CN210078040U - Intelligent blind guiding device - Google Patents
Intelligent blind guiding device Download PDFInfo
- Publication number
- CN210078040U CN210078040U CN201920256845.5U CN201920256845U CN210078040U CN 210078040 U CN210078040 U CN 210078040U CN 201920256845 U CN201920256845 U CN 201920256845U CN 210078040 U CN210078040 U CN 210078040U
- Authority
- CN
- China
- Prior art keywords
- user
- controller
- obstacle
- blind guiding
- shell
- 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.)
- Expired - Fee Related
Links
- 230000007246 mechanism Effects 0.000 claims abstract description 55
- 238000004891 communication Methods 0.000 claims abstract description 9
- 238000005259 measurement Methods 0.000 claims abstract description 5
- 210000005069 ears Anatomy 0.000 claims description 3
- 230000004888 barrier function Effects 0.000 abstract description 10
- 238000012545 processing Methods 0.000 description 8
- 238000001514 detection method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010295 mobile communication Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Landscapes
- Rehabilitation Tools (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The utility model relates to a blind device is led to intelligence, including the device body and with the at least one bluetooth headset that this body communication of device is connected: the device body is used for wearing in the front of the chest of the user, has a shell and is installed on a power supply, a switch, a controller, a GPS positioning mechanism, a barrier image acquisition mechanism and a ranging mechanism of the shell, the power supply is connected with the controller and the switch respectively, and the controller is connected with a Bluetooth headset, the GPS positioning mechanism, the barrier image acquisition mechanism and the ranging mechanism respectively. Compared with the prior art, the utility model discloses can improve the precision and the distance measurement's of barrier discernment accuracy to the user suggestion road with keep away barrier information, let the user can obtain accurate, abundant road environment information, the safety and the route of the remote trip of guarantee user are accurate, simultaneously can reduce cost, portable.
Description
Technical Field
The utility model relates to a lead blind device, especially relate to a blind device is led to intelligence.
Background
With the development of road transportation career, the complexity of road environment and the improvement of living standard of people, the safety problem of the blind people in going out is more and more emphasized.
The current common blind guiding devices comprise a blind guiding stick, an intelligent blind guiding crutch, an intelligent blind guiding dog and the like. Along with the complexity of the environment, the information provided by the blind guiding stick is too little, and the blind guiding stick is not suitable for long-distance travel. In the aspect of obstacle identification, most of intelligent blind guiding devices adopt sensors such as a sound wave radar, a laser radar and a GPS positioning device to acquire information, for example, chinese patent CN20643455U discloses a wearable blind guiding device, which comprises a wearable blind guiding device body, wherein the wearable blind guiding device body comprises a switch, a power supply module, a controller, a voice chip, a mobile communication module, a wireless communication module, a GPS positioning module and a ranging module; the power supply module is respectively electrically connected with the controller and the switch; the controller is respectively and electrically connected with the voice chip, the mobile communication module, the wireless communication module, the GPS positioning module and the ranging module; the wearable blind guiding device body is provided with a wearable carrier for fixing the wearable blind guiding device body. However, the existing intelligent blind guiding equipment is single in means and poor in working reliability under the condition that road information and obstacle information are complex, and is difficult to popularize. The intelligent guide dog needs to be provided with a driving device, is large in size and inconvenient to carry, and can be poor in capacity when meeting road conditions such as stairs.
SUMMERY OF THE UTILITY MODEL
The utility model aims at providing an intelligent blind guiding device for overcoming the defects existing in the prior art.
The purpose of the utility model can be realized through the following technical scheme:
the utility model provides a blind device is led to intelligence, includes device body and with device body communication connection's at least one bluetooth headset: the device body be used for wearing in the user chest, have the casing and install in power, switch, controller, GPS positioning mechanism, obstacle image acquisition mechanism and the ranging mechanism of casing, the power is connected with controller and switch respectively, the controller is connected with bluetooth headset, GPS positioning mechanism, obstacle image acquisition mechanism and ranging mechanism respectively.
Preferably, the controller is a siemens ARM9, the GPS positioning mechanism is a G-mouse GPS module, the obstacle image acquisition mechanism is an OV9655 camera, and the distance measurement mechanism is an AJ-SR04M ultrasonic sensor.
Preferably, the casing be flat cuboid shape, obstacle image acquisition mechanism, range finding mechanism and switch set up on the casing and lie in the front of casing, power and controller are located the casing, GPS positioning mechanism installs on the controller, still is equipped with the hole of charging that is used for charging for the power on the casing.
Preferably, the device body wear at the user chest through wearing subassembly detachably, the subassembly of wearing be the magic subsides, the primary and secondary face of magic subsides sets up respectively in the back of casing and user chest.
Preferably, the device also comprises a vibration motor, wherein the vibration motor is arranged on the device body or the Bluetooth headset and is in communication connection with the controller.
Preferably, the number of the bluetooth earphones is two, the two bluetooth earphones are respectively used for being worn on two ears of a user, and the vibration motor is arranged on the bluetooth earphones and forms a vibration type bluetooth earphone with the bluetooth earphones.
Further preferably, the vibration motor is a flat button type vibration motor. Small volume and light weight.
The utility model discloses a theory of operation does:
the controller is provided with a path planning unit, an obstacle identification unit, an obstacle avoidance path planning unit, a voice processing unit and an information feedback unit, and is also provided with a data storage unit. Wherein: the Bluetooth headset, the vibration motor, the voice processing unit and the information feedback unit form a man-machine interaction module which is used for receiving voice information of a user and feeding back road environment information (front obstacle category, size and the like) and obstacle avoidance paths to the user (through voice and vibration); the GPS positioning mechanism and the path planning unit form a GPS navigation module for setting an (optimal) path according to the departure place and the destination of the user; the obstacle image acquisition mechanism and the obstacle identification unit form an obstacle identification module which is used for identifying obstacles such as front vehicles, pedestrians and the like; the distance measuring mechanism and the obstacle avoidance path planning unit form an obstacle avoidance module, and the obstacle avoidance module is used for measuring the distance between a user and an obstacle and planning a corresponding obstacle avoidance path.
Compared with the prior art, the utility model discloses following beneficial effect has:
(1) the obstacle image acquisition mechanism is combined with the ranging mechanism, and the obstacle image acquisition mechanism has obstacle image capturing capacity and ranging capacity, can prompt road environment information such as the type and size of obstacles in front and obstacle avoidance paths, improves the accuracy of obstacle identification and the accuracy of distance measurement, and ensures the safety and the accuracy of a long-distance trip of a user.
(2) The user can obtain accurate and sufficient road environment information through sound and vibration modes so as to make reasonable judgment. The user may be alerted by vibration when the distance is too close (e.g., when the distance is less than 1.5 m).
(3) Keep away the left right direction of barrier and be very important, the utility model discloses when using two bluetooth headset and all set up vibrating motor on two bluetooth headset, when the distance is too near (for example when being less than 1.5m) the vibration of vibrating motor on can be through controlling left ear or the right ear, play the effect of reminding the user to walk left or right fast, keep away the barrier more effectively.
(4) Wear and convenient to use, the size is small and exquisite, portable, and the device adopts camera and ultrasonic sensor moreover, low price.
Drawings
Fig. 1 is a schematic view of the apparatus of the present invention in example 1;
FIG. 2 is a schematic view of the working principle of the present invention;
fig. 3 is a rear view of the housing of the present invention;
FIG. 4 is a schematic diagram of the speech processing of the present invention;
fig. 5 is a schematic diagram of obstacle recognition according to the present invention;
FIG. 6 is a schematic diagram of the obstacle size detection of the present invention;
fig. 7 is a schematic diagram of obstacle identification and obstacle avoidance path planning according to the present invention.
In the figure, 1 is the device body, 11 is the casing, and 12 is the switch, and 13 is the controller, and 14 is GPS positioning mechanism, and 15 is obstacle image acquisition mechanism, and 16 is range finding mechanism, and 17 are the hole of charging, and 2 are bluetooth headset, and 3 are vibrating motor, and 4 are the magic subsides.
Detailed Description
The present invention will be described in detail below with reference to the accompanying drawings and specific embodiments.
Example 1
The utility model provides a blind device is led to intelligence, as shown in fig. 1 ~ 2, includes device body 1 and with device body 1 communication connection's at least one bluetooth headset 2: device body 1 is used for wearing in the front of the user's chest, has casing 11 and installs in casing 11's power, switch 12, controller 13, GPS positioning mechanism 14, obstacle image acquisition mechanism 15 and ranging mechanism 16, and the power is connected with controller 13 and switch 12 respectively, and controller 13 is connected with bluetooth headset 2, GPS positioning mechanism 14, obstacle image acquisition mechanism 15 and ranging mechanism 16 respectively.
