CN109189885A - Real-time control method based on intelligent equipment camera and intelligent equipment - Google Patents

Real-time control method based on intelligent equipment camera and intelligent equipment Download PDF

Info

Publication number
CN109189885A
CN109189885A CN201811014511.3A CN201811014511A CN109189885A CN 109189885 A CN109189885 A CN 109189885A CN 201811014511 A CN201811014511 A CN 201811014511A CN 109189885 A CN109189885 A CN 109189885A
Authority
CN
China
Prior art keywords
camera
books
image
target image
user
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
CN201811014511.3A
Other languages
Chinese (zh)
Inventor
杨昊民
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.)
Guangdong Genius Technology Co Ltd
Original Assignee
Guangdong Genius 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 Guangdong Genius Technology Co Ltd filed Critical Guangdong Genius Technology Co Ltd
Priority to CN201811014511.3A priority Critical patent/CN109189885A/en
Publication of CN109189885A publication Critical patent/CN109189885A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/40Document-oriented image-based pattern recognition
    • GPHYSICS
    • G09EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09BEDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B7/00Electrically-operated teaching apparatus or devices working with questions and answers
    • G09B7/02Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N23/00Cameras or camera modules comprising electronic image sensors; Control thereof
    • H04N23/60Control of cameras or camera modules

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Educational Technology (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The invention discloses a real-time control method based on an intelligent device camera and an intelligent device, and relates to the field of intelligent control. When students study independently, the problems encountered by the students are difficult to solve in time, and the learning efficiency of the students is greatly influenced. A real-time control method based on a camera of an intelligent device comprises the following steps: opening a camera in real time, and acquiring a target image in a shooting area; when a voice signal of a user is collected, carrying out voice recognition on the voice signal to identify a problem brought forward by the user; performing image recognition on the target image, and recognizing the content of the designated area of the user on the book; searching out answers of questions raised aiming at the contents of the specified area on the book by combining the questions raised by the user and the contents of the specified area on the book; the answer to the question presented for the content of the specified area on the book is displayed. When students independently learn through the invention, the problems encountered can be solved in time, and the learning efficiency of the students is increased.

Description

A kind of real-time control method and smart machine based on smart machine camera
Technical field
The present invention relates to field of intelligent control, espespecially a kind of real-time control method and intelligence based on smart machine camera Equipment.
Background technique
With the continuous development of society, the education that people also gradually recognize is important for human development and family Property, parent can also accompany regularly child at one's side, teach child's operation, lay good base for the study of child from now on Plinth.
Student lower for grade would ordinarily be encountered various problem in the study, such as certain some word will not Read, certain some topic will not be done or the meaning of certain some sentence can not understand etc., due to its problem of settling a dispute by the parties concerned themselves ability not It is enough to solve current problems faced.Therefore, always like asking adult at one's side in the study when encountering problems, such as " father this How a topic is done ", " how this word of father is read ", " father's the words what meaning " etc..
When adult not student at one's side, when student's independent study, the problem of student encounters, is difficult to solve in time, to student Learning efficiency have large effect.
Summary of the invention
The object of the present invention is to provide a kind of real-time control method and smart machine based on smart machine camera, favorably In user in independent study, the problem of encountering, can solve in time, increase the learning efficiency of user.
Technical solution provided by the invention is as follows:
A kind of real-time control method based on smart machine camera, comprising: camera is opened in real time, in imaging area Obtain target image;
When collecting the voice signal of user, speech recognition is carried out to the voice signal, identifies that the user mentions Out the problem of;
Image recognition is carried out to the target image, identifies that the user specifies the content in region on books;
The content that region is specified on the problem of proposing in conjunction with the user and the books, searches out and specifies on books The content in region proposes the answer of problem;
Answer of the display for the content proposition problem for specifying region on books.
Further, after obtaining target image in imaging area, before the voice signal for acquiring user further include: analysis The target image adjusts the shooting angle of the camera according to the book image in the target image.
Further, the target image is analyzed, according to the book image in the target image, adjusts the camera Shooting angle specifically includes: analyzing the target image, when the book image in the target image is imperfect, analysis is published books Originally the placement location in the imaging area;
According to placement location of the books in the imaging area, the shooting angle of the camera is automatically adjusted.
Further, the target image is analyzed, according to the book image in the target image, adjusts the camera Shooting angle specifically includes: analyzing in the same period, multiple target images of different time judge the target image Whether the position of middle book image changes;
When the position of the book image described in the target image changes, the position according to the book image becomes Change, analysis obtains the direction of motion of books;
According to the direction of motion of the books, the shooting angle of the camera is automatically adjusted.
Further, before camera is opened in real time further include: whether there is book in the imaging area of real-time detection camera This;
When, there are when books, camera is opened in real time in the imaging area for detecting camera;Otherwise, camera is closed.
An object of the present invention, which also resides in, provides a kind of smart machine, comprising: image collection module, including open in real time Camera, for obtaining target image in imaging area;
Voice module carries out speech recognition for acquiring the voice signal of user, and to the voice signal, identifies institute State the problem of user proposes;
Picture recognition module identifies that the user refers on books for carrying out image recognition to the target image Determine the content in region;
Answer search module is searched for specifying the content in region in conjunction with the problem of user proposition and on the books Rope goes out the answer for being directed to and the content in region being specified to propose problem on books;
Answer display module, for showing the answer for being directed to and the content in region being specified to propose problem on books.
Further, further includes: image analysis module, for analyzing the target image, angular adjustment module is used for foundation Book image in the target image adjusts the shooting angle of the camera.
Further, when the book image in the target image is imperfect, described image analysis module analyzes books Placement location in the imaging area;
Placement location of the angular adjustment module according to the books in the imaging area is taken the photograph described in automatic adjustment As the shooting angle of head.
Further, described image analysis module is for analyzing in the same period, multiple target figures of different time Picture, judges whether the position of book image in the target image changes;
When the position of the book image described in the target image changes, the position according to the book image becomes Change, described image analysis module is analyzed to obtain the direction of motion of books;
The direction of motion of the angular adjustment module according to the books, automatically adjusts the shooting angle of the camera.
Further, further includes: books detection module, for whether there is book in the imaging area of real-time detection camera This;
When, there are when books, described image obtains module control camera and beats in real time in the imaging area for detecting camera It opens;Otherwise, described image obtains module control camera and closes.
Compared with prior art, a kind of real-time control method and intelligence based on smart machine camera provided by the invention Equipment has the advantages that
1, user only needs finger point oneself on books to need the position putd question to, and the problem of propose oneself, intelligence Equipment can search out the answer of proposition problem automatically, and answer is shown, be conducive to user in independent study, encounter The problem of can solve in time, increase the learning efficiency of user.
2, the voice signal of user is acquired, and identifies the problem of user proposes, and image knowledge is carried out to target image Not, identify that user specifies the content in region on books, two identification process are mutually indepedent, and do not interfere with each other.
3, when controller is analyzed there are when book image in imaging area, controller can change the shooting angle of camera Degree, camera is tracked books, avoid books be detached from camera imaging area, realize camera to The real-time tracing of family books realizes positioning of the camera to the position of books, ensure that the correctness of subsequent operation.
4, it can be imaged by adding the devices such as proximity sensor or infrared sensor to detect desktop on smart machine It whether there is books in the imaging area of head, and when detecting books, open camera, realize the real-time inspection to books It surveys.Simultaneously when books are not detected in smart machine, or in camera opening procedure, after books are taken away from desktop, take the photograph As books are not present in the imaging area of head, camera turns off, reduces unnecessary waste, realize energy-efficient effect.
5, when analyzing the target image after the mobile preceding movement with books of books, controller can also learn books in time Moving direction changes the shooting angle of camera further according to the moving direction of books, enables shifting of the camera to books It is dynamic to place rotation, then realize that books can be always positioned in shooting area, reduce books due to being moved out shooting area Possibility.
Detailed description of the invention
Below by clearly understandable mode, preferred embodiment is described with reference to the drawings, one kind is taken the photograph based on smart machine As the real-time control method of head and above-mentioned characteristic, technical characteristic, advantage and its implementation of smart machine give furtherly It is bright.
Fig. 1 is a kind of flow diagram of the real-time control method based on smart machine camera of the present invention;
Fig. 2 is the flow diagram of another real-time control method based on smart machine camera of the invention;
Fig. 3 is the flow diagram of another real-time control method based on smart machine camera of the invention;
Fig. 4 is the flow diagram of another real-time control method based on smart machine camera of the invention;
Fig. 5 is a kind of structural schematic diagram of smart machine of the present invention;
Fig. 6 is the structural schematic diagram of another smart machine of the invention;
Fig. 7 is a kind of concrete structure schematic diagram of smart machine of the present invention;
Fig. 8 is the concrete structure schematic diagram of another smart machine of the invention.
Drawing reference numeral explanation: 10. image collection modules, 20. voice modules, 30. picture recognition modules, 40. answers search Module, 50. answer display modules, 60. image analysis modules, 70. angular adjustment modules, 80. books detection modules.
Specific embodiment
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, Detailed description of the invention will be compareed below A specific embodiment of the invention.It should be evident that drawings in the following description are only some embodiments of the invention, for For those of ordinary skill in the art, without creative efforts, it can also be obtained according to these attached drawings other Attached drawing, and obtain other embodiments.
To make simplified form, part related to the present invention is only schematically shown in each figure, they are not represented Its practical structures as product.In addition, there is identical structure or function in some figures so that simplified form is easy to understand Component only symbolically depicts one of those, or has only marked one of those.Herein, "one" is not only indicated " only this ", can also indicate the situation of " more than one ".
A kind of embodiment provided according to the present invention, as shown in Figure 1, a kind of real-time control based on smart machine camera Method, comprising:
S10, camera are opened in real time, and target image is obtained in imaging area.
Specifically, in the present embodiment, the camera on smart machine can be opened in real time, or by the control of user Afterwards, the camera on smart machine can be opened in real time, or after smart machine controls, and beat in real time in smart machine work It opens.
Camera can be in the outside of smart machine, and the shooting end of camera is towards imaging area, and camera can be It takes pictures after opening to imaging area, obtains the target image of imaging area, imaging area refers mainly to one piece of area on front side of camera Domain, i.e. imaging area refer mainly to the working face on smart machine.
After camera is opened in real time, camera can carry out real-time photography to target area, and can in camera By programming in logic, the shooting action of camera is controlled, imaging area is shot with different shooting intervals, and in real time more Fresh target image, so that real time monitoring effect of the subsequent camera to books can continue to carry out.
S20, when collecting the voice signal of user, to the voice signal carry out speech recognition, identify the use The problem of family proposes.
The voice acquisition device i.e. microphone for acquiring user voice signal is additionally provided on smart machine, microphone also can It is enough to be opened in real time in smart machine work, or open or close according to the demand of user.
For microphone in the voice signal for collecting user, collected voice signal can be sent to control by microphone Device, controller refer mainly to be arranged in the computer in smart machine;And when can be opened in real time due to microphone, microphone can Getting user in time, what is said or talked about, and converts voice signal for the sound that user issues;And in sound acquisition, wheat Gram wind is after receiving voice signal, and the voice signal received can also be carried out noise reduction process by microphone, to obtain more Clearly voice signal.
After voice signal is sent to controller by microphone, controller can be according to sound characteristic or the sound of voice signal Color and audio, are compared with database, and identification obtains the problem of user proposes.
S30, image recognition is carried out to the target image, identifies that the user specifies the content in region on books.
After camera collects target image, camera can be at interval of the regular hour by the target image of shooting It is sent to controller, controller is after obtaining target image, by getting the feature in target image, with characteristic Library is compared, to analyze in target image whether have existed books.
It when being identified to target image, is matched using big data and artificial intelligence, identifies user is using anything Books, how much pages of this this book, user how many sections or how many row specified on books.Controller can also be by getting Target head portrait color characteristic, and be compared with the color characteristic of skin, to analyze the position of the finger in target image It sets, and by the position of the finger tips in target image, to analyze the position of user's finger direction.
Controller when detecting books, controller can also and Text region, to identify to obtain bookish text, And the books in text and database are subjected to fuzzy search, analysis obtains books representated by the book image in target image Type, and analyze the current number of pages of books.
By the method for image recognition, the content for the books that user is currently pointed at can be got, controller can obtain Get the content for needing to search for.User can be user using finger or matched pen in books when specifying region on books On the region pointing out or sketch out.
The voice signal of acquisition user in smart machine, and identify the process for the problem of user proposes, and to mesh Logo image carries out image recognition, identifies that user specifies the process of the content in region on books, two identification process are mutually only It is vertical, and do not interfere with each other.
S40, the content that region is specified in conjunction with the problem of user proposition and on the books, search out on books The content in specified region proposes the answer of problem.
The problem of identification obtains user's proposition and identifies the content for specifying region on books and then start to search for Process, and in search process, the object of search is the content that region is specified on books, and the condition searched for is asked from what user proposed Topic shows the answer that search obtains to obtain, and after the search is completed.
Controller is according to searching a large amount of answer, and by the matching degree of answer, chooses that matching degree is highest to be answered The answer for the problem of case is proposed as user.
S50, display propose the answer of problem for the content in region specified on books.
For various forms of answers, smart machine can be shown in different ways, such as voice broadcast, display screen It has been shown that, the modes such as tripleplane can be as the display modes of the display device in the present invention.Controller is detecting difference Answer when, controller can also be chosen different according to the type of answer.Such as when detecting the answer of pronunciation class, pass through When the mode of voice broadcast shows that answer or answer are image or model, answer is shown by way of tripleplane.
When user's finger has referred in some bookish word, due to opening in real time, smart machine can obtain camera Finger and its pointed position to user.When user gets " how this word is read ", smart machine may recognize that use Word at the finger tips of family, and pronunciation search is carried out to the word, and the word is read by loudspeaker, or pass through display screen or projection Smart machine shows the pronunciation of the word.Or when user gets " how this problem does ", controller be may recognize that at finger Large area image identifies the topic, and scans for the topic, obtains the answer of topic, and show by display device Out.
User only needs finger point oneself on books to need the position putd question to, and the problem of propose oneself, intelligently sets It is standby to search out the answer of proposition problem automatically, and answer is shown, be conducive to user in independent study, encounter Problem can solve in time, increase the learning efficiency of user.
Another embodiment provided according to the present invention, as shown in Fig. 2, a kind of real-time control based on smart machine camera Method processed, comprising:
S10, camera are opened in real time, and target image is obtained in imaging area.
S11, the analysis target image adjust the bat of the camera according to the book image in the target image Take the photograph angle.
S20, when collecting the voice signal of user, to the voice signal carry out speech recognition, identify the use The problem of family proposes.
S30, image recognition is carried out to the target image, identifies that the user specifies the content in region on books.
S40, the content that region is specified in conjunction with the problem of user proposition and on the books, search out on books The content in specified region proposes the answer of problem.
S50, display propose the answer of problem for the content in region specified on books.
Preferably, before camera is opened in real time further include:
S01, real-time detection camera imaging area in whether there is books.
S02, when, there are when books, camera is opened in real time in the imaging area for detecting camera;Otherwise, camera closes It closes.
Specifically, in the present embodiment, camera opening after, camera imaging area can be carried out shooting obtain Target image is taken, when there is book image in the target image, smart machine can analyze the presence of book image, intelligence The regulating device for adjusting camera shooting angle is additionally provided in equipment.
When smart machine is analyzed there are when book image in imaging area, controller can change the shooting angle of camera Degree, camera is tracked books, avoid books be detached from camera imaging area, realize camera to The real-time tracing of family books realizes positioning of the camera to the position of books, ensure that the correctness of subsequent operation.
Smart machine also can by changing camera position, such as coordinate of the change camera on working face, It realizes the change of camera position, then realizes the change of imaging area;And the angle of the position change and camera of camera Change can also carry out simultaneously, for changing the imaging area of camera, then realize the real-time tracing to books.
Camera can have multiple control modes, such as voice control mode, real-time control mode etc., the present embodiment tool Body describes the real-time control mode to camera;It is different to choose on intelligent devices by modes such as gesture or buttons Control mode.
After choosing completion real-time control mode, addition proximity sensor or infrared sensing can be passed through on smart machine The devices such as device open camera shooting to detect with the presence or absence of books in the desktop i.e. imaging area of camera, and when detecting books Head realizes the real-time detection to books.Simultaneously when books are not detected in smart machine, or after camera opening, books After taking away from desktop, smart machine is able to detect that the imaging area of camera there is no books, and camera no longer needs to out It opens, smart machine controls camera and closes, and reduces unnecessary waste, realizes energy-efficient effect.
Camera can again shoot imaging area at interval of a period of time, camera, get new target Image is easy to implement and detects to books to replace original target image, and book image occurs in detecting target image When variation, smart machine can be in time modified the shooting angle of camera, realize the real time monitoring to books.
Another embodiment provided according to the present invention, as shown in figure 3, a kind of real-time control based on smart machine camera Method processed, comprising:
S10, camera are opened in real time, and target image is obtained in imaging area.
S111, the analysis target image analyze books and exist when the book image in the target image is imperfect Placement location in the imaging area.
S112, the placement location according to the books in the imaging area, automatically adjust the shooting of the camera Angle.
S20, when collecting the voice signal of user, to the voice signal carry out speech recognition, identify the use The problem of family proposes.
S30, image recognition is carried out to the target image, identifies that the user specifies the content in region on books.
S40, the content that region is specified in conjunction with the problem of user proposition and on the books, search out on books The content in specified region proposes the answer of problem.
S50, display propose the answer of problem for the content in region specified on books.
Specifically, in the present embodiment, after camera gets target image, target image can be sent to by camera Controller, smart machine can recognize that the position of the book image in target image, in identification process, additionally it is possible to combining target It whether include complete book image in the image of books in image, to judge books whether in shooting area.
After smart machine analyzes placement location of the books in imaging area simultaneously, the shooting angle of camera is automatically adjusted Degree, and books are entirely fallen in imaging area, so as to the execution of subsequent step.
Camera is preferably arranged on intelligent devices by bulb connection;It is detected in target image in smart machine When book image is imperfect, i.e. a part of books is not photographed, at this point, books are not entirely fallen in imaging area, control Device can obtain the positional relationship of books and imaging area, and the direction where controlling camera to books is rotated, thus Books are fallen in imaging area.Under current state, the imaging area of camera is changed, therefore, camera New target image can be obtained again, and when detecting that book image is imperfect, executes the shooting of above-mentioned camera again Angle change movement, until camera can get the target image comprising complete book image.Meanwhile camera is multiple Target image is obtained, is also convenient for realizing the real-time positioning to books.
Since imaging area is greater than books, accounting of the book image in target image is also smaller, therefore, controller The spacing between book image and target image edge can also be controlled again, is realized after getting whole book images Spacing between book image and target image edge is all larger than preset spacing, and the books under current state can fall in camera shooting The middle part in region is reduced since after the mobile books of user, camera reduces there is still a need for the possibility for changing its shooting angle Unnecessary waste.
The another embodiment provided according to the present invention, as shown in figure 4, a kind of real-time control based on smart machine camera Method processed, comprising:
S10, camera are opened in real time, and target image is obtained in imaging area.
S113, it analyzes in the same period, multiple target images of different time judge book in the target image Whether the position of this image changes.
Position when changing of S114, the book image described in the target image, according to the book image Change in location, analysis obtain the direction of motion of books.
S115, according to the direction of motion of the books, automatically adjust the shooting angle of the camera.
S20, when collecting the voice signal of user, to the voice signal carry out speech recognition, identify the use The problem of family proposes.
S30, image recognition is carried out to the target image, identifies that the user specifies the content in region on books.
S40, the content that region is specified in conjunction with the problem of user proposition and on the books, search out on books The content in specified region proposes the answer of problem.
S50, display propose the answer of problem for the content in region specified on books.
Specifically, in the present embodiment, camera is continuously shot imaging area, and shooting process in, the position of books It sets when changing, corresponding variation has occurred in position of the book image on target image, and smart machine can be learnt in time The shift action of books;Smart machine is in the target image before analyzing books movement and after books are mobile simultaneously, smart machine Also the moving direction that can learn books in time, the shooting angle of camera is changed further according to the moving direction of books, so that Camera can be rotated to the moving direction of books, then realized that books can be always positioned in shooting area, reduced books Due to being moved out the possibility of shooting area.
During judging multiple target images, when judging whether books move, at least need under same shooting angle Two target images, the moving distance of the book image in two target images is greater than default moving distance, at this point, controller is It can determine whether that books start to move.
Simultaneously smart machine also can by the target image under different shooting angles, the background of combining target image and The acquisition parameters of video camera when shooting further to judge whether books have occurred the change of position, and then realize judgement book Whether this is moved, and in books motion process, is had adjusted the imaging area of camera in time, is realized on the move The real time monitoring of books.
When detecting the books in motion process, additionally it is possible in conjunction with the regulative mode of above-described embodiment, to enable books Enough it is located at the middle part of camera shooting area, finally realizes camera to the stability monitoring of books.
A kind of embodiment provided according to the present invention, as shown in figure 5, a kind of smart machine, comprising:
Image collection module 10, including the camera opened in real time, for obtaining target image in imaging area.
Voice module 20 carries out speech recognition for acquiring the voice signal of user, and to the voice signal, identifies The problem of user proposes.
Picture recognition module 30 identifies the user on books for carrying out image recognition to the target image The content in specified region.
Answer search module 40, for specifying the content in region in conjunction with the problem of user proposition and on the books, Search out the answer for the content proposition problem for specifying region on books.
Answer display module 50, for showing the answer for being directed to and the content in region being specified to propose problem on books.
Specifically, in the present embodiment, the camera on smart machine can be opened in real time, or by the control of user Afterwards, the camera on smart machine can be opened in real time, or after smart machine controls, and beat in real time in smart machine work It opens.
Camera can be in the outside of smart machine, and the shooting end of camera is towards imaging area, and camera can be It takes pictures after opening to imaging area, obtains the target image of imaging area, imaging area refers mainly to one piece of area on front side of camera Domain, i.e. imaging area refer mainly to the working face on smart machine.
After camera is opened in real time, camera can carry out real-time photography to target area, and can in camera By programming in logic, the shooting action of camera is controlled, imaging area is shot with different shooting intervals, and in real time more Fresh target image, so that real time monitoring effect of the subsequent camera to books can continue to carry out.
The voice acquisition device i.e. microphone for acquiring user voice signal is additionally provided on smart machine, microphone also can It is enough to be opened in real time in smart machine work, or open or close according to the demand of user.
For microphone in the voice signal for collecting user, collected voice signal can be sent to control by microphone Device, controller refer mainly to be arranged in the computer in smart machine;And when can be opened in real time due to microphone, microphone can Getting user in time, what is said or talked about, and converts voice signal for the sound that user issues;And in sound acquisition, wheat Gram wind is after receiving voice signal, and the voice signal received can also be carried out noise reduction process by microphone, to obtain more Clearly voice signal.
After voice signal is sent to controller by microphone, controller can be according to sound characteristic or the sound of voice signal Color and audio, are compared with database, and identification obtains the problem of user proposes.
After camera collects target image, camera can be at interval of the regular hour by the target image of shooting It is sent to controller, controller is after obtaining target image, by getting the feature in target image, with characteristic Library is compared, to analyze in target image whether have existed books.
It when being identified to target image, is matched using big data and artificial intelligence, identifies user is using anything Books, how much pages of this this book, user how many sections or how many row specified on books.Controller can also be by getting Target head portrait color characteristic, and be compared with the color characteristic of skin, to analyze the position of the finger in target image It sets, and by the position of the finger tips in target image, to analyze the position of user's finger direction.
Controller when detecting books, controller can also and Text region, to identify to obtain bookish text, And the books in text and database are subjected to fuzzy search, analysis obtains books representated by the book image in target image Type, and analyze the current number of pages of books.
By the method for image recognition, the content for the books that user is currently pointed at can be got, controller can obtain Get the content for needing to search for.User can be user using finger or matched pen in books when specifying region on books On the region pointing out or sketch out.
The voice signal of acquisition user in smart machine, and identify the process for the problem of user proposes, and to mesh Logo image carries out image recognition, identifies that user specifies the process of the content in region on books, two identification process are mutually only It is vertical, and do not interfere with each other.
The problem of identification obtains user's proposition and identifies the content for specifying region on books and then start to search for Process, and in search process, the object of search is the content that region is specified on books, and the condition searched for is asked from what user proposed Topic shows the answer that search obtains to obtain, and after the search is completed.
Controller is according to searching a large amount of answer, and by the matching degree of answer, chooses that matching degree is highest to be answered The answer for the problem of case is proposed as user.
For various forms of answers, smart machine can be shown in different ways, such as voice broadcast, display screen It has been shown that, the modes such as tripleplane can be as the display modes of the display device in the present invention.Controller is detecting difference Answer when, controller can also be chosen different according to the type of answer.Such as when detecting the answer of pronunciation class, pass through When the mode of voice broadcast shows that answer or answer are image or model, answer is shown by way of tripleplane.
When user's finger has referred in some bookish word, due to opening in real time, smart machine can obtain camera Finger and its pointed position to user.When user gets " how this word is read ", smart machine may recognize that use Word at the finger tips of family, and pronunciation search is carried out to the word, and the word is read by loudspeaker, or pass through display screen or projection Smart machine shows the pronunciation of the word.Or when user gets " how this problem does ", controller be may recognize that at finger Large area image identifies the topic, and scans for the topic, obtains the answer of topic, and show by display device Out.
User only needs finger point oneself on books to need the position putd question to, and the problem of propose oneself, intelligently sets It is standby to search out the answer of proposition problem automatically, and answer is shown, be conducive to user in independent study, encounter Problem can solve in time, increase the learning efficiency of user.
As shown in Figure 7 and Figure 8, smart machine refers mainly to learning machine, point reader, and intelligent desk lamp or intelligent desk lamp are intelligently set It is standby;Image collection module 10 refers mainly to that camera on intelligent devices is arranged;Voice module 20 refers mainly to setting and sets intelligently Standby upper microphone, the voice signal of the input for acquiring user;Picture recognition module 30 and the searched module of answer refer mainly to Controller in smart machine is set, more specifically, referring mainly to be arranged in the microcomputer in smart machine;Answer is shown Module 50 is mainly disposed on the outside of smart machine, predominantly one or more in the devices such as loudspeaker, projection arrangement, display screen It is a.
Another embodiment provided according to the present invention, as shown in fig. 6, a kind of smart machine, comprising:
Image collection module 10, including the camera opened in real time, for obtaining target image in imaging area.
Voice module 20 carries out speech recognition for acquiring the voice signal of user, and to the voice signal, identifies The problem of user proposes.
Picture recognition module 30 identifies the user on books for carrying out image recognition to the target image The content in specified region.
Answer search module 40, for specifying the content in region in conjunction with the problem of user proposition and on the books, Search out the answer for the content proposition problem for specifying region on books.
Answer display module 50, for showing the answer for being directed to and the content in region being specified to propose problem on books.
Image analysis module 60, for analyzing the target image.
Angular adjustment module 70, for adjusting the shooting of the camera according to the book image in the target image Angle.
Preferably, further includes:
Books detection module 80, for whether there is books in the imaging area of real-time detection camera.
When, there are when books, it is real-time that described image obtains the control camera of module 10 in the imaging area for detecting camera It opens;Otherwise, described image obtains module 10 and controls camera closing.
Specifically, in the present embodiment, camera opening after, camera imaging area can be carried out shooting obtain Target image is taken, when there is book image in the target image, smart machine can analyze the presence of book image, intelligence The regulating device for adjusting camera shooting angle is additionally provided in equipment.
When smart machine is analyzed there are when book image in imaging area, controller can change the shooting angle of camera Degree, camera is tracked books, avoid books be detached from camera imaging area, realize camera to The real-time tracing of family books realizes positioning of the camera to the position of books, ensure that the correctness of subsequent operation.
Books detection module 80 is mainly the infrared sensor or proximity sensor being arranged on intelligent devices, for detecting It whether there is books on desktop.
Smart machine also can by changing camera position, such as coordinate of the change camera on working face, It realizes the change of camera position, then realizes the change of imaging area;And the angle of the position change and camera of camera Change can also carry out simultaneously, for changing the imaging area of camera, then realize the real-time tracing to books.
Camera can have multiple control modes, such as voice control mode, real-time control mode etc., the present embodiment tool Body describes the real-time control mode to camera;It is different to choose on intelligent devices by modes such as gesture or buttons Control mode.
After choosing completion real-time control mode, addition proximity sensor or infrared sensing can be passed through on smart machine The devices such as device open camera shooting to detect with the presence or absence of books in the desktop i.e. imaging area of camera, and when detecting books Head realizes the real-time detection to books.Simultaneously when books are not detected in smart machine, or after camera opening, books After taking away from desktop, smart machine is able to detect that the imaging area of camera there is no books, and camera no longer needs to out It opens, smart machine controls camera and closes, and reduces unnecessary waste, realizes energy-efficient effect.
Camera can again shoot imaging area at interval of a period of time, camera, get new target Image is easy to implement and detects to books to replace original target image, and book image occurs in detecting target image When variation, smart machine can be in time modified the shooting angle of camera, realize the real time monitoring to books.
Another embodiment provided according to the present invention, a kind of smart machine, comprising:
Image collection module 10, including the camera opened in real time, for obtaining target image in imaging area.
Voice module 20 carries out speech recognition for acquiring the voice signal of user, and to the voice signal, identifies The problem of user proposes.
Picture recognition module 30 identifies the user on books for carrying out image recognition to the target image The content in specified region.
Answer search module 40, for specifying the content in region in conjunction with the problem of user proposition and on the books, Search out the answer for the content proposition problem for specifying region on books.
Answer display module 50, for showing the answer for being directed to and the content in region being specified to propose problem on books.
Image analysis module 60, for analyzing the target image.
Angular adjustment module 70, for adjusting the shooting of the camera according to the book image in the target image Angle.
When the book image in the target image is imperfect, described image analysis module 60 analyzes books described Placement location in imaging area.
Placement location of the angular adjustment module 70 according to the books in the imaging area, described in automatic adjustment The shooting angle of camera.
Specifically, after camera gets target image, target image can be sent to controller by camera, intelligence Equipment can recognize that the position of the book image in target image, in identification process, additionally it is possible to the book in combining target image It whether include complete book image in this image, to judge books whether in shooting area.
After smart machine analyzes placement location of the books in imaging area simultaneously, the shooting angle of camera is automatically adjusted Degree, and books are entirely fallen in imaging area, so as to the execution of subsequent step.
Camera is preferably arranged on intelligent devices by bulb connection;It is detected in target image in smart machine When book image is imperfect, i.e. a part of books is not photographed, at this point, books are not entirely fallen in imaging area, control Device can obtain the positional relationship of books and imaging area, and the direction where controlling camera to books is rotated, thus Books are fallen in imaging area.Under current state, the imaging area of camera is changed, therefore, camera New target image can be obtained again, and when detecting that book image is imperfect, executes the shooting of above-mentioned camera again Angle change movement, until camera can get the target image comprising complete book image.Meanwhile camera is multiple Target image is obtained, is also convenient for realizing the real-time positioning to books.
It is further preferred that in the present embodiment, since imaging area is greater than books, book image is in target image Interior accounting is also smaller, and therefore, controller can also control again book image and mesh after getting whole book images Spacing between logo image edge realizes that the spacing between book image and target image edge is all larger than preset spacing, when Books under preceding state can fall in the middle part of imaging area, reduce since after the mobile books of user, camera still needs The possibility for changing its shooting angle reduces unnecessary waste.
The another embodiment provided according to the present invention, a kind of smart machine, comprising:
Image collection module 10, including the camera opened in real time, for obtaining target image in imaging area.
Voice module 20 carries out speech recognition for acquiring the voice signal of user, and to the voice signal, identifies The problem of user proposes.
Picture recognition module 30 identifies the user on books for carrying out image recognition to the target image The content in specified region.
Answer search module 40, for specifying the content in region in conjunction with the problem of user proposition and on the books, Search out the answer for the content proposition problem for specifying region on books.
Answer display module 50, for showing the answer for being directed to and the content in region being specified to propose problem on books.
Image analysis module 60, for analyzing the target image.
Angular adjustment module 70, for adjusting the shooting of the camera according to the book image in the target image Angle.
Described image analysis module 60 for analyzing in the same period, sentence by multiple target images of different time Whether the position of book image in the target image of breaking changes;The position of the book image described in the target image When changing, according to the change in location of the book image, the analysis of described image analysis module 60 obtains the movement side of books To.
The direction of motion of the angular adjustment module 70 according to the books, automatically adjusts the shooting angle of the camera Degree.
Specifically, in the present embodiment, camera is continuously shot imaging area, and shooting process in, the position of books It sets when changing, corresponding variation has occurred in position of the book image on target image, and smart machine can be learnt in time The shift action of books;Smart machine is in the target image before analyzing books movement and after books are mobile simultaneously, smart machine Also the moving direction that can learn books in time, the shooting angle of camera is changed further according to the moving direction of books, so that Camera can be rotated to the moving direction of books, then realized that books can be always positioned in shooting area, reduced books Due to being moved out the possibility of shooting area.
In the present embodiment, it during judging multiple target images, when judging whether books move, at least needs same Two target images under shooting angle, the moving distance of the book image in two target images are greater than default moving distance, At this point, controller can determine whether that books start to move.
Simultaneously smart machine also can by the target image under different shooting angles, the background of combining target image and The acquisition parameters of video camera when shooting further to judge whether books have occurred the change of position, and then realize judgement book Whether this has sent movement, in books motion process, has adjusted the imaging area of camera in time, realizes on the move The real time monitoring of books.
When detecting the books in motion process, additionally it is possible in conjunction with the regulative mode of above-described embodiment, to enable books Enough it is located at the middle part of camera shooting area, finally realizes camera to the stability monitoring of books.
It should be noted that above-described embodiment can be freely combined as needed.The above is only of the invention preferred Embodiment, it is noted that for those skilled in the art, in the premise for not departing from the principle of the invention Under, several improvements and modifications can also be made, these modifications and embellishments should also be considered as the scope of protection of the present invention.

Claims (10)

1. a kind of real-time control method based on smart machine camera characterized by comprising
Camera is opened in real time, and target image is obtained in imaging area;
When collecting the voice signal of user, speech recognition is carried out to the voice signal, identifies what the user proposed Problem;
Image recognition is carried out to the target image, identifies that the user specifies the content in region on books;
The content that region is specified on the problem of proposing in conjunction with the user and the books is searched out for region specified on books Content propose problem answer;
Answer of the display for the content proposition problem for specifying region on books.
2. a kind of real-time control method based on smart machine camera according to claim 1, which is characterized in that taking the photograph After obtaining target image in region, before the voice signal for acquiring user further include:
The target image is analyzed, according to the book image in the target image, adjusts the shooting angle of the camera.
3. a kind of real-time control method based on smart machine camera according to claim 2, which is characterized in that analysis The target image, according to the book image in the target image, the shooting angle for adjusting the camera is specifically included:
The target image is analyzed, when the book image in the target image is imperfect, analyzes books in the camera shooting Placement location in region;
According to placement location of the books in the imaging area, the shooting angle of the camera is automatically adjusted.
4. a kind of real-time control method based on smart machine camera according to claim 2, which is characterized in that analysis The target image, according to the book image in the target image, the shooting angle for adjusting the camera is specifically included:
It analyzes in the same period, multiple target images of different time judge book image in the target image Whether position changes;
When the position of the book image described in the target image changes, according to the change in location of the book image, Analysis obtains the direction of motion of books;
According to the direction of motion of the books, the shooting angle of the camera is automatically adjusted.
5. a kind of real-time control method based on smart machine camera described in any one of -4 according to claim 1, It is characterized in that, before camera is opened in real time further include:
It whether there is books in the imaging area of real-time detection camera;
When, there are when books, camera is opened in real time in the imaging area for detecting camera;Otherwise, camera is closed.
6. a kind of smart machine characterized by comprising
Image collection module, including the camera opened in real time, for obtaining target image in imaging area;
Voice module carries out speech recognition for acquiring the voice signal of user, and to the voice signal, identifies the use The problem of family proposes;
Picture recognition module identifies that the user specifies area on books for carrying out image recognition to the target image The content in domain;
Answer search module is searched out for specifying the content in region in conjunction with the problem of user proposition and on the books For the answer for the content proposition problem for specifying region on books;
Answer display module, for showing the answer for being directed to and the content in region being specified to propose problem on books.
7. a kind of smart machine according to claim 6, which is characterized in that further include:
Image analysis module, for analyzing the target image;
Angular adjustment module, for adjusting the shooting angle of the camera according to the book image in the target image.
8. a kind of smart machine according to claim 7, it is characterised in that:
When the book image in the target image is imperfect, described image analysis module analyzes books in the imaging region Placement location in domain;
Placement location of the angular adjustment module according to the books in the imaging area, automatically adjusts the camera Shooting angle.
9. a kind of smart machine according to claim 7, it is characterised in that:
Described image analysis module is for analyzing in the same period, multiple target images of different time, described in judgement Whether the position of book image changes in target image;The position of the book image described in the target image becomes When change, according to the change in location of the book image, described image analysis module is analyzed to obtain the direction of motion of books;
The direction of motion of the angular adjustment module according to the books, automatically adjusts the shooting angle of the camera.
10. a kind of smart machine according to any one of claim 6-9, which is characterized in that further include:
Books detection module, for whether there is books in the imaging area of real-time detection camera;
When, there are when books, described image obtains module control camera and opens in real time in the imaging area for detecting camera; Otherwise, described image obtains module control camera and closes.
CN201811014511.3A 2018-08-31 2018-08-31 Real-time control method based on intelligent equipment camera and intelligent equipment Pending CN109189885A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811014511.3A CN109189885A (en) 2018-08-31 2018-08-31 Real-time control method based on intelligent equipment camera and intelligent equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811014511.3A CN109189885A (en) 2018-08-31 2018-08-31 Real-time control method based on intelligent equipment camera and intelligent equipment

Publications (1)

Publication Number Publication Date
CN109189885A true CN109189885A (en) 2019-01-11

Family

ID=64917530

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811014511.3A Pending CN109189885A (en) 2018-08-31 2018-08-31 Real-time control method based on intelligent equipment camera and intelligent equipment

Country Status (1)

Country Link
CN (1) CN109189885A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109726333A (en) * 2019-01-23 2019-05-07 广东小天才科技有限公司 Image-based question searching method and family education equipment
CN109753554A (en) * 2019-01-14 2019-05-14 广东小天才科技有限公司 Searching method based on three-dimensional space positioning and family education equipment
CN109783613A (en) * 2019-01-23 2019-05-21 广东小天才科技有限公司 Question searching method and system
CN110764110A (en) * 2019-11-12 2020-02-07 深圳创维数字技术有限公司 Path navigation method, device and computer readable storage medium
CN111078983A (en) * 2019-06-09 2020-04-28 广东小天才科技有限公司 Method for determining page to be identified and learning device
CN112328308A (en) * 2020-02-26 2021-02-05 北京字节跳动网络技术有限公司 Method and device for recognizing text
CN116300092A (en) * 2023-03-09 2023-06-23 北京百度网讯科技有限公司 Control method, device and equipment of intelligent glasses and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104104867A (en) * 2014-04-28 2014-10-15 三星电子(中国)研发中心 Method for controlling image photographing device for photographing and device thereof
CN104217197A (en) * 2014-08-27 2014-12-17 华南理工大学 Touch reading method and device based on visual gestures
CN105301585A (en) * 2015-11-02 2016-02-03 小米科技有限责任公司 Information display method and device
CN106713773A (en) * 2017-03-31 2017-05-24 联想(北京)有限公司 Shooting control method and electronic device
CN107480129A (en) * 2017-07-18 2017-12-15 上海斐讯数据通信技术有限公司 A kind of article position recognition methods and the system of view-based access control model identification and speech recognition
US9852264B1 (en) * 2014-07-21 2017-12-26 Padmanabaiah Srirama Authentic and verifiable electronic wellness record
CN107798931A (en) * 2017-12-05 2018-03-13 上海电机学院 A kind of intelligent children education learning system and method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104104867A (en) * 2014-04-28 2014-10-15 三星电子(中国)研发中心 Method for controlling image photographing device for photographing and device thereof
US9852264B1 (en) * 2014-07-21 2017-12-26 Padmanabaiah Srirama Authentic and verifiable electronic wellness record
CN104217197A (en) * 2014-08-27 2014-12-17 华南理工大学 Touch reading method and device based on visual gestures
CN105301585A (en) * 2015-11-02 2016-02-03 小米科技有限责任公司 Information display method and device
CN106713773A (en) * 2017-03-31 2017-05-24 联想(北京)有限公司 Shooting control method and electronic device
CN107480129A (en) * 2017-07-18 2017-12-15 上海斐讯数据通信技术有限公司 A kind of article position recognition methods and the system of view-based access control model identification and speech recognition
CN107798931A (en) * 2017-12-05 2018-03-13 上海电机学院 A kind of intelligent children education learning system and method

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109753554A (en) * 2019-01-14 2019-05-14 广东小天才科技有限公司 Searching method based on three-dimensional space positioning and family education equipment
CN109753554B (en) * 2019-01-14 2021-03-30 广东小天才科技有限公司 Searching method based on three-dimensional space positioning and family education equipment
CN109726333A (en) * 2019-01-23 2019-05-07 广东小天才科技有限公司 Image-based question searching method and family education equipment
CN109783613A (en) * 2019-01-23 2019-05-21 广东小天才科技有限公司 Question searching method and system
CN109783613B (en) * 2019-01-23 2021-08-24 广东小天才科技有限公司 Question searching method and system
CN111078983A (en) * 2019-06-09 2020-04-28 广东小天才科技有限公司 Method for determining page to be identified and learning device
CN111078983B (en) * 2019-06-09 2023-04-28 广东小天才科技有限公司 Method for determining page to be identified and learning equipment
CN110764110A (en) * 2019-11-12 2020-02-07 深圳创维数字技术有限公司 Path navigation method, device and computer readable storage medium
CN110764110B (en) * 2019-11-12 2022-04-08 深圳创维数字技术有限公司 Path navigation method, device and computer readable storage medium
CN112328308A (en) * 2020-02-26 2021-02-05 北京字节跳动网络技术有限公司 Method and device for recognizing text
CN116300092A (en) * 2023-03-09 2023-06-23 北京百度网讯科技有限公司 Control method, device and equipment of intelligent glasses and storage medium
CN116300092B (en) * 2023-03-09 2024-05-14 北京百度网讯科技有限公司 Control method, device and equipment of intelligent glasses and storage medium

Similar Documents

Publication Publication Date Title
CN109192204A (en) Voice control method based on intelligent equipment camera and intelligent equipment
CN109189885A (en) Real-time control method based on intelligent equipment camera and intelligent equipment
CN106228982B (en) A kind of interactive learning system and exchange method based on education services robot
CN101393599B (en) Game role control method based on human face expression
CN106599881A (en) Student state determination method, device and system
WO2019028592A1 (en) Teaching assistance method and teaching assistance system using said method
CN110119672A (en) A kind of embedded fatigue state detection system and method
CN110085068A (en) Learning tutoring method and device based on image recognition
WO2008069519A1 (en) Gesture/speech integrated recognition system and method
CN109035919A (en) Intelligent device and system for assisting user in solving problems
CN111796752A (en) Interactive teaching system based on PC
WO2022052941A1 (en) Intelligent identification method and system for giving assistance with piano teaching, and intelligent piano training method and system
Wei et al. Real-time head nod and shake detection for continuous human affect recognition
CN108471486A (en) A kind of intelligent reading operations method and device suitable for electronic viewing aid
CN104835361B (en) A kind of electronic dictionary
CN109754653B (en) Method and system for personalized teaching
CN109323159A (en) Illuminating bracket formula multimedia equipment
CN207851897U (en) The tutoring system of artificial intelligence based on TensorFlow
JP2022014890A (en) Concentration determination program
CN111857338A (en) Method suitable for using mobile application on large screen
CN109871123B (en) Teaching method based on gesture or eye control
CN109766413B (en) Searching method applied to family education equipment and family education equipment
CN113743319A (en) Self-monitoring intelligent fitness scheme generation method and device
CN113506027A (en) Course quality assessment and improvement method based on student visual attention and teacher behavior
CN111860294A (en) Face capture equipment convenient to trail

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20190111

RJ01 Rejection of invention patent application after publication