Movatterモバイル変換


[0]ホーム

URL:


CN113038148A - Commodity dynamic demonstration method, commodity dynamic demonstration device and storage medium - Google Patents

Commodity dynamic demonstration method, commodity dynamic demonstration device and storage medium
Download PDF

Info

Publication number
CN113038148A
CN113038148ACN201911250523.0ACN201911250523ACN113038148ACN 113038148 ACN113038148 ACN 113038148ACN 201911250523 ACN201911250523 ACN 201911250523ACN 113038148 ACN113038148 ACN 113038148A
Authority
CN
China
Prior art keywords
commodity
video
audience
image
dynamic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201911250523.0A
Other languages
Chinese (zh)
Inventor
唐自信
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Hode Information Technology Co Ltd
Original Assignee
Shanghai Hode Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Hode Information Technology Co LtdfiledCriticalShanghai Hode Information Technology Co Ltd
Priority to CN201911250523.0ApriorityCriticalpatent/CN113038148A/en
Publication of CN113038148ApublicationCriticalpatent/CN113038148A/en
Pendinglegal-statusCriticalCurrent

Links

Images

Classifications

Landscapes

Abstract

The invention relates to a method and a device for dynamically demonstrating commodities and a storage medium, and belongs to the technical field of the Internet. In the method, a first video is played at first, and the first video is associated with commodity information; simultaneously shooting and playing audience videos; and then the figure images in the video of the audience can be identified, and the wearing effect of the commodity combined with the figure images is demonstrated in the video of the audience according to the identification result, so that the audience can visually see the appearance of the commodity sold in the video, and can more easily judge whether the commodity is suitable for the audience and decide whether to purchase the commodity. The dynamic commodity demonstration method greatly improves the initiative and the participation degree of audiences when watching the commodity display video, can provide important reference for the audiences to buy commodities, and is beneficial to commodity sales.

Description

Commodity dynamic demonstration method, commodity dynamic demonstration device and storage medium
Technical Field
The invention relates to the technical field of internet, in particular to the technical field of internet videos, and specifically relates to a method and a device for dynamically demonstrating commodities and a storage medium.
Background
Network video is a very popular internet business at present. With the continuous development of the mobile internet, the network video resources are more and more abundant, so that the network video resources become an important part of internet application.
It follows that more and more e-commerce platforms start to use web video for product sales, first product demonstration video and progress to product introduction live video similar to television sales. Product introduction live video benefits from network video technology, with greatly increased audience engagement. The audience can interact with the main broadcast while watching the live video to know the product information, and ask questions about the concerned questions. The anchor answers the relevant questions, and then carries out appropriate product demonstration, can make its product demonstration more accord with audience's demand, satisfy audience's understanding to the commodity. Therefore, live video becomes a very important commodity sales channel.
However, the prior art has the disadvantage that the audience can only know the commodity information through the picture provided by the anchor, and the demonstration of trying on and trying on can not be realized on the platform, so that the effect of wearing the relevant product can not be known.
Therefore, how to provide a dynamic commodity demonstration method capable of overcoming the above disadvantages becomes an urgent problem to be solved in the field.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a dynamic commodity demonstration method, a dynamic commodity demonstration device and a storage medium, wherein the dynamic commodity demonstration method, the dynamic commodity demonstration device and the storage medium are based on a human body recognition technology, and are used for demonstrating the commodity try-on effect combined with audiences while playing a commodity introduction video, so that the audiences can visually see the appearance of the commodities worn by the audiences.
In order to achieve the above object, the method for dynamically demonstrating a commodity according to the present invention comprises the steps of:
playing a first video, wherein the first video is associated with commodity information;
shooting and playing the video of the audience;
identifying the figure image in the audience video to obtain an identification result;
and demonstrating the wearing effect of the combination of the commodity and the character image in the audience video according to the identification result.
In the dynamic demonstration method of the commodity, the commodity information comprises a commodity image and a wearing part;
the identification of the figure image in the audience video to obtain the identification result specifically comprises the following steps:
and identifying a person image in the audience video, and identifying each human body part in the person image.
The method is characterized in that according to the identification result, the wearing effect of the combination of the commodity and the figure image is demonstrated in the audience video, and specifically comprises the following steps:
and judging whether the wearing part is included in each human body part, if so, generating the wearing effect by using the commodity image, and demonstrating the wearing effect in the audience video.
In the dynamic commodity demonstration method, the commodity information comprises a multi-angle commodity image;
the judging whether the human body parts comprise the wearing parts or not is carried out, if yes, the commodity images are used for generating the wearing effect, and the method specifically comprises the following steps:
and judging whether the wearing part is included in each human body part, if so, determining the posture of the wearing part in the audience video, and selecting a commodity image matched with the posture from the multi-angle commodity images to generate the wearing effect.
In the dynamic commodity demonstration method, the first video is related to more than two commodity information,
the first video or the audience video playing interface comprises a commodity selection interface, the audience selects a commodity through the commodity selection interface,
demonstrating the wearing effect of the combination of the commodity and the figure image in the audience video, specifically comprising the following steps:
and demonstrating the wearing effect of the selected commodity combined with the character image in the audience video.
In the method for dynamically demonstrating the commodity, the playing of the first video specifically comprises the following steps:
and playing the first video, identifying whether the first video has commodities, and if so, determining commodity information associated with the first video according to the identified commodities.
The commodity dynamic demonstration method further comprises the following steps:
and identifying the character action in the audience video, and displaying a sales interface associated with the commodity according to the identified character action.
In the dynamic commodity demonstration method, the first video is a live video.
The present invention also provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the above-mentioned dynamic merchandise demonstration method.
The invention also provides a dynamic commodity demonstration device which comprises a processor, a memory, a display and a camera, wherein the memory is stored with a computer program, and the computer program is executed by the processor to realize the dynamic commodity demonstration method.
In the dynamic commodity demonstration device, the first video and the audience video are simultaneously displayed on the same display.
