CN108844545A - A kind of auxiliary traveling method and system based on image recognition - Google Patents
A kind of auxiliary traveling method and system based on image recognition Download PDFInfo
- Publication number
- CN108844545A CN108844545A CN201810700675.5A CN201810700675A CN108844545A CN 108844545 A CN108844545 A CN 108844545A CN 201810700675 A CN201810700675 A CN 201810700675A CN 108844545 A CN108844545 A CN 108844545A
- Authority
- CN
- China
- Prior art keywords
- information
- image
- module
- time
- blind
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/10—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration
- G01C21/12—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning
- G01C21/16—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by using measurements of speed or acceleration executed aboard the object being navigated; Dead reckoning by integrating acceleration or speed, i.e. inertial navigation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/758—Involving statistics of pixels or of feature values, e.g. histogram matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/20—Scenes; Scene-specific elements in augmented reality scenes
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention discloses a kind of auxiliary traveling method and system based on image recognition, method include that voice collecting analysis, route planning design, real-time navigation information be determining, navigation casting in time；System includes that memory module, voice acquisition module, language data process module, positioning device module, communication module, highway route design determine algoritic module, real-time navigation information determining module and information transmission broadcasting module.It is the reliable and stable, good in anti-interference performance of the present invention, applied widely, it conveniently can timely guide traveling of the blind person in complex environment, high, the advanced science of method with system intelligent degree, the advantages that travelling route safety and precise, substantially increase the freedom of action of blind person, with practicability and realizability, there are higher practical value and broad application prospect.
Description
Technical field
The present invention relates to field of intelligent control technology, and in particular to a kind of auxiliary traveling method based on image recognition and is
System.
Background technique
Blind person is the disadvantaged group of society, currently, the tool of assisting blind daily trip is mainly seeing-eye dog and blind-guiding stick.
Seeing-eye dog training cost is high, needs general consumption, restricted lifetime, a possibility that without being widely popularized.Blind-guiding stick by strut and
Handle composition gives blind person's walking support.Although blind person has blind man's stick that can explore the way, for direction of travel and track route
Navigation in terms of, be only unable to reach by crutch or seeing-eye dog, even if blind person asks the way, also due to the obstacle of its eyesight, he
People also can not correctly guide blind person at all.Therefore only by current guide tool, blind person can not independently reach unfamiliar
Place, trip are largely dependent upon the help of kith and kin.Existing, navigation crutch for blind man typically is provided with simple road surface barrier
Hinder detection, GPS navigation and voice prompting function, but can not rationally intelligent path optimizing and effective hazard recognition, operation answer
Miscellaneous, sensitivity is not high, can not be suitable for complex environment, and the development with human-computer interaction, computer vision and video sensor becomes
In maturation, how more intelligent, multifunction, and the part of video acquisition and image procossing is incorporated, blind person is assisted independently to support
Become urgent problem up to destination.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of auxiliary traveling method and system based on image recognition, surely
It is fixed reliable, good in anti-interference performance, applied widely, can conveniently timely traveling of the guidance blind person in complex environment, have
The advantages that system intelligent degree height, the advanced science of method, travelling route safety and precise, substantially increase the freedom of action of blind person
Property, there is practicability and realizability, there is higher practical value and broad application prospect.
The present invention solves technical problem and adopts the following technical scheme that：
The present invention provides a kind of auxiliary traveling method based on image recognition, includes the following steps：
S1, voice command information is received and identified, completes authorization and enters, initializes Navigator and destination confirmation,
It specifically includes：
S11, voice messaging is received, voice messaging is carried out to include speech signal samples, anti aliasing bandpass filtering pre-treatment；
S12, feature extraction is carried out to voice messaging after pretreatment, extracts vocal print feature information in input voice and anti-
Reflect the parameters,acoustic of text information；
S13, vocal print feature information is matched with the information that authorization enters in personnel's vocal print library, if successful match,
Navigator is initialized, and is entered in next step, otherwise prompt re-starts voice input；
S14, similarity between parameters,acoustic and the acoustic pattern library for storing various place nouns is calculated, by similarity
Maximum location name word voice output waits user speech confirmation, if receiving confirmation signal as a purpose by the place,
Otherwise prompt re-starts voice input；
S2, route planning design is carried out, specifically included：
S21, location information is obtained：User current location information is obtained by navigation positional device, and according to determining
Destination information obtains destination locations information；
S22, according to current location information and destination locations information planning path, determine traffic path, specifically include：
S221, electronic map is recalled by mobile network, import road topology file, save each crossing as one
Point, the walking path between node is as section length, and according to two node real-time road congestion informations by weight between grade setting node；
S222, positioning starting point and destination coordinate；
S223, beginning and end will be selected to be respectively matched in the node in road using node matching algorithm；
S224, interconnection analysis, judgement are carried out using breadth-first search two nodes matched to beginning and end
Whether connection；
If S225, using the special pulling method of Dick Si, can be grown according to the weight of setting, section with connection, calculate optimal road
Diameter ultimately forms navigation scheme；
S3, it is specifically included according to navigation scheme into the determination of face-to-face real-time navigation information：
S31, the benchmark template that blind way gray scale upper limit threshold, lower threshold and all kinds of barriers is stored in advance；
S32, in real time acquisition blind person's direction of advance video data, pre-process the video image data of acquisition, specifically
Including：
S321, edge enhancing processing is executed to image to obtain edge enhanced images；
S322, edge enhanced images are handled using the wavelet filtering based on 2 rank Haar wavelet basis, to filter out the edge
Enhance the Gaussian noise in image, obtains wavelet filtering image
S323, adaptive recursive filtering processing is executed to wavelet filtering image, to obtain adaptive recursive filtering image；
S324, change of scale enhancing processing is executed to adaptive recursive filtering image, to enhance target and background in image
Contrast, obtain contrast enhance image；
S33, blind way gray scale upper limit threshold, lower limit is being stored in advance in grey scale pixel value in the contrast enhancing image of acquisition
All pixels in threshold range form blind way image, and judge whether there is barrier above blind way：
If S331, have above blind way obstructions chart picture by the benchmark template of attachment above blind way and all kinds of barriers one by one
Matching, successful match obtain obstacle information；
S332, range radar wave is issued, and records the time of transmitting and receives the time of back wave, when passing through transmitting
Between, the spread speed of reflection interval and range radar wave calculate at a distance between obstacle and blind person, specific formula for calculation is：
S=(V0×T-V1×T)/2
Wherein, S is the distance between barrier and blind person, V0For range radar velocity of wave propagation, V1 be blind person walk away from
From T is the time of transmitting and the time for receiving back wave；
S34, picture construction mixed Gauss model is enhanced to the contrast of acquisition, while the road conditions image of acquisition is carried on the back
Scape analysis obtains image background, obtains foreground image information, carries out signature analysis to foreground image information, obtains traffic light
Location information, and determine signal lamp state；
The histograms of oriented gradients feature of this outer analysis foreground image, and with prestore pedestrian's template matching, successful match is then
It is judged as pedestrian, and triggers ranging service, obtain pedestrian position information, next step is waited to broadcast to blind users；
The Harr feature for analyzing foreground image simultaneously, matches with car modal is prestored, and successful match is then judged as vehicle, and
Ranging service is triggered, vehicle position information is obtained, next step is waited to broadcast to blind users；
The determining signal lamp state is realized by the following method：To image within the scope of traffic light according to red, yellow, and green
Three kinds of colors carry out image segmentation, analyze the edge of each cut zone, obtain shape, carry out with traffic lights template is prestored
Matching, and identification is combined to traffic signals, finally determine traffic signal light condition；
The ranging service obtains pedestrian and vehicle position information using method identical with step S332；
S4, the road information that step S3 is analyzed, obstacle information and signal information, casting is to blind person in real time
User issues straight trip, turning, evacuation barrier and the command information by traffic light intersection in time.
Preferably, the S4 is further comprising the steps of：
According to step S332 calculated distance, vibrating alert is set according to apart from size, apart from smaller vibration frequency
It is faster, it sustained vibration and is sounded an alarm when distance is lower than predetermined value.
It preferably, further include step S5：
By be arranged state sensor including three-axis gyroscope and accelerometer including to user's tumble or collision information into
Row real time monitoring and record, are simultaneously emitted by warning information, and not cancelling alarm in setting delay time user, then automatic poking is urgent
Urgent telegram words.
The present invention also provides a kind of auxiliary travel system based on image recognition, including：
Memory module, for pre-stored authorization enter personnel's vocal print library, acoustic pattern library, blind way gray scale upper limit threshold, under
The benchmark template of threshold value and all kinds of barriers is limited, and stores the environment speech data information of acquisition；
Voice acquisition module, for acquiring environment speech data information in real time；
Language data process module, it is complete for receiving and identifying the environment speech data information of voice acquisition module acquisition
Enter at authorization, initialize Navigator and destination confirmation, specifically includes：
Voice messaging is received, voice messaging is carried out to include speech signal samples, anti aliasing bandpass filtering pre-treatment；
Feature extraction is carried out to voice messaging after pretreatment, extracts vocal print feature information and reflection text in input voice
The parameters,acoustic of word information；
Vocal print feature information is matched with the information that authorization enters in personnel's vocal print library, if successful match, initially
Change Navigator, and enter in next step, otherwise prompt re-starts voice input；
The similarity between parameters,acoustic and the acoustic pattern library for storing various place nouns is calculated, by similarity maximum
Location name word voice output, wait user speech confirmation, if receiving confirmation signal as a purpose by the place, otherwise
Prompt re-starts voice input；
Positioning device module obtains mesh for obtaining user current location information, and according to determining destination information
Location information；
Communication module, the communication module are connect for providing the other modules of system with internet, and real-time update stores number
According to；
Highway route design determines algoritic module, is used for according to current location information and destination locations information planning path, really
Determine traffic path, specifically includes：Recall electronic map by communication module, import road topology file, using each crossing as
Node is arranged by grade as section length, and according to two node real-time road congestion informations in one node, the walking path between node
Between weight, then position starting point and destination coordinate, then beginning and end will be selected to match respectively using node matching algorithm
In node into road, then connection is carried out using breadth-first search two nodes matched to beginning and end and is divided
Analysis, judges whether connection, if, using the special pulling method of Dick Si, can be grown, be calculated optimal according to the weight of setting, section with connection
Path ultimately forms navigation scheme；
Real-time navigation information determining module, including video acquisition module, image analysis module, range finder module and traffic signals
Lamp analysis module；
The video acquisition module for acquiring blind person's direction of advance video data in real time；
Described image analysis module is specifically included for pre-processing to the video image data of acquisition：Image is held
The enhancing processing of row edge is to obtain edge enhanced images；To edge enhanced images using the small echo filter based on 2 rank Haar wavelet basis
Wave processing obtains wavelet filtering image to filter out the Gaussian noise in the edge enhanced images；Wavelet filtering image is executed
Adaptive recursive filtering processing, to obtain adaptive recursive filtering image；Change of scale is executed to adaptive recursive filtering image
Enhancing processing, to enhance the contrast of target and background in image, obtaining contrast enhances image；The contrast of acquisition is enhanced
In image grey scale pixel value blind way gray scale upper limit threshold is stored in advance, all pixels within the scope of lower threshold form blind way figure
Picture, and judge whether there is barrier above blind way：If there is obstructions chart picture by attachment above blind way and all kinds of barriers above blind way
The benchmark template of object is hindered to match one by one, successful match obtains obstacle information；
The range finder module records the time of transmitting and receives the time of back wave for issuing range radar wave,
It is calculated at a distance between obstacle and blind person by the spread speed of launch time, reflection interval and range radar wave, it is specific to calculate
Formula is：
S=(V0×T-V1×T)/2
Wherein, S is the distance between barrier and blind person, V0For range radar velocity of wave propagation, V1 be blind person walk away from
From T is the time of transmitting and the time for receiving back wave；
The traffic lights analysis module is used to enhance picture construction mixed Gauss model to the contrast of acquisition, simultaneously
Context analyzer is carried out to the road conditions image of acquisition and obtains image background, obtains foreground image information, foreground image information is carried out
Signature analysis obtains the location information of traffic light, and determines signal lamp state；
Information transmits broadcasting module, road information, obstacle information and the signal lamp letter for analyzing step S3
Breath, in real time casting issue straight trip, turning, evacuation barrier in time and are believed by the instruction of traffic light intersection to blind users
Breath.
Preferably, real-time navigation information determining module further includes moving target position determining module, for analyzing foreground picture
The histograms of oriented gradients feature of picture, and with prestore pedestrian's template matching, successful match is then judged as pedestrian, and trigger ranging clothes
Business obtains pedestrian position information, and next step is waited to broadcast to blind users；The Harr feature for analyzing foreground image, and prestores
Car modal matching, successful match is then judged as vehicle, and triggers ranging service, obtains vehicle position information, waits in next step
Rapid casting is to blind users；
The ranging service uses the range finder module in real-time navigation information determining module.
Preferably, further include vibrating alert module, for according to obtained user between barrier at a distance from size mention
It is faster apart from smaller vibration frequency for vibrating alert, it sustained vibration and is sounded an alarm when distance is lower than predetermined value.
Preferably, further include that emergency judges alarm module, be provided with including three-axis gyroscope and accelerometer
State sensor is simultaneously emitted by warning information, is setting for user's tumble or collision information to be monitored in real time and recorded
Delay time user does not cancel alarm then automatic dialing emergency call.
Preferably, the video acquisition module includes photographic device and adjustment device；
The photographic device includes main photographic device and second camera device, and the second camera device is two, respectively
There is 50% visual field that is superimposed with main photographic device, without superimposition between the second camera device；
The adjustment device is used to adjust the angle and direction of the video acquisition of photographic device.
Compared with prior art, the present invention has following beneficial effect：
(1) a kind of auxiliary traveling method based on image recognition of the invention passes through whole voice control, realizes voice
Authorization enters, automatic destination is analyzed, and reduces using threshold, convenient and efficient accuracy is good, can be based on real-time road condition information
Optimization processing is carried out to route, the time has been saved, has facilitated stroke, real-time information of road surface is carried out by image processing means
Analysis can continue locking road, fast and accurately have identified barrier, and obtain in time the specifying information of barrier with
And the distance with blind person, pre-warning time length can be effectively improved, road conditions traffic lights, identification signal can be additionally locked
Lamp state reduces the danger being likely to occur, really so that provide comprehensively and effectively road surface for blind person commands navigation feature in real time
The blind person's active homing with practical significance for having accomplished timely efficiently and accurately, realizes the independent trip of blind safety, has
Good market popularization value and meaning.
(2) it is of the invention it is a kind of based on the auxiliary traveling method of image recognition during determining route, reflected using crossing
Penetrate node cooperation using real-time congestion information as the weight of standard setting, using road conditions real time information as route formulate it is important according to
According to, while beginning and end will be selected to be respectively matched to the node in road using node matching algorithm, it can be realized nearest original
Then, distance is reduced, then interconnection analysis is carried out using breadth-first search, various factors is comprehensively considered, is calculated optimal
Navigation routine, route setting is rationally effective, can maximize and save the time, blind person is facilitated to go on a journey.
(3) a kind of auxiliary traveling method based on image recognition of the invention is by increasing image preprocessing, including edge
By force, wavelet filtering, adaptive recursive filtering, change of scale enhancing processing, a series of this variation, synergistic effect reduce noise
The influence of illumination improves the signal-to-noise ratio of target and image, efficiently separates background, can fast and accurately identify locking blind way,
Barrier improves accuracy of the forecast and timeliness so as to complete track and identify Deng follow-up works；Furthermore video acquisition mould
Block can accurately collect video image information by photographic device and adjustment device on a large scale in real time, and can continue
Photographic device is adjusted, so that acquisition becomes apparent from, experience is more preferably.
(4) a kind of auxiliary traveling method based on image recognition of the invention, by the direction gradient for analyzing foreground image
The Harr feature of histogram feature and analysis foreground image, obtains pedestrian and information of vehicles, and lockup period location information in time, mentions
The high diversity of navigation data, covering it is comprehensive, improve its use adaptability and reliability under complex environment.
(5) a kind of auxiliary travel system based on image recognition of the invention provides a kind of convenient, fast, efficient, low
The dynamic object of cost running is locked with mode, and system flexibility, the degree of automation are higher, and recognition speed is fast, accuracy rate is high, together
When also have the advantages that it is versatile, open it is strong, scalability is strong.
(6) the emergency judgement alarm mould that a kind of auxiliary travel system based on image recognition of the invention passes through setting
Block, the parameter that the sensors such as three-axis gyroscope and accelerometer wherein included obtain can judge in time whether blind person endangers
Automatic emergency alarm is realized in danger under triggering situation, substantially increases the anti-risk performance of system, and the comprehensive trip for blind person is protected
Drive convoy.
(7) a kind of auxiliary travel system based on image recognition of the invention is passed through by the vibrating alert module of setting
Using barrier between blind person at a distance from as standard setting vibration frequency, prevent user voice messaging reception there is noise or note
When power of anticipating dispersion, issues remind in time, in case of emergency sound an alarm, reach dual warning, effectively increase system has
Effect property.
(8) a kind of auxiliary traveling method and system based on image recognition of the invention be reliable and stable, good in anti-interference performance,
It is applied widely, traveling of the blind person in complex environment conveniently can be timely guided, there is system intelligent degree height, method
The advantages that advanced science, travelling route safety and precise, substantially increases the freedom of action of blind person, has practicability and can realize
Property, there are higher practical value and broad application prospect.
Detailed description of the invention
Upon reading the detailed description of non-limiting embodiments with reference to the following drawings, other feature of the invention,
Objects and advantages will become more apparent upon：
Fig. 1 is a kind of auxiliary traveling method flow chart based on image recognition of the invention；
Fig. 2 is the specific flow chart of the step S1 of auxiliary traveling method based on image recognition of the invention a kind of；
Fig. 3 is the specific flow chart of the step S2 of auxiliary traveling method based on image recognition of the invention a kind of；
Fig. 4 is the specific flow chart of the step S3 of auxiliary traveling method based on image recognition of the invention a kind of；
Fig. 5 is the specific flow chart of the step S32 of auxiliary traveling method based on image recognition of the invention a kind of；
Fig. 6 is a kind of real-time navigation information determining module of auxiliary travel system based on image recognition of the invention；
Fig. 7 is a kind of structural schematic diagram of auxiliary travel system based on image recognition of the invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
In addition, those skilled in the art will appreciate that, various aspects of the invention can be implemented as system, method or
Computer program product.Therefore, various aspects of the invention can be implemented as the form of software and hardware combining, can unite here
Referred to as circuit, " module " or " system ".In addition, in some embodiments, various aspects of the invention are also implemented as
The form of computer program product in one or more microprocessors readable medium, comprising micro- in the microprocessor readable medium
The readable program code of processor.
Below with reference to according to the method for the embodiment of the present invention, the flow chart of device (system) and computer program product
And/or the block diagram description present invention.It should be appreciated that each in each box and flowchart and or block diagram of flowchart and or block diagram
The combination of box can be realized by computer program instructions.These computer program instructions can be supplied to general purpose computer,
The processor of special purpose computer or other programmable data processing units, so that a kind of machine is produced, so that these computers
Program instruction when executed by a processor of a computer or other programmable data processing device, produces implementation flow chart
And/or the device of function action specified in one or more boxes in block diagram.It can also be these computer program instructions
Storage in computer-readable medium, these instruct so that computer, other programmable data processing units or other equipment with
Ad hoc fashion work, thus, the instruction stored in computer-readable medium is just produced including implementation flow chart and/or block diagram
In one or more boxes specified in function action instruction manufacture (article of manufacture).?
Computer program instructions can be loaded into computer, other programmable data processing units or other equipment make it is a series of
Operating procedure is executed in computer, other programmable devices or other equipment, is formed computer and is realized process, so as to
The instruction executed on a computer or other programmable device provides the one or more side realized in flowchart and or block diagram
The process of function action specified in frame.
As shown in figs. 1-7, a kind of auxiliary traveling method based on image recognition of the present embodiment, includes the following steps：
S1, voice command information is received and identified, completes authorization and enters, initializes Navigator and destination confirmation,
It specifically includes：
S11, voice messaging is received, voice messaging is carried out to include speech signal samples, anti aliasing bandpass filtering pre-treatment；
S12, feature extraction is carried out to voice messaging after pretreatment, extracts vocal print feature information in input voice and anti-
Reflect the parameters,acoustic of text information；
S13, vocal print feature information is matched with the information that authorization enters in personnel's vocal print library, if successful match,
Navigator is initialized, and is entered in next step, otherwise prompt re-starts voice input；
S14, similarity between parameters,acoustic and the acoustic pattern library for storing various place nouns is calculated, by similarity
Maximum location name word voice output waits user speech confirmation, if receiving confirmation signal as a purpose by the place,
Otherwise prompt re-starts voice input；
S2, route planning design is carried out, specifically included：
S21, location information is obtained：User current location information is obtained by navigation positional device, and according to determining
Destination information obtains destination locations information；
S22, according to current location information and destination locations information planning path, determine traffic path, specifically include：
S221, electronic map is recalled by mobile network, import road topology file, save each crossing as one
Point, the walking path between node is as section length, and according to two node real-time road congestion informations by weight between grade setting node；
S222, positioning starting point and destination coordinate；
S223, beginning and end will be selected to be respectively matched in the node in road using node matching algorithm；
S224, interconnection analysis, judgement are carried out using breadth-first search two nodes matched to beginning and end
Whether connection；
If S225, using the special pulling method of Dick Si, can be grown according to the weight of setting, section with connection, calculate optimal road
Diameter ultimately forms navigation scheme；
S3, it is specifically included according to navigation scheme into the determination of face-to-face real-time navigation information：
S31, the benchmark template that blind way gray scale upper limit threshold, lower threshold and all kinds of barriers is stored in advance；
S32, in real time acquisition blind person's direction of advance video data, pre-process the video image data of acquisition, specifically
Including：
S321, edge enhancing processing is executed to image to obtain edge enhanced images；
S322, edge enhanced images are handled using the wavelet filtering based on 2 rank Haar wavelet basis, to filter out the edge
Enhance the Gaussian noise in image, obtains wavelet filtering image
S323, adaptive recursive filtering processing is executed to wavelet filtering image, to obtain adaptive recursive filtering image；
S324, change of scale enhancing processing is executed to adaptive recursive filtering image, to enhance target and background in image
Contrast, obtain contrast enhance image；
S33, blind way gray scale upper limit threshold, lower limit is being stored in advance in grey scale pixel value in the contrast enhancing image of acquisition
All pixels in threshold range form blind way image, and judge whether there is barrier above blind way：
If S331, have above blind way obstructions chart picture by the benchmark template of attachment above blind way and all kinds of barriers one by one
Matching, successful match obtain obstacle information；
S332, range radar wave is issued, and records the time of transmitting and receives the time of back wave, when passing through transmitting
Between, the spread speed of reflection interval and range radar wave calculate at a distance between obstacle and blind person, specific formula for calculation is：
S=(V0×T-V1×T)/2
Wherein, S is the distance between barrier and blind person, V0For range radar velocity of wave propagation, V1 be blind person walk away from
From T is the time of transmitting and the time for receiving back wave；
S34, picture construction mixed Gauss model is enhanced to the contrast of acquisition, while the road conditions image of acquisition is carried on the back
Scape analysis obtains image background, obtains foreground image information, carries out signature analysis to foreground image information, obtains traffic light
Location information, and determine signal lamp state；
S4, the road information that step S3 is analyzed, obstacle information and signal information, casting is to blind person in real time
User issues straight trip, turning, evacuation barrier and the command information by traffic light intersection in time；
Step S5：
By be arranged state sensor including three-axis gyroscope and accelerometer including to user's tumble or collision information into
Row real time monitoring and record, are simultaneously emitted by warning information, and not cancelling alarm in setting delay time user, then automatic poking is urgent
Urgent telegram words.
Determine that signal lamp state is realized by the following method in the step S34 of the present embodiment：To within the scope of traffic light
Image carries out image segmentation according to three kinds of colors of red, yellow, and green, analyzes the edge of each cut zone, obtains shape, hands over prestoring
Ventilating signal lamp template is matched, and is combined identification to traffic signals, finally determines traffic signal light condition.
The step S34 of the present embodiment is further comprising the steps of：
Analyze foreground image histograms of oriented gradients feature, and with prestore pedestrian's template matching, successful match then judges
For pedestrian, and ranging service is triggered, obtain pedestrian position information, next step is waited to broadcast to blind users；
The Harr feature for analyzing foreground image, matches, successful match is then judged as vehicle, and triggers with car modal is prestored
Ranging service obtains vehicle position information, and next step is waited to broadcast to blind users；
The ranging service obtains pedestrian and vehicle position information using method identical with step S332.
The step S4 of the present embodiment is further comprising the steps of：
According to step S332 calculated distance, vibrating alert is set according to apart from size, apart from smaller vibration frequency
It is faster, it sustained vibration and is sounded an alarm when distance is lower than predetermined value.
A kind of auxiliary travel system based on image recognition of the present embodiment, including：
Memory module, for pre-stored authorization enter personnel's vocal print library, acoustic pattern library, blind way gray scale upper limit threshold, under
The benchmark template of threshold value and all kinds of barriers is limited, and stores the environment speech data information of acquisition；
Voice acquisition module, for acquiring environment speech data information in real time；
Language data process module, it is complete for receiving and identifying the environment speech data information of voice acquisition module acquisition
Enter at authorization, initialize Navigator and destination confirmation, specifically includes：
Voice messaging is received, voice messaging is carried out to include speech signal samples, anti aliasing bandpass filtering pre-treatment；
Feature extraction is carried out to voice messaging after pretreatment, extracts vocal print feature information and reflection text in input voice
The parameters,acoustic of word information；
Vocal print feature information is matched with the information that authorization enters in personnel's vocal print library, if successful match, initially
Change Navigator, and enter in next step, otherwise prompt re-starts voice input；
The similarity between parameters,acoustic and the acoustic pattern library for storing various place nouns is calculated, by similarity maximum
Location name word voice output, wait user speech confirmation, if receiving confirmation signal as a purpose by the place, otherwise
Prompt re-starts voice input；
Positioning device module obtains mesh for obtaining user current location information, and according to determining destination information
Location information；
Communication module, the communication module are connect for providing the other modules of system with internet, and real-time update stores number
According to；
Highway route design determines algoritic module, is used for according to current location information and destination locations information planning path, really
Determine traffic path, specifically includes：Recall electronic map by communication module, import road topology file, using each crossing as
Node is arranged by grade as section length, and according to two node real-time road congestion informations in one node, the walking path between node
Between weight, then position starting point and destination coordinate, then beginning and end will be selected to match respectively using node matching algorithm
In node into road, then connection is carried out using breadth-first search two nodes matched to beginning and end and is divided
Analysis, judges whether connection, if, using the special pulling method of Dick Si, can be grown, be calculated optimal according to the weight of setting, section with connection
Path ultimately forms navigation scheme；
Real-time navigation information determining module, including video acquisition module, image analysis module, range finder module and traffic signals
Lamp analysis module；
The video acquisition module for acquiring blind person's direction of advance video data in real time；
Described image analysis module is specifically included for pre-processing to the video image data of acquisition：Image is held
The enhancing processing of row edge is to obtain edge enhanced images；To edge enhanced images using the small echo filter based on 2 rank Haar wavelet basis
Wave processing obtains wavelet filtering image to filter out the Gaussian noise in the edge enhanced images；Wavelet filtering image is executed
Adaptive recursive filtering processing, to obtain adaptive recursive filtering image；Change of scale is executed to adaptive recursive filtering image
Enhancing processing, to enhance the contrast of target and background in image, obtaining contrast enhances image；The contrast of acquisition is enhanced
In image grey scale pixel value blind way gray scale upper limit threshold is stored in advance, all pixels within the scope of lower threshold form blind way figure
Picture, and judge whether there is barrier above blind way：If there is obstructions chart picture by attachment above blind way and all kinds of barriers above blind way
The benchmark template of object is hindered to match one by one, successful match obtains obstacle information；
The range finder module records the time of transmitting and receives the time of back wave for issuing range radar wave,
It is calculated at a distance between obstacle and blind person by the spread speed of launch time, reflection interval and range radar wave, it is specific to calculate
Formula is：
S=(V0×T-V1×T)/2
Wherein, S is the distance between barrier and blind person, V0For range radar velocity of wave propagation, V1 be blind person walk away from
From T is the time of transmitting and the time for receiving back wave；
The traffic lights analysis module is used to enhance picture construction mixed Gauss model to the contrast of acquisition, simultaneously
Context analyzer is carried out to the road conditions image of acquisition and obtains image background, obtains foreground image information, foreground image information is carried out
Signature analysis obtains the location information of traffic light, and determines signal lamp state；
Information transmits broadcasting module, road information, obstacle information and the signal lamp letter for analyzing step S3
Breath, in real time casting issue straight trip, turning, evacuation barrier in time and are believed by the instruction of traffic light intersection to blind users
Breath.
The real-time navigation information determining module of the present embodiment further includes moving target position determining module, for analyzing prospect
The histograms of oriented gradients feature of image, and with prestore pedestrian's template matching, successful match is then judged as pedestrian, and triggers ranging
Service obtains pedestrian position information, and next step is waited to broadcast to blind users；The Harr feature of foreground image is analyzed, and it is pre-
Bicycle parking template matching, successful match are then judged as vehicle, and trigger ranging service, obtain vehicle position information, wait next
Step is broadcasted to blind users；The ranging service uses the range finder module in real-time navigation information determining module.
The system of the present embodiment further includes vibrating alert module, for according to obtained user between barrier at a distance from
Size provides vibrating alert, faster apart from smaller vibration frequency, sustained vibration and sounds an alarm when distance is lower than predetermined value.
The system of the present embodiment further includes that emergency judges alarm module, is provided with including three-axis gyroscope and accelerometer
State sensor inside, for user fall or collision information monitor in real time and record, be simultaneously emitted by warning information,
Alarm then automatic dialing emergency call is not cancelled in setting delay time user.
Video acquisition module includes photographic device and adjustment device in the system of the present embodiment；
Photographic device includes main photographic device and second camera device, and the second camera device is two, respectively with master
Photographic device has a 50% superposition visual field, without superimposition between the second camera device；
Adjustment device is used to adjust the angle and direction of the video acquisition of photographic device.
Significant progress and substantive distinguishing features in the present embodiment compared with the existing technology are analyzed as follows：
The present invention passes through whole voice control, and control mode is simple and clear, reduces in the prior art to blind person's walking
The interference of burden property, for example need to be manually entered confirmation, while the present invention realizes voice authorization entrance, the analysis of automatic destination,
It reduces using threshold, convenient and efficient accuracy is good, can carry out optimization processing to route based on real-time road condition information, save
Time facilitates stroke, is analyzed real-time information of road surface by image processing means, and locking road can be continued,
Barrier is fast and accurately had identified, and obtains the specifying information of barrier and the distance with blind person in time, it can be effective
Pre-warning time length is improved, road conditions traffic lights, marker lamp state can be additionally locked, to provide entirely for blind person
Navigation feature is commanded on the effective road surface in face in real time, reduces the danger being likely to occur, and has been truly realized the tool of timely efficiently and accurately
The blind person's active homing being of practical significance realizes the independent trip of blind safety；
Using the information entered vocal print feature information and authorization in personnel's vocal print library during present invention authorization enters
It is matched, improves the accuracy of identification user, while calculated parameters,acoustic and storing the sound mould of various place nouns
The maximum location name word voice output of similarity is waited user speech confirmation by the similarity between formula library, and double insurance determines
Destination, while also constructive destination is fed back into user, achieve the effect that fuzzy search；
Present invention determine that using mapping node cooperation in crossing using real-time congestion information as standard setting during route
Weight, the important evidence that road conditions real time information is formulated as route, while starting point and end will be selected using node matching algorithm
The node that point is respectively matched in road can be realized nearby principle, reduce distance, then carry out using breadth-first search
Interconnection analysis comprehensively considers various factors, and optimal navigation routine is calculated, and route setting is rationally effective, can maximize section
It makes an appointment, blind person is facilitated to go on a journey.
The present invention passes through to image preprocessing, including edge enhancing, wavelet filtering, adaptive recursive filtering, change of scale
Enhancing processing, a series of this variation, synergistic effect reduce the influence of noise light photograph, improve the signal-to-noise ratio of target and image,
Background is efficiently separated, can fast and accurately identify locking blind way, barrier, so as to complete to track and identify etc. subsequent
Business improves accuracy of the forecast and timeliness；Furthermore video acquisition module, can be accurate in real time by photographic device and adjustment device
Video image information, and the adjustment photographic device that can continue are collected on a large scale, so that acquisition becomes apparent from, experience is more
It is good；
The present invention by building Gauss model, carry out display foreground extraction, then to image within the scope of traffic light according to
Three kinds of colors of red, yellow, and green carry out image segmentations, analyze the edge of each cut zone, obtain shape, and prestore traffic lights
Template is matched, and is combined identification to traffic signals, is finally determined traffic signal light condition, can be greatly improved signal
Lamp extracts the accuracy of judgement, and the identification of associativity can reduce the generation of error, cooperate the monitoring of traffic, be capable of providing
Give blind person's accurately real-time intersection information；
The present invention passes through the histograms of oriented gradients feature of analysis foreground image and the Harr feature of analysis foreground image, and
When obtain pedestrian and information of vehicles, and lockup period location information, improve the diversity of navigation data, covering it is comprehensive, mention
Its high use adaptability and reliability under complex environment；
A kind of auxiliary travel system based on image recognition of the invention provides a kind of convenient, fast, efficient, inexpensive
The dynamic object of running is locked with mode, and system flexibility, the degree of automation are higher, and recognition speed is fast, accuracy rate is high, simultaneously also
Have the advantages that it is versatile, open it is strong, scalability is strong；
The emergency that the present invention also passes through setting judges alarm module, three-axis gyroscope and accelerometer wherein included etc.
The parameter that sensor obtains can judge in time whether blind person danger occurs, automatic emergency alarm be realized under triggering situation, greatly
The anti-risk performance of system is improved greatly, the comprehensive trip for blind person escorts；
The present invention by setting vibrating alert module, by using barrier between blind person at a distance from for standard setting vibration
Frequency prevents user when noise or dispersion attention occurs in voice messaging reception, issues remind in time, in case of emergency
It sounds an alarm, reaches dual warning, effectively increase the validity of system.
The flow chart and block diagram in the drawings show the system of multiple embodiments according to the present invention, method and computer journeys
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, section or code of table, a part of the module, section or code include one or more use
The executable instruction of the logic function as defined in realizing.It should also be noted that in some implementations as replacements, being marked in box
The function of note can also occur in a different order than that indicated in the drawings.For example, two continuous boxes can actually base
Originally it is performed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.It is also noted that
It is the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, can uses and execute rule
The dedicated hardware based system of fixed function or movement is realized, or can use the group of specialized hardware and computer instruction
It closes to realize.
A kind of auxiliary traveling method based on image recognition of the invention is reliable and stable, good in anti-interference performance, the scope of application
Extensively, traveling of the blind person in complex environment conveniently can be timely guided, there is system intelligent degree height, the advanced section of method
The advantages that, travelling route safety and precise, the freedom of action of blind person is substantially increased, there is practicability and realizability, have
Higher practical value and broad application prospect.
It is obvious to a person skilled in the art that invention is not limited to the details of the above exemplary embodiments, Er Qie
In the case where without departing substantially from spirit or essential attributes of the invention, the present invention can be realized in other specific forms.Therefore, no matter
From the point of view of which point, the present embodiments are to be considered as illustrative and not restrictive, and the scope of the present invention is by appended power
Benefit requires rather than above description limits, it is intended that all by what is fallen within the meaning and scope of the equivalent elements of the claims
Variation is included within the present invention.Any reference signs in the claims should not be construed as limiting the involved claims.
In addition, it should be understood that although this specification is described in terms of embodiments, but not each embodiment is only wrapped
Containing an independent technical solution, this description of the specification is merely for the sake of clarity, and those skilled in the art should
It considers the specification as a whole, the technical solutions in the various embodiments may also be suitably combined, forms those skilled in the art
The other embodiments being understood that.
Claims (8)
1. a kind of auxiliary traveling method based on image recognition, which is characterized in that include the following steps：
S1, voice command information is received and identified, completes authorization and enter, initialize Navigator and destination confirmation, specifically
Including：
S11, voice messaging is received, voice messaging is carried out to include speech signal samples, anti aliasing bandpass filtering pre-treatment；
S12, feature extraction is carried out to voice messaging after pretreatment, extracts vocal print feature information and reflection text in input voice
The parameters,acoustic of word information；
S13, vocal print feature information is matched with the information that authorization enters in personnel's vocal print library, if successful match, initially
Change Navigator, and enter in next step, otherwise prompt re-starts voice input；
S14, similarity between parameters,acoustic and the acoustic pattern library for storing various place nouns is calculated, by similarity maximum
Location name word voice output, wait user speech confirmation, if receiving confirmation signal as a purpose by the place, otherwise
Prompt re-starts voice input；
S2, route planning design is carried out, specifically included：
S21, location information is obtained：User current location information is obtained by navigation positional device, and according to determining purpose
Ground information obtains destination locations information；
S22, according to current location information and destination locations information planning path, determine traffic path, specifically include：
S221, electronic map being recalled by mobile network, importing road topology file, each crossing is mapped into a node, section
Walking path between point is grown as section, and according to two node real-time road congestion informations by weight between grade setting node；
S222, positioning starting point and destination coordinate；
S223, beginning and end will be selected to be respectively matched in the node in road using node matching algorithm；
S224, interconnection analysis is carried out using breadth-first search two nodes matched to beginning and end, judged whether
Connection；
If S225, using the special pulling method of Dick Si, can be grown according to the weight of setting, section with connection, calculate optimal path, most
End form is at navigation scheme；
S3, it is specifically included according to navigation scheme into the determination of face-to-face real-time navigation information：
S31, the benchmark template that blind way gray scale upper limit threshold, lower threshold and all kinds of barriers is stored in advance；
S32, in real time acquisition blind person's direction of advance video data, pre-process the video image data of acquisition, specifically include：
S321, edge enhancing processing is executed to image to obtain edge enhanced images；
S322, edge enhanced images are handled using the wavelet filtering based on 2 rank Haar wavelet basis, to filter out the edge enhancing
Gaussian noise in image obtains wavelet filtering image；
S323, adaptive recursive filtering processing is executed to wavelet filtering image, to obtain adaptive recursive filtering image；
S324, change of scale enhancing processing is executed to adaptive recursive filtering image, to enhance pair of target and background in image
Than degree, obtaining contrast enhances image；
S33, blind way gray scale upper limit threshold, lower threshold is being stored in advance in grey scale pixel value in the contrast enhancing image of acquisition
All pixels in range form blind way image, and judge whether there is barrier above blind way：
If S331, have above blind way obstructions chart picture by the benchmark template of attachment above blind way and all kinds of barriers one by one
Match, successful match obtains obstacle information；
S332, range radar wave is issued, and records the time of transmitting and receives the time of back wave, by launch time, instead
The spread speed for penetrating time and range radar wave calculates at a distance between obstacle and blind person, and specific formula for calculation is：
S=(V0×T-V1×T)/2
Wherein, S is the distance between barrier and blind person, V0For range radar velocity of wave propagation, V1 is blind person's travel distance, and T is
The time of transmitting and the time for receiving back wave；
S34, picture construction mixed Gauss model is enhanced to the contrast of acquisition, while background point is carried out to the road conditions image of acquisition
Analysis obtains image background, obtains foreground image information, carries out signature analysis to foreground image information, obtains the position of traffic light
Confidence breath, and determine signal lamp state；
The histograms of oriented gradients feature of this outer analysis foreground image, and with prestore pedestrian's template matching, successful match then judges
For pedestrian, and ranging service is triggered, obtain pedestrian position information, next step is waited to broadcast to blind users；
The Harr feature for analyzing foreground image simultaneously, matches, successful match is then judged as vehicle, and triggers with car modal is prestored
Ranging service obtains vehicle position information, and next step is waited to broadcast to blind users；
The determining signal lamp state is realized by the following method：To image within the scope of traffic light according to three kinds of red, yellow, and green
Color carries out image segmentation, analyzes the edge of each cut zone, obtains shape, carries out with traffic lights template is prestored
Match, and identification is combined to traffic signals, finally determines traffic signal light condition；
The ranging service obtains pedestrian and vehicle position information using method identical with step S332；
S4, the road information that step S3 is analyzed, obstacle information and signal information, casting is used to blind person in real time
Family issues straight trip, turning, evacuation barrier and the command information by traffic light intersection in time.
2. a kind of auxiliary traveling method based on image recognition according to claim 1, which is characterized in that the S4 is also wrapped
Include following steps：
According to step S332 calculated distance, vibrating alert is set according to apart from size, it is faster apart from smaller vibration frequency,
It sustained vibration and is sounded an alarm when distance is lower than predetermined value.
3. a kind of auxiliary traveling method based on image recognition according to claim 1, which is characterized in that further include step
S5：
It is fallen by the state sensor being arranged including three-axis gyroscope and accelerometer to user or collision information carries out in fact
When monitor and record, be simultaneously emitted by warning information, do not cancel alarm in setting delay time user then automatic dialing is promptly electric
Words.
4. a kind of auxiliary travel system based on image recognition, which is characterized in that including：
Memory module enters personnel's vocal print library, acoustic pattern library, blind way gray scale upper limit threshold, lower limit threshold for pre-stored authorization
The benchmark template of value and all kinds of barriers, and store the environment speech data information of acquisition；
Voice acquisition module, for acquiring environment speech data information in real time；
Language data process module is completed to award for receiving and identifying the environment speech data information of voice acquisition module acquisition
Power enters, initialization Navigator and destination confirm, specifically includes：
Voice messaging is received, voice messaging is carried out to include speech signal samples, anti aliasing bandpass filtering pre-treatment；
Feature extraction is carried out to voice messaging after pretreatment, extracts vocal print feature information and reflection text letter in input voice
The parameters,acoustic of breath；
Vocal print feature information is matched with the information that authorization enters in personnel's vocal print library, if successful match, initialization is led
Voyage sequence, and enter in next step, otherwise prompt re-starts voice input；
The similarity between parameters,acoustic and the acoustic pattern library for storing various place nouns is calculated, maximumly by similarity
Roll-call word voice output waits user speech confirmation, if receiving confirmation signal as a purpose by the place, otherwise prompts
Re-start voice input；
Positioning device module obtains destination for obtaining user current location information, and according to determining destination information
Location information；
Communication module, the communication module are connect for providing the other modules of system with internet, real-time update storing data；
Highway route design determines algoritic module, for determining according to current location information and destination locations information planning path
Walking along the street line, specifically includes：Electronic map is recalled by communication module, road topology file is imported, using each crossing as one
Node, the walking path between node are arranged between node by grade according to two node real-time road congestion informations and are weighed as section length
Then weight positions starting point and destination coordinate, then beginning and end will be selected to be respectively matched to using node matching algorithm
In node in road, then using breadth-first search two nodes progress interconnection analysis matched to beginning and end, sentence
It is disconnected that whether connection according to the weight of setting, saves and grows, calculate optimal path if the special pulling method of Dick Si can be used with connection,
Ultimately form navigation scheme；
Real-time navigation information determining module, including video acquisition module, image analysis module, range finder module and traffic lights point
Analyse module；
The video acquisition module for acquiring blind person's direction of advance video data in real time；
Described image analysis module is specifically included for pre-processing to the video image data of acquisition：Side is executed to image
Edge enhancing processing is to obtain edge enhanced images；To edge enhanced images using at the wavelet filtering based on 2 rank Haar wavelet basis
Reason obtains wavelet filtering image to filter out the Gaussian noise in the edge enhanced images；Wavelet filtering image is executed adaptive
Recursive filtering is answered to handle, to obtain adaptive recursive filtering image；Change of scale enhancing is executed to adaptive recursive filtering image
Processing, to enhance the contrast of target and background in image, obtaining contrast enhances image；The contrast of acquisition is enhanced into image
Middle grey scale pixel value blind way gray scale upper limit threshold is stored in advance, all pixels within the scope of lower threshold form blind way image,
And judge whether there is barrier above blind way：If there is obstructions chart picture by attachment above blind way and all kinds of barriers above blind way
Benchmark template match one by one, successful match obtains obstacle information；
The range finder module records the time of transmitting and receives the time of back wave for issuing range radar wave, passes through
The spread speed of launch time, reflection interval and range radar wave calculate at a distance between obstacle and blind person, specific formula for calculation
For：
S=(V0×T-V1×T)/2
Wherein, S is the distance between barrier and blind person, V0For range radar velocity of wave propagation, V1 is blind person's travel distance, and T is
The time of transmitting and the time for receiving back wave；
The traffic lights analysis module is used to enhance the contrast of acquisition picture construction mixed Gauss model, while to obtaining
The road conditions image taken carries out context analyzer and obtains image background, obtains foreground image information, carries out feature to foreground image information
Analysis obtains the location information of traffic light, and determines signal lamp state；
Information transmits broadcasting module, and road information, obstacle information and signal information for analyzing step S3 are real
When casting to blind users, issue straight trip, turning, evacuation barrier and the command information by traffic light intersection in time.
5. a kind of auxiliary travel system based on image recognition according to claim 4, which is characterized in that described to lead in real time
Information determination module of navigating further includes moving target position determining module, and the histograms of oriented gradients for analyzing foreground image is special
Sign, and with prestore pedestrian's template matching, successful match is then judged as pedestrian, and triggers ranging service, obtain pedestrian position information,
Next step is waited to broadcast to blind users；The Harr feature for analyzing foreground image, matches, successful match with car modal is prestored
Then it is judged as vehicle, and triggers ranging service, obtain vehicle position information, next step is waited to broadcast to blind users；
The ranging service uses the range finder module in real-time navigation information determining module.
6. a kind of auxiliary travel system based on image recognition according to claim 4, which is characterized in that further include vibration
Reminding module, for according to obtained user between barrier at a distance from size vibrating alert, distance more small vibration frequency are provided
Rate is faster, sustained vibration and sounds an alarm when distance is lower than predetermined value.
7. a kind of auxiliary travel system based on image recognition according to claim 4, which is characterized in that further include urgent
Situation judges alarm module, the state sensor being provided with including three-axis gyroscope and accelerometer, for falling to user
Or collision information is monitored in real time and is recorded, and warning information is simultaneously emitted by, and does not cancel alarm in setting delay time user
Then automatic dialing emergency call.
8. a kind of auxiliary travel system based on image recognition according to claim 4, which is characterized in that the video is adopted
Collection module includes photographic device and adjustment device；
The photographic device includes main photographic device and second camera device, and the second camera device is two, respectively with master
Photographic device has a 50% superposition visual field, without superimposition between the second camera device；
The adjustment device is used to adjust the angle and direction of the video acquisition of photographic device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810700675.5A CN108844545A (en) | 2018-06-29 | 2018-06-29 | A kind of auxiliary traveling method and system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810700675.5A CN108844545A (en) | 2018-06-29 | 2018-06-29 | A kind of auxiliary traveling method and system based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108844545A true CN108844545A (en) | 2018-11-20 |
Family
ID=64200778
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810700675.5A Withdrawn CN108844545A (en) | 2018-06-29 | 2018-06-29 | A kind of auxiliary traveling method and system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108844545A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109827587A (en) * | 2019-02-25 | 2019-05-31 | 广州信沃达电子科技有限公司 | A kind of intelligent route planning system of new-energy automobile |
| CN111060074A (en) * | 2019-12-25 | 2020-04-24 | 深圳壹账通智能科技有限公司 | Navigation method, device, computer equipment and medium based on computer vision |
| CN111529324A (en) * | 2020-05-07 | 2020-08-14 | 重庆工程学院 | Blind guide instrument based on computer vision |
| CN111832356A (en) * | 2019-04-19 | 2020-10-27 | 中科寒武纪科技股份有限公司 | Information processing apparatus, method and related product |
| CN111942285A (en) * | 2020-07-10 | 2020-11-17 | 夏牧谣 | Intelligent vision-impaired person service method and system based on vehicle-mounted glass vibration feedback |
| CN112650300A (en) * | 2021-01-07 | 2021-04-13 | 深圳市君航品牌策划管理有限公司 | Unmanned aerial vehicle obstacle avoidance method and device |
| TWI799807B (en) * | 2021-03-09 | 2023-04-21 | 翼允禎 | speed warning |
| CN116698045A (en) * | 2023-08-02 | 2023-09-05 | 国政通科技有限公司 | Walking auxiliary navigation method and system for vision disturbance people in nursing home |
| CN117589177A (en) * | 2024-01-18 | 2024-02-23 | 青岛创新奇智科技集团股份有限公司 | Autonomous navigation method based on industrial large model |
-
2018
- 2018-06-29 CN CN201810700675.5A patent/CN108844545A/en not_active Withdrawn
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109827587B (en) * | 2019-02-25 | 2023-01-17 | 三明学院 | Intelligent route planning system for new energy automobile |
| CN109827587A (en) * | 2019-02-25 | 2019-05-31 | 广州信沃达电子科技有限公司 | A kind of intelligent route planning system of new-energy automobile |
| CN111832356A (en) * | 2019-04-19 | 2020-10-27 | 中科寒武纪科技股份有限公司 | Information processing apparatus, method and related product |
| WO2021128834A1 (en) * | 2019-12-25 | 2021-07-01 | 深圳壹账通智能科技有限公司 | Navigation method and apparatus based on computer vision, computer device, and medium |
| CN111060074A (en) * | 2019-12-25 | 2020-04-24 | 深圳壹账通智能科技有限公司 | Navigation method, device, computer equipment and medium based on computer vision |
| CN111529324A (en) * | 2020-05-07 | 2020-08-14 | 重庆工程学院 | Blind guide instrument based on computer vision |
| CN111942285A (en) * | 2020-07-10 | 2020-11-17 | 夏牧谣 | Intelligent vision-impaired person service method and system based on vehicle-mounted glass vibration feedback |
| CN112650300A (en) * | 2021-01-07 | 2021-04-13 | 深圳市君航品牌策划管理有限公司 | Unmanned aerial vehicle obstacle avoidance method and device |
| CN112650300B (en) * | 2021-01-07 | 2024-05-24 | 深圳市智胜联合科技有限公司 | Unmanned aerial vehicle obstacle avoidance method and device |
| TWI799807B (en) * | 2021-03-09 | 2023-04-21 | 翼允禎 | speed warning |
| CN116698045A (en) * | 2023-08-02 | 2023-09-05 | 国政通科技有限公司 | Walking auxiliary navigation method and system for vision disturbance people in nursing home |
| CN116698045B (en) * | 2023-08-02 | 2023-11-10 | 国政通科技有限公司 | Walking auxiliary navigation method and system for vision disturbance people in nursing home |
| CN117589177A (en) * | 2024-01-18 | 2024-02-23 | 青岛创新奇智科技集团股份有限公司 | Autonomous navigation method based on industrial large model |
| CN117589177B (en) * | 2024-01-18 | 2024-04-05 | 青岛创新奇智科技集团股份有限公司 | Autonomous navigation method based on industrial large model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108844545A (en) | A kind of auxiliary traveling method and system based on image recognition | |
| CN108743266A (en) | A kind of blindmen intelligent navigation avoidance trip householder method and system | |
| CN109031306A (en) | A kind of navigation methods and systems for disturbance people | |
| CN108871340A (en) | One kind is based on real-time road condition information optimization blind-guiding method and system | |
| CN108670747A (en) | A kind of blindmen intelligent auxiliary traveling method and system | |
| CN108836770A (en) | Real Time Obstacle Avoiding optimization guide monitoring method and system under a kind of actual traffic environment | |
| CN109059920A (en) | A kind of blind traffic safety monitoring intelligent navigation methods and systems | |
| CN109044754A (en) | A kind of intelligent blind men navigation method and system | |
| CN108670745A (en) | A kind of blind man navigation method and system based on speech recognition access | |
| CN105496740B (en) | A kind of intelligent blind-guiding device and the blind-guiding stick for being provided with the device | |
| CN108417087B (en) | Vehicle safe passing system and method | |
| US11860639B2 (en) | Vehicle-based road obstacle identification system | |
| CN108743265A (en) | A kind of blind-guiding method and system for public transport road | |
| RU2719499C1 (en) | Method, device and railway vehicle, in particular, rail vehicle, for recognition of obstacles in railway connection, in particular in rail connection | |
| CN102973395B (en) | Multifunctional intelligent blind guiding method, processor and multifunctional intelligent blind guiding device | |
| US20210209942A1 (en) | On-board vehicle stop cause determination system | |
| US11473917B2 (en) | System for augmenting autonomous vehicle perception using smart nodes | |
| CN114995451A (en) | Control method, road side equipment and system for cooperative automatic driving of vehicle and road | |
| CN101391589A (en) | Vehicle intelligent alarming method and device | |
| US11403943B2 (en) | Method and system for vehicle navigation using information from smart node | |
| US20220017115A1 (en) | Smart node network for autonomous vehicle perception augmentation | |
| CN108877269A (en) | A kind of detection of intersection vehicle-state and V2X broadcasting method | |
| CN108670746A (en) | A kind of high resolution path optimization intelligent monitoring blind-guiding method and system | |
| JP2004171159A (en) | Road environment information reporting apparatus, on-board annunciator, device inside information center, and road environment information reporting program | |
| US20220019225A1 (en) | Smart node for autonomous vehicle perception augmentation |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181120 |