This embodiment is when using, and device body 1 wears at the user chest through wearing subassembly detachably, and it is magic subsides 4 to wear the subassembly, and the primary and secondary face of magic subsides 4 sets up respectively in the back (as shown in figure 3) of casing and user chest. In this embodiment, the housing 11 is shaped like a flat rectangular parallelepiped, the obstacle image acquiring mechanism 15, the distance measuring mechanism 16, and the switch 12 are disposed on the housing 11 and located on the front surface of the housing 11, the power supply and the controller 13 are located in the housing 11, the GPS positioning mechanism 14 is mounted on the controller 13, and the housing 11 is further provided with a charging hole 17 for charging the power supply. And further selecting the controller 13 as ARM9, the GPS positioning mechanism 14 as a G-mouse GPS module, the obstacle image acquisition mechanism 15 as an OV9655 camera, and the ranging mechanism 16 as an AJ-SR04M ultrasonic sensor.
The device can also comprise a vibration motor 3, wherein the vibration motor 3 is arranged on the device body 1 or the Bluetooth headset 2 and is in communication connection with the controller 13. The user can obtain accurate and sufficient road environment information through sound and vibration modes so as to make reasonable judgment. The user may be alerted by vibration when the distance is too close (e.g., when the distance is less than 1.5 m). Keep away the left and right sides direction of barrier and be very important, in this embodiment, bluetooth headset 2 is two, is used for wearing two ears at the user respectively, and vibrating motor 3 sets up on bluetooth headset 2 to constitute vibrating bluetooth headset (can also utilize prior art's vibrating bluetooth headset) with bluetooth headset 2. The utility model discloses when using two bluetooth headset and all set up vibrating motor on two bluetooth headset, when the distance is too near (for example when being less than 1.5m) the vibration of vibrating motor on can controlling left ear or the right ear, play quick (for pronunciation say) remind the user left or right walking's effect, keep away the barrier more effectively.
The working principle of the blind guiding device in the embodiment is as follows:
the controller in the embodiment has a path planning unit, an obstacle recognition unit, an obstacle avoidance path planning unit, a voice processing unit, an information feedback unit, and a data storage unit. Wherein: the Bluetooth headset, the vibration motor, the voice processing unit and the information feedback unit form a man-machine interaction module which is used for receiving voice information of a user and feeding back road environment information (front obstacle category, size and the like) and obstacle avoidance paths to the user (through voice and vibration); the GPS positioning mechanism and the path planning unit form a GPS navigation module for setting an (optimal) path according to the departure place and the destination of the user; the obstacle image acquisition mechanism and the obstacle identification unit form an obstacle identification module which is used for identifying obstacles such as front vehicles, pedestrians and the like; the distance measuring mechanism and the obstacle avoidance path planning unit form an obstacle avoidance module, and the obstacle avoidance module is used for measuring the distance between a user and an obstacle and planning a corresponding obstacle avoidance path.
In step S1, a network module of each module is first established. And acquiring a voice database, training an LSTM voice recognition network model off line by adopting a Keras framework, and establishing a voice processing unit. 5000 positive sample pictures and 5000 negative sample pictures of road images in front of pedestrians are obtained, the positive sample pictures and the negative sample pictures comprise various categories of pedestrians, vehicles, bicycles, garbage cans and the like, and obstacle recognition network model training is carried out. And (3) establishing an obstacle recognition unit by adopting a dark net frame and training a tiny-yolov3 network model in an off-line manner.
Step S2, when the device is turned on and the system is started, the user sets the destination by the bluetooth headset voice, the voice processing unit of the human-computer interaction module extracts the characteristic information of the voice after receiving the voice, inputs the characteristic information into the LSTM voice network model, classifies the voice by the softmax classifier through the full connection layer, and finally recognizes the voice command of the user, the working principle is as shown in fig. 4, and transmits the command to the GPS navigation module. The route planning unit of the GPS navigation module sets an initial point and a destination according to the requirements of a user through an electronic map, determines a related route, stores route data, records frequently-visited places of the user and is convenient for the user to use for a long time. After the user selects the route, the device positions the user in real time through the GPS and ensures that the route of the user is correct through the Bluetooth headset voice navigation.
And step S3, when the user walks according to the indicated route, the obstacle identification module and the obstacle avoidance module start working. The main body device worn on the chest of the user is provided with a camera and an ultrasonic sensor. The camera collects video signals of a front road in real time, restores the video signals into a frame of image, and transmits the frame of image to the obstacle identification unit after passing through the image processing unit. The working principle of the obstacle identification unit is as shown in fig. 5, firstly, a frame of image is obtained, the acquired image is processed by an obstacle detection method based on a convolutional neural network and by adopting an off-line trained tiny-yolov3 obstacle identification network model, finally, the obstacle is identified by characteristic extraction of a multilayer convolutional network, the type of the obstacle, a detection frame (w, h) and a central coordinate (x, y) of the obstacle in a pixel coordinate are obtained, and data for identifying the obstacle are transmitted to an obstacle avoidance module.
In step S4, the ultrasonic sensor on the main body device collects data and measures a distance. And screening and matching the distance data of the ultrasonic waves according to the central position coordinates of the obstacles of the obstacle identification unit, and determining the distance between the obstacles and the user. And calculating the real size of the obstacle according to the measured distance and the size of the obstacle in the pixel coordinates. As shown in fig. 6, in the world coordinate system, W represents the width of the obstacle, D is the distance between the obstacle and the camera, the camera forms an image with a relevant scale size on an image plane according to the light reflected by the obstacle, the width of the obstacle after imaging is W, the focal length of the lens is f, and the world coordinate system and the pixel coordinate system approximate mapping relationship is as follows:
W:D≈w:f
the distance D between the obstacle and the camera is measured by the acoustic wave sensor, so that the real width W of the obstacle in front can be estimated as long as the width of the pixel occupied by the obstacle in front in the image is known. As shown in fig. 6 to 7, in the pixel coordinate system, the obstacle avoidance path planning unit combines the width w of the obstacle and the body width M of the user according to the position of the center coordinate (X, y) of the obstacle relative to the central axis X of the image, where X is M<M is, ifGo straight, if
Then to the right
Avoidance of distance, when x>M is, if
Go straight, ifThen move to the left
Distance. And (4) calculating the real moving distance X of the user in the world coordinate system by combining the real width W of the obstacle. After the real size of the obstacle is obtained, the center coordinates (x, y) of the obstacle and the central axis of the image are used for calculating the center coordinates of the obstacleAnd planning an obstacle avoidance path according to the position relation of the line.
And step S5, transmitting the data to an information feedback unit of the man-machine interaction module, and providing the front road environment information for the user in a voice mode, wherein the information is that 'D meters in front of the user appear C type obstacles with width of W, and the user is required to walk by moving X meters to the right at the central position'. And when the distance is less than 1.5m, the user is reminded to make reasonable response through the vibration mechanism.
The models in the above steps may be based on prior art correlation models.
The utility model discloses a blind guiding device, accurate discernment the place ahead barrier type, distance, size and position plan out the obstacle-avoiding route to the place ahead barrier, remind user walking safety through vibration and pronunciation, provide accurate abundant road environment information for the user. The device has the advantages of high detection precision, convenient control, low cost and convenient carrying.
The embodiments described above are intended to facilitate the understanding and use of the invention by those skilled in the art. It will be readily apparent to those skilled in the art that various modifications to these embodiments may be made, and the generic principles described herein may be applied to other embodiments without the use of the inventive faculty. Therefore, the present invention is not limited to the above embodiments, and those skilled in the art should make improvements and modifications within the scope of the present invention according to the disclosure of the present invention.
Claims (6)
1. The intelligent blind guiding device is characterized by comprising a device body (1) and at least one Bluetooth headset (2) in communication connection with the device body (1): device body (1) be used for wearing in user's chest, have casing (11) and install in power, switch (12), controller (13), GPS positioning mechanism (14), obstacle image acquisition mechanism (15) and ranging mechanism (16) of casing (11), the power is connected with controller (13) and switch (12) respectively, controller (13) are connected with bluetooth headset (2), GPS positioning mechanism (14), obstacle image acquisition mechanism (15) and ranging mechanism (16) respectively.
2. The intelligent blind guiding device as claimed in claim 1, wherein the controller (13) is an ARM9, the GPS positioning mechanism (14) is a G-mouse GPS module, the obstacle image acquisition mechanism (15) is an OV9655 camera, and the distance measurement mechanism (16) is an AJ-SR04M ultrasonic sensor.
3. The intelligent blind guiding device is characterized in that the shell (11) is in a flat cuboid shape, the obstacle image acquisition mechanism (15), the distance measurement mechanism (16) and the switch (12) are arranged on the shell (11) and located on the front face of the shell (11), the power supply and the controller (13) are located in the shell (11), the GPS positioning mechanism (14) is installed on the controller (13), and the shell (11) is further provided with a charging hole (17) for charging the power supply.
4. The intelligent blind guiding device according to claim 3, wherein the device body (1) is detachably worn in front of the chest of the user through a wearing assembly, the wearing assembly is a magic tape (4), and the primary and secondary surfaces of the magic tape (4) are respectively arranged on the back surface of the shell and the front of the chest of the user.
5. The intelligent blind guiding device is characterized by further comprising a vibration motor (3), wherein the vibration motor (3) is arranged on the device body (1) or the Bluetooth headset (2) and is in communication connection with the controller (13).
6. The intelligent blind guiding device as claimed in claim 5, wherein the number of the Bluetooth earphones (2) is two, the two Bluetooth earphones are respectively worn on two ears of a user, and the vibration motor (3) is arranged on the Bluetooth earphones (2) and forms a vibration type Bluetooth earphone with the Bluetooth earphones (2).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920256845.5U CN210078040U (en) | 2019-02-28 | 2019-02-28 | Intelligent blind guiding device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201920256845.5U CN210078040U (en) | 2019-02-28 | 2019-02-28 | Intelligent blind guiding device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN210078040U true CN210078040U (en) | 2020-02-18 |
Family
ID=69471095
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201920256845.5U Expired - Fee Related CN210078040U (en) | 2019-02-28 | 2019-02-28 | Intelligent blind guiding device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN210078040U (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112263217A (en) * | 2020-08-27 | 2021-01-26 | 上海大学 | Non-melanoma skin cancer pathological image lesion area detection method based on improved convolutional neural network |
| CN113191333A (en) * | 2021-05-29 | 2021-07-30 | 山东新一代信息产业技术研究院有限公司 | Blind guiding method, system and blind guiding equipment based on artificial intelligence |
| CN114159281A (en) * | 2022-01-06 | 2022-03-11 | 延安大学 | Device and method capable of realizing stair detection |
-
2019
- 2019-02-28 CN CN201920256845.5U patent/CN210078040U/en not_active Expired - Fee Related
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112263217A (en) * | 2020-08-27 | 2021-01-26 | 上海大学 | Non-melanoma skin cancer pathological image lesion area detection method based on improved convolutional neural network |
| CN112263217B (en) * | 2020-08-27 | 2023-07-18 | 上海大学 | Improved convolutional neural network-based non-melanoma skin cancer pathological image lesion area detection method |
| CN113191333A (en) * | 2021-05-29 | 2021-07-30 | 山东新一代信息产业技术研究院有限公司 | Blind guiding method, system and blind guiding equipment based on artificial intelligence |
| CN114159281A (en) * | 2022-01-06 | 2022-03-11 | 延安大学 | Device and method capable of realizing stair detection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN210078040U (en) | Intelligent blind guiding device | |
| CN205494329U (en) | Intelligence is saved oneself and is led blind walking stick | |
| CN202409427U (en) | Portable intelligent electronic blind guide instrument | |
| CN106859929A (en) | A kind of Multifunctional blind person guiding instrument based on binocular vision | |
| CN111609851B (en) | Mobile blind guiding robot system and blind guiding method | |
| KR101575776B1 (en) | A object recognitive stick for the blind | |
| CN204709328U (en) | A kind of smart guide glasses | |
| CN110623820A (en) | Blind device is led to wearable intelligence | |
| CN110584962A (en) | Combined obstacle-detection intelligent blind-guiding system | |
| CN105979442A (en) | Noise suppression method and device and mobile device | |
| KR102351584B1 (en) | System for providing navigation service for visually impaired person | |
| CN103892995A (en) | Electronic seeing-eye dog robot | |
| CN104367447A (en) | Auxiliary walking system and method | |
| CN110478206B (en) | Intelligent blind guiding system and equipment | |
| CN103312899A (en) | Smart phone with blind guide function | |
| CN205459716U (en) | Blind system is led to intelligence based on ultrasonic ranging | |
| CN111195191A (en) | Intelligent system and method for guiding travel of blind people | |
| CN109106563A (en) | A kind of automation blind-guide device based on deep learning algorithm | |
| CN108245387A (en) | A kind of intelligent blind guiding system based on wearable device | |
| CN111840016A (en) | Flexible and configurable intelligent navigation device for blind people | |
| CN109998873A (en) | A kind of wearable blindmen intelligent positioning and blind guiding system | |
| CN208942782U (en) | Distance perception blind-guiding walking stick based on vibration intensity | |
| CN210776078U (en) | Real-time navigation bluetooth glasses | |
| CN113181015A (en) | Head-mounted multi-source auxiliary navigation device and method for blind person | |
| CN114533503B (en) | Glasses system for intelligent blind-assisting travel and interaction method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200218 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |