CN105184276B - Parts Recognition method during intelligent glasses maintenance - Google Patents
Parts Recognition method during intelligent glasses maintenance Download PDFInfo
- Publication number
- CN105184276B CN105184276B CN201510628119.8A CN201510628119A CN105184276B CN 105184276 B CN105184276 B CN 105184276B CN 201510628119 A CN201510628119 A CN 201510628119A CN 105184276 B CN105184276 B CN 105184276B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- maintenance
- intelligent glasses
- database
- straight panel
- 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.)
- Active
Links
- 238000012423 maintenance Methods 0.000 title claims abstract description 106
- 239000011521 glass Substances 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000005452 bending Methods 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 6
- 230000015556 catabolic process Effects 0.000 claims description 3
- 238000009434 installation Methods 0.000 claims description 3
- 238000011017 operating method Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 2
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 2
- 230000008439 repair process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 210000003128 head Anatomy 0.000 description 3
- 238000012797 qualification Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000000465 moulding Methods 0.000 description 1
- 235000021110 pickles Nutrition 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000035922 thirst Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/017—Head mounted
- G02B27/0176—Head mounted characterised by mechanical features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/02—Electrically-operated educational appliances with visual presentation of the material to be studied, e.g. using film strip
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/017—Head mounted
- G02B2027/0178—Eyeglass type
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Optics & Photonics (AREA)
- Business, Economics & Management (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Processing Or Creating Images (AREA)
Abstract
Parts Recognition method during intelligent glasses maintenance, the invention belongs to automobile maintenance fields, and to solve in the prior art, the acquisition of intelligent glasses data and the bad technical problem in touch control operation position, technical essential are:There are one convolution bendings for temple tool, the side of convolution bending connects the first straight panel, first straight panel is provided with towards the Trackpad on the outside of temple, the other side of convolution bending connects the second straight panel, the upper and lower both sides of second straight panel have the bottom plate stretched out, the holding part of camera is formed with the second straight panel, second straight panel is equipped with camera mounting hole, described two bottom plates are connect with ray machine, and the ray machine is located at the front with its more similar lens frame, lens frame is connected to the first straight panel and is set to convolution bending more nearby, and the first straight panel and the second straight panel are substantially vertical.Effect is:So that the acquisition of intelligent glasses data is preferable with touch control operation position.
Description
Technical field
The invention belongs to a kind of Parts Recognition methods during automobile maintenance field more particularly to intelligent glasses maintenance.
Background technology
Domestic car owner is also to rely on the shops 4s mostly when automobile goes wrong or needs maintenance.But the shops 4S
There are two apparent drawbacks, costly and time consuming.
When people, which have to take the second best, selects numberless informal repair shop, although convenient and cheap,
Expect that the love vehicle of oneself, which is handed those, does not have the mechanic of formal qualification, is tantamount to not practise medicine handing body
The doctor of qualification when sending child to the teacher there of the not system of qualifying for teachers, and hangs back a little.
Also some manipulative abilities have a mind to do-it-yourself car owner, due to by the study of profession, not setting about always
Some are not self-confident, and then lose interest.Certainly also there is other car owner, be not expert to auto repair, it is also not interested.But
A storm may arise from a clear sky, and driving is away from home, and can inevitably meet some emergency situations, for example blow out, leak, oil leak etc..Oneself
It repaiies, and has no way of doing it;Deng rescue, and Distant water cannot quench present thirst.
Based on above various pickles, the intelligent glasses applied to automobile maintenance field come into being.
Invention content
The present invention proposes a kind of Parts Recognition method during intelligent glasses maintenance, it is therefore an objective to pass through intelligent glasses pair
Auto parts carry out Image Acquisition, are then identified so that recognition result can accurately show the title of the part, type
Number, the information such as price facilitate Automobile Service worker to carry out selection reference to it.
To achieve the goals above, the technical solution adopted by the present invention is:Parts Recognition during intelligent glasses maintenance
Method includes the following steps:
S1:First to existing part structure offline feature library, to support the part acquired with follow-up intelligent glasses
Information carries out characteristic matching, and this feature inventory is stored in server database module;
S2:Intelligent glasses pattern is adjusted to recognition mode, by the front camera on intelligent glasses, to be identified zero
Part carries out multi-angled shooting, and shooting image must have lap, captured picture is reached server by communication module
Three-dimensional reconstruction is carried out, spatial context feature is extracted;
S3:The spatial context feature of extraction is compared with the part feature in offline feature library, is calculated using LAPJV
Method carries out Optimum Matching operation to eigenmatrix, keeps cost value minimum;
S4:The auto parts corresponding to Least-cost value are chosen in offline feature database as currently to be detected zero
The most matched part of part;
S5:Server sends the information such as the title, model, price of matched part to intelligent glasses, control module control
Imaged output module carries out the displaying of parts information;
The intelligent glasses include spectacle-frame (2) and temple (1), it is characterised in that:There are one one of temple (1) tools
The side of convolution bending (3), convolution bending (3) connects the first straight panel (4), which is provided with towards on the outside of temple
(13) Trackpad (5), the other side the second straight panel of connection (14) of convolution bending (3), upper and lower the two of second straight panel (14)
Side has the bottom plate (6) stretched out, and the holding part of camera (15) is formed with the second straight panel (14), and the second straight panel (14) is equipped with camera shooting
Head mounting hole, described two bottom plates (6) connect with ray machine (7), and the ray machine (7) is located at and its more similar lens frame (16)
Front, lens frame is connected to the first straight panel (4) and is set to convolution bending (3) more nearby, the first straight panel (4) and the second straight panel
(14) substantially vertical.
Light source is installed and corresponding to the light source hole (8) in the second straight panel (14), microphone in camera (15) holding part
(11) it is mounted near the spectacle-frame (2) on the inside of the first straight panel (4) and convolution bending (3) junction;Loudspeaker (12) are installed on
Position when wearing intelligent glasses in temple (1) close to ear;Camera (15) is mounted on camera shooting by camera bracket (9) support
In head (15) holding part, gyroscope sets different vibration signals with to the intelligence for making automobile maintenance to identify vibration signal
Glasses execute respective action.
The camera (15), light source, microphone (11) and loudspeaker (12) are connected to control panel (10), the control panel (10)
With wireless communication module, the signal sent out for receiving camera (15), light source, microphone (11), and the reception can be believed
Number data processing is carried out, and the control panel (10) is equipped with wireless signal transceiver module, and using the signal transmitting and receiving module to remote
Journey server sends and receives signal.
Control panel (10) includes image recognition matching module, is used for the pretreatment of image, feature extraction, Classification and Identification;Control
Molding block executes corresponding operating and feedback after input information identification not.Image output module, for operator into
Row image feedback;Audio output module, to carry out sound feedback to operator;Vibrational feedback module, it is anti-shake
Feedback;Server database module, the retrieval for servicing end data.
Control panel (10) is also connected with memory, which passes through signal wire and camera (15), light source, microphone
(11) it connects, and is integrated in a mainframe box with loudspeaker (12), the control panel (10) is synchronous to carry out data processing and signal transmitting and receiving.
The license plate image of camera (15) acquisition, only executes figure identifying processing by control panel (10), obtains car plate letter
Breath, is directly sent in remote server by license board information.
Remote server has vehicle information database, travelling data database, vehicle structure model database, maintenance stream
Journey database, tool model database, vehicle failure intelligent analysis system, the vehicle information database store license plate number, and
Vehicle Identify Number, owner information, vehicle maintenance record and the vehicle service record of the corresponding vehicle of the license plate number, and also store the car plate
Vehicle, year money under number and vehicle configuration information;The travelling data database purchase is by under license plate number or the license plate number
The corresponding vehicle of Vehicle Identify Number OBD data and error code;The vehicle structure model data library storage is by vehicle, year money and vehicle
The explanation and 3D modeling figure of the corresponding vehicle composition of configuration information and component part;The maintenance flow data library storage should
License plate number or the corresponding VMT Vehicle-Miles of Travel of Vehicle Identify Number and fault message and maintenance process description;The tool model database
Storage needs the explanation and 3D modeling figure of tool to be used, the vehicle failure intellectual analysis for different vehicle breakdown maintenance
System, integrating remote server has vehicle information database, travelling data database, vehicle structure model database, maintenance
Flow database, analysis vehicle trouble and determining maintenance flow.
The method for carrying out vehicle maintenance using intelligent glasses, which is characterized in that include the following steps:
S1. start the intelligent glasses for automobile maintenance, initially enter recognition mode:By camera acquisition come video
Whether data there is license plate number in automatically scanning picture, if there is license plate number, identify license plate number;Pass through the vehicle identified
The trade mark obtains Vehicle Identify Number from vehicle information database or Direct Recognition goes out Vehicle Identify Number;According to Vehicle Identify Number, in information of vehicles number
According to the corresponding vehicle of the Vehicle Identify Number, year money is obtained in library, mileage travelled, OBD data and event are obtained in travelling data database
Hinder code;By vehicle failure intelligent analysis system, determine that vehicle needs the maintenance project done by mileage travelled;Pass through vehicle failure
Intelligent analysis system determines that vehicle needs the maintenance items done by OBD data and error code;
S2. enter operation mode:User is inputted by voice and gesture, selects the maintenance project of system prompt;
S3. enter teaching pattern:If the maintenance project of user's selection is video teaching, pass through maintenance flow database
Maintenance flow video is obtained, and starts to play;
S4. it plays maintenance video and enters operation mode in the process:User is inputted by voice and gesture, controls maintenance flow
The broadcasting of video;
S5. enter teaching pattern:If the maintenance project of user's selection is word image teaching, pass through maintenance flow number
Maintenance flow is obtained according to library, if need to prompt user's operation auto parts in maintenance flow, into recognition mode;
S6. enter recognition mode:The particular automobile part occurred in identification frame out, and prompt the installation of user's part
Position returns again to teaching pattern;
S7. enter teaching pattern:The 3D models of the part are obtained from vehicle structure model database, and are shown in video
Output system, and the position that should be operated of user and operating method are prompted in the form of animation on 3D models;
S8. it plays in teaching animation process and enters operation mode:User is inputted by voice and gesture, operates 3D at the moment
Model, including rotation, amplify, and reduce, and split, and combined action makes the more detailed understanding teaching process of user;
S9 exits teaching and operation mode:Operation and teaching are completed, is exited.
Advantageous effect:The use of above-mentioned technical proposal of the present invention, allows professional mechanic more specification:Because intelligent glasses can
By background data base, more detailed car status information is obtained, in order to provide to general repair work more specification, completely
Meet the maintenance flow of official standard.People are allowed to select the non-shops 4S mechanic that can also not have trouble and worry.Make enthusiast more professional:
Because intelligent glasses can obtain more detailed car status information by background data base, it is more professional user can be given
Maintenance project, can allow enthusiast it is more professional do it yourself complete repair and maintenance.Make green hand more calm:Because of Brilliant Eyes
Mirror can obtain more detailed car status information by background data base, can inform at the first time helpless
User how to extricate oneself from a predicament.
The function of increasing the intelligent glasses for auto repair can be identified auto parts using glasses.It is logical
Cross intelligent glasses and carry out multi-angle image acquisition, carry out three-dimensional modeling, avoid due to single direction Image Acquisition and caused by
The incomplete situation of image shape feature extraction.Large-scale part feature database is established, almost covers and owns on the market
Part space characteristics.The present invention takes three-dimensional coordinate as feature point coordinates, and to spheric region determined by characteristic point into
Row average area divides, and avoids because certain concentration characteristic points caused by being divided using logarithm are divided because region area is too small
The case where opening improves the accuracy of characteristic matching.Since the Hungary Algorithm that tradition carries out Optimum Matching takes longer, this hair
It is bright to substitute Hungary Algorithm using LAPJV algorithms, the time of algorithm operation is saved, the algorithm speed of service is improved.
Description of the drawings
Fig. 1 is the structural schematic diagram of the Parts Recognition method during the intelligent glasses maintenance of the present invention;
Fig. 2 is the front view of the Parts Recognition method during the intelligent glasses maintenance of the present invention;
Fig. 3 is the rearview of the Parts Recognition method during the intelligent glasses maintenance of the present invention;
Fig. 4 is the left view of the Parts Recognition method during the intelligent glasses maintenance of the present invention;
Fig. 5 is the right view of the Parts Recognition method during the intelligent glasses maintenance of the present invention;
Fig. 6 is the vertical view of the Parts Recognition method during the intelligent glasses maintenance of the present invention;
Fig. 7 is the upward view of the Parts Recognition method during the intelligent glasses maintenance of the present invention;
Fig. 8 is the exploded view of the Parts Recognition method during the intelligent glasses maintenance of the present invention.
Wherein:1. temple, 2. spectacle-frames, 3. convolution bendings, 4. first straight panels, 5. Trackpads, 6. bottom plates, 7. ray machines, 8.
Light source hole, 9. camera brackets, 10. control panels, 11. microphones, 12. loudspeaker, 13. temples outside, 14. second straight panels, 15. take the photograph
As head, 16. lens frames.
Specific implementation mode
In order to more clearly illustrate the invention, the present invention is further described in conjunction with specific embodiments.
Embodiment 1:
A kind of Parts Recognition method during intelligent glasses maintenance, includes the following steps:
S1:First to existing part structure offline feature library, to support the part acquired with follow-up intelligent glasses
Information carries out characteristic matching, and this feature inventory is stored in server database module;
S2:Intelligent glasses pattern is adjusted to recognition mode, by the front camera on intelligent glasses, to be identified zero
Part carries out multi-angled shooting, and shooting image must have lap, captured picture is reached server by communication module
Three-dimensional reconstruction is carried out, spatial context feature is extracted;
S3:The spatial context feature of extraction is compared with the part feature in offline feature library, is calculated using LAPJV
Method carries out Optimum Matching operation to eigenmatrix, keeps cost value minimum;
S4:The auto parts corresponding to Least-cost value are chosen in offline feature database as currently to be detected zero
The most matched part of part;
S5:Server sends the information such as the title, model, price of matched part to intelligent glasses, control module control
Imaged output module carries out the displaying of parts information;
Above-mentioned intelligent glasses, including spectacle-frame 2 and temple 1, for the tool of one of temple 1 there are one convolution bending 3, convolution is curved
The side of folding 3 connects the first straight panel 4, which is provided with the Trackpad 5 towards on the outside of temple 13, convolution bending 3
The other side connects the second straight panel 14, and the upper and lower both sides of second straight panel 14 have the bottom plate 6 stretched out, with the formation of the second straight panel 14
The holding part of camera 15, the second straight panel 14 are equipped with 15 mounting hole of camera, and described two bottom plates 6 are connect with ray machine 7, and the light
Machine 7 is located at the front with its more similar lens frame 16, and lens frame 16, which is connected to the first straight panel 4 and is set to convolution, bends 3
More nearby, the first straight panel 4 and the second straight panel 14 are substantially vertical, described substantially vertical for vertical 0-5 degree of deviation or so so that the two
Substantially perpendicular angle.
Convolution of the present invention bending is mainly used for connecting Trackpad and camera, and so that two kinds of components can be with
In substantially vertical position, and this of Image Acquisition and touch control operation kind position relationship so that user in use, with it is a kind of more
Comfortable interaction locations, and this kind of positional structure, but also ray machine may be at immediately ahead of frame, this kind of picture position with
Touch control operation position is the better position during maintenance, facilitates operation when maintenance and viewing picture, and lens frame is connected to
First straight panel and be set to convolution bending more nearby so that realize that intelligentized component is directly undertaken by temple, not to eye
Frame causes unnecessary improvement and influences point of view range.And camera function is the part during intelligent glasses maintenance
One major function of recognition methods, thus camera is placed in holding part, and a kind of protection to camera, this kind of structure
Also space is more saved.
Embodiment 2:With 1 technical solution having the same of embodiment, difference is:In 15 holding part of camera install light source and
Corresponding to the light source hole 8 in the second straight panel 14, microphone 11 is mounted on 4 inside of the first straight panel, spectacle-frame 2 and convolution bending connection
Near place;Loudspeaker 12 are installed on the position in temple 1 close to ear when wearing intelligent glasses;Camera 15 is by camera 15
The support of frame 9 is mounted in 15 holding part of camera, and gyroscope sets different vibration signals with right to identify vibration signal
The intelligent glasses of automobile maintenance are made to execute respective action.Light source, microphone and loudspeaker are to realize to carry out maintenance using intelligent glasses
Multi-faceted interactive means, a kind of comprehensive intelligent interaction is realized, to improve the intelligence of intelligent glasses.
Embodiment 3:With 2 technical solution having the same of embodiment, difference is:Camera 15, light source, microphone 11 and loudspeaker
12 be connected to control panel 10, which has wireless communication module, for receiving camera 15, light source, microphone 11
The signal sent out, and data processing can be carried out to the reception signal, and the control panel 10 is equipped with wireless signal transceiver module, and
It is sent and received signal to remote server using the signal transmitting and receiving module, wireless signal includes Wifi, bluetooth, GPS, FM.By
It is directly to be connect with control panel in intelligent glasses, control panel carries out signal interaction with remote server again, and control panel can also be right
The reception signal carries out data processing, more i.e., simple identification operation or other operations, can completely again control panel into
Row identification or other processing, or are formerly pre-processed by control panel, can alleviate the processing pressure of remote server, and into one
Step improves processing speed, and especially pretreated signal meets at remote server and complete subsequent processing, can greatly contract again
Subtract the processing time of remote server so that user more quickly obtains handling result.
Embodiment 4:It is with embodiment 1 or 2 or 3 technical solutions having the same, difference:Control panel 10 includes that image is known
Other matching module is used for the pretreatment of image, feature extraction, Classification and Identification;Control module is held after input information identification
Row corresponding operating and feedback;Image output module, for carrying out image feedback to operator;Audio output module, to give
Operator carries out sound feedback;Vibrational feedback module, to carry out vibrational feedback;Server database module is used for server-side
The retrieval of data;The program operation that above-mentioned each module of control panel is loaded under being in control panel is achieved, and sets above-mentioned mould
Block, it is therefore intended that the signals such as image, the sound of acquisition are handled, corresponding output result is desirably to obtain.
Embodiment 5:With arbitrary technical solution having the same of embodiment 1-4, difference is:Control panel 10 is also connected with storage
Device, which is connect by signal wire with camera 15, light source, microphone 11 and loudspeaker 12, and is integrated in a mainframe box
Interior, which, which synchronizes, carries out data processing and signal transmitting and receiving.Purpose of controller connection memory is at this, due to intelligence
When energy glasses maintenance, it is possible to which network failure etc. occur can not be with the situation of remote server interaction data, still, intelligence
Glasses still need gathered data, then the data acquired can not stop temporarily, advanced row data storage is extensive in network
When multiple, continue the transmission with regard to data.
Embodiment 6:With arbitrary technical solution having the same of embodiment 1-5, difference is:The car plate figure of camera acquisition
Picture only executes figure identifying processing by control panel, obtains the license board information, license board information is directly sent in remote server.
Camera acquires license board information, which is directly identified by the control panel of intelligent glasses, by the information after identification
It sends out again and remote server, the advantages of this kind of mode is:Image to the remote server for directly transmitting car plate is identified again
Matching, the signal not only transmitted is relatively more, consuming the time, server receive the signal be identified processing time it is very long, and
At the scene to pictorial information processing, the data identified are transmitted, and signal transmission time is short, and speed is fast, can be as early as possible
The user for being obtains the information of vehicles under the car plate or other information.
Embodiment 7:With arbitrary technical solution having the same of embodiment 1-6, difference is:Remote server has vehicle
Information database, travelling data database, vehicle structure model database, maintenance flow database, tool model database, vapour
The Vehicle Identify Number of vehicle intelligent fault analysis system, the vehicle information database storage license plate number and the corresponding vehicle of the license plate number,
Owner information, vehicle maintenance record and vehicle service record, and also store the vehicle under the license plate number, year money and vehicle configuration letter
Breath;The travelling data database purchase by the corresponding vehicle of Vehicle Identify Number under license plate number or the license plate number OBD data
And error code;The vehicle structure model data library storage be made of vehicle, year money and the corresponding vehicle of vehicle configuration information and
The explanation and 3D modeling figure of component part;The maintenance flow data library storage license plate number or the corresponding vehicle row of Vehicle Identify Number
Sail mileage and fault message and maintenance process description;The tool model database purchase is needed for different vehicle breakdown maintenance
The explanation and 3D modeling figure of tool to be used, the vehicle failure intelligent analysis system, integrating remote server has vehicle
Information database, travelling data database, vehicle structure model database, maintenance flow database, analysis vehicle trouble and
Determine maintenance flow.
Above-mentioned database is set in remote server, for the information about vehicle maintenance of intelligent glasses acquisition, all may be used
To transfer the data in Relational database, and feedback user is as a result, shown and prompted in ray machine, loudspeaker etc., is to realize intelligence
The content of the database is established, perfected to energy glasses for the intelligentized guarantee of vehicle maintenance, can be related to intelligent glasses
The function that intelligent glasses are used for vehicle maintenance is enriched in the processing of each gathered data.
Embodiment 8:The invention further relates to a kind of methods carrying out vehicle maintenance using intelligent glasses, use above-mentioned technical side
The Parts Recognition method during intelligent glasses maintenance described in any of case, includes the following steps:
S1. start the Parts Recognition method during intelligent glasses maintenance, initially enter recognition mode:
By camera acquisition come video data, whether there is license plate number in automatically scanning picture, if there is car plate
Number, identify license plate number;By the license plate number identified, obtains Vehicle Identify Number from vehicle information database or Direct Recognition goes out
Vehicle Identify Number;According to Vehicle Identify Number, the corresponding vehicle of the Vehicle Identify Number, year money are obtained in vehicle information database, in travelling data number
According to acquirement mileage travelled, OBD data and error code in library;By vehicle failure intelligent analysis system, vehicle is determined by mileage travelled
Need the maintenance project done;By vehicle failure intelligent analysis system, determine what vehicle needs were done by OBD data and error code
Maintenance items;
S2. enter operation mode:User is inputted by voice and gesture, selects the maintenance project of system prompt;
S3. enter teaching pattern:If the maintenance project of user's selection is video teaching, pass through maintenance flow database
Maintenance flow video is obtained, and starts to play;
S4. it plays maintenance video and enters operation mode in the process:User is inputted by voice and gesture, controls maintenance flow
The broadcasting of video;
S5. enter teaching pattern:If the maintenance project of user's selection is word image teaching, pass through maintenance flow number
Maintenance flow is obtained according to library, if need to prompt user's operation auto parts in maintenance flow, into recognition mode;
S6. enter recognition mode
The particular automobile part occurred in identification frame out, and the installation site of user's part is prompted, return again to teaching
Pattern;
S7. enter teaching pattern
The 3D models of the part are obtained from vehicle structure model database, and are shown in video output system, and
The position and operating method that prompt user should be operated in the form of animation on 3D models;
S8. it plays in teaching animation process and enters operation mode
User is inputted by voice and gesture, operates 3D models at the moment, including rotation, amplifies, reduce, split, merges
Action, make the more detailed understanding teaching process of user;
S9 exits teaching and operation mode
Operation and teaching are completed, is exited.
When intelligent glasses are applied to vehicle maintenance, 3 patterns (identification operates, teaching) are separated, 3 patterns are mutually interdependent
Support is supported mutually, is converted mutually, with realize the information collection of vehicle maintenance, auxiliary with from the purpose realized, and 3 patterns
All rely on vehicle information database, travelling data database, vehicle structure model database, maintenance flow database, automobile
The range of information systems such as intelligent fault analysis system (RDM).And it presents one and is completely assisted using intelligent glasses
The process of vehicle maintenance.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Any one skilled in the art in the technical scope of present disclosure, according to the technique and scheme of the present invention and its
Inventive concept is subject to equivalent substitution or change, should be covered by the protection scope of the present invention.
Claims (5)
1. a kind of Parts Recognition method during intelligent glasses maintenance, is as follows:
S1:First to existing part structure offline feature library, to support the parts information acquired with follow-up intelligent glasses
Characteristic matching is carried out, and this feature inventory is stored in server database module;
S2:Intelligent glasses pattern is adjusted to recognition mode, by the front camera on intelligent glasses, to part to be identified into
Row multi-angled shooting, shooting image must have lap, and captured picture is reached server by communication module to carry out
Three-dimensional reconstruction extracts spatial context feature;
S3:The spatial context feature of extraction is compared with the part feature in offline feature library, using LAPJV algorithms pair
Eigenmatrix carries out Optimum Matching operation, keeps cost value minimum;
S4:The auto parts corresponding to Least-cost value are chosen in offline feature database as currently part to be detected most
Matched part;
S5:Server sends the title, model, pricing information of matched part to intelligent glasses, and control module controls image
Output module carries out the displaying of parts information;
Above-mentioned intelligent glasses, including spectacle-frame (2) and temple (1), there are one convolution bendings (3) for one of temple (1) tool, return
The side of rotation bending (3) connects the first straight panel (4), which is provided with the Trackpad towards (13) on the outside of temple
(5), the other side of convolution bending (3) connects the second straight panel (14), and the upper and lower both sides of second straight panel (14) have stretching
Bottom plate (6), with the second straight panel (14) formed camera (15) holding part, the second straight panel (14) be equipped with camera mounting hole, two
A bottom plate (6) connect with ray machine (7), and the ray machine (7) is located at the front with its more similar lens frame (16), and lens frame connects
It is connected to the first straight panel (4) and is set to convolution bending (3) more nearby, the first straight panel (4) and the second straight panel (14) are substantially vertical;
Control panel (10) includes image recognition matching module, is used for the pretreatment of image, feature extraction, Classification and Identification;Control mould
Block executes corresponding operating and feedback after input information identification;Image output module, for carrying out image to operator
Feedback;Audio output module, to carry out sound feedback to operator;Vibrational feedback module, to carry out vibrational feedback;Service
Device database module, the retrieval for servicing end data;
Remote server has vehicle information database, travelling data database, vehicle structure model database, maintenance flow number
According to library, tool model database, vehicle failure intelligent analysis system, the vehicle information database storage license plate number and the vehicle
Vehicle Identify Number, owner information, vehicle maintenance record and the vehicle service record of the corresponding vehicle of the trade mark, and also store under the license plate number
Vehicle, year money and vehicle configuration information;The travelling data database purchase is by the vehicle under license plate number or the license plate number
The OBD data and error code of the corresponding vehicle of frame number;The vehicle structure model data library storage is matched by vehicle, year money and vehicle
Confidence ceases the explanation and 3D modeling figure of corresponding vehicle composition and component part;The maintenance flow data library storage car plate
Number or the corresponding VMT Vehicle-Miles of Travel of Vehicle Identify Number and fault message and maintenance process description;The tool model database purchase
The explanation and 3D modeling figure of tool to be used, vehicle failure intellectual analysis system are needed for different vehicle breakdown maintenance
System, integrate remote server have vehicle information database, travelling data database, vehicle structure model database, maintenance
Flow database, analysis vehicle trouble and determining maintenance flow;
It realizes the method for carrying out vehicle maintenance using intelligent glasses, includes the following steps:
S1. start the Parts Recognition method during intelligent glasses maintenance, initially enter recognition mode:By camera acquisition come
Video data, whether there is license plate number in automatically scanning picture, if there is license plate number, identify license plate number;Pass through identification
The license plate number gone out obtains Vehicle Identify Number from vehicle information database or Direct Recognition goes out Vehicle Identify Number;According to Vehicle Identify Number, in vehicle
The corresponding vehicle of the Vehicle Identify Number, year money are obtained in information database, and mileage travelled, OBD numbers are obtained in travelling data database
According to and error code;By vehicle failure intelligent analysis system, determine that vehicle needs the maintenance project done by mileage travelled;Pass through vapour
Vehicle intelligent fault analysis system determines that vehicle needs the maintenance items done by OBD data and error code;
S2. enter operation mode:User is inputted by voice and gesture, selects the maintenance project of system prompt;
S3. enter teaching pattern:If the maintenance project of user's selection is video teaching, obtained by maintenance flow database
Maintenance flow video, and start to play;
S4. it plays maintenance video and enters operation mode in the process:User is inputted by voice and gesture, controls maintenance flow video
Broadcasting;
S5. enter teaching pattern:If the maintenance project of user's selection is word image teaching, pass through maintenance flow database
Maintenance flow is obtained, if need to prompt user's operation auto parts in maintenance flow, into recognition mode;
S6. enter recognition mode:The particular automobile part occurred in identification frame out, and prompt the installation position of user's part
It sets, returns again to teaching pattern;
S7. enter teaching pattern:The 3D models of the part are obtained from vehicle structure model database, and are shown in video output
System, and the position that should be operated of user and operating method are prompted in the form of animation on 3D models;
S8. it plays in teaching animation process and enters operation mode:User is inputted by voice and gesture, operates 3D moulds at the moment
Type, including rotation, amplify, and reduce, and split, and combined action makes the more detailed understanding teaching process of user;
S9 exits teaching and operation mode:Operation and teaching are completed, is exited.
2. the Parts Recognition method during intelligent glasses maintenance as described in claim 1, it is characterised in that:Camera (15)
Light source is installed in holding part and corresponding to the light source hole (8) in the second straight panel (14), microphone (11) is mounted on the first straight panel (4)
Near the spectacle-frame (2) of inside and convolution bending (3) junction;Loudspeaker (12) are installed on the temple (1) when wearing intelligent glasses
The position of upper close ear;Camera (15) is mounted on by camera bracket (9) support in camera (15) holding part, gyro
Instrument sets different vibration signals so that the intelligent glasses of automobile maintenance execute respective action to identify vibration signal.
3. the Parts Recognition method during intelligent glasses maintenance as claimed in claim 2, it is characterised in that:The camera
(15), light source, microphone (11) and loudspeaker (12) are connected to control panel (10), which has wireless communication module,
The signal sent out for receiving camera (15), light source, microphone (11), and the collection of letters number can be docked and carry out data processing, and should
Control panel (10) is equipped with wireless signal transceiver module, and sends and receives letter to remote server using the signal transmitting and receiving module
Number.
4. the Parts Recognition method during intelligent glasses maintenance as claimed in claim 3, it is characterised in that:Control panel (10)
It is also connected with memory, which is connected by signal wire and camera (15), light source, microphone (11) and loudspeaker (12)
It connects, and is integrated in a mainframe box, the control panel (10) is synchronous to carry out data processing and signal transmitting and receiving.
5. the Parts Recognition method during intelligent glasses maintenance as described in claim 1, it is characterised in that:Camera (15)
The license plate image of acquisition only executes figure identifying processing by control panel (10), obtains license board information, directly send license board information
In remote server.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510628119.8A CN105184276B (en) | 2015-09-28 | 2015-09-28 | Parts Recognition method during intelligent glasses maintenance |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510628119.8A CN105184276B (en) | 2015-09-28 | 2015-09-28 | Parts Recognition method during intelligent glasses maintenance |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105184276A CN105184276A (en) | 2015-12-23 |
CN105184276B true CN105184276B (en) | 2018-10-19 |
Family
ID=54906343
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510628119.8A Active CN105184276B (en) | 2015-09-28 | 2015-09-28 | Parts Recognition method during intelligent glasses maintenance |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105184276B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107153962A (en) * | 2016-03-04 | 2017-09-12 | 苏州俊峰伟业信息技术有限公司 | Vehicle maintenance Maintenance price method and system |
CN106980846A (en) * | 2017-05-01 | 2017-07-25 | 刘至键 | A kind of auto parts machinery identifying device based on depth convolutional network |
EP3877831A4 (en) | 2018-11-09 | 2022-08-03 | Beckman Coulter, Inc. | Service glasses with selective data provision |
WO2020214897A1 (en) | 2019-04-18 | 2020-10-22 | Beckman Coulter, Inc. | Securing data of objects in a laboratory environment |
CN111104542B (en) * | 2020-01-07 | 2023-04-18 | 成都睿琪科技有限责任公司 | Part identification management method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101271582A (en) * | 2008-04-10 | 2008-09-24 | 清华大学 | Three-dimensional reconstruction method based on multi-vision angle two-dimension image combined with SIFT algorithm |
CN202394110U (en) * | 2011-11-09 | 2012-08-22 | 张红泉 | Remote diagnostic device for automobile fault |
CN104321684A (en) * | 2012-03-21 | 2015-01-28 | 谷歌公司 | Wearable device with input and output structures |
CN104316033A (en) * | 2014-11-04 | 2015-01-28 | 无锡港湾网络科技有限公司 | Visual inspection system for automobile parts |
-
2015
- 2015-09-28 CN CN201510628119.8A patent/CN105184276B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101271582A (en) * | 2008-04-10 | 2008-09-24 | 清华大学 | Three-dimensional reconstruction method based on multi-vision angle two-dimension image combined with SIFT algorithm |
CN202394110U (en) * | 2011-11-09 | 2012-08-22 | 张红泉 | Remote diagnostic device for automobile fault |
CN104321684A (en) * | 2012-03-21 | 2015-01-28 | 谷歌公司 | Wearable device with input and output structures |
CN104316033A (en) * | 2014-11-04 | 2015-01-28 | 无锡港湾网络科技有限公司 | Visual inspection system for automobile parts |
Non-Patent Citations (2)
Title |
---|
3D Shape Matching with 3D Shape Contexts;Marcel Kortgen 等;《The 7th central European seminar on computer graphics》;20031231;第 卷(第 期);第5-17页 * |
基于三维特征的零件自动识别系统;陈华成 等;《传感器学报》;20061230;第19卷(第6期);第2634-2642页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105184276A (en) | 2015-12-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105158927B (en) | The method of part dismounting of the intelligent glasses during automobile maintenance | |
CN105182535B (en) | The method that automobile maintenance is carried out using intelligent glasses | |
CN105182536B (en) | Intelligent glasses pass through Car license recognition and the method that obtains information of vehicles during automobile maintenance | |
CN105184276B (en) | Parts Recognition method during intelligent glasses maintenance | |
CN105223706B (en) | The method of vehicle damage degree is judged for the intelligent glasses during vehicle maintenance | |
CN105355196A (en) | Speech instruction recognition method for intelligent glasses applied to field of car maintenance | |
CN105224923B (en) | Intelligent glasses are applied to the method for the division part setting loss grade during maintenance | |
CN105259657B (en) | The means of illumination of intelligent glasses during automobile maintenance | |
CN105158900B (en) | Head pose on automobile maintenance intelligent glasses knows method for distinguishing | |
CN105353510A (en) | Application method of smart glasses for automobile long-distance maintenance support | |
US20190005310A1 (en) | Public service system and method using autonomous smart car | |
CN105205471B (en) | The method that blind area during intelligent glasses maintenance is checked | |
CN105723431B (en) | Drive assistant images generating means, display device, display system and generation method | |
CN105916750A (en) | Vehicle driving aid device and vehicle having same | |
CN105353508A (en) | Detection method of automobile liquid residues through adoption of smart glasses | |
CN105242401B (en) | The method that intelligent glasses share the other equipment data for automobile maintenance | |
CN105182537B (en) | Leakage recognition methods during intelligent glasses maintenance | |
CN105223694B (en) | Intelligent glasses are applied to the method for the indoor positioning and image recognition during automobile maintenance | |
JP2021176235A (en) | Image processing method | |
CN109963144A (en) | A kind of vehicle-mounted identifying system based on AR-HUD | |
CN205080316U (en) | Smart spectacles | |
CN105204643A (en) | Gesture recognition method for intelligent glasses used in vehicle maintaining process | |
CN105158931A (en) | Oil stain preventing method for parallel usage of touchpad and keys of intelligent glasses in the vehicle maintenance process | |
CN105158901B (en) | Intelligent glasses for automobile maintenance | |
CN105353509A (en) | Determination method of abnormal sound of vehicle through adoption of smart glasses in process of vehicle maintenance |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |