CN106821693B - One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's stair - Google Patents
One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's stair Download PDFInfo
- Publication number
- CN106821693B CN106821693B CN201611048783.6A CN201611048783A CN106821693B CN 106821693 B CN106821693 B CN 106821693B CN 201611048783 A CN201611048783 A CN 201611048783A CN 106821693 B CN106821693 B CN 106821693B
- Authority
- CN
- China
- Prior art keywords
- stair
- camera
- depth
- rgb
- plane
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H3/00—Appliances for aiding patients or disabled persons to walk about
- A61H3/06—Walking aids for blind persons
- A61H3/061—Walking aids for blind persons with electronic detecting or guiding means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/016—Input arrangements with force or tactile feedback as computer generated output to the user
-
- 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 Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Veterinary Medicine (AREA)
- Life Sciences & Earth Sciences (AREA)
- Rehabilitation Therapy (AREA)
- Human Computer Interaction (AREA)
- Physical Education & Sports Medicine (AREA)
- Pain & Pain Management (AREA)
- Epidemiology (AREA)
- Multimedia (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses one kind based on RGB-D camera and stereosonic visually impaired people's stair detection system and method.This method utilizes RGB-D camera sampling depth image, and the attitude angle information of camera is obtained using attitude angle transducer.Compact processor utilizes depth information and attitude angle information, it calculates and obtains three-dimensional coordinate and surface normal information, the plane in three-dimensional scenic is extracted using surface normal information, differentiate and whether there is stair in current scene, if there is stair, distance and the direction for then calculating every level-one stair, finally pass to visually impaired people using bone conduction earphone and assist, and can meet the needs of visually impaired people predicts stair well.
Description
Technical field
The invention belongs to visually impaired people's ancillary technique, three-dimensional environment cognition technology, stair detection technique, stereo interactive skills
Art field is related to a kind of based on RGB-D camera and stereosonic visually impaired people's stair detection glasses.
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.
Traditional visually impaired people's auxiliary tool such as bland person walking stick, visually impaired people need to move repeatedly walking stick, are just only capable of
The case where knowing foot side, in stair activity, the use of bland person walking stick is also inconvenient.
Seeing-eye dog can provide help for visually impaired people, but seeing-eye dog is rapider in stair activity, it is difficult to look after
Visually impaired people is accurately positioned the demand of every level-one stair.The maintenance of seeing-eye dog, training expenses are high, and average family is difficult to undertake.
Bionic eye can help visually impaired people's recovered part vision, but bionic eye can only help visually impaired people to see low resolution
The gray level image of rate, it is difficult to distinguish stair and other scenes.Bionic eye, which is only applicable to retinal pigment degeneration, leads to the blind of blindness
People.
Ultrasonic technology, laser ranging technique etc. can provide the function of ranging and barrier early warning, but can not reflect field
The information of scape cannot be distinguished stair and other barriers or road conditions, and be easy by environmental disturbances, and power consumption is big.
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 stair 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 stair detect glasses, and the glasses include lens body, an and RGB-D camera being fixed on lens body, and one
A attitude angle transducer, a usb hub, a compact processor, a bone conduction earphone module, two osteoacusis vibrations
Module and a battery module.The RGB-D camera is fixed on above eyeglass, and two osteoacusis vibration moulds are located at two mirrors
Place to the rear among foot is bonded in front of blind person's ear at skull；Usb hub, attitude angle transducer and compact processor are embedded in one
In a mirror pin；Bone conduction earphone module and battery module are in another mirror pin；RGB-D camera passes through with attitude angle transducer
Usb hub is connected with compact processor, and battery module is connected with compact processor.Two osteoacusis shock modules pass through bone
Conduction handset module is connected with compact processor.RGB-D camera acquires the depth image of three-dimensional scenic in real time.Attitude angle sensing
Device obtains the attitude angle of RGB-D camera in real time.One amplitude deepness image and attitude angle information are transmitted to small-sized processing by usb hub
Device.Compact processor handles depth image and attitude angle information, obtains the three-dimensional coordinate of every bit in three-dimensional scenic, and
The local surfaces normal vector for calculating every bit is partitioned into three-dimensional scenic using normal information and is parallel to the flat of horizontal plane
Face, and clustering processing is carried out to the height of plane, distance and the direction of every level-one stair are finally obtained, stereo signal is switched to,
And it is transmitted to bone conduction earphone module.Stereo signal is switched to osteoacusis vibration signal by bone conduction earphone module, is transmitted to two bones
Shock module is conducted, osteoacusis shock module transmits osteoacusis vibration signal to user visually impaired.
The method of above-mentioned Glasses detection stair is as follows:
(1) camera calibration is carried out to RGB-D camera, obtains the focal length f of depth camera, the principle point location of depth camera
(cx,cy)。
(2) the depth image Depth of RGB-D camera acquisition three-dimensional scenic.
(3) X, the corner Angle of tri- axis direction of Y, Z of attitude angle transducer acquisition RGB-D cameraX, AngleY, AngleZ。
(4) usb hub is by depth image Depth, the corner Angle of three axis directionsX, AngleY, AngleZIt is transmitted to small-sized
Processor.
(5) compact processor is according to depth image Depth, the focal length f of depth camera, the principle point location (c of depth camerax,
cy), three-dimensional coordinate (X of the every bit under camera coordinates system can be calculatedc,Yc,Zc).Some coordinates are in depth image Depth
(u, v), depth value 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 respectively 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) three-dimensional coordinate (X according to every bit in depth image under world coordinate systemw,Yw,Zw), every bit can be calculated
Local surfaces normal vector (nx,ny,nz).Specifically: to every bit P, take the K nearest from it point Pi, i ∈ 1,2 ...,
K}.According to the three-dimensional coordinate of this K point, a part plan is fitted with least square method, the normal vector of the plane is carried out
Normalized obtains the local surfaces normal vector (n of point Px,ny,nz)。
(8) in three-dimensional scenic every bit local surfaces normal vector component nyWhether the part plan that the point can be characterized puts down
Row rejects surface normal component n in horizontal planeyAbsolute value | ny| it is less than threshold value thresholdnPoint (thresholdnIt is logical
Often it is 0.85~0.95), obtain the point in three-dimensional scenic in the plane for being parallel to horizontal plane.
(9) height value of horizontal plane where being parallel to the point in the plane of horizontal plane to RGB-D camera in three-dimensional scenic is H
It can be by the three-dimensional coordinate method Y under the world coordinate systemwIt indicates.To the height value H of the point in the plane for being parallel to horizontal plane
Clustering processing is carried out, the plane of multiple parallel water planes is obtained, calculates the average height of each planeThe method of clustering processing
It can be K-Means clustering algorithm, hierarchical clustering algorithm, SOM clustering algorithm, FCM clustering algorithm.
(10) height is extracted with N number of plane that Δ h is incremented by successively or successively decreases, the upper plane (one of as every level-one stair
It is N grades total).If N is greater than 1, illustrate that there are stair in current scene.Δ h be stair height, generally 0.2~0.3 meter.
(11) the distance D of every level-one stair can be by the mean depth of the point in the upper plane of every level-one stairIt indicates, often
The deflection θ of level-one stair can be by the average level coordinate of the point in the upper plane of every level-one stairWith mean depthIt
The arc tangent expression of quotient, i.e.,
(12) indicate that N grades of stair, the sounding of different musical instruments indicate building not at the same level with the (instrumental) ensemble of the musical instrument of N kind difference tone color
Ladder.When the distance D of level-one stair is smaller, then the loudness Volume for corresponding to the musical instrument of this level-one stair is bigger.Each musical instrument
Sounding be all it is stereo, the deflection θ of stereosonic direction and corresponding level-one stair is corresponding.The optional piano of musical instrument small mentions
Qin, gong, trumpet, xylophone etc. have special tone color and melodious.
(13) stereo signal is transmitted to bone conduction earphone module by compact processor.
(14) stereo signal is switched to osteoacusis vibration signal by bone conduction earphone module.
(15) 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, it can detect that and go upstairs and go downstairs.Due to using the plane for being parallel to horizontal plane for extracting every level-one stair
Method, therefore go upstairs or go downstairs in scene and all can be detected；
2, how many grade stair be can determine whether.As using the method for clustering and extracting a series of plane similar in differences in height,
Can determine whether how many grade stair altogether, visually impaired people how many grade stair altogether can also be known by listening musical instrument to judge；
3, sufficient information content is fed back.Compared to the voice broadcast of semantic formula, stereosonic interaction feedback using different loudness,
The musical instrument of different tone colors indicates stair not at the same level, can simultaneously, fully transmit distance and the direction of scene stair not at the same level；
4, it timely feeds back.Compared to the voice broadcast of semantic formula, stereosonic interaction feedback is timely, not postpone.
Visually impaired people can timely judge and stair activity, ensure that the safety of this method；
5, it can also be detected when someone passes through on stair.Due to being parallel to the flat of horizontal plane using the every level-one stair of extraction
The method in face, the not continuity of particular/special requirement plane, therefore someone still can detecte by that will not interfere on stair
The position of the presence of stair and the every level-one stair of acquisition out；
6, user's stair activity visually impaired can be helped naturally.Due to indicate every time nearest level-one stair musical instrument loudness most
Greatly, thus user visually impaired can perception to nearest level-one stair it is most sensitive and most accurate, thus naturally, one by one up and down
Stair.
7, ears are not take up.This method delivers a signal to user visually impaired using bone conduction earphone, does not interfere user to listen to outer
The sound on boundary.
It is not take up both hands.This method uses RGB-D camera, attitude angle transducer and compact processor, is all portable and can
Wearing, 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 stair detection system；
Fig. 2 is the structural schematic diagram of visually impaired people's stair detection system；
Fig. 3 is that the stair after gray proces detect figure, indicates that someone by that can also detect stair well on stair；
Fig. 4 is the detection figure of going upstairs after gray proces, and nearest two-stage stair are marked out in figure；
Fig. 5 is the detection figure of going downstairs after gray proces, and nearest two-stage stair are marked out in figure.
Specific embodiment
As shown in Fig. 2, a kind of detect glasses, the glasses packet based on RGB-D camera and stereosonic visually impaired people's stair
Containing 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.
Shown in Fig. 1, RGB-D camera is connected by usb hub with compact processor with attitude angle transducer, battery module
It 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 depth image of three-dimensional scenic in real time.Attitude angle transducer obtains the attitude angle of RGB-D camera in real time.USB set
One amplitude deepness image and attitude angle information are transmitted to compact processor by line device.Compact processor is to depth image and attitude angle information
It is handled, obtains the three-dimensional coordinate of every bit in three-dimensional scenic, and calculate the local surfaces normal vector of every bit, utilize normal direction
Amount information is partitioned into the plane for being parallel to horizontal plane in three-dimensional scenic, and carries out clustering processing to the height of plane, finally obtains
Distance and the direction for taking every level-one stair, switch to stereo signal, and be transmitted to bone conduction earphone module.Bone conduction earphone module will
Stereo signal switchs to osteoacusis vibration signal, is transmitted to two osteoacusis shock modules, and osteoacusis shock module transmits osteoacusis
Vibration signal gives user visually impaired.
The method of above-mentioned Glasses detection stair is as follows:
(1) camera calibration is carried out to RGB-D camera, obtains the focal length f of depth camera, the principle point location of depth camera
(cx,cy)。
(2) the depth image Depth of RGB-D camera acquisition three-dimensional scenic.
(3) X, the corner Angle of tri- axis direction of Y, Z of attitude angle transducer acquisition RGB-D cameraX, AngleY, AngleZ。
(4) usb hub is by depth image Depth, the corner Angle of three axis directionsX, AngleY, AngleZIt is transmitted to small-sized
Processor.
(5) compact processor is according to depth image Depth, the focal length f of depth camera, the principle point location (c of depth camerax,
cy), three-dimensional coordinate (X of the every bit under camera coordinates system can be calculatedc,Yc,Zc).Some coordinates are in depth image Depth
(u, v), depth value 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 respectively 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) three-dimensional coordinate (X according to every bit in depth image under world coordinate systemw,Yw,Zw), every bit can be calculated
Local surfaces normal vector (nx,ny,nz).Specifically: to every bit P, take the K nearest from it point Pi, i ∈ 1,2 ...,
K}.According to the three-dimensional coordinate of this K point, a part plan is fitted with least square method, the normal vector of the plane is carried out
Normalized obtains the local surfaces normal vector (n of point Px,ny,nz)。
(8) in three-dimensional scenic every bit local surfaces normal vector component nyWhether the part plan that the point can be characterized puts down
Row rejects surface normal component n in horizontal planeyAbsolute value | ny| it is less than threshold value thresholdnPoint (thresholdnIt is logical
Often it is 0.85~0.95), obtain the point in three-dimensional scenic in the plane for being parallel to horizontal plane.
(9) height value of horizontal plane where being parallel to the point in the plane of horizontal plane to RGB-D camera in three-dimensional scenic is H
It can be by the three-dimensional coordinate method Y under the world coordinate systemwIt indicates.To the height value H of the point in the plane for being parallel to horizontal plane
Clustering processing is carried out, the plane of multiple parallel water planes is obtained, calculates the average height of each planeThe method of clustering processing
It can be K-Means clustering algorithm, hierarchical clustering algorithm, SOM clustering algorithm, FCM clustering algorithm.
(10) height is extracted with N number of plane that Δ h is incremented by successively or successively decreases, the upper plane (one of as every level-one stair
It is N grades total).If N is greater than 1, illustrate that there are stair in current scene.Δ h be stair height, generally 0.25~0.35 meter.
(11) the distance D of every level-one stair can be by the mean depth of the point in the upper plane of every level-one stairIt indicates, often
The deflection θ of level-one stair can be by the average level coordinate of the point in the upper plane of every level-one stairWith mean depthIt
The arc tangent expression of quotient, i.e.,
(12) indicate that N grades of stair, the sounding of different musical instruments indicate building not at the same level with the (instrumental) ensemble of the musical instrument of N kind difference tone color
Ladder.When the distance D of level-one stair is smaller, then the loudness Volume for corresponding to the musical instrument of this level-one stair is bigger.Each musical instrument
Sounding be all it is stereo, the deflection θ of stereosonic direction and corresponding level-one stair is corresponding.The optional piano of musical instrument small mentions
Qin, gong, trumpet, xylophone etc. have special tone color and melodious.
(13) stereo signal is transmitted to bone conduction earphone module by compact processor.
(14) stereo signal is switched to osteoacusis vibration signal by bone conduction earphone module.
(15) 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 stair, the glasses include lens body, with
And it is fixed on a RGB-D camera on lens body, an attitude angle transducer, a usb hub, a small-sized processing
Device, a bone conduction earphone module, two osteoacusis shock modules and a battery module；The RGB-D camera is fixed on eye
Above mirror eyeglass, two osteoacusis vibration moulds are located at place to the rear among two mirror pins, in front of fitting blind person's ear at skull；USB
Hub, attitude angle transducer and compact processor are in a mirror pin；Bone conduction earphone module and battery module are embedded in another
In one mirror pin；RGB-D camera is connected by usb hub with compact processor with attitude angle transducer, battery module with it is small
Type processor is connected；Two osteoacusis shock modules pass through bone conduction earphone module and are connected with compact processor；RGB-D camera
The depth image of three-dimensional scenic is acquired in real time；Attitude angle transducer obtains the attitude angle of RGB-D camera in real time；Usb hub
One amplitude deepness image and attitude angle information are transmitted to compact processor；Compact processor carries out depth image and attitude angle information
Processing, obtains the three-dimensional coordinate of every bit in three-dimensional scenic, and calculates the local surfaces normal vector of every bit, is believed using normal vector
The plane for being parallel to horizontal plane being partitioned into three-dimensional scenic is ceased, and clustering processing is carried out to the height of plane, it is final to obtain often
The distance of level-one stair and direction switch to stereo signal, and are transmitted to bone conduction earphone module；Bone conduction earphone module will be three-dimensional
Acoustical signal switchs to osteoacusis vibration signal, is transmitted to two osteoacusis shock modules, and osteoacusis shock module transmits osteoacusis vibration
Signal gives user visually impaired；Detect stair method the following steps are included:
(1) camera calibration is carried out to RGB-D camera, obtains the focal length f of depth camera, the principle point location (c of depth camerax,
cy)；
(2) the depth image Depth of RGB-D camera acquisition three-dimensional scenic；
(3) X, the corner Angle of tri- axis direction of Y, Z of attitude angle transducer acquisition RGB-D cameraX, AngleY, AngleZ；
(4) usb hub is by depth image Depth, the corner Angle of three axis directionsX, AngleY, AngleZIt is transmitted to small-sized processing
Device；
(5) compact processor is according to depth image Depth, the focal length f of depth camera, the principle point location (c of depth camerax,cy),
Three-dimensional coordinate (X of the every bit under camera coordinates system can be calculatedc,Yc,Zc)；In depth image Depth some coordinates be (u,
V), depth value 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 respectively 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) three-dimensional coordinate (X according to every bit in depth image under world coordinate systemw,Yw,Zw), the office of every bit can be calculated
Portion surface normal (nx,ny,nz)；Specifically: to every bit P, take the K nearest from it point Pi, i ∈ { 1,2 ..., K }；Root
According to the three-dimensional coordinate of this K point, a part plan is fitted with least square method, the normal vector of the plane is normalized
Processing obtains the local surfaces normal vector (n of point Px,ny,nz)；
(8) in three-dimensional scenic every bit local surfaces normal vector component nyWhether the part plan that the point can be characterized is parallel to
Horizontal plane rejects surface normal component nyAbsolute value | ny| it is less than threshold value thresholdnPoint, thresholdnIt is 0.85
~0.95, obtain the point in three-dimensional scenic in the plane for being parallel to horizontal plane；
(9) height value of horizontal plane where being parallel to point in the plane of horizontal plane to RGB-D camera in three-dimensional scenic is that H can be by
Three-dimensional coordinate method Y under the world coordinate systemwIt indicates；The height value H of point in the plane for being parallel to horizontal plane is carried out
Clustering processing obtains the plane of multiple parallel water planes, calculates the average height of each planeThe method of clustering processing can be
K-Means clustering algorithm, hierarchical clustering algorithm, SOM clustering algorithm, FCM clustering algorithm；
(10) height is extracted with N number of plane that Δ h is incremented by successively or successively decreases, the upper plane of as every level-one stair, N altogether
Grade；If N is greater than 1, illustrate that there are stair in current scene；Δ h be stair height, generally 0.2~0.3 meter；
(11) the distance D of every level-one stair can be by the mean depth of the point in the upper plane of every level-one stairIt indicates, every level-one
The deflection θ of stair can be by the average level coordinate of the point in the upper plane of every level-one stairWith mean depthQuotient
Arc tangent expression, i.e.,
(12) indicate that N grades of stair, the sounding of different musical instruments indicate stair not at the same level with the (instrumental) ensemble of the musical instrument of N kind difference tone color；
When the distance D of level-one stair is smaller, then the loudness Volume for corresponding to the musical instrument of this level-one stair is bigger；The sounding of each musical instrument
All to be stereo, the deflection θ of stereosonic direction and corresponding level-one stair is corresponding；
(13) stereo signal is transmitted to bone conduction earphone module by compact processor；
(14) stereo signal is switched to osteoacusis vibration signal by bone conduction earphone module；
(15) osteoacusis signal is passed to user visually impaired by osteoacusis shock module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611048783.6A CN106821693B (en) | 2016-11-23 | 2016-11-23 | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's stair |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611048783.6A CN106821693B (en) | 2016-11-23 | 2016-11-23 | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's stair |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106821693A CN106821693A (en) | 2017-06-13 |
| CN106821693B true CN106821693B (en) | 2019-02-12 |
Family
ID=59146047
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611048783.6A Active CN106821693B (en) | 2016-11-23 | 2016-11-23 | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's stair |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106821693B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110919653B (en) * | 2019-11-29 | 2021-09-17 | 深圳市优必选科技股份有限公司 | Stair climbing control method and device for robot, storage medium and robot |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| US9251417B1 (en) * | 2014-10-15 | 2016-02-02 | Hrl Laboratories, Llc | Fast open doorway detection for autonomous robot exploration |
| CN105759836A (en) * | 2016-03-14 | 2016-07-13 | 武汉卓拔科技有限公司 | Unmanned aerial vehicle obstacle avoidance method and device based on 3D camera |
| CN105910604A (en) * | 2016-05-25 | 2016-08-31 | 武汉卓拔科技有限公司 | Multi-sensor-based autonomous obstacle avoidance navigation system |
-
2016
- 2016-11-23 CN CN201611048783.6A patent/CN106821693B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9251417B1 (en) * | 2014-10-15 | 2016-02-02 | Hrl Laboratories, Llc | Fast open doorway detection for autonomous robot exploration |
| 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 |
| CN105759836A (en) * | 2016-03-14 | 2016-07-13 | 武汉卓拔科技有限公司 | Unmanned aerial vehicle obstacle avoidance method and device based on 3D camera |
| CN105910604A (en) * | 2016-05-25 | 2016-08-31 | 武汉卓拔科技有限公司 | Multi-sensor-based autonomous obstacle avoidance navigation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106821693A (en) | 2017-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106821692B (en) | One kind is based on RGB-D camera and stereosonic visually impaired people's stair detection system and method | |
| CN106203390B (en) | A kind of intelligent blind auxiliary system | |
| CN106597690B (en) | One kind predicting glasses based on RGB-D camera and stereosonic visually impaired people's access | |
| US9792501B1 (en) | Method and device for visually impaired assistance | |
| CN106651873B (en) | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's zebra stripes | |
| CN106846350B (en) | One kind is based on RGB-D camera and stereosonic visually impaired people's barrier early warning system and method | |
| CN107341789B (en) | System and method for predicting pathway of visually impaired people based on RGB-D camera and stereo | |
| CN106214437B (en) | A kind of intelligent blind auxiliary eyeglasses | |
| EP1928296B1 (en) | A device for controlling an external unit | |
| US7755744B1 (en) | Environment sensor that conveys information about objects in the vicinity of the visually impaired user | |
| CN105788185A (en) | Method and device for monitoring sitting posture | |
| KR20140033009A (en) | An optical device for the visually impaired | |
| Liu et al. | Electronic travel aids for the blind based on sensory substitution | |
| CN109087485A (en) | Assisting automobile driver method, apparatus, intelligent glasses and storage medium | |
| CN106821693B (en) | One kind detecting glasses based on RGB-D camera and stereosonic visually impaired people's stair | |
| CN107049717B (en) | One kind is based on RGB-D camera and stereosonic visually impaired people's zebra stripes detection system and method | |
| CN112402194A (en) | Auxiliary terminal system for visually impaired people | |
| TWI691328B (en) | Smart aid system for visually impaired | |
| Srinivas et al. | A new method for recognition and obstacle detection for visually challenged using smart glasses powered with Raspberry Pi | |
| CN208355727U (en) | A kind of blind-guiding stick based on double ultrasonic waves | |
| Calder | Assistive technology interfaces for the blind | |
| CN215779677U (en) | AI vision of 5G technique leads blind instrument | |
| KR20160081589A (en) | Front detection device of glasses type | |
| TWI714014B (en) | Intelligent laser sensing virtual walking stick device for the blind | |
| Chaudhary et al. | State of art on wearable device to assist visually impaired person navigation in outdoor environment |
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. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |