CN106651873B - One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes - Google Patents
One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes Download PDFInfo
- Publication number
- CN106651873B CN106651873B CN201611049926.5A CN201611049926A CN106651873B CN 106651873 B CN106651873 B CN 106651873B CN 201611049926 A CN201611049926 A CN 201611049926A CN 106651873 B CN106651873 B CN 106651873B
- Authority
- CN
- China
- Prior art keywords
- zebra stripes
- camera
- rgb
- depth
- region
- 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
Classifications
-
- G—PHYSICS
- G02—OPTICS
- G02C—SPECTACLES; SUNGLASSES OR GOGGLES INSOFAR AS THEY HAVE THE SAME FEATURES AS SPECTACLES; CONTACT LENSES
- G02C11/00—Non-optical adjuncts; Attachment thereof
- G02C11/10—Electronic devices other than hearing aids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Acoustics & Sound (AREA)
- General Health & Medical Sciences (AREA)
- Otolaryngology (AREA)
- General Physics & Mathematics (AREA)
- Ophthalmology & Optometry (AREA)
- Optics & Photonics (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses one kind to detect glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes.The glasses obtain the attitude angle information of camera using attitude angle transducer using RGB-D camera acquisition color image and depth image.Compact processor calculates the three-dimensional coordinate for obtaining scene according to depth information and attitude angle information.Compact processor handles three-dimensional information, removes the interference that aerial object detects zebra stripes in color image.Compact processor calculates each piece of bipolarity to color image piecemeal, filter out may be zebra stripes block, utilize connected domain analysis to detect zebra stripes region.This method is assisted eventually by the distance and direction of bone conduction earphone transmitting zebra stripes to visually impaired people, can meet the needs of visually impaired people predicts zebra stripes well.
Description
Technical field
The invention belongs to visually impaired people's ancillary technique, three-dimensional environment cognition technology, zebra stripes detection technique, stereo interactions
Technical field, more particularly to it is a kind of based on RGB-D camera and stereosonic visually impaired people's zebra stripes detection glasses, utilize RGB-D
Camera acquires color image and depth image, and the attitude angle information of camera is obtained using attitude angle transducer.Compact processor benefit
With depth information and attitude angle information, the three-dimensional coordinate for obtaining scene is calculated.Compact processor handles three-dimensional information, goes
Except the interference that aerial object detects zebra stripes in color image.Compact processor calculates each piece to color image piecemeal
Bipolarity, filter out may be zebra stripes block, using connected domain analysis detect zebra stripes region, passed eventually by bone
The distance of guide lug machine transmitting zebra stripes and direction are assisted to visually impaired people.
Background technique
It is counted according to world health organization, there are 2.85 hundred million dysopia personages in the whole world.Visually impaired people has lost normally
Vision, all highly difficult to the understanding of color, shape, distance, movement, their live in daily life, trip etc. all receives
Tremendous influence.The especially passage at crossing finds zebra stripes region, and crossing the street in security is the big pain spot of visually impaired people.
Traditional visually impaired people goes across the road householder method, by listening the sound of the variation of traffic lights at crossing, and listens road
Mouthful vehicle by sound guess zebra stripes region, this judgement is extremely inaccurate, and the traffic lights at many crossings
The damage of sound broadcasting system, can not provide help to visually impaired people.
Seeing-eye dog can go across the road for visually impaired people and provide help, but seeing-eye dog is rapider when going across the road, it is difficult to shine
Care for the demand that visually impaired people is accurately positioned zebra stripes region.The maintenance of seeing-eye dog, training expenses are high, and average family is difficult to hold
Load.In addition the seeing-eye dog training in many cities is underproof, limited to the help of visually impaired people.
Zebra stripes detection based on color camera, there is very the standard that maximum probability is interfered by aerial object etc., and zebra stripes detect
True property is limited, nor can know the accurate distance and orientation in zebra stripes region, limited to the help of visually impaired people.
The interactive mode of traditional visually impaired people's auxiliary mainly has voice prompting, tactile vibration.Semanteme prompt usually casting letter
Short information, needs the regular hour to play, and causes delay and accident risk, and transferable information content is few.Tactile vibration
It is hardware by vibration waistband or vibration vest, the problem of prompting some azimuth informations to shake, can solve delay, but
Burden is brought to visually impaired people, the wearing feeling of different people is by difference.
Summary of the invention
In view of the above-mentioned deficiencies in the prior art, it is an object of the present invention to provide a kind of based on RGB-D camera and stereosonic view
Hinder personage's zebra stripes and detects glasses.
The purpose of the present invention is what is be achieved through the following technical solutions: a kind of based on RGB-D camera and stereosonic visually impaired
Personage's zebra stripes detect glasses, and the glasses include lens body and a RGB-D camera being fixed on lens body,
One attitude angle transducer, a usb hub, a compact processor, a bone conduction earphone module, two osteoacusis shakes
Dynamic model block and a battery module.The RGB-D camera is fixed on above eyeglass, and two osteoacusis vibration moulds are located at two
Place to the rear among mirror pin is bonded in front of blind person's ear at skull;Usb hub, attitude angle transducer and compact processor are embedded in
In one mirror pin;Bone conduction earphone module and battery module are in another mirror pin;RGB-D camera and attitude angle transducer are logical
It crosses usb hub to be connected with compact processor, battery module is connected with compact processor;Two osteoacusis shock modules pass through
Bone conduction earphone module is connected with compact processor.RGB-D camera acquires the color image and depth map of three-dimensional scenic in real time
Picture.Attitude angle transducer obtains the attitude angle of RGB-D camera in real time.The color image that compact processor acquires RGB-D camera
And depth image, the attitude angle information of attitude angle transducer acquisition are analyzed, and detect the zebra stripes region of three-dimensional scenic, and
Zebra stripes region and direction are calculated, and converts stereo signal for processing result, passes to bone conduction earphone module.Osteoacusis
Stereo signal is converted osteoacusis vibration signal by handset module, passes to two osteoacusis shock modules.Final osteoacusis shake
Dynamic model block gives user visually impaired by vibration transmission stereo signal, informs the region in zebra stripes region in user's current scene visually impaired
The direction and.
The zebra line detecting method of above-mentioned glasses is as follows:
(1) camera calibration is carried out to RGB-D camera, obtains the focal length f, principle point location (c of RGB-D camerax,cy)。
(2) the depth image Depth and color image Color of RGB-D camera acquisition three-dimensional scenic.
(3) the corner Angle of attitude angle transducer acquisition tri- axis direction of RGB-D camera X, Y, ZX, AngleY, AngleZ。
(4) usb hub is by depth image Depth, color image Color, the corner Angle of three axis directionsX, AngleY,
AngleZIt is transmitted to compact processor.
(5) compact processor is according to depth image Depth, the focal length f of RGB-D camera, principle point location (cx,cy), it can calculate
Three-dimensional coordinate (X of the every bit under camera coordinates system outc,Yc,Zc).Some coordinates are (u, v), depth in depth image Depth
Angle value is depth, then three-dimensional coordinate (X under camera coordinates systemc,Yc,Zc) can be calculated by formula (1):
(6) three-dimensional coordinate (X according to every bit in depth image under camera coordinates systemc,Yc,Zc) and attitude angle biography
The corner of three axis direction of sensor is distributed as AngleX=α, AngleY=β, AngleZ=γ can then be calculated each by formula (2)
Three-dimensional coordinate (X of the point under world coordinate systemw,Yw,Zw):
(7) the height value H of horizontal plane can be by the world coordinate system where the every bit in three-dimensional scenic to RGB-D camera
Under three-dimensional coordinate component YwIt indicates.
(8) pass through the component Y of all the points in depth image DepthwEach point is identified, YwIn (H0-Δh,H0+Δ
H) it then indicates that the point is the point on ground in, is otherwise non-ground points;Wherein, H0For the vertical height of RGB-D camera to horizontal plane
Degree, Δ h are generally 0.1 meter;The color of non-ground points in color image Color is set to Transparent color, acquisition leaves behind Horizon
The color image Color of point on faceG, that is, remove the interference that aerial object detects zebra stripes.
(9) the color image Color to the point left behind on ground levelGIt is divided into the fritter that size is M × N, and M, N are equal
Greater than the width of zebra stripes.
(10) adaptive binarization of gray value processing is carried out to each fritter, obtains the binarization threshold of the small images, it will
The all pixels of fritter are divided into two parts.The pixel grey scale of first part is lower than threshold value, and the average gray of these pixels is μ1, account for
The ratio of all pixels is α, and the pixel grey scale of second part is more than or equal to threshold value, and the average gray of these pixels is μ2, account for institute
The ratio for having pixel is 1- α.The gray variance of all pixels is in fritterTo can define a bipolarity γ, indicate
In white and black degree of fritter, bipolarity γ can be calculated by formula (3):
The variation range of bipolarity γ is 0~1, and bipolarity γ is bigger, closer in white and black zebra line pattern.
(11) to each fritter, if bipolarity γ is greater than threshold value threshold, (value range of the threshold value is usual
It is 0.85~0.95), then this small image block is the candidate region of zebra stripes.
(12) connected domain analysis is carried out to the candidate regions of all zebra stripes, remove some scrappy fritters (i.e. not with its
The fritter of his candidate region connection), the fritter of connection forms a monolith zebra stripes region.
(13) according to the three-dimensional coordinate (X of every bit in the zebra stripes regionw,Yw,Zw), it can get zebra stripes region to view
Barrier user distance be(by the mean depth of all the points in zebra stripes regionIndicate), the deflection θ in zebra stripes region
(by the average level coordinate at zebra stripes region midpointWith mean depthQuotient arc tangent indicate, i.e.,
(14) zebra stripes region, the distance in zebra stripes region are indicated with a kind of musical instrument of special tamberIt is bigger, then should
The loudness Volume of musical instrument is bigger.The sounding of the musical instrument be it is stereo, stereo direction is opposite with the deflection θ in zebra stripes region
It answers.The optional piano of musical instrument, violin, gong, trumpet, xylophone etc. have special tone color and melodious.
(15) stereo signal is transmitted to bone conduction earphone module by compact processor.
(16) stereo signal is switched to osteoacusis vibration signal by bone conduction earphone module.
(17) osteoacusis signal is passed to user visually impaired by osteoacusis shock module.
This method is essentially consisted in compared to the advantage of previous visually impaired people's householder method:
1, distance and the direction in zebra stripes region be can detecte out.Due to carrying out zebra stripes region using RGB-D camera
Detection, can know three-dimensional information, thus can detect zebra stripes region to user visually impaired distance, and user's visually impaired
What orientation, this provides a great convenience and helps in the passage of the outdoor scenes such as crossing for visually impaired people.
2, can removing aerial object etc., other are not the interference that the object of ground region detects zebra stripes.Due to using
RGB-D camera and attitude angle transducer, can get scene in object true height value, therefore can only to ground level near
The image of altitude range detected, will not be zebra stripes by aerial object error detection, this is very big to improve zebra stripes inspection
The accuracy and reliability of survey facilitates visually impaired people and accurately judges and pass through at crossing.
3, processing speed is fast.Since this method eliminates many interference in color image using three-dimensional information, eliminate
Processing to these regions, and need to only calculate bipolarity of block image etc. during detecting zebra stripes and simply grasp
Make, therefore calculation amount is small, processing speed is fast, can timely export as a result, and feeding back to visually impaired people to assist.
4, someone or there is vehicle that can also timely respond on zebra stripes region.Since someone on zebra stripes region or vehicle pass through
When, these will not be removed in the point of height above ground level range, therefore can generate variation in detection result, pass to visually impaired people
Stereo signal can also change, visually impaired people is so as to judge that zebra stripes region is occupied by people or vehicle, early warning spot
The collision of pedestrian, vehicle on horse line.
5, visually impaired people can be helped to go across the road naturally.It is three-dimensional because visually impaired people is remoter with a distance from zebra stripes region
The loudness of sound is bigger, and the distance in zebra stripes region is closer, and stereosonic loudness is smaller.Therefore visually impaired people is far from zebra stripes area
Domain can recognize the orientation in zebra stripes region, and sound intensity is big at this time, and visually impaired people can be very accurate to location discrimination.And work as
For visually impaired people when close to zebra stripes region, sound intensity is small, only prompts visually impaired people in correct travelling route, will not
Biggish interference is caused to the ears of visually impaired people.The excessive variation of the size of sound intensity can be assisted naturally enough visually impaired
Personage goes across the road.
6, ears are not take up.This method delivers a signal to visually impaired people using bone conduction earphone, does not interfere visually impaired people to exist
Road conditions listen to extraneous sound when current.For example visually impaired people can judge that two sides are close either with or without automobile by the sound of wagon flow.
7, both hands are not take up.This method use RGB-D camera, attitude angle transducer and compact processor, be all it is portable and
Wearable, very big burden will not be brought to user visually impaired, take auxiliary tool with hand without visually impaired people.
Detailed description of the invention
Fig. 1 is the module connection diagram of visually impaired people's zebra stripes detection system;
Fig. 2 is the structural schematic diagram of visually impaired people's zebra stripes detection system;
Fig. 3 is zebra stripes region detection effect grayscale image;
Fig. 4 is zebra stripes region detection effect grayscale image;
Fig. 5 is zebra stripes region detection effect grayscale image.
Specific embodiment
As shown in Fig. 2, a kind of detect glasses, the glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes
Include lens body and a RGB-D camera being fixed on lens body, an attitude angle transducer, a USB set line
Device, a compact processor, a bone conduction earphone module, two osteoacusis shock modules and a battery module.It is described
RGB-D camera is fixed on above eyeglass, and two osteoacusis vibration moulds are located at place to the rear among two mirror pins, is bonded blind person's ear
In front of piece at skull;Usb hub, attitude angle transducer and compact processor are in a mirror pin;Bone conduction earphone module
With battery module in another mirror pin;
As shown in Figure 1, RGB-D camera is connected by usb hub with compact processor with attitude angle transducer, battery mould
Block is connected with compact processor;Two osteoacusis shock modules pass through bone conduction earphone module and are connected with compact processor.
RGB-D camera acquires the color image and depth image of three-dimensional scenic in real time.Attitude angle transducer obtains RGB-D camera in real time
Attitude angle.The color image and depth image that compact processor acquires RGB-D camera, the posture of attitude angle transducer acquisition
Angle information is analyzed, and detects the zebra stripes region of three-dimensional scenic, and calculates zebra stripes region and direction, and processing is tied
Fruit is converted into stereo signal, passes to bone conduction earphone module.Stereo signal is converted osteoacusis by bone conduction earphone module
Vibration signal passes to two osteoacusis shock modules.Final osteoacusis shock module is by vibration transmission stereo signal to view
Hinder user, informs the region and direction in zebra stripes region in user's current scene visually impaired.
The zebra line detecting method of above system is as follows:
(1) camera calibration is carried out to RGB-D camera, obtains the focal length f, principle point location (c of RGB-D camerax,cy)。
(2) the depth image Depth and color image Color of RGB-D camera acquisition three-dimensional scenic.
(3) the corner Angle of attitude angle transducer acquisition tri- axis direction of RGB-D camera X, Y, ZX, AngleY, AngleZ。
(4) usb hub is by depth image Depth, color image Color, the corner Angle of three axis directionsX, AngleY,
AngleZIt is transmitted to compact processor.
(5) compact processor is according to depth image Depth, the focal length f of RGB-D camera, principle point location (cx,cy), it can calculate
Three-dimensional coordinate (X of the every bit under camera coordinates system outc,Yc,Zc).Some coordinates are (u, v), depth in depth image Depth
Angle value is depth, then three-dimensional coordinate (X under camera coordinates systemc,Yc,Zc) can be calculated by formula (1):
(6) three-dimensional coordinate (X according to every bit in depth image under camera coordinates systemc,Yc,Zc) and attitude angle biography
The corner of three axis direction of sensor is distributed as AngleX=α, AngleY=β, AngleZ=γ can then be calculated each by formula (2)
Three-dimensional coordinate (X of the point under world coordinate systemw,Yw,Zw):
(7) the height value H of horizontal plane can be by the world coordinate system where the every bit in three-dimensional scenic to RGB-D camera
Under three-dimensional coordinate component YwIt indicates.
(8) pass through the component Y of all the points in depth image DepthwEach point is identified, YwIn (H0-Δh,H0+Δ
H) it then indicates that the point is the point on ground in, is otherwise non-ground points;Wherein, H0For the vertical height of RGB-D camera to horizontal plane
Degree, Δ h are generally 0.1 meter;The color of non-ground points in color image Color is set to Transparent color, acquisition leaves behind Horizon
The color image Color of point on faceG, that is, remove the interference that aerial object detects zebra stripes.
(9) the color image Color to the point left behind on ground levelGIt is divided into the fritter that size is M × N, and M, N are equal
Greater than the width of zebra stripes.
(10) adaptive binarization of gray value processing is carried out to each fritter, obtains the binarization threshold of the small images, it will
The all pixels of fritter are divided into two parts.The pixel grey scale of first part is lower than threshold value, and the average gray of these pixels is μ1, account for
The ratio of all pixels is α, and the pixel grey scale of second part is more than or equal to threshold value, and the average gray of these pixels is μ2, account for institute
The ratio for having pixel is 1- α.The gray variance of all pixels is in fritterTo can define a bipolarity γ, indicate
In white and black degree of fritter, bipolarity γ can be calculated by formula (3):
The variation range of bipolarity γ is 0~1, and bipolarity γ is bigger, closer in white and black zebra line pattern.
(11) to each fritter, if bipolarity γ is greater than threshold value threshold, (value range of the threshold value is usually
0.85~0.95), then this small image block be zebra stripes candidate region.
(12) connected domain analysis is carried out to the candidate regions of all zebra stripes, remove some scrappy fritters (i.e. not with its
The fritter of his candidate region connection), the fritter of connection forms a monolith zebra stripes region.
(13) according to the three-dimensional coordinate (X of every bit in the zebra stripes regionw,Yw,Zw), it can get zebra stripes region to view
Barrier user distance be(by the mean depth of all the points in zebra stripes regionIndicate), the deflection θ in zebra stripes region
(by the average level coordinate at zebra stripes region midpointWith mean depthQuotient arc tangent indicate, i.e.,
(14) zebra stripes region, the distance in zebra stripes region are indicated with a kind of musical instrument of special tamberIt is bigger, then should
The loudness Volume of musical instrument is bigger.The sounding of the musical instrument be it is stereo, stereo direction is opposite with the deflection θ in zebra stripes region
It answers.The optional piano of musical instrument, violin, gong, trumpet, xylophone etc. have special tone color and melodious.
(15) stereo signal is transmitted to bone conduction earphone module by compact processor.
(16) stereo signal is switched to osteoacusis vibration signal by bone conduction earphone module.
(17) osteoacusis signal is passed to user visually impaired by osteoacusis shock module.
Claims (1)
1. one kind detects glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes, the glasses include lens body,
And it is fixed on a RGB-D camera on lens body, an attitude angle transducer, a usb hub, a small-sized place
Manage device, a bone conduction earphone module, two osteoacusis shock modules and a battery module;The RGB-D camera is fixed on
Above eyeglass, two osteoacusis shock modules are located at place to the rear among two mirror pins, cranium in front of fitting visually impaired people's ear
At bone;Usb hub, attitude angle transducer and compact processor are in a mirror pin;Bone conduction earphone module and battery mould
Block is in another mirror pin;RGB-D camera is connected by usb hub with compact processor with attitude angle transducer, battery
Module is connected with compact processor;Two osteoacusis shock modules pass through bone conduction earphone module and are connected with compact processor;
RGB-D camera acquires the color image and depth image of three-dimensional scenic in real time;Attitude angle transducer obtains RGB-D camera in real time
Attitude angle;The color image and depth image that compact processor acquires RGB-D camera, the posture of attitude angle transducer acquisition
Angle information is analyzed, and detects the zebra stripes region of three-dimensional scenic, and calculates zebra stripes region and direction, and processing is tied
Fruit is converted into stereo signal, passes to bone conduction earphone module;Stereo signal is converted osteoacusis by bone conduction earphone module
Vibration signal passes to two osteoacusis shock modules;Final osteoacusis shock module is by vibration transmission stereo signal to view
Hinder user, informs the region and direction in zebra stripes region in user's current scene visually impaired;The glasses are by the following method to view
Hinder personage and carry out intelligent auxiliary:
(1) camera calibration is carried out to RGB-D camera, obtains the focal length f, principle point location (c of RGB-D camerax,cy);
(2) the depth image Depth and color image Color of RGB-D camera acquisition three-dimensional scenic;
(3) the corner Angle of attitude angle transducer acquisition tri- axis direction of RGB-D camera X, Y, ZX, AngleY, AngleZ;
(4) usb hub is by depth image Depth, color image Color, the corner Angle of three axis directionsX, AngleY,
AngleZIt is transmitted to compact processor;
(5) compact processor is according to depth image Depth, the focal length f of RGB-D camera, principle point location (cx,cy), it can calculate every
Some three-dimensional coordinate (X under camera coordinates systemc,Yc,Zc);Some coordinates are (u, v), depth value in depth image Depth
For depth, then three-dimensional coordinate (X under camera coordinates systemc,Yc,Zc) can be calculated by formula (1):
(6) three-dimensional coordinate (X according to every bit in depth image under camera coordinates systemc,Yc,Zc) and attitude angle transducer
The corner of three axis directions is distributed as AngleX=α, AngleY=β, AngleZ=γ then can calculate every bit by formula (2) and exist
Three-dimensional coordinate (X under world coordinate systemw,Yw,Zw):
(7) the height value H of horizontal plane can be by under the world coordinate system where the every bit in three-dimensional scenic to RGB-D camera
The component Y of three-dimensional coordinatewIt indicates;
(8) pass through the component Y of all the points in depth image DepthwEach point is identified, YwIn (H0-Δh,H0In+Δ h)
It then indicates that the point is the point on ground, is otherwise non-ground points;Wherein, H0For the vertical height of RGB-D camera to horizontal plane, Δ
H is 0.1 meter;The color of non-ground points in color image Color is set to Transparent color, obtains the point left behind on ground level
Color image ColorG, that is, remove the interference that aerial object detects zebra stripes;
(9) the color image Color to the point left behind on ground levelGIt is divided into the fritter that size is M × N, and M, N are all larger than
The width of zebra stripes;
(10) adaptive binarization of gray value processing is carried out to each fritter, the binarization threshold of the small images is obtained, by fritter
All pixels be divided into two parts;The pixel grey scale of first part is lower than threshold value, and the average gray of these pixels is μ1, Zhan Suoyou
The ratio of pixel is α, and the pixel grey scale of second part is more than or equal to threshold value, and the average gray of these pixels is μ2, account for all pictures
The ratio of element is 1- α;The gray variance of all pixels is in fritterTo can define a bipolarity γ, fritter is indicated
In white and black degree, bipolarity γ can calculate by formula (3):
The variation range of bipolarity γ is 0~1, and bipolarity γ is bigger, closer in white and black zebra line pattern;
(11) to each fritter, if bipolarity γ is greater than threshold value threshold, the value range of the threshold value is usually 0.85
~0.95, then this small image block is the candidate region of zebra stripes;
(12) connected domain analysis is carried out to the candidate region of all zebra stripes, removes some scrappy fritters, i.e., do not waited with other
The fritter of the fritter of favored area connection, connection forms a monolith zebra stripes region;
(13) according to the three-dimensional coordinate (X of every bit in the zebra stripes regionw,Yw,Zw), it can get zebra stripes region to use visually impaired
The distance at familyWith the deflection θ in zebra stripes region;It is indicated by the mean depth of all the points in zebra stripes region, zebra stripes
The deflection θ in region by zebra stripes region midpoint average level coordinateWith mean depthQuotient arc tangent indicate, i.e.,
(14) zebra stripes region, the distance in zebra stripes region are indicated with a kind of musical instrument of special tamberIt is bigger, then the musical instrument
Loudness Volume it is bigger;The sounding of the musical instrument be it is stereo, stereo direction is corresponding with the deflection θ in zebra stripes region;
(15) stereo signal is transmitted to bone conduction earphone module by compact processor;
(16) stereo signal is switched to osteoacusis vibration signal by bone conduction earphone module;
(17) osteoacusis signal is passed to user visually impaired by osteoacusis shock module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611049926.5A CN106651873B (en) | 2016-11-23 | 2016-11-23 | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611049926.5A CN106651873B (en) | 2016-11-23 | 2016-11-23 | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106651873A CN106651873A (en) | 2017-05-10 |
CN106651873B true CN106651873B (en) | 2019-11-22 |
Family
ID=58811878
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611049926.5A Active CN106651873B (en) | 2016-11-23 | 2016-11-23 | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106651873B (en) |
Families Citing this family (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
TWI643498B (en) * | 2018-01-02 | 2018-12-01 | 元智大學 | Method and image capture device for computing a lens angle in a single image |
CN108764150A (en) * | 2018-05-29 | 2018-11-06 | 杭州视氪科技有限公司 | A kind of blind person's auxiliary eyeglasses for the detection of zebra line style crossing |
CN108805060A (en) * | 2018-05-29 | 2018-11-13 | 杭州视氪科技有限公司 | A kind of zebra line style crossing detection method |
CN111031468B (en) * | 2019-11-13 | 2021-02-05 | 电子科技大学 | Visual auxiliary method and device based on individualized HRTF stereo |
CN111932866A (en) * | 2020-08-11 | 2020-11-13 | 中国科学技术大学先进技术研究院 | Wearable blind person outdoor traffic information sensing equipment |
CN114419697B (en) * | 2021-12-23 | 2022-12-02 | 北京深睿博联科技有限责任公司 | Vision-impaired person prompting method and device based on mechanical vibration |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104287946A (en) * | 2014-10-24 | 2015-01-21 | 中国科学院计算技术研究所 | Device and method for prompting blind persons to avoid obstacles |
CN104899869A (en) * | 2015-05-14 | 2015-09-09 | 浙江大学 | Plane and barrier detection method based on RGB-D camera and attitude sensor |
CN204744865U (en) * | 2015-06-08 | 2015-11-11 | 深圳市中科微光医疗器械技术有限公司 | Device for environmental information around reception and registration of visual disability personage based on sense of hearing |
CN105267014A (en) * | 2015-09-22 | 2016-01-27 | 西交利物浦大学 | Depth map-based auxiliary walking device for blind and auxiliary method thereof |
CN105761235A (en) * | 2014-12-19 | 2016-07-13 | 天津市巨海机电设备安装有限公司 | Vision auxiliary method converting vision information to auditory information |
-
2016
- 2016-11-23 CN CN201611049926.5A patent/CN106651873B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104287946A (en) * | 2014-10-24 | 2015-01-21 | 中国科学院计算技术研究所 | Device and method for prompting blind persons to avoid obstacles |
CN105761235A (en) * | 2014-12-19 | 2016-07-13 | 天津市巨海机电设备安装有限公司 | Vision auxiliary method converting vision information to auditory information |
CN104899869A (en) * | 2015-05-14 | 2015-09-09 | 浙江大学 | Plane and barrier detection method based on RGB-D camera and attitude sensor |
CN204744865U (en) * | 2015-06-08 | 2015-11-11 | 深圳市中科微光医疗器械技术有限公司 | Device for environmental information around reception and registration of visual disability personage based on sense of hearing |
CN105267014A (en) * | 2015-09-22 | 2016-01-27 | 西交利物浦大学 | Depth map-based auxiliary walking device for blind and auxiliary method thereof |
Also Published As
Publication number | Publication date |
---|---|
CN106651873A (en) | 2017-05-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106651873B (en) | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes | |
CN106203390B (en) | A kind of intelligent blind auxiliary system | |
CN106859929B (en) | A kind of Multifunctional blind person guiding instrument based on binocular vision | |
CN106597690B (en) | One kind predicting glasses based on RGB-D camera and stereosonic visually impaired people's access | |
CN106214437B (en) | A kind of intelligent blind auxiliary eyeglasses | |
CN106265004A (en) | Multi-sensor intelligent blind person's guiding method and device | |
CN109383525A (en) | Driver status grasps device, driver status grasps system and method | |
CN107341789B (en) | System and method for predicting pathway of visually impaired people based on RGB-D camera and stereo | |
CN108545019A (en) | A kind of safety driving assist system and method based on image recognition technology | |
CN106846350B (en) | One kind is based on RGB-D camera and stereosonic visually impaired people's barrier early warning system and method | |
WO2022041869A1 (en) | Road condition prompt method and apparatus, and electronic device, storage medium and program product | |
CN106821692B (en) | One kind is based on RGB-D camera and stereosonic visually impaired people's stair detection system and method | |
CN106412394A (en) | Safe travel device suitable for phubbing on roads | |
CN109087485A (en) | Assisting automobile driver method, apparatus, intelligent glasses and storage medium | |
CN109730910A (en) | Vision-aided system and its ancillary equipment, method, the readable storage medium storing program for executing of trip | |
CN106915303B (en) | Automobile A-column blind area perspective method based on depth data and fish eye images | |
CN101234601A (en) | Automobile cruise control method based on monocular vision and implement system thereof | |
CN106817577A (en) | One kind is based on RGB D cameras and stereosonic visually impaired people's barrier early warning glasses | |
CN105686936A (en) | Sound coding interaction system based on RGB-IR camera | |
TW201927610A (en) | Safety confirmation evaluating device, on-vehicle device, safety confirmation evaluation system having the two, safety confirmation evaluation method, and safety confirmation evaluation program | |
CN107049717B (en) | One kind is based on RGB-D camera and stereosonic visually impaired people's zebra stripes detection system and method | |
CN105701811A (en) | Sound coding interaction method based on RGB-IR camera | |
CN210078040U (en) | Intelligent blind guiding device | |
JP4375879B2 (en) | Walking support system and information recording medium for the visually impaired | |
CN207502722U (en) | Vehicle and vehicle sensory perceptual system |
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 | ||
CB02 | Change of applicant information |
Address after: 9, 181, 310000, Wuchang Road, Wuchang Street, Yuhang District, Zhejiang, Hangzhou, 202-7 Applicant after: Hangzhou vision krypton Technology Co., Ltd. Address before: Room 589, C building, No. 525 Xixi Road, Xihu District, Zhejiang, Hangzhou 310012, China Applicant before: Hangzhou vision krypton Technology Co., Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |