CN102868934A - Method and device for retrieving video object information based on smart television - Google Patents
Method and device for retrieving video object information based on smart television Download PDFInfo
- Publication number
- CN102868934A CN102868934A CN2012102735662A CN201210273566A CN102868934A CN 102868934 A CN102868934 A CN 102868934A CN 2012102735662 A CN2012102735662 A CN 2012102735662A CN 201210273566 A CN201210273566 A CN 201210273566A CN 102868934 A CN102868934 A CN 102868934A
- Authority
- CN
- China
- Prior art keywords
- information
- people
- video
- visual signature
- video pictures
- 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.)
- Granted
Links
Images
Abstract
The invention discloses a method and a device for retrieving video object information based on a smart television. According to the invention, the method comprises the following steps of: receiving a video image capture request, responding to the video image capture request, and capturing the current played video image; and identifying face visual feature information in the captured video image, and querying, acquiring and showing information matched with the identified face visual feature information. By the method and the device, a retrieval flow can be simplified, and the time required by retrieval can be reduced.
Description
Technical field
The present invention relates to digital television techniques, relate in particular to a kind of object video information retrieval method and device based on intelligent television.
Background technology
Along with the development of the national integration of three networks, TV market is ripe gradually, and increasing enterprise begins to develop intelligent television (DTV, Definition Television).Intelligent television refers to possess open operating system and chip, have open application platform, can realize two-way human-computer interaction function, can realize new function or value-added service by autonomous set up applications, and can be by the terminal application platform of the satisfied variation such as three net accesses, 3C fusions and individual demand.
Different users has respectively the performer who oneself likes, thereby, the user is when watching the movie and television play of performer's performance of oneself liking, wishing can be by the retrieval to this actor information, understanding is about some information of this performer, for example, the movie and television play information once performed of this performer's recent developments information, this performer, perform the strange actor information etc. of TV play with this performer.
Fig. 1 is existing actor information search method schematic flow sheet based on intelligent television.Referring to Fig. 1, this flow process comprises:
In this step, the user is in watching the process of movie and television play, if need to understand some information about this performer, then can send the actor information retrieval request to intelligent TV set by remote controller key, after intelligent TV set receives the actor information retrieval request, eject search interface, carry out the actor information retrieval for the user.
Actual in using, can carry out in advance the button of actor information retrieval remote controller setting, when the user presses this button, automatically generate the actor information retrieval request, export intelligent TV set to.
In this step, the user is in the frame retrieval of the search interface that ejects, input the keyword relevant with performer to be retrieved, for example, input " high round " in frame retrieval, intelligent TV set receive comprise high round search key after, from pre-stored electronic program guides (EPG, Electronic Program Guide) or by the server on the Internet, search and the high round information that is complementary of keyword, and the information that will mate is presented to the user.
By as seen above-mentioned, existing actor information search method based on intelligent television, by the input keyword relevant with the performer, the information with keyword match is obtained in inquiry, no matter the user is with keyboard or handwriting input, all needs to enter search interface, inputs keyword in frame retrieval, operate comparatively loaded down with trivial detailsly, it is longer to retrieve the required time; Further, need the user to be familiar with the performer, for the performer who forgets or do not know name, can't directly input its performer's keyword and retrieve, and needs are referred to as keyword by the name of movie and television play works first, each actor information of these movie and television play works of performance is obtained in inquiry, therefrom obtain the actor information that needs retrieval, retrieve as keyword with this actor information again, so that operating process is more loaded down with trivial details, it is longer to retrieve the required time, has reduced user's business experience.
Summary of the invention
Embodiments of the invention provide a kind of object video information retrieval method based on intelligent television, simplify retrieval flow, reduce the required time of retrieval.
Embodiments of the invention also provide a kind of object video information indexing device based on intelligent television, simplify retrieval flow, reduce the required time of retrieval.
For achieving the above object, a kind of object video information retrieval method based on intelligent television that the embodiment of the invention provides comprises:
Receiver, video picture crawl request in response to described video pictures crawl request, is grasped the video pictures of current broadcast;
People's face visual signature information in the video pictures of identification crawl, inquiry obtain with know the information of others face visual signature information matches and show.
Described receiver, video picture crawl request comprises:
The button of crawl video pictures is set at remote controller in advance;
Receive the operational order that the user presses crawl video pictures button, generating video picture crawl request is exported to intelligent TV set.
Described receiver, video picture crawl request comprises:
Monitor user's operation and contact with the intelligent TV set screen, trigger and eject the function menu that sets in advance;
Monitor the user and operate the video pictures crawl control of choosing in the function menu, output video picture crawl request.
Described function menu comprises: video pictures crawl control, object video information retrieval control and channel toggle control.
,, further comprise before the function menu that the triggering ejection sets in advance with after the intelligent TV set screen contact in the described user of monitoring operation:
Judge whether the time that user operation contact with the intelligent TV set screen surpass the time threshold that sets in advance, if so, the function menu that the triggering ejection sets in advance, otherwise, do not deal with.
The video pictures of the current broadcast of described crawl comprises:
By the camera that intelligent TV set is built-in the video pictures of current broadcast is made a video recording; Or,
By the shooting software of installing in the intelligent TV set video pictures of current broadcast is made a video recording; Or,
By the camera that intelligent TV set is external the video pictures of current broadcast is made a video recording; Or,
Obtain the temporal information of current broadcast, from the video pictures frame of storage, obtain the video pictures frame that the temporal information with current broadcast is complementary.
Behind the video pictures of the current broadcast of described crawl, further comprise:
The video pictures of crawl is showed, received the user to the editor of video pictures, obtain the video pictures that comprises object to be retrieved.
People's face visual signature information in the video pictures of described identification crawl comprises:
Utilize face recognition technology, identify the people's face in the video pictures;
Extract the face characteristic part of identification, obtain people's face visual signature information.
The information that described inquiry is obtained with this people's face visual signature information matches comprises:
Obtain in advance the people's face visual signature information bank that comprises people's face visual signature information and object video information mapping relations;
People's face visual signature information that will obtain from video pictures is mated with people's face visual signature information bank, obtains the people's face visual signature information that is complementary with the people's face visual signature information that obtains;
According to the mapping relations of people's face visual signature information and object video information, obtain the object video information of this people's face visual signature information mapping;
According to the object video information of obtaining, inquiry is obtained with the information of this object video information matches and is showed.
Described people's face visual signature information that will obtain from video pictures is mated with people's face visual signature information bank, obtains the people's face visual signature information that is complementary with the people's face visual signature information that obtains and comprises:
Vector distance in the people's face visual signature information that calculates and the people's face visual signature information bank between each one the face visual signature information;
If the minimum vector distance that calculates, is chosen the people's face visual signature information in people's face visual signature information bank corresponding to this minimum vector distance less than the Vector Threshold that sets in advance, be people's face visual signature information of coupling.
The information that described inquiry is obtained with this object video information matches comprises:
From pre-stored electronic program guides, obtain the information with this object video information matches; Or,
By the server on the Internet, obtain the information with this object video information matches.
A kind of object video information indexing device based on intelligent television, this device comprises: video pictures handling module, identification module and enquiry module, wherein,
The video pictures handling module is used for receiver, video picture crawl request, and in response to described video pictures crawl request, grasps the video pictures of current broadcast;
Identification module is for people's face visual signature information of the video pictures of identifying crawl;
Enquiry module is used for inquiry and obtains the information that is complementary with others face visual signature information of identification module knowledge, and shows.
Further comprise:
Editor module is used for the video pictures of crawl is showed, receives the user to the editor of video pictures, obtains the video pictures that comprises object to be retrieved.
Described video pictures handling module comprises: the first monitoring means, the second monitoring means and video pictures placement unit, wherein,
The first monitoring means is used for triggering and ejecting the function menu that sets in advance after monitoring user's operation and the intelligent TV set screen contacts;
The second monitoring means is used for after monitoring user's operation and choosing the video pictures crawl control of function menu output video picture crawl request.
The video pictures placement unit is used for grasping the video pictures of current broadcast according to the video pictures crawl request that receives.
Described enquiry module comprises: people's face visual signature information bank unit, matching unit, object video information acquisition unit and query unit, wherein,
People's face visual signature information bank unit is used for obtaining in advance the people's face visual signature information bank that comprises people's face visual signature information and object video information mapping relations;
Matching unit is used for people's face visual signature information that will obtain from video pictures, mates with people's face visual signature information bank, obtains the people's face visual signature information that is complementary with the people's face visual signature information that obtains;
The object video information acquisition unit is used for the mapping relations according to people's face visual signature information and object video information, obtains the object video information of this people's face visual signature information mapping;
Query unit, according to the object video information of obtaining, inquiry is obtained with the information of this object video information matches and is showed.
As seen from the above technical solution, a kind of object video information retrieval method and device based on intelligent television that the embodiment of the invention provides, the crawl of receiver, video picture is asked, and grasps the video pictures of current broadcast; People's face visual signature information in the video pictures of identification crawl, inquiry are obtained with the information of this people's face visual signature information matches and are showed.Like this, need not the user and input key word information, also need not the user and remember the associated video object information, simplified retrieval flow, reduced the required time of retrieving.
Description of drawings
In order to be illustrated more clearly in the embodiment of the invention or technical scheme of the prior art, below will do to introduce simply to the accompanying drawing of required use in embodiment or the description of the Prior Art.Apparently, the accompanying drawing in below describing only is some embodiments of the present invention, for those of ordinary skills, can also obtain according to these accompanying drawing illustrated embodiments other embodiment and accompanying drawing thereof.
Fig. 1 is existing actor information search method schematic flow sheet based on intelligent television.
Fig. 2 is that the embodiment of the invention is based on the object video information retrieval method schematic flow sheet of intelligent television.
Fig. 3 is that the embodiment of the invention is based on the object video information retrieval method idiographic flow schematic diagram of intelligent television.
Fig. 4 is that the embodiment of the invention is based on the object video information indexing device structural representation of intelligent television.
Embodiment
Below with reference to accompanying drawing the technical scheme of various embodiments of the present invention is carried out clear, complete description, obviously, described embodiment only is a part of embodiment of the present invention, rather than whole embodiment.Based on the embodiment among the present invention, those of ordinary skills are resulting all other embodiment under the prerequisite of not making creative work, all belong to the scope that the present invention protects.
Existing performer's (object video) information retrieval method based on intelligent television obtains performer's relevant information by input keyword in frame retrieval, and the operation of input keyword is comparatively loaded down with trivial details; Further, for the performer who forgets or do not know name, need to repeatedly retrieve just and can obtain relevant information, operating process is more loaded down with trivial details.
Face recognition technology refers to utilize and analyzes, compares people's face visual signature information, carries out the computer technology that identity is differentiated, is one of biometrics identification technology.Be widely used in field or the scenes such as work attendance, gate inhibition, information security, intelligent video monitoring, customs, current check, by gathering people's face visual signature information, mate with pre-stored people's face visual signature information bank, thereby can determine user profile corresponding to people's face visual signature information that gathers.
In the embodiment of the invention, consider to adopt face recognition technology, object video to be retrieved carries out recognition of face in the TV programme that the user is watched, and automatically identifies object video, and inquiry is obtained with the information of this object video coupling and showed.Thereby, need not the user and input key word information, also need not the user and remember the associated video object information, simplified retrieval flow, reduce the required time of retrieving, thereby promoted user's business experience.
Preferably, in the embodiment of the invention, object video is the performer.
Fig. 2 is that the embodiment of the invention is based on the object video information retrieval method schematic flow sheet of intelligent television.Referring to Fig. 2, this flow process comprises:
In this step, receiver, video picture crawl request comprises:
A11 arranges the button that grasps video pictures at remote controller in advance;
In this step, with existing to carry out the button of object video information retrieval remote controller setting in advance similar, can by the function button on the expansion remote controller, increase the function button of crawl video pictures.
A12 receives the operational order that the user presses crawl video pictures button, and generating video picture crawl request is exported to intelligent TV set.
In this step, the user is in watching the process of movie and television play, if need to understand some information about this object video, then can be by pressing the crawl video pictures button on the remote controller, to remote controller output function instruction, remote controller is according to this operational order, generating video picture crawl request, to intelligent TV set output, intelligent TV set receives this video pictures crawl request, triggering following flow process.If the user presses the button that carries out the object video information retrieval that arranges on the remote controller, then operate according to existing procedure, do not repeat them here.
Certainly, in the practical application, receiver, video picture crawl request also can comprise:
A21 monitors user's operation and contacts with the intelligent TV set screen, triggers and ejects the function menu that sets in advance;
In this step, if be provided with operating system in the intelligent TV set, then can adopt the method, similar with the mobile phone operation of touch-screen, can in intelligent TV set, pre-set the function menu that the user needs, for example, comprise in the function menu that sets in advance: video pictures crawl control, object video information retrieval control, channel toggle control etc.
In the embodiment of the invention, user's operation comprises: user's mouse action, felt pen operation and finger manipulation.
The user if need understanding about some information of this object video, then can by touching intelligent TV set screen, wish intelligent TV set is operated with expression in watching the process of movie and television play.
In the practical application, in order effectively to reduce the user owing to misoperation touching intelligent TV set screen causes the ejection function menu, in the embodiment of the invention, after monitoring user's operation and the intelligent TV set screen contacts, trigger and eject before the function menu that sets in advance, further comprise:
Judge whether the time that user operation contact with the intelligent TV set screen surpass the time threshold that sets in advance, if so, the function menu that the triggering ejection sets in advance, otherwise, do not deal with.
In this step,, user's operation resides in the time of intelligent TV set screen by being set, to determine whether the user really need to operate intelligent TV set, if the time that user's operation contacts with the intelligent TV set screen does not have to surpass the time threshold that sets in advance, show that this user is operating as misoperation, does not then deal with.
A22 monitors the user and operates the video pictures crawl control of choosing in the function menu, output video picture crawl request.
In this step, the user is according to the function menu that ejects, therefrom choose the function that needs execution, by the functionality controls that click is chosen, trigger request corresponding to this functionality controls of carrying out that generate, for example, if the object video information retrieval control in user's click function menu, if then generating video object information retrieval request and output is the crawl of the video pictures in user's click function menu control, then generating video picture crawl request and output.
The video pictures that grasps current broadcast comprises:
By the camera that intelligent TV set is built-in the video pictures of current broadcast is made a video recording; Or,
By the shooting software of installing in the intelligent TV set video pictures of current broadcast is made a video recording; Or,
By the camera that intelligent TV set is external the video pictures of current broadcast is made a video recording; Or,
Obtain the temporal information of current broadcast, from the video pictures frame of storage, obtain the video pictures frame that the temporal information with current broadcast is complementary.
In this step, the mode that grasps the video pictures of current broadcast has multiple, both can grasp video pictures by camera, also can by shooting software crawl video pictures, can also and obtain video pictures according to the temporal information inquiry.Mode by shooting software and temporal information crawl video pictures can also be reduced in the cost that intelligent TV set arranges camera.
In the embodiment of the invention, behind the video pictures of the current broadcast of crawl, can further include:
The video pictures of crawl is showed, received the user to the editor of video pictures, obtain the video pictures that comprises object to be retrieved.
In this step, behind the video pictures of the current broadcast of crawl, in the video pictures of current crawl, may include a plurality of objects, process the required resource overhead of video pictures in order to reduce intelligent TV set, in the embodiment of the invention, can edit the video pictures of crawl, make the video pictures behind the editor only comprise object to be retrieved as far as possible, for example, only comprise the people face part of object to be retrieved.
In this step, the people's face visual signature information in the video pictures of identification crawl comprises:
A31 utilizes face recognition technology, identifies the people's face in the video pictures;
In this step, identify based on people's face feature, can adopt the regional characteristics analysis algorithm to identify.About face recognition technology, be prior art, specifically can referring to the correlation technique document, not repeat them here.
A32 extracts the face characteristic part of identification, obtains people's face visual signature information.
In this step, by extracting the face characteristic part (people's face textural characteristics) in the characteristic area, carry out calculation system, obtain people's face visual signature information.
People's face visual signature information comprises: the contour feature dot information of people's face and face organ's characteristic point information etc., wherein, face organ's characteristic point information can comprise: left eye characteristic point information, right eye characteristic point information, ear characteristic point information, mouth characteristic point information and nose characteristic point information.In the embodiment of the invention, the left eye characteristic point information can be the positional information of left eye.
In database, inquire about to obtain with others information of face visual signature information matches of know and comprise:
A41, obtaining in advance the people's face visual signature information bank that comprises people's face visual signature information and object video information mapping relations is database;
In this step, people's face visual signature information bank can be by the person skilled of each operator, by face recognition technology and training method, obtain people's face visual signature information of each object video, and set up the mapping relations of people's face visual signature information and object video information, form people's face visual signature information bank.
A42, people's face visual signature information that will obtain from video pictures is mated with people's face visual signature information bank, obtains the people's face visual signature information that is complementary with the people's face visual signature information that obtains;
In this step, the method of coupling can be the vector distance between each one the face visual signature information in people's face visual signature information of calculating and the people's face visual signature information bank, if the minimum vector distance that calculates is less than the Vector Threshold that sets in advance, choose the people's face visual signature information in people's face visual signature information bank corresponding to this minimum vector distance, be people's face visual signature information of coupling.
Vector distance can be Euclidean distance, also can be two inner product distances between the vector.
In the practical application, if through overmatching, there is not the people's face visual signature information that is complementary with the people's face visual signature information that obtains in people's face visual signature information bank, then can be further to user's information of showing that it fails to match, the user can re-start retrieval by the existing mode that sends the object video information retrieval requests according to the information of showing that it fails to match.
A43 according to the mapping relations of people's face visual signature information and object video information, obtains the object video information of this people's face visual signature information mapping;
In this step, in people's face visual signature information bank, obtain people's face visual signature information of coupling, according to the mapping relations of people's face visual signature information and object video information in people's face visual signature information bank, can obtain the object video information of people's face visual signature information mapping of this coupling.
A44, according to the object video information of obtaining, inquiry is obtained with the information of this object video information matches and is showed.
In this step, inquire about the information of obtaining with this object video information matches and comprise:
From pre-stored electronic program guides, obtain the information with this object video information matches; Or,
By the server on the Internet, obtain the information with this object video information matches.
Fig. 3 is that the embodiment of the invention is based on the object video information retrieval method idiographic flow schematic diagram of intelligent television.Referring to Fig. 3, take object video as example as the performer, this flow process comprises:
Step 301 receives operational order, crawl current video picture;
In this step, intelligent TV set grasps video pictures and the storage of current broadcast according to the operational order that the user issues.
Step 302, identification and extraction face characteristic partial information in the video pictures of crawl;
In this step, utilize face recognition technology, identify the people's face in the video pictures, then, by the extraction algorithm that sets in advance, extract the face characteristic partial information.
Step 303 is mated performer's face feature information of storing in the face characteristic partial information of described extraction and the database;
Step 304 determines to store in the described database performer's face feature information that the face characteristic partial information with described extraction is complementary, and tabling look-up draws this performer's name;
In this step, if a certain performer's face feature information of storing in the face characteristic partial information of extracting and the database conforms to, then can by tabling look-up, draw this performer's name.
Step 305 is retrieved as keyword take this performer's name, obtains the information that the name with this performer is complementary.
In this step, can in electronic program guides, retrieve, also can retrieve by the server on the Internet.
Like this, the object video information retrieval method of the embodiment of the invention by the recognition of face in the video pictures, obtains the face data of object video, and face data is synchronized to high in the clouds, carries out the identification of object video, is very suitable for using when seeing TV; Further, the face data that can upgrade or add object video by EPG or internet system platform, thereby realize related according to the facial feature of object video and name, when watching the movie and television play program, can carry out rapidly the object video information searching; And the present invention passes through crawl current video picture, and automatically identifies the object video identity, and the information relevant with this object video that further search is obtained is presented on the video screen, therefore, has effectively improved the efficient of object video acquisition of information.
Fig. 4 is that the embodiment of the invention is based on the object video information indexing device structural representation of intelligent television.Referring to Fig. 4, this device comprises: video pictures handling module, identification module and enquiry module, wherein,
The video pictures handling module is used for receiver, video picture crawl request, and in response to described video pictures crawl request, grasps the video pictures of current broadcast;
Identification module is for people's face visual signature information of the video pictures of identifying crawl;
Enquiry module is used for inquiry and obtains the information that is complementary with others face visual signature information of identification module knowledge, and shows.
Preferably, this device further comprises:
Editor module is used for the video pictures of crawl is showed, receives the user to the editor of video pictures, obtains the video pictures that comprises object to be retrieved.
Wherein,
The video pictures handling module comprises: the first monitoring means, the second monitoring means and video pictures placement unit (not shown), wherein,
The first monitoring means is used for triggering and ejecting the function menu that sets in advance after monitoring user's operation and the intelligent TV set screen contacts;
The second monitoring means is used for after monitoring user's operation and choosing the video pictures crawl control of function menu output video picture crawl request.
The video pictures placement unit is used for grasping the video pictures of current broadcast according to the video pictures crawl request that receives.
Enquiry module comprises: people's face visual signature information bank unit, matching unit, object video information acquisition unit and query unit (not shown), wherein,
People's face visual signature information bank unit is used for obtaining in advance the people's face visual signature information bank that comprises people's face visual signature information and object video information mapping relations;
Matching unit is used for people's face visual signature information that will obtain from video pictures, mates with people's face visual signature information bank, obtains the people's face visual signature information that is complementary with the people's face visual signature information that obtains;
The object video information acquisition unit is used for the mapping relations according to people's face visual signature information and object video information, obtains the object video information of this people's face visual signature information mapping;
Query unit, according to the object video information of obtaining, inquiry is obtained with the information of this object video information matches and is showed.
Obviously, those skilled in the art can carry out various changes and modification to the present invention and not break away from the spirit and scope of the present invention.Like this, if of the present invention these are revised and modification belongs within the scope of claim of the present invention and equivalent technologies thereof, then the present invention also comprises these changes and modification interior.
Claims (15)
1. object video information retrieval method based on intelligent television comprises:
Receiver, video picture crawl request in response to described video pictures crawl request, is grasped the video pictures of current broadcast;
People's face visual signature information in the video pictures of identification crawl, inquiry obtain with know the information of others face visual signature information matches and show.
2. method according to claim 1, wherein, described receiver, video picture crawl request comprises:
The button of crawl video pictures is set at remote controller in advance;
Receive the operational order that the user presses crawl video pictures button, generating video picture crawl request is exported to intelligent TV set.
3. method according to claim 1, wherein, described receiver, video picture crawl request comprises:
Monitor user's operation and contact with the intelligent TV set screen, trigger and eject the function menu that sets in advance;
Monitor the user and operate the video pictures crawl control of choosing in the function menu, output video picture crawl request.
4. method according to claim 3, wherein, described function menu comprises: video pictures crawl control, object video information retrieval control and channel toggle control.
5. method according to claim 4 wherein,,, further comprises before the function menu that the triggering ejection sets in advance with after the intelligent TV set screen contact in the described user's of monitoring operation:
Judge whether the time that user operation contact with the intelligent TV set screen surpass the time threshold that sets in advance, if so, the function menu that the triggering ejection sets in advance, otherwise, do not deal with.
6. according to claim 1 to 5 each described methods, wherein, the video pictures of the current broadcast of described crawl comprises:
By the camera that intelligent TV set is built-in the video pictures of current broadcast is made a video recording; Or,
By the shooting software of installing in the intelligent TV set video pictures of current broadcast is made a video recording; Or,
By the camera that intelligent TV set is external the video pictures of current broadcast is made a video recording; Or,
Obtain the temporal information of current broadcast, from the video pictures frame of storage, obtain the video pictures frame that the temporal information with current broadcast is complementary.
7. method according to claim 6 wherein, behind the video pictures of the current broadcast of described crawl, further comprises:
The video pictures of crawl is showed, received the user to the editor of video pictures, obtain the video pictures that comprises object to be retrieved.
8. method according to claim 1, wherein, the people's face visual signature information in the video pictures of described identification crawl comprises:
Utilize face recognition technology, identify the people's face in the video pictures;
Extract the face characteristic part of identification, obtain people's face visual signature information.
9. method according to claim 8, wherein, described inquiry is obtained with others information of face visual signature information matches of know and is comprised:
Obtain in advance the people's face visual signature information bank that comprises people's face visual signature information and object video information mapping relations;
People's face visual signature information that will obtain from video pictures is mated with people's face visual signature information bank, obtains the people's face visual signature information that is complementary with the people's face visual signature information that obtains;
According to the mapping relations of people's face visual signature information and object video information, obtain the object video information of this people's face visual signature information mapping;
According to the object video information of obtaining, inquiry is obtained with the information of this object video information matches and is showed.
10. method according to claim 9, wherein, described people's face visual signature information that will obtain from video pictures is mated with people's face visual signature information bank, obtains the people's face visual signature information that is complementary with the people's face visual signature information that obtains and comprises:
Vector distance in the people's face visual signature information that calculates and the people's face visual signature information bank between each one the face visual signature information;
If the minimum vector distance that calculates, is chosen the people's face visual signature information in people's face visual signature information bank corresponding to this minimum vector distance less than the Vector Threshold that sets in advance, be people's face visual signature information of coupling.
11. method according to claim 10, wherein, the information that described inquiry is obtained with this object video information matches comprises:
From pre-stored electronic program guides, obtain the information with this object video information matches; Or,
By the server on the Internet, obtain the information with this object video information matches.
12. the object video information indexing device based on intelligent television is characterized in that this device comprises: video pictures handling module, identification module and enquiry module, wherein,
The video pictures handling module is used for receiver, video picture crawl request, and grasps the video pictures of current broadcast based on described video pictures crawl request;
Identification module is for people's face visual signature information of the video pictures of identifying crawl;
Enquiry module is used for inquiry and obtains the information that is complementary with others face visual signature information of identification module knowledge, and shows.
13. device according to claim 12 is characterized in that, further comprises:
Editor module is used for the video pictures of crawl is showed, receives the user to the editor of video pictures, obtains the video pictures that comprises object to be retrieved.
14. according to claim 12 or 13 described devices, it is characterized in that described video pictures handling module comprises: the first monitoring means, the second monitoring means and video pictures placement unit, wherein,
The first monitoring means is used for triggering and ejecting the function menu that sets in advance after monitoring user's operation and the intelligent TV set screen contacts;
The second monitoring means is used for after monitoring user's operation and choosing the video pictures crawl control of function menu output video picture crawl request.
The video pictures placement unit is used for grasping the video pictures of current broadcast according to the video pictures crawl request that receives.
15. according to claim 12 or 13 described devices, it is characterized in that described enquiry module comprises: people's face visual signature information bank unit, matching unit, object video information acquisition unit and query unit, wherein,
People's face visual signature information bank unit is used for obtaining in advance the people's face visual signature information bank that comprises people's face visual signature information and object video information mapping relations;
Matching unit is used for people's face visual signature information that will obtain from video pictures, mates with people's face visual signature information bank, obtains the people's face visual signature information that is complementary with the people's face visual signature information that obtains;
The object video information acquisition unit is used for the mapping relations according to people's face visual signature information and object video information, obtains the object video information of this people's face visual signature information mapping;
Query unit, according to the object video information of obtaining, inquiry is obtained with the information of this object video information matches and is showed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210273566.2A CN102868934B (en) | 2012-08-01 | 2012-08-01 | Video object information search method and device based on intelligent television |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210273566.2A CN102868934B (en) | 2012-08-01 | 2012-08-01 | Video object information search method and device based on intelligent television |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102868934A true CN102868934A (en) | 2013-01-09 |
| CN102868934B CN102868934B (en) | 2016-06-29 |
Family
ID=47447491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210273566.2A Active CN102868934B (en) | 2012-08-01 | 2012-08-01 | Video object information search method and device based on intelligent television |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102868934B (en) |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103428537A (en) * | 2013-07-30 | 2013-12-04 | 北京小米科技有限责任公司 | Video processing method and video processing device |
| CN103826142A (en) * | 2013-11-15 | 2014-05-28 | 安徽科大讯飞信息科技股份有限公司 | Customizing and pushing method and system based on real-time program content |
| CN103870559A (en) * | 2014-03-06 | 2014-06-18 | 海信集团有限公司 | Method and equipment for obtaining information based on played video |
| CN104063512A (en) * | 2014-07-10 | 2014-09-24 | 福州瑞芯微电子有限公司 | Information recommending device and method based on feature recognition |
| CN104184923A (en) * | 2014-08-27 | 2014-12-03 | 天津三星电子有限公司 | System and method used for retrieving figure information in video |
| CN104391711A (en) * | 2014-08-28 | 2015-03-04 | 小米科技有限责任公司 | Method and device for setting screen protection |
| CN104602128A (en) * | 2014-12-31 | 2015-05-06 | 北京百度网讯科技有限公司 | Video processing method and device |
| CN104754413A (en) * | 2013-12-30 | 2015-07-01 | 北京三星通信技术研究有限公司 | Image search based television signal identification and information recommendation method and device |
| CN104881407A (en) * | 2014-02-27 | 2015-09-02 | 福州瑞芯微电子有限公司 | Information recommending system and information recommending method based on feature recognition |
| CN104967889A (en) * | 2015-06-30 | 2015-10-07 | 小米科技有限责任公司 | Method used for controlling intelligent television to carry out video information processing and device |
| CN105122242A (en) * | 2013-03-14 | 2015-12-02 | 谷歌公司 | Methods, systems, and media for presenting mobile content corresponding to media content |
| CN105260473A (en) * | 2015-10-28 | 2016-01-20 | 汤占宇 | Information inquiring system and method |
| CN106131704A (en) * | 2016-08-30 | 2016-11-16 | 天脉聚源(北京)传媒科技有限公司 | A kind of method and apparatus of program searching |
| CN106528568A (en) * | 2015-09-11 | 2017-03-22 | 中兴通讯股份有限公司 | Method and system for information supply |
| CN107124569A (en) * | 2016-09-12 | 2017-09-01 | 平安科技（深圳）有限公司 | Video calling adjusting method and device |
| CN107480236A (en) * | 2017-08-08 | 2017-12-15 | 深圳创维数字技术有限公司 | A kind of information query method, device, equipment and medium |
| CN108388397A (en) * | 2018-02-13 | 2018-08-10 | 维沃移动通信有限公司 | A kind of information processing method and terminal |
| CN109919105A (en) * | 2019-03-11 | 2019-06-21 | 四川长虹电器股份有限公司 | A kind of object identifying method and system based on smart television picture |
| US10333767B2 (en) | 2013-03-15 | 2019-06-25 | Google Llc | Methods, systems, and media for media transmission and management |
| US10448110B2 (en) | 2013-12-31 | 2019-10-15 | Google Llc | Methods, systems, and media for presenting supplemental information corresponding to on-demand media content |
| US10924818B2 (en) | 2013-12-31 | 2021-02-16 | Google Llc | Methods, systems, and media for presenting supplemental content relating to media content based on state information that indicates a subsequent visit to the content interface |
| US10997235B2 (en) | 2013-12-31 | 2021-05-04 | Google Llc | Methods, systems, and media for generating search results based on contextual information |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1867039A (en) * | 2005-05-16 | 2006-11-22 | 日本胜利株式会社 | Electronic appliance |
| EP1772816A1 (en) * | 2005-10-09 | 2007-04-11 | Omron Corporation | Apparatus and method for detecting particular subject |
| CN101291400A (en) * | 2008-05-14 | 2008-10-22 | 深圳创维－Rgb电子有限公司 | Television indicating user to operate remote control by screen |
| CN101663676A (en) * | 2007-02-28 | 2010-03-03 | 霍尼韦尔国际公司 | Method and system for indexing and searching objects of interest across a plurality of video streams |
| CN101917566A (en) * | 2010-09-04 | 2010-12-15 | 冠捷显示科技（厦门）有限公司 | Method for intelligently controlling televisions based on human face analysis |
| CN101957911A (en) * | 2010-09-29 | 2011-01-26 | 汉王科技股份有限公司 | Face identification method and system |
| CN102012919A (en) * | 2010-11-26 | 2011-04-13 | 深圳市同洲电子股份有限公司 | Method and device for searching association of image screenshots from televisions and digital television terminal |
| CN102509235A (en) * | 2011-10-31 | 2012-06-20 | 福州博远无线网络科技有限公司 | Purchase interactive method based on mobile video of intelligent handheld device |
-
2012
- 2012-08-01 CN CN201210273566.2A patent/CN102868934B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1867039A (en) * | 2005-05-16 | 2006-11-22 | 日本胜利株式会社 | Electronic appliance |
| EP1772816A1 (en) * | 2005-10-09 | 2007-04-11 | Omron Corporation | Apparatus and method for detecting particular subject |
| CN101663676A (en) * | 2007-02-28 | 2010-03-03 | 霍尼韦尔国际公司 | Method and system for indexing and searching objects of interest across a plurality of video streams |
| CN101291400A (en) * | 2008-05-14 | 2008-10-22 | 深圳创维－Rgb电子有限公司 | Television indicating user to operate remote control by screen |
| CN101917566A (en) * | 2010-09-04 | 2010-12-15 | 冠捷显示科技（厦门）有限公司 | Method for intelligently controlling televisions based on human face analysis |
| CN101957911A (en) * | 2010-09-29 | 2011-01-26 | 汉王科技股份有限公司 | Face identification method and system |
| CN102012919A (en) * | 2010-11-26 | 2011-04-13 | 深圳市同洲电子股份有限公司 | Method and device for searching association of image screenshots from televisions and digital television terminal |
| CN102509235A (en) * | 2011-10-31 | 2012-06-20 | 福州博远无线网络科技有限公司 | Purchase interactive method based on mobile video of intelligent handheld device |
Cited By (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105122242A (en) * | 2013-03-14 | 2015-12-02 | 谷歌公司 | Methods, systems, and media for presenting mobile content corresponding to media content |
| US10333767B2 (en) | 2013-03-15 | 2019-06-25 | Google Llc | Methods, systems, and media for media transmission and management |
| CN103428537A (en) * | 2013-07-30 | 2013-12-04 | 北京小米科技有限责任公司 | Video processing method and video processing device |
| CN103428537B (en) * | 2013-07-30 | 2017-03-01 | 小米科技有限责任公司 | A kind of method for processing video frequency and device |
| CN103826142A (en) * | 2013-11-15 | 2014-05-28 | 安徽科大讯飞信息科技股份有限公司 | Customizing and pushing method and system based on real-time program content |
| CN104754413A (en) * | 2013-12-30 | 2015-07-01 | 北京三星通信技术研究有限公司 | Image search based television signal identification and information recommendation method and device |
| US11350182B2 (en) | 2013-12-31 | 2022-05-31 | Google Llc | Methods, systems, and media for presenting supplemental content relating to media content based on state information that indicates a subsequent visit to the content interface |
| US10997235B2 (en) | 2013-12-31 | 2021-05-04 | Google Llc | Methods, systems, and media for generating search results based on contextual information |
| US10448110B2 (en) | 2013-12-31 | 2019-10-15 | Google Llc | Methods, systems, and media for presenting supplemental information corresponding to on-demand media content |
| US10924818B2 (en) | 2013-12-31 | 2021-02-16 | Google Llc | Methods, systems, and media for presenting supplemental content relating to media content based on state information that indicates a subsequent visit to the content interface |
| US11941046B2 (en) | 2013-12-31 | 2024-03-26 | Google Llc | Methods, systems, and media for generating search results based on contextual information |
| US11743557B2 (en) | 2013-12-31 | 2023-08-29 | Google Llc | Methods, systems, and media for presenting supplemental content relating to media content based on state information that indicates a subsequent visit to the content interface |
| US10992993B2 (en) | 2013-12-31 | 2021-04-27 | Google Llc | Methods, systems, and media for presenting supplemental information corresponding to on-demand media content |
| CN104881407A (en) * | 2014-02-27 | 2015-09-02 | 福州瑞芯微电子有限公司 | Information recommending system and information recommending method based on feature recognition |
| CN103870559A (en) * | 2014-03-06 | 2014-06-18 | 海信集团有限公司 | Method and equipment for obtaining information based on played video |
| CN104063512A (en) * | 2014-07-10 | 2014-09-24 | 福州瑞芯微电子有限公司 | Information recommending device and method based on feature recognition |
| CN104184923A (en) * | 2014-08-27 | 2014-12-03 | 天津三星电子有限公司 | System and method used for retrieving figure information in video |
| CN104184923B (en) * | 2014-08-27 | 2018-01-09 | 天津三星电子有限公司 | System and method for retrieving people information in video |
| CN104391711B (en) * | 2014-08-28 | 2018-05-29 | 小米科技有限责任公司 | A kind of method and device that screen protection is set |
| CN104391711A (en) * | 2014-08-28 | 2015-03-04 | 小米科技有限责任公司 | Method and device for setting screen protection |
| CN104602128A (en) * | 2014-12-31 | 2015-05-06 | 北京百度网讯科技有限公司 | Video processing method and device |
| CN104967889A (en) * | 2015-06-30 | 2015-10-07 | 小米科技有限责任公司 | Method used for controlling intelligent television to carry out video information processing and device |
| CN106528568A (en) * | 2015-09-11 | 2017-03-22 | 中兴通讯股份有限公司 | Method and system for information supply |
| CN105260473A (en) * | 2015-10-28 | 2016-01-20 | 汤占宇 | Information inquiring system and method |
| CN106131704A (en) * | 2016-08-30 | 2016-11-16 | 天脉聚源(北京)传媒科技有限公司 | A kind of method and apparatus of program searching |
| CN107124569B (en) * | 2016-09-12 | 2018-05-22 | 平安科技（深圳）有限公司 | Video calling adjusting method and device |
| CN107124569A (en) * | 2016-09-12 | 2017-09-01 | 平安科技（深圳）有限公司 | Video calling adjusting method and device |
| CN107480236A (en) * | 2017-08-08 | 2017-12-15 | 深圳创维数字技术有限公司 | A kind of information query method, device, equipment and medium |
| CN108388397A (en) * | 2018-02-13 | 2018-08-10 | 维沃移动通信有限公司 | A kind of information processing method and terminal |
| CN109919105A (en) * | 2019-03-11 | 2019-06-21 | 四川长虹电器股份有限公司 | A kind of object identifying method and system based on smart television picture |
| CN109919105B (en) * | 2019-03-11 | 2022-04-05 | 四川长虹电器股份有限公司 | Object identification method and system based on smart television picture |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102868934B (en) | 2016-06-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102868934B (en) | Video object information search method and device based on intelligent television | |
| CN107480236B (en) | Information query method, device, equipment and medium | |
| US11393205B2 (en) | Method of pushing video editing materials and intelligent mobile terminal | |
| CN109688475B (en) | Video playing skipping method and system and computer readable storage medium | |
| KR102191177B1 (en) | Display device and operating method thereof | |
| CN105122242A (en) | Methods, systems, and media for presenting mobile content corresponding to media content | |
| KR101783115B1 (en) | Telestration system for command processing | |
| CN105872838A (en) | Sending method and device of special media effects of real-time videos | |
| KR101884291B1 (en) | Display apparatus and control method thereof | |
| JP6986187B2 (en) | Person identification methods, devices, electronic devices, storage media, and programs | |
| JP2013143141A (en) | Display apparatus, remote control apparatus, and searching methods thereof | |
| CN111010598B (en) | Screen capture application method and smart television | |
| KR20160070805A (en) | Tv program identification method, apparatus, terminal, server and system | |
| CN109389088B (en) | Video recognition method, device, machine equipment and computer readable storage medium | |
| US20150331598A1 (en) | Display device and operating method thereof | |
| CN111343512B (en) | Information acquisition method, display device and server | |
| CN108958503A (en) | input method and device | |
| CN101655875A (en) | Image indication method and digital photo frame | |
| KR102298066B1 (en) | Method for providing image contents and image contents providing apparatus | |
| CN110647732B (en) | Voice interaction method, system, medium and device based on biological recognition characteristics | |
| CN112052784A (en) | Article searching method, device, equipment and computer readable storage medium | |
| CN109769130B (en) | Remote controller personalized setting method and system based on big viewing data | |
| CN111274449B (en) | Video playing method, device, electronic equipment and storage medium | |
| CN104049833A (en) | Terminal screen image displaying method based on individual biological characteristics and terminal screen image displaying device based on individual biological characteristics | |
| CN104936003A (en) | Screenshot method and screenshot device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C41 | Transfer of patent application or patent right or utility model | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20170110 Address after: 266100 Shandong Province, Qingdao city Laoshan District Songling Road No. 399 Patentee after: Poly Polytron Technologies Inc Address before: 266061 Laoshan, Qingdao province Hongkong District No. East Road, room 248, room 131 Patentee before: Hisense Media Networks Co., Ltd. |