CN-121994266-A - Blind person navigation method, device, electronic equipment, readable storage medium and product

CN121994266ACN 121994266 ACN121994266 ACN 121994266ACN-121994266-A

Abstract

The application provides a navigation method, a device, an electronic device, a readable storage medium and a product for the blind, the technical proposal of the application is that navigation information of the blind is obtained in the process of going out of the blind, thus obtaining the current video data of the blind in the process of moving to a destination by the user, thereby identifying the video data and obtaining the identification result, the method and the device can accurately judge whether the blind user currently has ground or air obstacles to cause the blind user to move normally through the identification result, thereby generating prompt voice to prompt the blind user to move, realizing the real-time consideration of the space obstacle information of the surrounding environment of the blind user in the navigation process of the blind user, and improving the navigation effect.

Inventors

LI ZHIFU
YAO CHAOQUAN
MIAO JINGHUA
YANG JIN

Assignees

北京京东方显示技术有限公司
京东方科技集团股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260330

Claims (12)

1. A method of navigation for a blind person, applied to an AR device, the method comprising: acquiring navigation information input by a blind user, wherein the navigation information comprises a departure place and a destination of the blind user; Acquiring video data of the current position of the blind user in the process that the blind user moves to the destination based on the navigation information, wherein the video data comprises environment information of the current position; identifying the video data to obtain an identification result, wherein the identification result is used for indicating the space obstacle information of the current position and whether the space obstacle information influences the blind user to move towards the destination; And generating prompt voice according to the recognition result, wherein the prompt voice is used for guiding the blind user to move to the destination.
2. The method of claim 1, wherein prior to the obtaining navigation information entered by the blind user, the method further comprises: After the blind user wears the AR equipment, initializing the AR equipment; Wherein the initializing process includes: Scanning the appearance of the blind user to acquire physiological parameter information of the blind user, wherein the physiological parameter information comprises height data, weight data and stature data corresponding to the blind user, and the stature data comprises at least one of chest circumference, waistline and hip circumference of the blind user; Identifying the space where the blind person user is located, and determining a target plane space, wherein the target plane space is a plane space with a preset area; Generating movement test voice according to the target plane space, wherein the movement test voice is used for indicating the blind user to move in the target plane space; And detecting the moving distance and moving time corresponding to the blind user in the process that the blind user moves in the target plane space based on the moving test voice, and determining moving data of the blind according to the moving distance and the moving time, wherein the moving data comprises the moving speed and the stride of the blind.
3. The method according to claim 2, wherein, in the case that the video data includes a blind track, the identifying the video data to obtain an identification result includes: decoding the video data to obtain a first image sequence comprising a plurality of first image data; inputting the first image sequence into a pre-trained feature detection network to perform feature recognition, and obtaining a first recognition result, wherein the first recognition result comprises position information of the blind road and barrier information of the blind road, and the position information of the blind road comprises at least one of the extending direction of the blind road, the width of the blind road and the length of the blind road; The generating the prompt voice according to the recognition result comprises the following steps: And generating a first prompt voice for guiding the blind user to move on the blind road under the condition that the obstacle information indicates that the blind road is free of obstacles.
4. A method according to claim 3, characterized in that the method further comprises: Calculating the volume occupied by the stationary obstacle on the blind road under the condition that the obstacle information indicates that the stationary obstacle exists in the blind road, so as to obtain a first calculation result; generating a second prompt voice for guiding the blind user to move on the blind road under the condition that the first calculation result is smaller than a preset obstacle volume, wherein the preset obstacle volume is generated based on the stature data and the weight data; And generating a third prompt voice for guiding the blind user to bypass the static obstacle to move under the condition that the first calculation result is larger than or equal to the preset obstacle volume.
5. A method according to claim 3, characterized in that the method further comprises: Calculating the height of the air obstacle under the condition that the obstacle information indicates that the blind sidewalk has the air obstacle, so as to obtain a second calculation result; Generating a first judgment result based on the second calculation result and the height data; generating fourth prompting voice under the condition that the first judging result indicates that the blind user cannot collide with the air obstacle when moving on the blind road, wherein the fourth prompting voice is used for guiding the blind user to move on the blind road; And generating a fifth prompting voice under the condition that the first judging result indicates that the blind user collides with the air obstacle when moving on the blind road, wherein the fifth prompting voice is used for guiding the blind user to bypass the air obstacle to move.
6. A method according to claim 3, characterized in that the method further comprises: Calculating the time of the moving obstacle reaching the blind road and the position of the moving obstacle reaching the blind road under the condition that the obstacle information indicates that the blind road has the moving obstacle, so as to obtain a third calculation result; generating a second judgment result based on the third calculation result and the movement data; Generating a sixth prompting voice when the second judging result indicates that the blind user does not collide with the moving obstacle when moving on the blind road, wherein the sixth prompting voice is used for guiding the blind user to move on the blind road; And under the condition that the second judging result indicates that the blind user collides with the moving obstacle when moving on the blind road, generating a seventh prompting voice, wherein the seventh prompting voice is used for guiding the blind user to move around the moving obstacle.
7. The method according to claim 2, wherein, in the case where the video data includes zebra stripes, the identifying the video data to obtain the identification result includes: decoding the video data to obtain a second image sequence comprising a plurality of second image data; inputting the second image sequence into a pre-trained feature detection network for feature recognition to obtain a second recognition result, wherein the second recognition result comprises the position information of the zebra stripes, and the position information of the zebra stripes comprises at least one of the extending direction of the zebra stripes, the width of the zebra stripes and the length of the zebra stripes; The generating the prompt voice according to the recognition result comprises the following steps: Generating an eighth prompting voice and guiding the blind user to move on the zebra stripes based on the eighth prompting voice.
8. The method of claim 7, wherein the method further comprises: acquiring a first duration corresponding to a traffic light when the zebra crossing comprises the traffic light; Calculating the time of the blind user passing through the zebra stripes according to the movement data and the position information of the zebra stripes to obtain a second time length; Generating a ninth prompting voice under the condition that the first time length is smaller than the second time length, wherein the ninth prompting voice is used for guiding the blind user to wait in situ; and generating tenth prompt voice under the condition that the first time length is greater than or equal to the second time length, wherein the tenth prompt voice is used for guiding the blind user to move on the zebra stripes.
9. A navigation device for the blind, applied to an AR apparatus, comprising: The first acquisition module is used for acquiring navigation information input by a blind user, wherein the navigation information comprises a departure place and a destination of the blind user; The second acquisition module is used for acquiring video data of the current position of the blind user in the process that the blind user moves to the destination based on the navigation information, wherein the video data comprises environment information of the current position; The identification module is used for identifying the video data to obtain an identification result, wherein the identification result is used for indicating the space obstacle information of the current position and whether the space obstacle information affects the blind user to move towards the destination; And the generation module is used for generating prompt voice according to the recognition result, and the prompt voice is used for guiding the blind user to move to the destination.
10. An electronic device comprising a processor, a memory and a program stored on the memory and executable on the processor, the program when executed by the processor implementing the steps of the method according to any one of claims 1 to 8.
11. A computer readable storage medium, characterized in that it has stored thereon a computer program which, when executed by a processor, implements the steps of the method according to any of claims 1 to 8.
12. A computer program product comprising computer instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 8.

Description

Blind person navigation method, device, electronic equipment, readable storage medium and product Technical Field The invention relates to the technical field of computers, in particular to a navigation method and device for a blind person, electronic equipment, a readable storage medium and a product. Background The visually impaired people face multiple security threats in outdoor travel, and the blind sticks, which are auxiliary tools necessary for the blind to go out, cannot detect air obstacles and cannot analyze surrounding dangerous environments. In the prior art, a global positioning system (Global Positioning System, GPS) is generally arranged in an electronic navigation crutch to realize real-time navigation, however, microscopic topography cannot be identified in the mode, and an ultrasonic obstacle avoidance device often misjudges fallen leaves as fixed obstacles, so that the problem of poor navigation effect occurs. Disclosure of Invention The invention provides a navigation method, a navigation device, electronic equipment, a readable storage medium and a product for the blind, which solve the problem of poor navigation effect in the prior art. To solve the above problems, the present invention is achieved as follows: In a first aspect, a navigation method for a blind person is provided, applied to an AR device, the method including: acquiring navigation information input by a blind user, wherein the navigation information comprises a departure place and a destination of the blind user; Acquiring video data of the current position of the blind user in the process that the blind user moves to the destination based on the navigation information, wherein the video data comprises environment information of the current position; identifying the video data to obtain an identification result, wherein the identification result is used for indicating the space obstacle information of the current position and whether the space obstacle information influences the blind user to move towards the destination; And generating prompt voice according to the recognition result, wherein the prompt voice is used for guiding the blind user to move to the destination. Optionally, before the navigation information input by the blind user is obtained, the method further includes: After the blind user wears the AR equipment, initializing the AR equipment; Wherein the initializing process includes: Scanning the appearance of the blind user to acquire physiological parameter information of the blind user, wherein the physiological parameter information comprises height data, weight data and stature data corresponding to the blind user, and the stature data comprises at least one of chest circumference, waistline and hip circumference of the blind user; Identifying the space where the blind person user is located, and determining a target plane space, wherein the target plane space is a plane space with a preset area; Generating movement test voice according to the target plane space, wherein the movement test voice is used for indicating the blind user to move in the target plane space; And detecting the moving distance and moving time corresponding to the blind user in the process that the blind user moves in the target plane space based on the moving test voice, and determining moving data of the blind according to the moving distance and the moving time, wherein the moving data comprises the moving speed and the stride of the blind. Optionally, in the case that the video data includes a blind track, the identifying the video data to obtain an identifying result includes: decoding the video data to obtain a first image sequence comprising a plurality of first image data; inputting the first image sequence into a pre-trained feature detection network to perform feature recognition, and obtaining a first recognition result, wherein the first recognition result comprises position information of the blind road and barrier information of the blind road, and the position information of the blind road comprises at least one of the extending direction of the blind road, the width of the blind road and the length of the blind road; The generating the prompt voice according to the recognition result comprises the following steps: And generating a first prompt voice for guiding the blind user to move on the blind road under the condition that the obstacle information indicates that the blind road is free of obstacles. Optionally, the method further comprises: Calculating the volume occupied by the stationary obstacle on the blind road under the condition that the obstacle information indicates that the stationary obstacle exists in the blind road, so as to obtain a first calculation result; generating a second prompt voice for guiding the blind user to move on the blind road under the condition that the first calculation result is smaller than a preset obstacle volume, wherein the preset obstacle volume is generated based on the