TWI736955B - Blind-man navigation method and blind-man navigation device - Google Patents

Abstract

The invention provides a blind-man navigation method and a blind-man navigation device. The method includes: obtaining a road condition image by a camera unit; identifying the road condition image to get a road condition and sending the road condition and location information of the road condition to a database, wherein, the database stores the road condition image and the location information of the road condition; outputting a name of an object in the road condition image and a distance and orientation between the object and the camera unit according to the identified road condition information; determining whether an obstacle is in the road condition information according to the distance and orientation between the object and the camera unit; outputting the name of the obstacle and the distance between the obstacle and the camera unit if the obstacle is in the road condition information.

Description

Blind navigation method and blind navigation device

The invention relates to the field of navigation for the blind, in particular to a navigation method for the blind and a navigation device for the blind.

As a special group of people in society, travel safety always worries family and friends. Although the current society provides corresponding convenience for this part of the special group in hardware packages, the travel of the blind and weak people Still relying on the help of family members or the assistance of a guide dog, the existing walking sticks for the blind and impaired people mostly use sensors to sense the road conditions, which can prompt the blind and impaired people about the road conditions ahead, but they do not have the navigation function. , The user experience is poor.

In view of the above content, it is necessary to propose a navigation method and device for the blind to provide navigation services to the visually impaired and impaired in a smarter way to improve user experience.

The first aspect of the present application provides a navigation method for the blind. The navigation method for the blind is applied to a navigation device for the blind. The method includes: acquiring an image with road conditions collected by a camera unit; identifying the road conditions in the image, and Sending the road conditions and location information corresponding to the road conditions to a database, wherein the database stores images containing road conditions and location information corresponding to the road conditions; According to the recognized road condition, output the name of the object in the image and the distance and orientation between the object and the camera unit; determine whether the road condition is in accordance with the distance and orientation between the object and the camera unit There is an obstacle; if there is an obstacle, the name of the obstacle and the distance between the obstacle and the camera unit are output in a preset manner to prompt information.

Preferably, the method further includes: searching for road conditions at a preset distance from the camera unit in the database, and outputting prompt information in a preset manner if there are obstacles in the road conditions at the preset distance.

Preferably, the method further includes: uploading the real-time acquired road condition to the database when the road condition of a preset distance from the obstacle found in the database does not match the real-time obtained road condition , And delete the corresponding historical road conditions in the database.

Preferably, the method further includes: receiving the target location input by the user and obtaining the user's current location information; calculating and outputting the path between the current location and the target location; obtaining the road conditions in the database, and according to the preset The rule determines whether the path is suitable for blind people; and if the path is not suitable for blind people, a voice prompt is issued.

Preferably, the image is a 3D image; the camera unit is a 3D camera.

Preferably, the step of identifying the road conditions in the image includes: acquiring a 3D image collected by a 3D camera; splitting the 3D image into a depth image and a two-dimensional image; and identifying through an image recognition method The name of the object in the two-dimensional image; the distance and orientation between the object and the 3D camera are calculated by the time-of-flight method.

Preferably, the preset manner includes outputting prompt information through a voice broadcast unit provided on the navigation device for the blind and/or sending out a vibration prompt through a vibration unit provided on the navigation device for the blind.

A second aspect of the present application provides a navigation device for the blind. The device includes: a camera unit, the camera unit is a 3D camera for acquiring and collecting images in front of the road; a processor for executing computer program instructions; memory Body: used to store computer program instructions, which are run by the processor and execute the following steps: acquire images with road conditions collected by the camera unit; identify road conditions in the images, and The road conditions and the location information corresponding to the road conditions are sent to a database, wherein the database stores images containing road conditions and location information corresponding to the road conditions; according to the identified road conditions, the image is output The name of the object and the distance and orientation between the object and the camera unit; judge whether there is an obstacle in the road condition according to the distance and orientation between the object and the camera unit; if there is an obstacle, change The name of the obstacle and the distance between the obstacle and the camera unit output prompt information in a preset manner through the output unit.

Preferably, the navigation device for the blind includes any one of AR glasses, smart watches, smart belts, smart sticks, and smart wearable devices.

Preferably, the navigation device for the blind further includes a positioning unit, and when the computer command is executed by the processor, the following steps are performed: receiving the target position input by the user and obtaining the current position information of the user through the positioning unit; Calculate and output the path between the current position and the target position; Obtain road condition information in the database, and determine whether the path is suitable for blind people to pass according to preset rules; if it is not suitable, control the output unit to issue a voice prompt.

The navigation method for the blind of the present invention acquires real-time road conditions by using camera equipment, and prompts users about the road conditions through image recognition and distance positioning methods, so that the blind people travel more safely and conveniently.

1: Navigation device for the blind

2: computer device

11: Camera unit

12: Positioning unit

13: output unit

14: Sensing unit

15: processor

16: memory

101: Get modules

102: Identification Module

103: Judgment Module

104: Execution module

105: reminder module

FIG. 1 is a schematic diagram of the application environment architecture of the navigation method for the blind provided in the first embodiment of the present invention.

Fig. 2 is a flowchart of a navigation method for the blind provided by the second embodiment of the present invention.

Fig. 3 is a schematic structural diagram of a navigation device for the blind provided in the third embodiment of the present invention.

In order to be able to understand the above objectives, features and advantages of the present invention more clearly, the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other if there is no conflict.

In the following description, many specific details are explained in order to fully understand the present invention. The described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present invention.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments, and are not intended to limit the present invention.

Example one

Refer to FIG. 1, which is a schematic diagram of the application environment architecture of the navigation method for the blind provided by the first embodiment of the present invention.

The navigation method for the blind in the present invention is applied to the navigation device 1 for the blind, and the navigation device for the blind and a computer device 2 establish a communication connection through the network. The network can be a wired network or a wireless network, such as radio, wireless fidelity (WIFI), cellular, satellite, broadcast, etc.

The blind navigation device 1 may be an electronic device installed with navigation software for the blind. The navigation device for the blind includes but is not limited to any of AR glasses, smart watches, smart belts, smart sticks, and smart wearable devices. The blind navigation device 1 includes a camera unit 11, a positioning unit 12, an output unit 13, a sensing unit 14, a processor 15, and a memory 16. The schematic diagram of the hardware architecture of the blind navigation device is shown in FIG.

The computer device 2 is a server with processing and storage capabilities. The computer device 2 can be a personal computer, a server, etc., where the server can be a single server, a server cluster, or a cloud server.

Example two

Please refer to FIG. 2, which is a flowchart of the navigation method for the blind provided by the second embodiment of the present invention. According to different needs, the order of the steps in the flowchart can be changed, and some steps can be omitted.

Step S1: Obtain images with road conditions collected by the camera unit.

In one embodiment of the present invention, the camera unit 11 may be a 3D camera. In other embodiments of the present invention, the camera unit 11 may be a 360° panoramic 3D camera.

When the road condition is that a blind person is walking, the camera unit 11 collects all road conditions, pedestrian and vehicle conditions, conditions over the walking route, etc. within the range.

Step S2: Identify the road condition information in the image, and send the road condition information and the location information corresponding to the road condition to a database, wherein the database contains route information The image of and the location information corresponding to the road condition information.

In an embodiment of the present invention, the step of identifying the road conditions in the image may specifically include: acquiring a 3D image collected by a 3D camera; splitting the 3D image into a depth image and a two-dimensional image Recognize the name of the object in the two-dimensional image by image recognition method; calculate the distance and orientation between the object and the 3D camera by the time-of-flight method.

In one embodiment of the present invention, the current location information can be obtained by the positioning unit 12 on the navigation device for the blind, and the method for obtaining the current location by the positioning unit 12 can be obtained by the GPS global positioning system. The image containing the road condition and the location information corresponding to the image are sent to a database after image compression processing. The database stores the image containing the road condition and the location corresponding to the image News. The image compression method includes, but is not limited to, an image compression technology based on MPEG4 encoding and an image compression technology based on H.265 encoding.

For example, using a 3D camera to capture a 3D image with road conditions and send the 3D image to the computer device 2. The 3D camera outputs a four-channel image that contains the color information of each pixel And the depth of each image element, the color information of each image element is integrated into a two-dimensional image, and the depth information of each image element is integrated into a depth image. The image recognition method is used to recognize the name of the object in the two-dimensional image. The image recognition method includes, but is not limited to, a neural network algorithm based on deep learning, an image recognition method based on wavelet transform, and the like. The distance between the obstacle and the camera and the relative position and angle of the obstacle and the camera are calculated by the time-of-flight method. For example, the obstacle is located 10° in the direction and 10 meters in front of the camera.

Step S3: Output the name of the object in the image and the distance and orientation between the object and the camera unit according to the recognized road conditions.

For example, according to the road condition identified in step S2, the objects on the road condition image The body name and the distance and orientation between the object and the camera unit 11 are output. If it is recognized that there is a trash can at a position 10° to the right and 8 meters from the camera unit.

Step S4, judging whether there is an obstacle in the road condition according to the distance and orientation between the object and the camera unit.

The obstacles include vehicles, pedestrians, trees, steps, rocks, etc. that appear on the road when the user is walking. In one embodiment of the present invention, the user's movement track is acquired by the positioning unit 12, and the distance between the identified object and the camera unit 11 is used, and the angle between the movement track and the object's position is used to determine whether the angle changes with time. The progress gradually decreases and when the included angle is less than a preset value, it is determined that the object is an obstacle. For example, the camera unit 11 acquires a trash can 20° in front of the right side of the user, and there is a trash can in a 20-meter direction, and the included angle gradually decreases as time goes by. When it is less than 15°, it is determined that the trash can is an obstacle.

Step S5: If there is an obstacle, the name of the obstacle and the distance between the obstacle and the camera unit are output in a preset manner.

In one embodiment of the present invention, the preset method includes prompting through an output unit 13 provided on a navigation device for the blind. The output unit 13 may be a voice broadcaster or a vibrator on the navigation device for the blind.

For example, when there is an obstacle, the processor 15 calculates and monitors the distance between the obstacle and the camera unit 11. If the distance is less than a preset value, it is set on a navigation device for the blind through a voice broadcaster or The vibrator sends out a vibration response.

In other embodiments of the present invention, the step further includes searching for road conditions at a preset distance from the camera unit 11 in the database, and if there are obstacles in the road conditions at the preset distance, passing the output unit 13 Prompt information is output by default.

In an embodiment of the present invention, the road condition of a preset distance from the camera unit 11 is searched in the database, and the preset distance exceeds the field of view of the current camera unit 11, according to actual conditions. The conditions can be 50 meters, 100 meters, etc. According to the search results of the road conditions, if there are obstacles in the path, or there are roads that are not suitable for the blind and visually impaired, the user will be prompted through the voice broadcaster or the user will be re-planned. Action trajectory. The said roads that are not suitable for the blind and weak people to pass include the presence of water on the road, a large amount of gravel on the ice surface, and the road. In another embodiment of the present invention, there is a sensing unit 14 on the navigation device for the blind 1 to sense unknown objects suddenly appearing around the user and remind the user in the form of a voice broadcaster or vibration. Unidentified objects include boulders that fall suddenly, vehicles that turn sharply, etc.

The method further includes: uploading the real-time acquired road conditions to the database when the preset distance from the camera unit 11 is found in the database and the road conditions are not consistent with the real-time acquired road conditions, and uploading the real-time acquired road conditions to the database. Delete the corresponding historical traffic conditions.

For example, retrieve the road conditions within 100 meters from the camera unit in the database, and after searching, it is determined that there is an obstacle mark in the middle of the road ahead at a location 60 meters away from the first obstacle, but when the user walks to When the roadblock mark is 10 meters away, the recognition camera unit 11 instantly obtains the road condition that the roadblock mark does not exist, then uploads the real-time obtained road condition to the database, and deletes the historical road condition in the database .

In another embodiment of the present invention, the step further includes: receiving the target location input by the user and obtaining the user's current location information; calculating and outputting the path between the current location and the target location; obtaining the road conditions in the database , Determine whether the path is suitable for the blind to pass according to the preset rules; if it is not suitable, give a voice prompt.

For example, the computer device 2 receives the target location input by the user and the user's current location information, and calculates the path between the current location and the target location through a navigation path optimization algorithm. The navigation path optimization algorithm includes, but is not limited to, the dijkstra algorithm, the A-star algorithm, the highway hierarchies algorithm, and the like. Obtain the road conditions of the path in the database, and determine whether the path is suitable for the blind to pass according to preset rules. The preset rules include whether the path has puddles, ice or not. The road conditions are not suitable for blind people.

The above-mentioned FIG. 2 describes the navigation method for the blind of the present invention in detail. In conjunction with FIG. 3, the functional modules of the software device for implementing the navigation method for the blind and the hardware device architecture for the navigation method for the blind are introduced.

It should be understood that the embodiments are only for illustrative purposes, and are not limited by this structure in the scope of the patent application.

Example three

Fig. 3 is a structural diagram of a preferred embodiment of the navigation device for the blind of the present invention.

In some embodiments, the blind navigation device 1 includes a blind navigation device 1 including a camera unit 11, a positioning unit 12, an output unit 13, a sensing unit 14, a processor 15, and a memory 16. The memory 16 is used to store computer program instructions that are run by the processor 15 and execute the following functional modules. The functional modules include an acquisition module 101, an identification module 102, and a judgment module 103. The execution module 104 and the reminder module 105. The module referred to in the present invention refers to a series of computer program segments that can be executed by at least one processor and can complete fixed functions, which are stored in the memory.

The acquisition module 101 is used to acquire images with road conditions collected by the camera unit.

In one embodiment of the present invention, the camera unit 11 may be a 3D camera. In other embodiments of the present invention, the camera unit 11 may be a 360° panoramic 3D camera.

When the road condition is that a blind person is walking, the camera unit 11 collects all road conditions, pedestrian and vehicle conditions, conditions over the walking route, etc. within the range.

The identification module 102 is used to identify the road condition information in the image, and send the road condition information and the location information corresponding to the road condition to a database, wherein the database contains the route information Image and location information corresponding to the road condition information.

In an embodiment of the present invention, the step of identifying road conditions in the image may specifically include: Obtain the 3D image collected by the 3D camera; split the 3D image into a depth image and a two-dimensional image; identify the name of the object in the two-dimensional image by the image recognition method; calculate the data by the time-of-flight method The distance and orientation between the object and the 3D camera.

In one embodiment of the present invention, the current location information can be obtained by the positioning unit 12 on the navigation device for the blind, and the method for obtaining the current location by the positioning unit 12 can be obtained by the GPS global positioning system. The image containing the road condition and the location information corresponding to the image are sent to a database after image compression processing. The database stores the image containing the road condition and the location corresponding to the image News. The image compression method includes, but is not limited to, an image compression technology based on MPEG4 encoding and an image compression technology based on H.265 encoding.

For example, collect a 3D image with road conditions through a 3D camera, and send the 3D image to the recognition module 102, and the 3D camera outputs a four-channel image that contains the color of each image element Information and the depth of each image element, the color information of each image element is integrated into a two-dimensional image, and the depth information of each image element is integrated into a depth image. The image recognition method is used to recognize the name of the object in the two-dimensional image. The image recognition method includes, but is not limited to, a neural network algorithm based on deep learning, an image recognition method based on wavelet transform, and the like. The distance between the obstacle and the camera and the relative position and angle of the obstacle and the camera are calculated by the time-of-flight method. For example, the obstacle is located 10° in the direction and 10 meters in front of the camera.

The judgment module 103 is used to output the name of the object in the image and the distance and orientation between the object and the camera unit according to the recognized road conditions.

For example, according to the road condition identified in step S2, the name of the object on the road condition image and the distance and orientation between the object and the camera unit 11 are output. For example, it is recognized that the distance to the camera unit 11 from the front right is 10° and 8 meters There is a trash can in its location.

The execution module 104 is used for according to the distance between the object and the camera unit and The orientation determines whether there is an obstacle in the road condition.

The obstacles include vehicles, pedestrians, trees, steps, rocks, etc. that appear on the road when the user is walking. In one embodiment of the present invention, the user's movement track is obtained by the positioning unit 12, and the distance between the identified object and the camera unit 11 is used, and the angle between the movement track and the object's position is used to determine whether the angle changes with time. The progress gradually decreases and when the included angle is less than a preset value, it is determined that the object is an obstacle. For example, the camera unit 11 acquires that the user’s front right is 20°, and there is a trash can in the direction of 20 meters, and as time goes by, the included angle gradually decreases. When it is less than 15°, it is determined that the trash can is an obstacle. .

The reminder module 105 is used for outputting reminder information in a preset manner when there is an obstacle, the name of the obstacle and the distance between the obstacle and the camera unit.

In one embodiment of the present invention, the preset method includes prompting through an output unit 13 provided on a navigation device for the blind. The output unit 13 may be a voice broadcaster or a vibrator on the navigation device for the blind.

For example, when there is an obstacle, the execution module 104 calculates and monitors the distance between the obstacle and the camera unit 11, and if the distance is less than a preset value, it uses a voice broadcaster or a navigation device for the blind. The above vibrator sends out a vibration response.

In other embodiments of the present invention, the step further includes searching for road conditions at a preset distance from the camera unit 11 in the database, and if there are obstacles in the road conditions at the preset distance, passing the output unit 13 Prompt information is output by default.

In one embodiment of the present invention, the road condition of a preset distance from the camera unit 11 is searched in the database, and the preset distance is beyond the field of view of the current camera unit 11. According to the actual situation, 50 meters or 100 meters can be selected. According to the search result of the road conditions, if there are obstacles in the path, or a road that is not suitable for the blind and visually impaired, the user will be prompted through the voice broadcaster or the user's trajectory will be re-planned. The said roads that are not suitable for the blind and impaired people include the presence of water on the roads, There are a lot of rubble on the ice and on the road. In another embodiment of the present invention, there is a sensing unit 14 on the navigation device for the blind 1 to sense unknown objects suddenly appearing around the user, and remind the user in the form of a voice broadcaster or vibration, the Unidentified objects include boulders that fall suddenly, vehicles that turn sharply, etc.

The method further includes: uploading the real-time acquired road conditions to the database when the preset distance from the camera unit 11 is found in the database and the road conditions are not consistent with the real-time acquired road conditions, and uploading the real-time acquired road conditions to the database. Delete the corresponding historical traffic conditions.

For example, retrieve the road conditions within 100 meters from the camera unit in the database, and after searching, it is determined that there is an obstacle mark in the middle of the road ahead at a location 60 meters away from the first obstacle, but when the user walks to When the roadblock mark is 10 meters away, the recognition camera unit 11 instantly obtains the road condition that the roadblock mark does not exist, then uploads the real-time obtained road condition to the database, and deletes the historical road condition in the database .

In another embodiment of the present invention, the step further includes: receiving the target location input by the user and obtaining the user's current location information; calculating and outputting the path between the current location and the target location; obtaining the road conditions in the database , Determine whether the path is suitable for the blind to pass according to the preset rules; if it is not suitable, give a voice prompt.

For example, the execution module 104 receives the target location input by the user and the user's current location information, and calculates the path between the current location and the target location through a navigation path optimization algorithm. The navigation path optimization algorithm includes, but is not limited to, the dijkstra algorithm, the A-star algorithm, the highway hierarchies algorithm, and the like. Obtain the road conditions of the path in the database, and determine whether the path is suitable for blind people to pass by according to preset rules. The preset rules include whether the path has puddles, ice, a large number of rocks, etc. Road conditions that are not suitable for blind people to pass. .

If the integrated module/unit of the blind navigation device is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiments and methods, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the foregoing method embodiments. Wherein, the computer program includes computer program code, and the computer program code may be in the form of original program code, object code, executable file, or some intermediate forms. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only) Only Memory), Random Access Memory (RAM, Random Access Memory), electrical carrier signal, telecommunications signal, and software distribution media. It should be noted that the content contained in the computer-readable medium can be appropriately added or deleted according to the requirements of the legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to the legislation and patent practice, the computer-readable medium Does not include electrical carrier signals and telecommunication signals.

In the several embodiments provided by the present invention, it should be understood that the disclosed computer device and method can be implemented in other ways. For example, the embodiments of the computer device described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation.

In addition, the functional units in the various embodiments of the present invention may be integrated in the same processing unit, or each unit may exist alone physically, or two or more units may be integrated in the same unit. The above-mentioned integrated unit can be realized either in the form of hardware, or in the form of hardware plus software functional modules.

For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description, so it is intended to fall within the claims. All changes within the meaning and scope of the equivalent elements are included in the present invention. Should not Treat any reference signs in the request as the request involved in the restriction. In addition, it is obvious that the word "including" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or computer devices stated in the computer device request item can also be implemented by the same unit or computer device through software or hardware. Words such as first and second are used to denote names, but do not denote any specific order.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be Modifications or equivalent replacements are made without departing from the spirit and scope of the technical solutions of the present invention.

Claims (10)

A navigation method for the blind, which is applied to a navigation device for the blind. The method includes: acquiring an image with road conditions collected by a camera unit; identifying the road conditions in the image, and combining the road conditions with The location information corresponding to the road condition is sent to a database, where the image containing the road condition and the location information corresponding to the road condition are stored in the database; according to the identified road condition, the name of the object in the image and the location information are output The distance and orientation between the object and the camera unit; judging whether there is an obstacle in the road condition according to the distance and the orientation between the object and the camera unit, wherein the judging whether there is an obstacle in the road condition The object includes acquiring the user's movement track, and determining the angle between the movement track and the object's position according to the distance and orientation of the object and the camera unit, and judging whether the angle is gradually reduced over time And when the included angle is less than a predetermined value, it is determined that the object is an obstacle; if there is an obstacle, the name of the obstacle and the distance between the obstacle and the camera unit are determined in a predetermined manner Output prompt information. The navigation method for the blind according to claim 1, wherein the method further comprises: searching for road conditions at a preset distance from the camera unit in the database, and if there are obstacles in the road conditions at the preset distance , The prompt information will be output by default. The navigation method for the blind according to claim 2, wherein the method further comprises: when the road condition of a preset distance from the obstacle found in the database does not match the real-time access road condition, the method further comprises: Obtain the road conditions and upload them to the database, and delete the corresponding historical road conditions in the database. The navigation method for the blind according to claim 1, wherein the method further includes: Receive the target location input by the user and obtain the user's current location information; calculate and output the path between the current location and the target location; obtain the road conditions in the database, and determine whether the path is suitable for the blind to pass according to preset rules ; And if the path is not suitable for blind people to pass, a voice prompt is issued. The navigation method for the blind according to claim 1, wherein the image is a 3D image; and the camera unit is a 3D camera. The navigation method for the blind according to claim 5, wherein the step of identifying the road condition in the image includes: acquiring a 3D image collected by a 3D camera; splitting the 3D image into a depth image and two A three-dimensional image; the name of the object in the two-dimensional image is recognized by an image recognition method; the distance and orientation between the object and the 3D camera are calculated by the time-of-flight method. The navigation method for the blind according to claim 1, wherein the preset mode includes outputting prompt information through a voice broadcast unit provided on a navigation device for the blind and/or sending a vibration prompt through a vibration unit provided on the navigation device for the blind. A navigation device for the blind, the device comprising: a camera unit, the camera unit is a 3D camera for acquiring and collecting images in front of the road; a processor for executing computer program instructions; memory: for storing computer programs Instructions, the computer program instructions are run by the processor and perform the following steps: acquiring images with road conditions collected by the camera unit; identifying the road conditions in the images, and matching the road conditions with the road conditions The location information of is sent to the database, where the image containing the road conditions and the location corresponding to the road conditions are stored in the database Information; according to the recognized road condition, output the name of the object in the image and the distance and orientation between the object and the camera unit; judge the road condition based on the distance and orientation between the object and the camera unit Whether there is an obstacle in the road condition, wherein the judging whether there is an obstacle in the road condition includes obtaining the user's action trajectory, and determining the action trajectory and the object according to the distance and orientation of the object and the camera unit The included angle of the location, determine whether the included angle gradually decreases over time, and when the included angle is less than a preset value, determine that the object is an obstacle; if there is an obstacle, use the name of the obstacle And the distance between the obstacle and the camera unit through the output unit to output prompt information in a preset manner. The navigation device for the blind according to claim 8, wherein the navigation device for the blind includes any one of AR glasses, smart watches, smart belts, smart sticks, and smart wearable devices. The navigation device for the blind according to claim 8, wherein the navigation device for the blind further includes a positioning unit, and when the computer instructions are executed by the processor, the following steps are also executed: receiving the target position input by the user and passing the The positioning unit obtains the user’s current position information; calculates and outputs the path between the current position and the target position; obtains road condition information in the database, and judges whether the path is suitable for blind people to pass according to preset rules; if it is not, it controls the station The output unit issues a voice prompt.

Images