The invention discloses a method, a device and a storage medium for dynamically demonstrating commodities, wherein a first video is played at first, and the first video is associated with commodity information; simultaneously shooting and playing audience videos; and then the figure images in the video of the audience can be identified, and the wearing effect of the commodity combined with the figure images is demonstrated in the video of the audience according to the identification result, so that the audience can visually see the appearance of the commodity sold in the video, and can more easily judge whether the commodity is suitable for the audience and decide whether to purchase the commodity. The dynamic commodity demonstration method greatly improves the initiative and the participation degree of audiences when watching the commodity display video, can provide important reference for the audiences to buy commodities, and is beneficial to commodity sales.
Drawings
Fig. 1 is a flowchart illustrating steps of a dynamic commodity demonstration method according to the present invention.
FIG. 2 is a schematic diagram of an interface for realizing wig dynamic demonstration by using the commodity dynamic demonstration method of the present invention.
FIG. 3 is a schematic interface diagram of a dynamic contact lens demonstration implemented by the method for dynamically demonstrating a commodity according to the present invention.
Detailed Description
In order to clearly understand the technical contents of the present invention, the following examples are given in detail.
Fig. 1 is a flowchart showing steps of a dynamic commodity demonstration method according to the present invention.
In one embodiment, the method for dynamically demonstrating the commodities comprises the following steps:
playing a first video, wherein the first video is associated with commodity information, and the first video can be a live video or a recorded and played video, and is preferably a live video;
shooting and playing the video of the audience;
identifying the figure image in the audience video to obtain an identification result;
and demonstrating the wearing effect of the combination of the commodity and the character image in the audience video according to the identification result.
The commodity information comprises a commodity image and a wearing part;
the identification of the figure image in the audience video to obtain the identification result specifically comprises the following steps:
and identifying a person image in the audience video, and identifying each human body part in the person image.
The method is characterized in that according to the identification result, the wearing effect of the combination of the commodity and the figure image is demonstrated in the audience video, and specifically comprises the following steps:
and judging whether the wearing part is included in each human body part, if so, generating the wearing effect by using the commodity image, and demonstrating the wearing effect in the audience video.
In a preferred embodiment, the commodity information includes a commodity image of multiple angles;
the judging whether the human body parts comprise the wearing parts or not is carried out, if yes, the commodity images are used for generating the wearing effect, and the method specifically comprises the following steps:
and judging whether the wearing part is included in each human body part, if so, determining the posture of the wearing part in the audience video, and selecting a commodity image matched with the posture from the multi-angle commodity images to generate the wearing effect.
In another preferred embodiment, the first video is associated with more than two merchandise information,
the first video or the audience video playing interface comprises a commodity selection interface, the audience selects a commodity through the commodity selection interface,
demonstrating the wearing effect of the combination of the commodity and the figure image in the audience video, specifically comprising the following steps:
and demonstrating the wearing effect of the selected commodity combined with the character image in the audience video.
In another preferred embodiment, the playing the first video specifically includes:
and playing the first video, identifying whether the first video has commodities, and if so, determining commodity information associated with the first video according to the identified commodities.
In a further preferred embodiment, the dynamic commodity demonstration method further comprises the following steps:
and identifying the character action in the audience video, and displaying a sales interface associated with the commodity according to the identified character action.
The invention also provides a device for dynamically demonstrating the commodity and a computer readable storage medium. The commodity dynamic demonstration device comprises a processor, a memory, a display and a camera, wherein the memory is the computer readable storage medium, and a computer program is stored on the memory. When executed by the processor, the computer program realizes the dynamic commodity demonstration method according to the above embodiments. In the dynamic commodity demonstration apparatus, the first video and the viewer video are simultaneously displayed on the same display.
The following describes the implementation of the dynamic commodity demonstration method of the present invention in practical application by using several embodiments.
Example 1
Take watching wig sales video as an example.
The spectator first opens a wig sales live video interface (first video) using a device such as a cell phone or tablet, the first video being associated with at least one wig information. The wig information comprises multi-angle image information of a wig and wearing positions of the wig, namely the top position of the head;
at the same time, the front camera of the device starts to shoot the audience, and the self-timer video (audience video) is played on the device at the same time, and the interface is shown in fig. 2.
The device further generates a recognition result for the figure image in the audience video; specifically, the person image is recognized in the viewer video, and each body part is recognized in the person image, and in this embodiment, whether the person image includes a head is recognized. If yes, determining the posture of the wearing part in the audience video, namely determining the posture of the head, and further selecting a wig image matched with the posture from the multi-angle image information of the wig to generate a wearing effect. And demonstrates the wear effect in the audience video. The process of capturing the audience video, identifying, generating the wearing effect and demonstrating is a real-time dynamic process, that is, the dynamic effect of the audience wearing the wig can be shown in the audience video by using the embodiment.
On the basis of an actual implementation method of human body part recognition, the method can be implemented by using an open-source human body posture recognition project OpenPose or other similar methods. The OpenPose human posture recognition project is an open source library which is developed based on a convolutional neural network and supervised learning and taking cafe as a framework. The gesture estimation of human body action, facial expression, finger motion and the like can be realized. The related human posture estimation technology can be well applied to the fields of sports fitness, motion acquisition, 3D fitting and the like.
By using the method of the embodiment, the audience can clearly see the appearance of the wig worn by the audience when watching the wig selling live video, so that the user can judge whether the wig is suitable for the audience more intuitively, and the user experience is better.
The above contents are only exemplified by taking the wig as a commodity, and similar wearing commodities such as sunglasses, shoes and the like can be applicable after replacing proper commodity information.
Example 2
Take the example of watching a contact lens sales video.
Similar to example 1, the viewer first opens a live contact lens sales video interface (first video) using a device such as a mobile phone or tablet, and the first video is associated with at least one piece of contact lens information. The contact lens information comprises multi-angle image information of the contact lens and wearing parts of the contact lens, namely pupil positions of eyes;
at the same time, the front camera of the device starts to shoot the audience, and the self-timer video (audience video) is played on the device at the same time, and the interface is shown in fig. 3.
The difference from embodiment 1 is that the apparatus further generates a recognition result for the image of the person in the viewer's video; specifically, the person image is recognized in the viewer video, and each body part is recognized in the person image, and in this embodiment, whether the person image includes a head is recognized. If so, the facial expression of the person needs to be further recognized to identify the pupil images and positions of the two eyes. And then selecting a contact lens image matched with the pupil image, the size, the posture and the like from the multi-angle image information of the contact lens to generate a wearing effect. And demonstrates the wear effect in the audience video.
In the actual implementation method of human body part recognition, as described in embodiment 1, the method may be implemented by using an open-source human body gesture recognition project openpos or other similar methods.
In the practical implementation of facial expression recognition, the EmoPy project or other similar recognition techniques may be utilized. EmoPy focuses on Facial Expression Recognition (FER), and using the toolkit provided by EmoPy, developers can identify information such as pupils in the face from the facial image, and further determine the emotion of the person in the image.
Example 3
The difference from the above-described embodiments 1 and 2 is that the merchandise sales live video (first video) can be linked to more than two pieces of merchandise information, for example, selling a plurality of rings in one video.
At this time, the first video or the viewer video playing interface may include a commodity selection interface, and the viewer may select a commodity through the commodity selection interface, that is, the viewer may select a ring.
Then, like the above embodiment, when the finger image is recognized in the audience video, the wearing effect of the audience wearing the selected ring can be demonstrated.
In addition, the current demonstration commodity can be determined by identifying the commodity in the commodity sales live video (first video) for the audience to try on or try on. Also take the ring as an example, when a ring is worn or a certain ring is shown in the anchor of live broadcast video sold by the ring, the ring is a demonstration commodity, which is equivalent to a commodity selected by audiences, and the wearing effect of the same ring worn in the live broadcast video can be demonstrated in the audience video.
Example 4
The difference between the above embodiments is that the method may further identify a character motion, particularly a gesture, in the viewer video, and display a sales interface associated with the merchandise according to the identified character motion or gesture. Also taking the ring as an example, when the wearing effect of the ring is shown in the audience video, or after the ring is shown, the audience makes an OK gesture, and the equipment can show the sales interface of the ring immediately for the audience to purchase.
In the actual implementation method of the gesture recognition, LibHand or other software implementation with similar functions can be adopted. LibHand is an open source code library for presenting and recognizing gestures of a person. And provides a simple programming interface to acquire and analyze gesture images.
The embodiment provides a convenient switching mode from live video of commodity sales to demonstration of fitting and wearing effects and then to purchase so as to provide better consumption experience for users.
The invention discloses a method, a device and a storage medium for dynamically demonstrating commodities, wherein a first video is played at first, and the first video is associated with commodity information; simultaneously shooting and playing audience videos; and then the figure images in the video of the audience can be identified, and the wearing effect of the commodity combined with the figure images is demonstrated in the video of the audience according to the identification result, so that the audience can visually see the appearance of the commodity sold in the video, and can more easily judge whether the commodity is suitable for the audience and decide whether to purchase the commodity. The dynamic commodity demonstration method greatly improves the initiative and the participation degree of audiences when watching the commodity display video, can provide important reference for the audiences to buy commodities, and is beneficial to commodity sales.
In this specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes may be made thereto without departing from the broader spirit and scope of the invention. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense.

Claims (10)

CN201911250523.0A2019-12-092019-12-09Commodity dynamic demonstration method, commodity dynamic demonstration device and storage mediumPendingCN113038148A (en)

Priority Applications (1)

Application NumberPriority DateFiling DateTitle
CN201911250523.0ACN113038148A (en)2019-12-092019-12-09Commodity dynamic demonstration method, commodity dynamic demonstration device and storage medium

Applications Claiming Priority (1)

Application NumberPriority DateFiling DateTitle
CN201911250523.0ACN113038148A (en)2019-12-092019-12-09Commodity dynamic demonstration method, commodity dynamic demonstration device and storage medium

Publications (1)

Publication NumberPublication Date
CN113038148Atrue CN113038148A (en)2021-06-25

Family

ID=76451054

Family Applications (1)

Application NumberTitlePriority DateFiling Date
CN201911250523.0APendingCN113038148A (en)2019-12-092019-12-09Commodity dynamic demonstration method, commodity dynamic demonstration device and storage medium

Country Status (1)

CountryLink
CN (1)CN113038148A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
WO2023055297A3 (en)*2021-09-302023-05-11Lemon Inc.Social networking based on asset items

Citations (16)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
JP2002063132A (en)*2000-08-172002-02-28Yamada Denki Co LtdSimultaneous display and simultaneous comparison method for home page in the internet, and simultaneous comparison shopping method
JP2002109007A (en)*2000-10-042002-04-12Nippon Telegr & Teleph Corp <Ntt> Virtual fitting method and virtual fitting service system
CN101751648A (en)*2010-01-072010-06-23江周平Online try-on method based on webpage application
CN102004860A (en)*2010-12-022011-04-06天津市企商科技发展有限公司Network real-person fitting system and control method thereof
US20130219434A1 (en)*2012-02-202013-08-22Sony Corporation3d body scan input to tv for virtual fitting of apparel presented on retail store tv channel
CN104616190A (en)*2015-03-052015-05-13广州新节奏智能科技有限公司Multi-terminal 3D somatosensory shopping method and system based on internet and mobile internet
CN104680387A (en)*2015-02-272015-06-03百度在线网络技术(北京)有限公司Information display method and device
CN105869217A (en)*2016-03-312016-08-17南京云创大数据科技股份有限公司Virtual method for trying on clothes by real person
CN106162213A (en)*2016-07-112016-11-23福建方维信息科技有限公司A kind of merchandise display method and system based on net cast shopping
CN107551521A (en)*2017-08-172018-01-09广州视源电子科技股份有限公司Fitness guidance method and device, intelligent equipment and storage medium
US20180082479A1 (en)*2016-09-222018-03-22Boe Technology Group Co., Ltd.Virtual fitting method, virtual fitting glasses and virtual fitting system
US20180122096A1 (en)*2016-11-012018-05-03Wistron CorporationInteractive clothes and accessories fitting method and display system thereof
CN207458369U (en)*2017-05-192018-06-05深圳市奥拓电子股份有限公司A kind of intelligent training equipment in gymnasium
CN109151356A (en)*2018-09-052019-01-04传线网络科技(上海)有限公司video recording method and device
CN109345337A (en)*2018-09-142019-02-15广州多维魔镜高新科技有限公司A kind of online shopping examination method of wearing, virtual mirror, system and storage medium
CN109963201A (en)*2017-12-262019-07-02深圳Tcl新技术有限公司A kind of real-time shopping method, system, intelligent TV network and storage medium

