15 2021-08-20 盛铭睿 基于增强现实的智能试穿方法、系统、终端及介质

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102930447A (zh) * 2012-10-22 2013-02-13 广州新节奏数码科技有限公司 一种虚拟穿戴的实现方法及设备
CN104820930A (zh) * 2015-05-19 2015-08-05 北京五悦信息科技有限公司 一种智能试衣系统及其虚拟试衣方法
US20170148089A1 (en) * 2015-11-25 2017-05-25 Yuri Murzin Live Dressing Room
CN107346561A (zh) * 2017-06-13 2017-11-14 深圳市吉亚鲁电子有限公司 一种基于ar技术的3d试衣系统
CN107451896A (zh) * 2017-08-09 2017-12-08 陕西科技大学 家庭智能试衣镜系统
CN109978640A (zh) * 2017-12-27 2019-07-05 广东欧珀移动通信有限公司 服饰试穿方法、装置、存储介质及移动终端
CN109003168A (zh) * 2018-08-16 2018-12-14 深圳Tcl数字技术有限公司 虚拟试衣方法、智能电视以及计算机可读存储介质
CN113282177A (zh) * 2021-06-15 2021-08-20 盛铭睿 基于增强现实的智能试穿方法、系统、终端及介质

Also Published As

Publication number Publication date
CN113282177A (zh) 2021-08-20

Similar Documents

Publication Publication Date Title
US10417825B2 (en) Interactive cubicle and method for determining a body shape
EP3479296B1 (en) System of virtual dressing utilizing image processing, machine learning, and computer vision
US20200066052A1 (en) System and method of superimposing a three-dimensional (3d) virtual garment on to a real-time video of a user
WO2022262508A1 (zh) 基于增强现实的智能试穿方法、系统、终端及介质
CN106462979B (zh) 时尚偏好分析
US20200183969A1 (en) Method, System, and Device of Virtual Dressing Utilizing Image Processing, Machine Learning, and Computer Vision
Pachoulakis et al. Augmented reality platforms for virtual fitting rooms
US9304646B2 (en) Multi-user content interactions
CN111681070B (zh) 线上商品的购买方法、购买装置、存储装置及购买设备
KR20170133455A (ko) 제스처를 사용한 3차원 의복 수정 기법
CN104517219A (zh) 应用于淘宝网的虚拟试衣系统
US9213420B2 (en) Structured lighting based content interactions
WO2008145952A1 (en) Apparatus and method of body characterisation
US20130254066A1 (en) Shared user experiences
US9367124B2 (en) Multi-application content interactions
US11061533B2 (en) Large format display apparatus and control method thereof
KR20160067373A (ko) 아바타를 이용한 신변제품 착용 스타일 정보 제공 시스템 및 그 운용방법
CN111767817A (zh) 一种服饰搭配方法、装置、电子设备及存储介质
US20160042233A1 (en) Method and system for facilitating evaluation of visual appeal of two or more objects
Feng et al. A review of an interactive augmented reality customization clothing system using finger tracking techniques as input device
TW201721519A (zh) 虛擬試衣系統及虛擬試衣方法
CN109816492B (zh) 虚拟试衣间的实现方法、终端及介质
Dvořák et al. Presentation of historical clothing digital replicas in motion
JP5934425B2 (ja) 多様な環境における構造化照明ベースのコンテンツ対話
CN113011935A (zh) 智能试穿方法、装置、电子设备和存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22823990

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22823990

Country of ref document: EP

Kind code of ref document: A1