CN103778261A - Self-guided tour method based on mobile cloud computing image recognition - Google Patents
Self-guided tour method based on mobile cloud computing image recognition Download PDFInfo
- Publication number
- CN103778261A CN103778261A CN201410076300.8A CN201410076300A CN103778261A CN 103778261 A CN103778261 A CN 103778261A CN 201410076300 A CN201410076300 A CN 201410076300A CN 103778261 A CN103778261 A CN 103778261A
- Authority
- CN
- China
- Prior art keywords
- scenery
- scene image
- image
- guide information
- eigenwert
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Abstract
The invention discloses a self-guided tour method based on mobile cloud computing image recognition. The method includes the steps of obtaining a scenery image; preprocessing the scenery image; computing characteristic values of the scenery image; matching the characteristic values of the scenery image with scenery characteristic values in a database and determining scenery ID corresponding to the scenery image for obtaining guide information of a scenery. The scenery image comprises scenery appearance, characteristic signs, plane labels or three-dimensional labels. The scenery tour guide information comprises audio tour guide information or image tour guide information. The self-guided tour method based on mobile cloud computing image recognition has the advantages of being intelligent, easy to operate, simple in equipment, low in investment, low in energy consumption, and accurate and reliable in scenery positioning.
Description
Technical field
The present invention relates to mobile Internet and cloud computing technology field, particularly a kind of method and system of utilizing above-mentioned technology to realize self-help guide function.
Background technology
Along with the development of economic society and improving constantly of living standards of the people, tourism becomes people and loosens after work one of mode that body and mind takes exercises.During to scenic spot, visitor tends to use papery guide data to read and obtain sight spot information.Flourish along with tourist industry, the demand of the information to scenic spot, sight spot and scenery is increasing, and traditional paper material cannot meet the demand of real-time, and the information amount that can provide is also less.
Along with the develop rapidly of the rapidly universal and technology of smart mobile phone and panel computer, the difficulty of obtaining information reduces gradually, and the intelligent terminals that various relevant tourisms are conducted a sightseeing tour also arise at the historic moment, but the product of rarely seen widely popularization and application.
Some guide system equipment needed therebies are too complicated, also need to be specifically designed to RFID equipment, bluetooth equipment, the WIFI equipment that locate position at scenic spot and indoor laying, simultaneously: rent for visitor but also will prepare a collection of special multimedia guide's machine temporarily, drop into too large or too complexity of scheme, to such an extent as to it is larger to implement difficulty, and if utilize visitor's mobile phone, visitor's mobile phone also needs to possess the even sensor device such as gyroscope of GPS function, bluetooth.And aspect positioning precision, the more difficult demand that meets intelligent guide of GPS, location misplaces and sends wrong sight spot information is its drawbacks common.Particularly, the shortcoming of prior art mainly comprises:
1, support equipment complexity, invests hugely, and no matter troublesome maintenance, be RFID equipment, bluetooth equipment, the WIFI equipment of laying for location, position, and the modes such as special multimedia guide's machine are provided, and laying equipment is all great engineerings;
2, high to the requirement of universal intelligent terminal configuration, there is precision problem and the bad location that is difficult to of indoor signal in GPS location;
3, RFID mode cannot be general, is not also suitable for universal intelligent terminal;
4, GPS, bluetooth label, WIFI tag location mode are because need all the time in opening, so very power consumption;
5, GPS, bluetooth, RFID can only locate the place that visitor is in, cannot locate and obtain corresponding tour guide information for distant scenery, therefore obtaining corresponding scenery tour guide information by this kind of location technology needs user personally to arrive relevant position, in the time also not arriving scenery or user user and be not confirmed whether to wish to go to the visit of this scenery, this scheme is obviously infeasible;
6, adopt the scenery locator meamss such as bluetooth equipment, RFID equipment, wifi equipment or GPS, for example, cannot distinguish for the very near scenery (showpiece in museum) of distance.
Summary of the invention
Goal of the invention of the present invention is to provide that a kind of equipment is simple, widely applicable, easy to use, low power consumption and low cost have self-help tour-guiding method and the system thereof of high precision advantage.
For achieving the above object, the technical solution adopted in the present invention is:
Based on a self-help tour-guiding method for mobile cloud computing image recognition, comprise step:
Acquisition for mobile terminal scene image;
Search and determine the scenery that described scene image is corresponding;
Mobile terminal is shown the tour guide information of the scenery that scene image is corresponding.
Further, in the described self-help tour-guiding method based on mobile cloud computing image recognition, described in search and determine that the scenery that described scene image is corresponding specifically comprises the following steps:
Calculate the eigenwert of described scene image;
The eigenwert of existing scenery in the eigenwert of scene image and database is compared, determine the corresponding scenery ID of scene image.
Further, in the described self-help tour-guiding method based on mobile cloud computing image recognition, after acquisition for mobile terminal scene image, mobile terminal is uploaded onto the server the scene image getting by wireless network, and whois lookup is also determined scenery corresponding to described scene image;
Server is sent to mobile terminal by tour guide information corresponding scenery by wireless network;
Mobile terminal obtains described tour guide information by wireless network.
Further, in the described self-help tour-guiding method based on mobile cloud computing image recognition, described in search and determine that the scenery that described scene image is corresponding specifically comprises the following steps:
Mobile terminal calculates the eigenwert of described scene image;
Mobile terminal is compared the eigenwert of existing scenery in the eigenwert of scene image and mobile terminal data storehouse, and the ID of the corresponding scenery of definite scene image; Or mobile terminal uploads onto the server the eigenwert of scene image by wireless network, server is compared the eigenwert of existing scenery in the eigenwert of scene image and server database, and the ID of the corresponding scenery of definite scene image.
Further, in the described self-help tour-guiding method based on mobile cloud computing image recognition, described scene image can be static picture, can be also dynamic image.Described scene image comprises scenery appearance images, characteristic indication image, planar tags image or three-dimensional tag image; Described scenery tour guide information comprises text tour guide information, audio frequency tour guide information, video tour guide information or image tour guide information.
Further, in the described self-help tour-guiding method based on mobile cloud computing image recognition, search and scenery that definite scene image is corresponding before also comprise step: scene image is carried out to pre-service, obtains scene image pretreatment information; Described pre-service comprises classification, compression, extracts signature identification or character recognition; Described classification is specially: in default scenery classification, determine the classification of the scenery that scene image is corresponding; And in corresponding scenery category database, search and determine the scenery that described scene image is corresponding;
Describedly search and determine that the scenery that described scene image is corresponding specifically comprises step: utilize scene image pretreatment information to search and determine the scenery that described scene image is corresponding, or utilize scene image pretreatment information to search in conjunction with the eigenwert of scene image and determine the scenery that described scene image is corresponding.
Further, in the described self-help tour-guiding method based on mobile cloud computing image recognition, described search and the corresponding scenery of definite scene image also comprises step: send and confirm request or select request to user in the time finding the one or more scenery corresponding with scene image, and determine the corresponding scenery of scene image information according to the confirmation from user or selection information.
Based on a self-help guide system for mobile cloud computing image recognition, comprise mobile terminal and server;
Mobile terminal comprises the first processing unit and image acquisition unit, and the first processing unit calls image acquisition unit for obtaining scene image;
Mobile terminal or whois lookup are also determined scenery corresponding to described scene image;
Mobile terminal also comprises display driver unit and display unit or plays driver element and broadcast unit, the first processing unit calls display driver unit controls display unit and shows the tour guide information of corresponding scenery, and calls and play driver element and play the tour guide information of corresponding scenery in order to control broadcast unit.
Further, in the described self-help guide system based on mobile cloud computing image recognition, mobile terminal comprises the first storage unit and the first communication unit;
Server comprises the second storage unit, the second processing unit and the second communication unit;
The first storage unit or the second storage unit are used for storing scene features value and scenery tour guide information.
The first processing unit calculates the eigenwert of described scene image, the eigenwert of scene image is compared with the eigenwert of existing scenery in the first storage unit and determine the ID of the scenery that scene image is corresponding; The first processing unit calls the first communication unit and obtains the tour guide information of described scenery or transfer the tour guide information of described scenery from the first storage unit from server; Or
The first processing unit calls the first communication unit scene image is sent to server, the second processing unit calculates the eigenwert of described scene image, the eigenwert of scene image is mated with the eigenwert of existing scenery in the second storage unit and the ID of the scenery that definite scene image is corresponding; The first processing unit calls the first communication unit and obtains the tour guide information of described scenery or transfer the tour guide information of described scenery from the first storage unit from server; Or
The first processing unit calculates the eigenwert of described scene image, and calls the first communication unit the eigenwert of described scene image is sent to server; The second processing unit mates the eigenwert of scene image and the ID of the scenery that definite scene image is corresponding with the eigenwert of existing scenery in the first storage unit; The first processing unit calls the first communication unit and obtains the tour guide information of described scenery or transfer the tour guide information of described scenery from the first storage unit from server;
Described scene image comprises scenery appearance images, characteristic indication image, planar tags image or three-dimensional tag image;
Described scenery tour guide information comprises text tour guide information, audio frequency tour guide information, video tour guide information or image tour guide information.
Further, in the described self-help guide system based on mobile cloud computing image recognition, the first processing unit or the second processing unit are also for carrying out pre-service and obtaining pretreatment information to scene image; The first processing unit comprises sort module, compression module, signature identification extraction module or character recognition module;
Sort module is for determining the classification of the scenery that scene image is corresponding and searching in corresponding scenery category database and determine the scenery that described scene image is corresponding in default scenery classification; Search and determine that scenery that described scene image is corresponding specifically comprises and utilize scene image pretreatment information to search and determine the scenery that described scene image is corresponding, or utilize scene image pretreatment information to search in conjunction with the eigenwert of scene image and determine the scenery that described scene image is corresponding;
Compression module is for compressing pre-service to scene image;
Signature identification extraction module is for extracting signature identification from scene image;
Character recognition module is for carrying out character recognition pre-service to scene image;
In the time that the second processing unit matches scenery corresponding to one or more and described scene image, call the second communication unit and send and confirm request or select request to the first communication unit; When the first communication unit receives the confirmation request or selects request, the first processing unit calls display driver unit controls display unit and shows confirmation request or select request, and obtains user's confirmation or the ID of selection information definite described scenery; Or
In the time that the first processing unit finds scenery corresponding to one or more and described scene image, call display driver unit controls display unit and show and confirm request or select request, obtain user's confirmation or selection information and determine the ID of described scenery.
When using, the present invention makes full use of the image-acquisition functions of existing mobile terminal, utilize the computing power of mobile terminal itself maybe the image getting to be uploaded onto the server by wireless network, utilize the powerful arithmetic capability of server, find the scenery of coupling, and take full advantage of the feature of server stores magnanimity scene information, the tour guide information of this scenery is sent to mobile terminal for user's reference.Take technique scheme beneficial effect to be afterwards: the self-help tour-guiding method based on mobile cloud computing image recognition is easy to operate, equipment is simple, drop into low, energy consumption is little, scenery registration is reliable, do not need actual this scenery place that is in of user can easily obtain corresponding tour guide information, be convenient to user's reference to be confirmed whether to go to the value of visit simultaneously.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of a kind of self-help tour-guiding method based on mobile cloud computing image recognition in an embodiment of the present invention;
Fig. 2 is the high-level schematic functional block diagram of a kind of self-help guide system based on mobile cloud computing image recognition in another embodiment of the present invention.
Label declaration:
1-mobile terminal
2-server
11-the first processing unit
12-image acquisition unit
13-the first communication unit
14-display driver unit
15-display unit
16-plays driver element
17-broadcast unit
18-the first storage unit
21-the second processing unit
22-the second communication unit
23-the second storage unit
110-characteristic value calculating module
111-compression module
112-character recognition module
113-signature identification extraction module
114-sort module
Embodiment
By describing technology contents of the present invention, structural attitude in detail, being realized object and effect, below in conjunction with embodiment and coordinate accompanying drawing to be explained in detail.
Referring to Fig. 1, is the process flow diagram of a kind of self-help tour-guiding method based on mobile cloud computing image recognition in an embodiment of the present invention.
The described self-help tour-guiding method based on mobile cloud computing image recognition comprises step:
Step S10, obtain scene image.Scenery in the present embodiment can be natural views, can be also historical place, can be modern city sight spot, can also be history relic etc.The content of scene image can be the overall picture of above-mentioned scenery, can be also the part of scenery.Described scene image can be static picture, can be also dynamic image.
In step S10, be mainly that the scenery that its hope is obtained to tour guide information by user uses the first-class photographing device of shooting to take pictures to obtaining of scene image, image acquisition equipment carries out Image Acquisition.Device and the function of the Image Acquisition such as such as existing mobile terminal is taken pictures as the equipment such as mobile phone, flat board, intelligent watch, intelligent glasses all have, video, user can use these acquisition for mobile terminal images very like a cork.The object of taking pictures particularly, can be the object that outward appearance, signature identification, planar tags or the three-dimensional tag etc. of scenery can show this scene features from photo.For example,, when user is distant with mountain peak but while wanting to learn the tour guide information such as title, relevant legend on this mountain peak, can take pictures to the profile on mountain peak a long way off; In the time standing in the tour guide information of wanting to understand this waterfall before a waterfall, can take pictures to waterfall; Have certain distance before a statue or apart from it time, can take pictures to statue.In addition, can be thering is holding plane label or three-dimensional tag before the scenery that tour guide information and information introduction be worth, planar tags can comprise that Quick Response Code etc. has the image information of identification, for example, in botanical garden, between different plants, potential range is very near, the methods such as the GPS location in conventional solution are difficult to them to make a distinction, but just can be by the label that hangs on each plant or put before each plant to be confirmed to user wants the concrete plant of selecting and learning tour guide information in present embodiment, such location is enough accurately and not can make mistakes.
Step S11, scene image is carried out to pre-service, obtain pretreatment information.
In step S11, the pretreatment operation that scene image is carried out can comprise: classification, compression, signature identification extract or character recognition.Compression is processed and is mainly used for or crossing wireless network and send to server and carry out the occasion of further identifying processing through the scene image information exchange of other pre-service gained by scene image, the object that compression is processed is to reduce the data volume of required transmission, reduces required time and the resource of communication.Compression is processed the real needs in can be as the case may be and is determined the mode etc. of compression ratio, lossy compression method or Lossless Compression.After the information after compression is sent to server, server also will have a reverse decompression operation, namely by the information recovery to after compression the process reused.
The means of character recognition comprise optical character identification (OCR) technology, are to determine its shape by the shade pattern of the character in detected image, then obtain the process of Word message with character identifying method.Carrying out before character recognition, can take as the case may be different pre-service measures as binaryzation, noise remove, slant correction etc.Character recognition applicable situation is in the present embodiment the situation that comprises word in photo, for example architecturally have label or word, sight spot has on sight spot name, some mountain stone has famous expert to autograph etc., these will be all to identification scenery very effective information, and the character that also may identify gained according to OCR can directly match the scenery that scene image is corresponding.
Classification pre-service refers to the classification of determining the scenery that scene image is corresponding in default scenery classification; And in corresponding scenery category database, search and determine the scenery that described scene image is corresponding.
According to different mode classifications, scenery can be divided into: natural scene, artificial scenery; Also can be divided into mountains and rivers, river, lake, building etc.; Building aspect can also be further subdivided into Chinese style building, Western Buildings or ancient architecture, modern architecture etc.Present embodiment, by the image of identification is carried out to Classification and Identification in advance, is divided into scenery in corresponding scenery classification, to dwindle the data area of whois lookup, coupling, saves server resource, improves search efficiency, and can effectively improve and search success ratio.Present embodiment can also be attached to the Eigenvalue Extraction in pre-treatment step, OCR technology etc. in above-mentioned embodiment, utilizes the image feature value or the character that extract to classify to scenery corresponding to image.
Signature identification extraction pre-service refers to recognizes and extracts the information with signature identification effect from described scene image.Because all there is its characteristic mark at a lot of famous sight spots, certain graphical symbol of for example outer wall, mark, the tips of certain shape of building etc., can be used as signature identification to some figure to be extracted, then for comparison with confirm this scenery.
In certain embodiments, can directly utilize pretreatment information that pre-treatment step obtains to search and determine the scenery that described scene image is corresponding, in other embodiment, precision and the speed of mating with scenery in order to improve image, can utilize scene image pretreatment information to search in conjunction with the eigenwert of scene image and determine the scenery that described scene image is corresponding.For example can dwindle by classification the comparison scope of eigenwert, multiple the approaching in result of comparing or comparing out again, utilize pretreatment information to get rid of some option.
In other embodiments, the pretreatment operation described in step S11 can be omitted, and directly user is taken to gained scene image carries out the computing of next step.
Step S12, calculate the eigenwert of described scene image.
The eigenwert of scene image is calculated the extraction operation that can be considered as image feature information, specifically can comprise the image feature informations such as color histogram, grey level histogram, edge, skeleton, connected domain number, rectangular degree.For example, for the object of present embodiment, extracting in eigenwert process through the image outline of Fourier transform gained or border will be very useful in the time that the information in follow-up and database is compared.
Step S13, the eigenwert of scene image is mated with the eigenwert of existing scenery in database;
Step S14, in the time matching the one or more scenery corresponding with scene image, send and confirm request or select request to user, and determine the ID of the corresponding scenery of scene image according to the confirmation from user or selection information.The ID of scenery can be the title of scenery, can be also the numbering of scenery in database, can also be the code name etc. of scenery, in a word the ID of scenery can for uniqueness determine this scenery and confirm the corresponding relation of scenery and other data.
The technical program can improve the accuracy of tour guide information adaptation.For example, in the time finding the scenery matching with scene image, send and confirm request to user, and obtaining after user's confirmation, determining the corresponding scenery of scene image.In the time finding multinomial and scenery that scene image matches, send and select request to user, and determine the corresponding scenery of scene image after obtaining user the correct scenery in multinomial scenery is done to selection information.
In other embodiments, if only find the scenery matching with scene image, also can directly send scenery tour guide information to user without user confirms.
Step S15, obtain scenery tour guide information by wireless network.
In embodiment, after determining the ID of the corresponding scenery of scene image, obtain the tour guide information of described scenery by wireless networks such as WLAN, GSM, LTE, 3G, 4G.Certainly,, along with the development of technology, other are any can be applicable to present embodiment too for the technical scheme of wireless telecommunications.Scenery tour guide information can comprise text tour guide information, audio frequency tour guide information, video tour guide information or image tour guide information.After receiving scenery tour guide information, user can select to play or reading according to the demand of oneself.In other embodiments, likely the tour guide information of the scenery in this scenic spot is got on mobile terminal in advance, so after having determined the ID of the corresponding scenery of scene image, can browse or play the tour guide information of this scenery by calling the database of mobile terminal.
Referring to Fig. 2, is the high-level schematic functional block diagram of the self-help guide system based on mobile cloud computing image recognition described in another embodiment of the present invention.
The described self-help guide system based on mobile cloud computing image recognition comprises mobile terminal 1 and server 2; Mobile terminal 1 comprises the first processing unit 11, image acquisition unit 12, the first storage unit 18 and the first communication unit 13.The first processing unit 11 comprises characteristic value calculating module 110, compression module 111, character recognition module 112, signature identification extraction module 113 and sort module 114;
Server 2 comprises the second storage unit 23, the second processing unit 21 and the second communication unit 22.
Image acquisition unit 12 is for obtaining scene image; Described scene image comprises scenery outward appearance, signature identification, planar tags or three-dimensional tag.
Then the scene image that the first communication unit 13 obtains image acquisition unit 12 by wireless network is sent to server 2; Then the second processing unit 21 calculates the eigenwert of described scene image and compares and mate with the numerous scene image eigenwerts in the second storage unit 23.The occasion that need to save Internet resources and time cost at some, is sending scene image to before server 2, and the first processing unit 11 or the second processing unit are also for carrying out pre-service and obtaining pretreatment information to scene image; Compression module 111 can carry out squeeze operation to scene image in advance, then information is after compression sent to server 2.Character recognition module 112 carries out character recognition operation to scene image in advance, and the in the situation that of obviously having there is scenery title word on scene image, this can determine scenery the most quickly and easily; Signature identification extraction module 113 is for extracting characteristic information scenery to mark meaning from scene image; Sort module 114 is for determining the classification of the scenery that scene image is corresponding and searching in corresponding scenery category database and determine the scenery that described scene image is corresponding in default scenery classification; Search and determine that scenery that described scene image is corresponding specifically comprises and utilize scene image pretreatment information to search and determine the scenery that described scene image is corresponding, or utilize scene image pretreatment information to search in conjunction with the eigenwert of scene image and determine the scenery that described scene image is corresponding;
In the time that the second processing unit 21 matches scenery corresponding to one or more and described scene image according to the eigenwert of image scene, the second processing unit 21 calls the second communication unit 22 and sends and confirm request or select request to mobile terminal 1; When mobile terminal 1 receives the confirmation request or selects request, the first processing unit 11 calls display driver unit 14 and controls display unit 15 demonstration confirmation requests or select request, and obtains user's confirmation or selection information; Then call the first communication unit 13 ID of confirmation or the determined scenery of selection information is sent to server 2.Finally, by the first communication unit 13, the second storage unit 23 from server 2 is obtained scenery tour guide information.
Because mobile terminal 1 itself generally also has certain calculating and storage capacity, so in some image recognition operands and scenery total amount little occasion, can directly complete by mobile terminal 1 computing that eigenwert is calculated, scenery is adaptive and definite, particularly, can carry out the calculating of eigenwert by characteristic value calculating module 110, then determined scenery ID is sent to server 2, then obtain the tour guide information of this scenery from server 2.And comparatively complicated at other images, identification operand is large or the very large occasion of scenery total amount, memory space and the arithmetic capability of mobile terminal 1 are limited, or operation efficiency is not high, can directly send to server 2 or after pre-service, pre-service gained information is being sent to server 2 obtaining scene image, completing scenery identification and adaptive work by the server 2 with powerful storage capacity and computing power.To these two kinds of different embodiments, can in the process of concrete application, select according to different demands.
Mobile terminal 1 obtains scenery tour guide information from server 2 and completes by wireless network.Described wireless network comprises wlan network, LTE network, GSM network, 3G network or 4G network.The second storage unit 23 in server 2 comprises database; Scene information and scenery tour guide information are all stored in database.After determining scenery, the second processing unit 21 is transferred the scenery tour guide information of this scenery from database, comprise text tour guide information, video tour guide information, audio frequency tour guide information or image tour guide information, and send it to mobile terminal 1 by the second communication unit 22.
In the described self-help guide system based on mobile cloud computing image recognition, mobile terminal 1 also comprises display driver unit 14 and display unit 15 or plays driver element 16 and broadcast unit 17;
After receiving scenery tour guide information, the first processing unit 11 calls display driver unit 14 and controls display unit 15 and show described text tour guide information, video tour guide information or image tour guide information; And the first processing unit 11 calls to be play driver element 16 and controls broadcast unit 17 and play described audio frequency tour guide information.
In another embodiment, server 2 or mobile terminal 1 are searched and are determined that the scenery that described scene image is corresponding also comprises step: scene image is carried out to Classification and Identification, in default scenery classification, determine the classification of the scenery that scene image is corresponding; And in the scenery category database that is stored in the first storage unit 18 or the second storage unit 23, search and determine the scenery that described scene image is corresponding.
When coupling and the work of determining the scenery corresponding with scene image are while being completed by the first processing unit 11, after the first processing unit 11 finds the one or more scenery corresponding with scene image, directly calling display driver unit 14 controls display unit 15 demonstration confirmation requests or selects request, and obtain user's confirmation or selection information, and by being sent to server 2 according to the ID of user's confirmation or the determined scenery of selection information by the first communication unit 13, obtain scenery tour guide information from server 2.
In another embodiment, mobile terminal 1 obtains in advance the packet of scenery tour guide information in this scenic spot and is stored in the lane database in the first storage unit 18.So after the first processing unit 11 or the second processing unit 21 have been determined the ID of scenery, browse or play as long as directly recall the tour guide information of this scenery from the own database of mobile terminal 1.
The foregoing is only embodiments of the invention; not thereby limit the scope of the claims of the present invention; every equivalent structure or conversion of equivalent flow process that utilizes instructions of the present invention and accompanying drawing content to do; or be directly or indirectly used in other relevant technical fields, be all in like manner included in scope of patent protection of the present invention.
Claims (10)
1. the self-help tour-guiding method based on mobile cloud computing image recognition, is characterized in that, comprises step:
Acquisition for mobile terminal scene image;
Search and determine the scenery that described scene image is corresponding;
Mobile terminal is shown the tour guide information of the scenery that scene image is corresponding.
2. the self-help tour-guiding method based on mobile cloud computing image recognition as claimed in claim 1, is characterized in that, described in search and determine that the scenery that described scene image is corresponding specifically comprises the following steps:
Calculate the eigenwert of described scene image;
The eigenwert of existing scenery in the eigenwert of scene image and database is compared, determine the ID of the corresponding scenery of scene image.
3. the self-help tour-guiding method based on mobile cloud computing image recognition as claimed in claim 1 or 2, is characterized in that,
After acquisition for mobile terminal scene image, mobile terminal is uploaded onto the server the scene image getting by wireless network, and whois lookup is also determined scenery corresponding to described scene image;
Server is sent to mobile terminal by tour guide information corresponding scenery by wireless network;
Mobile terminal obtains described tour guide information by wireless network.
4. the self-help tour-guiding method based on mobile cloud computing image recognition as claimed in claim 1 or 2, is characterized in that: described in search and determine that the scenery that described scene image is corresponding specifically comprises the following steps:
Mobile terminal calculates the eigenwert of described scene image;
Mobile terminal is compared the eigenwert of existing scenery in the eigenwert of scene image and mobile terminal data storehouse, and the ID of the corresponding scenery of definite scene image; Or mobile terminal uploads onto the server the eigenwert of scene image by wireless network, server is compared the eigenwert of existing scenery in the eigenwert of scene image and server database, and the ID of the corresponding scenery of definite scene image.
5. the self-help tour-guiding method based on mobile cloud computing image recognition as claimed in claim 1 or 2, it is characterized in that, described scene image can be static picture or dynamic image, and described scene image comprises scenery appearance images, characteristic indication image, planar tags image or three-dimensional tag image; Described scenery tour guide information comprises text tour guide information, audio frequency tour guide information, video tour guide information or image tour guide information.
6. the self-help tour-guiding method based on mobile cloud computing image recognition as claimed in claim 1 or 2, it is characterized in that, search and scenery that definite scene image is corresponding before also comprise step: scene image is carried out to pre-service, obtains scene image pretreatment information; Described pre-service comprises classification, compression, extracts signature identification or character recognition; Described classification is specially: in default scenery classification, determine the classification of the scenery that scene image is corresponding; And in corresponding scenery category database, search and determine the scenery that described scene image is corresponding;
Describedly search and determine that the scenery that described scene image is corresponding specifically comprises step: utilize scene image pretreatment information to search and determine the scenery that described scene image is corresponding, or utilize scene image pretreatment information to search in conjunction with the eigenwert of scene image and determine the scenery that described scene image is corresponding.
7. the self-help tour-guiding method based on mobile cloud computing image recognition as claimed in claim 1 or 2, it is characterized in that, described search and the corresponding scenery of definite scene image also comprises step: send and confirm request or select request to user in the time finding the one or more scenery corresponding with scene image, and determine the corresponding scenery of scene image information according to the confirmation from user or selection information.
8. the self-help guide system based on mobile cloud computing image recognition, is characterized in that, comprises mobile terminal and server;
Mobile terminal comprises the first processing unit and image acquisition unit, and the first processing unit calls image acquisition unit for obtaining scene image;
Mobile terminal or whois lookup are also determined scenery corresponding to described scene image;
Mobile terminal also comprises display driver unit and display unit or plays driver element and broadcast unit, the first processing unit calls display driver unit controls display unit and shows the tour guide information of corresponding scenery, and calls and play driver element and play the tour guide information of corresponding scenery in order to control broadcast unit.
9. the self-help guide system based on mobile cloud computing image recognition as claimed in claim 8, is characterized in that, mobile terminal comprises the first storage unit and the first communication unit;
Server comprises the second storage unit, the second processing unit and the second communication unit;
The first storage unit or the second storage unit are used for storing scene features value and scenery tour guide information.
The first processing unit calculates the eigenwert of described scene image, the eigenwert of scene image is compared with the eigenwert of existing scenery in the first storage unit and determine the ID of the scenery that scene image is corresponding; The first processing unit calls the first communication unit and obtains the tour guide information of described scenery or transfer the tour guide information of described scenery from the first storage unit from server; Or
The first processing unit calls the first communication unit scene image is sent to server, the second processing unit calculates the eigenwert of described scene image, the eigenwert of scene image is mated with the eigenwert of existing scenery in the second storage unit and the ID of the scenery that definite scene image is corresponding; The first processing unit calls the first communication unit and obtains the tour guide information of described scenery or transfer the tour guide information of described scenery from the first storage unit from server; Or
The first processing unit calculates the eigenwert of described scene image, and calls the first communication unit the eigenwert of described scene image is sent to server; The second processing unit mates the eigenwert of scene image and the ID of the scenery that definite scene image is corresponding with the eigenwert of existing scenery in the first storage unit; The first processing unit calls the first communication unit and obtains the tour guide information of described scenery or transfer the tour guide information of described scenery from the first storage unit from server;
Described scene image comprises scenery appearance images, characteristic indication image, planar tags image or three-dimensional tag image;
Described scenery tour guide information comprises text tour guide information, audio frequency tour guide information, video tour guide information or image tour guide information.
10. the self-help guide system based on mobile cloud computing image recognition as claimed in claim 8 or 9, is characterized in that, the first processing unit or the second processing unit are also for carrying out pre-service and obtaining pretreatment information to scene image; The first processing unit comprises characteristic value calculating module, sort module, compression module, signature identification extraction module or character recognition module;
Described characteristic value calculating module is for computed image eigenwert, and sort module is for determining the classification of the scenery that scene image is corresponding in default scenery classification and searching in corresponding scenery category database and determine the scenery that described scene image is corresponding; Search and determine that scenery that described scene image is corresponding specifically comprises and utilize scene image pretreatment information to search and determine the scenery that described scene image is corresponding, or utilize scene image pretreatment information to search in conjunction with the eigenwert of scene image and determine the scenery that described scene image is corresponding;
Compression module is for compressing pre-service to scene image;
Signature identification extraction module is for extracting signature identification from scene image;
Character recognition module is for carrying out character recognition pre-service to scene image;
In the time that the second processing unit matches scenery corresponding to one or more and described scene image, call the second communication unit and send and confirm request or select request to the first communication unit; When the first communication unit receives the confirmation request or selects request, the first processing unit calls display driver unit controls display unit and shows confirmation request or select request, and obtains user's confirmation or the ID of selection information definite described scenery; Or
In the time that the first processing unit finds scenery corresponding to one or more and described scene image, call display driver unit controls display unit and show and confirm request or select request, obtain user's confirmation or selection information and determine the ID of described scenery.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410076300.8A CN103778261A (en) | 2014-03-04 | 2014-03-04 | Self-guided tour method based on mobile cloud computing image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410076300.8A CN103778261A (en) | 2014-03-04 | 2014-03-04 | Self-guided tour method based on mobile cloud computing image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103778261A true CN103778261A (en) | 2014-05-07 |
Family
ID=50570496
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410076300.8A Pending CN103778261A (en) | 2014-03-04 | 2014-03-04 | Self-guided tour method based on mobile cloud computing image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103778261A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504155A (en) * | 2015-01-15 | 2015-04-08 | 刘畅 | Data acquisition method and system based on image search |
| CN105279256A (en) * | 2015-10-15 | 2016-01-27 | 梁穆典 | Inquiry method combining geographic information and images and inquiry system combining geographic information and images |
| WO2016059530A1 (en) * | 2014-10-15 | 2016-04-21 | 在地实验文化事业有限公司 | Guiding system and method |
| CN105825568A (en) * | 2016-03-16 | 2016-08-03 | 广东威创视讯科技股份有限公司 | Portable intelligent interactive equipment |
| CN106021426A (en) * | 2016-05-16 | 2016-10-12 | 乐视控股（北京）有限公司 | Mobile terminal image recognition-based key matching method and device |
| CN106529375A (en) * | 2015-09-11 | 2017-03-22 | 上海乐今通信技术有限公司 | Mobile terminal and object feature identification method for image of mobile terminal |
| CN107045515A (en) * | 2016-08-29 | 2017-08-15 | 旗众科技有限公司 | A kind of information processing platform based on cloud computing |
| CN107066635A (en) * | 2017-06-27 | 2017-08-18 | 徐桐 | A kind of method and system of the architecture information guide to visitors recognized based on image comparison |
| CN107203638A (en) * | 2017-06-08 | 2017-09-26 | 北京深瞐科技有限公司 | Monitor video processing method, apparatus and system |
| CN108509621A (en) * | 2018-04-03 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | Sight spot recognition methods, device, server and the storage medium of scenic spot panorama sketch |
| CN109166057A (en) * | 2018-09-12 | 2019-01-08 | 厦门盈趣科技股份有限公司 | A kind of scenic spot guidance method and device |
| CN109325482A (en) * | 2018-09-29 | 2019-02-12 | 北京极致盘点科技有限公司 | Fixed assets checking method and device based on image recognition |
| CN109492121A (en) * | 2018-09-30 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Method, apparatus, server and the storage medium of intelligent recognition picture |
| CN110010043A (en) * | 2019-04-17 | 2019-07-12 | 镇江真慧玩网络科技有限公司 | A kind of intelligent guide system based on AI and geographical location matching technique |
| CN110060611A (en) * | 2019-03-15 | 2019-07-26 | 深圳壹账通智能科技有限公司 | Intelligent interaction guidance method, device and storage medium, server |
| CN110110823A (en) * | 2019-04-25 | 2019-08-09 | 浙江工业大学之江学院 | Object based on RFID and image recognition assists in identifying system and method |
| CN111462663A (en) * | 2020-06-19 | 2020-07-28 | 南京新研协同定位导航研究院有限公司 | Tour guide mode based on MR glasses |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070208749A1 (en) * | 2006-02-24 | 2007-09-06 | Chris Price | Location-relevant real-time multimedia delivery and control and editing systems and methods |
| CN101567159A (en) * | 2009-06-10 | 2009-10-28 | 北京豪仪测控工程有限公司 | Navigation method based on image identification technology and navigation apparatus |
| CN102063436A (en) * | 2009-11-18 | 2011-05-18 | 腾讯科技（深圳）有限公司 | System and method for realizing merchandise information searching by using terminal to acquire images |
| CN103294804A (en) * | 2013-05-30 | 2013-09-11 | 佛山电视台南海分台 | Method and system for augmenting acquisition and interaction of scenic resort information |
-
2014
- 2014-03-04 CN CN201410076300.8A patent/CN103778261A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070208749A1 (en) * | 2006-02-24 | 2007-09-06 | Chris Price | Location-relevant real-time multimedia delivery and control and editing systems and methods |
| CN101567159A (en) * | 2009-06-10 | 2009-10-28 | 北京豪仪测控工程有限公司 | Navigation method based on image identification technology and navigation apparatus |
| CN102063436A (en) * | 2009-11-18 | 2011-05-18 | 腾讯科技（深圳）有限公司 | System and method for realizing merchandise information searching by using terminal to acquire images |
| CN103294804A (en) * | 2013-05-30 | 2013-09-11 | 佛山电视台南海分台 | Method and system for augmenting acquisition and interaction of scenic resort information |
Cited By (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016059530A1 (en) * | 2014-10-15 | 2016-04-21 | 在地实验文化事业有限公司 | Guiding system and method |
| CN104504155B (en) * | 2015-01-15 | 2018-06-08 | 刘畅 | A kind of data capture method and system based on picture search |
| CN104504155A (en) * | 2015-01-15 | 2015-04-08 | 刘畅 | Data acquisition method and system based on image search |
| CN106529375A (en) * | 2015-09-11 | 2017-03-22 | 上海乐今通信技术有限公司 | Mobile terminal and object feature identification method for image of mobile terminal |
| CN105279256A (en) * | 2015-10-15 | 2016-01-27 | 梁穆典 | Inquiry method combining geographic information and images and inquiry system combining geographic information and images |
| CN105825568A (en) * | 2016-03-16 | 2016-08-03 | 广东威创视讯科技股份有限公司 | Portable intelligent interactive equipment |
| CN106021426A (en) * | 2016-05-16 | 2016-10-12 | 乐视控股（北京）有限公司 | Mobile terminal image recognition-based key matching method and device |
| CN107045515A (en) * | 2016-08-29 | 2017-08-15 | 旗众科技有限公司 | A kind of information processing platform based on cloud computing |
| CN107203638B (en) * | 2017-06-08 | 2020-09-25 | 北京深瞐科技有限公司 | Monitoring video processing method, device and system |
| CN107203638A (en) * | 2017-06-08 | 2017-09-26 | 北京深瞐科技有限公司 | Monitor video processing method, apparatus and system |
| CN107066635A (en) * | 2017-06-27 | 2017-08-18 | 徐桐 | A kind of method and system of the architecture information guide to visitors recognized based on image comparison |
| CN108509621A (en) * | 2018-04-03 | 2018-09-07 | 百度在线网络技术（北京）有限公司 | Sight spot recognition methods, device, server and the storage medium of scenic spot panorama sketch |
| CN108509621B (en) * | 2018-04-03 | 2021-05-18 | 百度在线网络技术（北京）有限公司 | Scenic spot identification method, device, server and storage medium for scenic spot panoramic image |
| CN109166057B (en) * | 2018-09-12 | 2020-05-26 | 厦门盈趣科技股份有限公司 | Scenic spot tour guide method and device |
| CN109166057A (en) * | 2018-09-12 | 2019-01-08 | 厦门盈趣科技股份有限公司 | A kind of scenic spot guidance method and device |
| CN109325482A (en) * | 2018-09-29 | 2019-02-12 | 北京极致盘点科技有限公司 | Fixed assets checking method and device based on image recognition |
| CN109492121A (en) * | 2018-09-30 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Method, apparatus, server and the storage medium of intelligent recognition picture |
| CN110060611A (en) * | 2019-03-15 | 2019-07-26 | 深圳壹账通智能科技有限公司 | Intelligent interaction guidance method, device and storage medium, server |
| CN110010043A (en) * | 2019-04-17 | 2019-07-12 | 镇江真慧玩网络科技有限公司 | A kind of intelligent guide system based on AI and geographical location matching technique |
| CN110110823A (en) * | 2019-04-25 | 2019-08-09 | 浙江工业大学之江学院 | Object based on RFID and image recognition assists in identifying system and method |
| CN111462663A (en) * | 2020-06-19 | 2020-07-28 | 南京新研协同定位导航研究院有限公司 | Tour guide mode based on MR glasses |
| CN111462663B (en) * | 2020-06-19 | 2020-10-27 | 南京新研协同定位导航研究院有限公司 | Tour guide method based on MR glasses |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103778261A (en) | Self-guided tour method based on mobile cloud computing image recognition | |
| US8965112B1 (en) | Sequence transcription with deep neural networks | |
| CN103617422B (en) | A social relation management method based on business card recognition | |
| CN103632626A (en) | Intelligent tour guide realizing method and intelligent tour guide device based on mobile network and mobile client | |
| US9436886B2 (en) | System and method of determining building numbers | |
| US20100135527A1 (en) | Image recognition algorithm, method of identifying a target image using same, and method of selecting data for transmission to a portable electronic device | |
| CN102147815A (en) | Method and system for searching images | |
| CN103995889A (en) | Method and device for classifying pictures | |
| CN103597500A (en) | System and method for recognizing text information in object | |
| CN102214222B (en) | Presorting and interacting system and method for acquiring scene information through mobile phone | |
| WO2018121006A1 (en) | Method and device for license plate positioning | |
| CN104936283A (en) | Indoor positioning method, server and system | |
| CN106326454A (en) | Image identification method | |
| JP2012203668A (en) | Information processing device, object recognition method, program and terminal device | |
| CN103335657A (en) | Method and system for strengthening navigation performance based on image capture and recognition technology | |
| US10963719B1 (en) | Optimized vehicle license plate recognition | |
| CN105824928A (en) | Mobile terminal, server, content-based image recognition searching method and system | |
| WO2014032419A1 (en) | Method and system for obtaining consultation information based on picture | |
| CN106203406A (en) | A kind of identification system based on cloud computing | |
| CN109753901B (en) | Indoor pedestrian tracing method and device based on pedestrian recognition, computer equipment and storage medium | |
| CN111323024A (en) | Positioning method and device, equipment and storage medium | |
| CN107403217A (en) | A kind of label aids in random frame identifying system | |
| CN104977011A (en) | Positioning method and positioning device based on street-photographing image in electronic map | |
| CN111383271B (en) | Picture-based direction marking method and device | |
| CN107045515A (en) | A kind of information processing platform based on cloud computing |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C53 | Correction of patent of invention or patent application | ||
| CB02 | Change of applicant information |
Address after: 350000, four floor, 258 key building, No. 54, Gulou Road, Gulou District, Fujian, Fuzhou Applicant after: FUJIAN RUIVEN INFORMATION TECHNOLOGY CO., LTD. Address before: 350000, four floor, 258 key building, No. 54, Gulou Road, Gulou District, Fujian, Fuzhou Applicant before: Fujian Ruitel Information & Technology Co., Ltd. |
|
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140507 |
|
| RJ01 | Rejection of invention patent application after publication |