Patent Citations (16)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
JP2002063132A (en)*2000-08-172002-02-28Yamada Denki Co LtdSimultaneous display and simultaneous comparison method for home page in the internet, and simultaneous comparison shopping method
JP2002109007A (en)*2000-10-042002-04-12Nippon Telegr & Teleph Corp <Ntt> Virtual fitting method and virtual fitting service system
CN101751648A (en)*2010-01-072010-06-23江周平Online try-on method based on webpage application
CN102004860A (en)*2010-12-022011-04-06天津市企商科技发展有限公司Network real-person fitting system and control method thereof
US20130219434A1 (en)*2012-02-202013-08-22Sony Corporation3d body scan input to tv for virtual fitting of apparel presented on retail store tv channel
CN104680387A (en)*2015-02-272015-06-03百度在线网络技术(北京)有限公司Information display method and device
CN104616190A (en)*2015-03-052015-05-13广州新节奏智能科技有限公司Multi-terminal 3D somatosensory shopping method and system based on internet and mobile internet
CN105869217A (en)*2016-03-312016-08-17南京云创大数据科技股份有限公司Virtual method for trying on clothes by real person
CN106162213A (en)*2016-07-112016-11-23福建方维信息科技有限公司A kind of merchandise display method and system based on net cast shopping
US20180082479A1 (en)*2016-09-222018-03-22Boe Technology Group Co., Ltd.Virtual fitting method, virtual fitting glasses and virtual fitting system
US20180122096A1 (en)*2016-11-012018-05-03Wistron CorporationInteractive clothes and accessories fitting method and display system thereof
CN207458369U (en)*2017-05-192018-06-05深圳市奥拓电子股份有限公司A kind of intelligent training equipment in gymnasium
CN107551521A (en)*2017-08-172018-01-09广州视源电子科技股份有限公司Fitness guidance method and device, intelligent equipment and storage medium
CN109963201A (en)*2017-12-262019-07-02深圳Tcl新技术有限公司A kind of real-time shopping method, system, intelligent TV network and storage medium
CN109151356A (en)*2018-09-052019-01-04传线网络科技(上海)有限公司video recording method and device
CN109345337A (en)*2018-09-142019-02-15广州多维魔镜高新科技有限公司A kind of online shopping examination method of wearing, virtual mirror, system and storage medium

Cited By (3)

* Cited by examiner, † Cited by third party
Publication numberPriority datePublication dateAssigneeTitle
WO2023055297A3 (en)*2021-09-302023-05-11Lemon Inc.Social networking based on asset items
US11763496B2 (en)2021-09-302023-09-19Lemon Inc.Social networking based on asset items
US12045912B2 (en)2021-09-302024-07-23Lemon Inc.Social networking based on collecting asset items

Similar Documents

PublicationPublication DateTitle
US11056225B2 (en)Analytics for livestreaming based on image analysis within a shared digital environment
CN103760968B (en)Method and device for selecting display contents of digital signage
JP4775671B2 (en) Information processing apparatus and method, and program
CN109740466A (en) Method for obtaining advertisement placement strategy, and computer-readable storage medium
KR20210110620A (en) Interaction methods, devices, electronic devices and storage media
TW202036355A (en)Personalized makeup information recommendation method
CN109729426A (en)A kind of generation method and device of video cover image
CN107633441A (en)Commodity in track identification video image and the method and apparatus for showing merchandise news
US20130290994A1 (en)Selection of targeted content based on user reactions to content
EP3425483B1 (en)Intelligent object recognizer
US20210097765A1 (en)Apparatus, system, and method of providing a three dimensional virtual local presence
ZhangEvoking presence in vlogging: A case study of UK beauty blogger Zoe Sugg
CN114125491B (en)Virtual live broadcast control method and device
CN111915737B (en)Human-object interaction system based on augmented reality
CN114025188A (en)Live broadcast advertisement display method, system, device, terminal and readable storage medium
CN115086693A (en)Virtual object interaction method and device, electronic equipment and storage medium
CN115546360A (en)Action result identification method and device
WO2023091564A1 (en)System and method for provision of personalized multimedia avatars that provide studying companionship
CN114445271B (en)Method for generating virtual fitting 3D image
Zhang et al.OdorAgent: Generate odor sequences for movies based on large language model
CN113038148A (en)Commodity dynamic demonstration method, commodity dynamic demonstration device and storage medium
CN113301362B (en)Video element display method and device
CN106113057B (en)Audio-video advertising method and system based on robot
JP6731532B1 (en) Video playback device, video playback method, and video delivery system
US20180165713A1 (en)Virtual Advertising Database with Command Input Data

Legal Events

DateCodeTitleDescription
PB01Publication
PB01Publication
SE01Entry into force of request for substantive examination
SE01Entry into force of request for substantive examination

[8]ページ先頭

©2009-2025 Movatter.jp