CN117452515A - Blind guiding system and method - Google Patents

Blind guiding system and method Download PDF

Info

Publication number
CN117452515A
CN117452515A CN202311399467.3A CN202311399467A CN117452515A CN 117452515 A CN117452515 A CN 117452515A CN 202311399467 A CN202311399467 A CN 202311399467A CN 117452515 A CN117452515 A CN 117452515A
Authority
CN
China
Prior art keywords
evaluation
path
environment
comprehensive
module
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.)
Pending
Application number
CN202311399467.3A
Other languages
Chinese (zh)
Inventor
闫瑞瑞
陈海鹏
曾景培
潘铄环
陈浩涛
吕志胜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangzhou Maritime University
Original Assignee
Guangzhou Maritime University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guangzhou Maritime University filed Critical Guangzhou Maritime University
Priority to CN202311399467.3A priority Critical patent/CN117452515A/en
Publication of CN117452515A publication Critical patent/CN117452515A/en
Pending legal-status Critical Current

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61FFILTERS IMPLANTABLE INTO BLOOD VESSELS; PROSTHESES; DEVICES PROVIDING PATENCY TO, OR PREVENTING COLLAPSING OF, TUBULAR STRUCTURES OF THE BODY, e.g. STENTS; ORTHOPAEDIC, NURSING OR CONTRACEPTIVE DEVICES; FOMENTATION; TREATMENT OR PROTECTION OF EYES OR EARS; BANDAGES, DRESSINGS OR ABSORBENT PADS; FIRST-AID KITS
    • A61F9/00Methods or devices for treatment of the eyes; Devices for putting-in contact lenses; Devices to correct squinting; Apparatus to guide the blind; Protective devices for the eyes, carried on the body or in the hand
    • A61F9/08Devices or methods enabling eye-patients to replace direct visual perception by another kind of perception
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20Instruments for performing navigational calculations
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3407Route searching; Route guidance specially adapted for specific applications
    • G01C21/3415Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01VGEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS
    • G01V11/00Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Life Sciences & Earth Sciences (AREA)
  • Vascular Medicine (AREA)
  • Geophysics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Ophthalmology & Optometry (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention discloses a blind guiding system and method, comprising a data acquisition module, a credibility evaluation and weight configuration module, an operation and environment evaluation module, a path planning and evaluation module, an optimal path selection and navigation execution module, wherein environment data are acquired in real time, credibility evaluation is carried out on each data source, corresponding weights are distributed for each data source according to an evaluation result, further, the values of each data source and the weights are comprehensively operated by a weighted average method to obtain a comprehensive environment evaluation value, whether the current environment is safe or not is judged according to a preset threshold value, a unique optimal path selection method is designed based on special requirements and safety consideration of blind users, each path is evaluated, an optimal path evaluation value of each path is calculated by using a mathematical formula, the paths with the highest evaluation values are ordered according to the optimal path evaluation values, and the paths with the highest evaluation values are selected as optimal paths.

Description

Blind guiding system and method
Technical Field
The invention relates to the technical field of blind guiding path calculation, in particular to a blind guiding system and a blind guiding method.
Background
Currently, blind-guide systems typically rely on only a single data source or sensor, such as an infrared sensor, an ultrasonic sensor, or an image recognition camera, to provide environmental information and routing, however, the use of such a single data source has some drawbacks;
the single data source cannot fully cover the environmental information under various conditions, so that inaccurate or missing detection of specific obstacles or road conditions is easily caused, noise and inaccurate data can be generated by the single data source due to errors of sensors or other factors, the reliability and accuracy of a system are reduced, a traditional blind guiding system often lacks a mechanism for acquiring and verifying real-time road conditions, the road condition change cannot be fed back in time, and inconvenience and safety risks are brought to blind users;
the invention aims at providing the solution to the defects that:
for the comprehensive operation of three data sources, carrying out weight configuration by combining the credibility, carrying out the comprehensive operation on the information of a plurality of data sources, and distributing weights according to the credibility, thereby improving the accuracy and the reliability of the environmental information;
the data intercommunication among the devices realizes the integration and verification of the sensor data through the sharing and the communication among the devices, and improves the performance and the credibility of the system;
the acquisition and updating mechanism of real-time road conditions is increased through the authenticity verification of the road condition information provided by other normal users, so that a blind guiding system can acquire accurate road condition information in time and provide corresponding prompt and adjustment advice for blind users;
by means of comprehensive operation, data intercommunication and road condition information verification, the problems of incomplete information, unreliable data and lack of real-time road condition information caused by a single data source are solved, the performance and the practicability of the blind guiding system are improved, and more accurate, reliable and convenient navigation service is provided for blind users.
Disclosure of Invention
The invention provides a blind guiding system and a blind guiding method for solving the technical problems.
The technical scheme of the invention is realized as follows: the blind guiding system comprises a data acquisition module, a credibility evaluation and weight configuration module, an operation and environment evaluation module, a path planning and evaluation module and an optimal path selection and navigation execution module;
the data acquisition module is connected with the credibility evaluation and weight configuration module and is used for acquiring environment data in real time and transmitting the acquired data to the credibility evaluation and weight configuration module;
the credibility evaluation and weight configuration module is connected with the data acquisition module and the operation and environment evaluation module and is used for carrying out credibility evaluation on each data source according to the acquired environment data, distributing corresponding weight for each data source and then transmitting an evaluation result and weight information to the comprehensive operation and environment evaluation module;
the operation and environment assessment module is connected with the credibility assessment and weight configuration module and the path planning and assessment module, and is used for receiving the assessment result and weight information transmitted by the credibility assessment and weight configuration module, carrying out comprehensive operation on the value and weight of each data source by using a weighted average method to obtain a comprehensive environment assessment value, simultaneously comparing the comprehensive environment assessment value with a preset threshold value to judge whether the current environment is safe or not, and triggering the path planning module to re-plan the path if the environment assessment result is unsafe;
the path planning and evaluating module is connected with the operation and environment evaluating module and the optimal path selecting and navigating executing module, and is used for designing a unique optimal path selecting method according to the special requirements and safety consideration of blind users under the instruction of the operation and environment evaluating module, wherein the module can consider a plurality of factors, such as avoiding obstacles such as slopes and steps, combining user feedback and personalized adjustment, and transmitting optimal path information to the optimal path selecting and navigating executing module after the planning is completed;
the optimal path selection and navigation execution module is connected with the path planning and evaluation module and is used for receiving the optimal path information transmitted by the path planning and evaluation module, sorting according to the optimal path evaluation value, selecting the path with the highest evaluation value as the optimal path, providing navigation guidance for blind users, continuously monitoring environment change, acquiring data source information in real time, recalculating the path evaluation value, and adjusting the path or giving an alarm according to the requirement so as to adapt to the real-time situation.
A blind guiding method comprises the following steps:
s1, acquiring environmental data by using an infrared sensor, an ultrasonic sensor and image recognition camera equipment;
s2, evaluating and assigning the credibility of each data source according to the sensor performance and the historical accuracy factors;
s3, giving weight to the comprehensive operation according to the credibility, and carrying out the comprehensive operation on the data of the three data sources:
comprehensive environmental assessment= (w1+w2+d2+w3+d3)/(w1+w2+w3)
Wherein w1, w2, w3 respectively represent weights of the infrared, ultrasonic and image data sources, and d1, d2, d3 respectively represent values of the corresponding data sources
S4, comparing the environment evaluation judgment with a preset threshold value according to the comprehensive environment evaluation result, and judging whether the current environment is safe or not;
if the comprehensive environment evaluation is more than or equal to the threshold value, the environment is relatively safe, and navigation can be continued;
if the comprehensive environment evaluation is less than the threshold value, the situation that the obstacle or the dangerous situation exists is indicated, and corresponding measures such as stopping or changing the navigation path are needed to be taken;
s5, designing a unique optimal path selection method according to the special requirements and safety requirements of the blind, and evaluating each path by considering factors such as safety, feasibility, individuation and the like;
s6, calculating an optimal path evaluation value of each path according to the path planning result by path evaluation calculation:
optimal path evaluation=w s *s+w_f*f+w_p*p
Wherein w is s W_f and w_p respectively represent weights of safety, feasibility and individualization indexes, and s, f and p respectively represent values of corresponding indexes;
s7, selecting optimal paths, sorting according to the optimal path evaluation values, and selecting a path with the highest evaluation value as the optimal path:
if the optimal path evaluation value is more than or equal to a threshold value, selecting the path as an optimal path, and navigating the blind user;
and if the optimal path evaluation value is less than the threshold value, the path needs to be re-planned or other measures are taken, so that the navigation safety is ensured.
Further, the data acquisition in the step S1 uses an infrared sensor, an ultrasonic sensor and an image recognition camera device, environmental data are collected through the sensors, the infrared sensor can detect the distance and heat distribution condition of surrounding objects, the ultrasonic sensor can emit ultrasonic waves and receive reflected signals of the ultrasonic waves for measuring the distance and the shape of the objects, and the image recognition camera can capture image information in the environment;
in the S2 stage, the credibility evaluation of each data source is performed according to the sensor performance and the historical accuracy factors, and the evaluation process comprises the following steps:
sensor performance evaluation: testing and evaluating the performance of each sensor, including precision, sensitivity and stability aspects, such as the measurement range and precision of the infrared sensor and the distance measurement precision of the ultrasonic sensor;
historical accuracy assessment: evaluating the accuracy of each sensor according to previous data collection, wherein the accuracy comprises the matching degree and the error range with the actual environmental conditions;
confidence assignment: based on the sensor performance and the historical accuracy assessment results, assigning a corresponding confidence value to each data source, the confidence typically being represented by a number between 0 and 1, higher values representing higher confidence for the data source;
after the reliability evaluation of the data source is completed in the step S2, the evaluation result can be further transmitted to a subsequent module (S3) for the comprehensive operation of the weighted average method and the calculation of the comprehensive environment evaluation.
Further, in the step S3, a corresponding confidence value is allocated to each data source according to the confidence evaluation result, and these confidence values will be used to perform a comprehensive operation and calculate a comprehensive environment evaluation:
the preset infrared sensor (I R), the Ultrasonic Sensor (US) and the image recognition camera (Cam) are respectively distributed with reliability values of w1, w2 and w3;
and (3) comprehensive operation: the comprehensive environmental assessment is calculated by the following formula: comprehensive environmental assessment= (w1×d1+w2×d2+w3×d3)/(w1+w2+w3);
wherein d1, d2 and d3 represent values of the corresponding data sources, respectively, which are the distances measured by the sensor, the results of the image processing;
weighted average method: in the comprehensive operation, by multiplying corresponding weights and carrying out weighted average on all data sources, the higher the weights are, the greater the contribution of the data sources to the comprehensive environment evaluation is indicated, so that the reliability difference of different data sources is considered;
preset, the reliability value of the infrared sensor (I R) is w1=0.8, the reliability value of the Ultrasonic Sensor (US) is w2=0.9, the reliability value of the image recognition camera (Cam) is w3=0.7, meanwhile, the distance measured by the ultrasonic sensor is d1=2 meters, the distance measured by the ultrasonic sensor is d2=3 meters, and the image recognition camera detects an object and estimates the distance to be d3=2.5 meters;
the calculation of the comprehensive environmental assessment is as follows:
comprehensive environmental assessment= (0.8×2+0.9×3+0.7×2.5)/(0.8+0.9+0.7)
=(1.6+2.7+1.75)/2.4
=6.05/2.4
=2.52
And obtaining a comprehensive environment evaluation result, namely, a comprehensive environment evaluation value is 2.52, and comparing the comprehensive environment evaluation value with a threshold value according to a specific application scene and a preset threshold value to judge the safety of the current environment.
Further, in the step S4, according to the preset data in step S3, there are three data sources: an infrared sensor (I R), an Ultrasonic Sensor (US) and an image recognition camera (Cam), each data source being assigned a respective confidence value and weight;
the preset data are as follows:
the reliability value of the infrared sensor (I R) is w1=0.8;
the confidence value of the Ultrasonic Sensor (US) is w2=0.9;
the credibility value of the image recognition camera (Cam) is w3=0.7;
the values acquired by the data sources are preset as follows:
the value of the infrared sensor (I R) is d1=2 meters;
the value of the Ultrasonic Sensor (US) is d2=3 meters;
the value of the image recognition camera (Cam) is d3=2.5 meters;
the comprehensive operation formula is as follows:
comprehensive environmental assessment= (w) 1 *d 1 +w 2 *d 2 +w 3 *d 3 )/(w 1 +w 2 +w 3 )
Substituting preset data for calculation:
comprehensive environmental assessment= (0.8×2+0.9×3+0.7×2.5)/(0.8+0.9+0.7)
=(1.6+2.7+1.75)/2.4
=6.05/2.4
=2.52
Based on the calculation result, the comprehensive environment evaluation value is 2.52;
in the S4 stage, the comprehensive environmental assessment value is compared with a preset threshold value to determine the safety of the current environment, and the specific operation is as follows:
if the comprehensive environment evaluation value is larger than or equal to a preset threshold value, the comprehensive environment evaluation value is larger than or equal to the threshold value, namely 2.52 is larger than or equal to the threshold value, the current environment is relatively safe, and the blind user can be continuously navigated;
if the comprehensive environmental assessment value is smaller than the preset threshold value, the comprehensive environmental assessment < threshold value, namely 2.52< threshold value, indicates that the current environment has an obstacle or dangerous condition, and corresponding measures such as stopping navigation, changing a navigation path or giving an alarm need to be taken to ensure the safety of navigation.
Further, in the step S6-S7, the following preset data are obtained by substituting the preset data of S3 into the actual calculation:
security weight: w (w) s =0.5
The feasibility weight: w_f=0.3
Personalized weights: w_p=0.2
For each path, the following index values are preset:
safety index of path 1: s is(s) 1 =0.8
Path 1 feasibility index: f1 =0.7
Personalized index for path 1: p1=0.9
Path 2 security index: s2=0.6
Path 2 feasibility index: f2 =0.8
Personalized index of path 2: p2=0.7
Next, an optimal path evaluation value for each path is calculated according to an optimal path evaluation formula:
optimal path evaluation 1=ws_s1+w_f_f1+w_p_p1
=0.5*0.8+0.3*0.7+0.2*0.9
=0.4+0.21+0.18
=0.79
Optimal path evaluation 2=ws_s2+w_f_f2+w_p_p2
=0.5*0.6+0.3*0.8+0.2*0.7
=0.3+0.24+0.14
=0.68
In the S7 stage, sorting the optimal path evaluation values, selecting the path with the highest evaluation value as the optimal path, and according to the calculation result, the optimal path evaluation 1 is 0.79, and the optimal path evaluation 2 is 0.68, so that the path 1 with the highest optimal path evaluation value is selected as the optimal path, and the blind person user is continuously navigated;
through the steps of S6 and S7, we evaluate each path and rank and select according to the optimal path evaluation value.
Further, the index value obtaining manner in the step S6-S7 is as follows: sensor data: acquiring environmental information, such as measuring obstacle distance, detecting traffic conditions, identifying road conditions, by using infrared sensors, ultrasonic sensors, camera sensor devices;
based on the processing and analysis of the sensor data, specific values of safety, feasibility and personalized indexes can be obtained;
map and path information: the map data and the path planning algorithm are utilized to obtain the information of the path, such as the path length, traffic condition and congestion degree;
these information are used as part of the feasibility index;
database and history data: the safety and feasibility of the path are measured by collecting and analyzing historical data and accident record information;
these data are used as part of an evaluation index to predict the risk and feasibility of the path.
Advantageous effects
The accuracy and the reliability of the environmental information are improved, the three data sources (infrared, ultrasonic and image) are comprehensively operated, the weight configuration is carried out by combining the credibility, the blind guiding system can evaluate the environmental state more accurately, the accuracy and the reliability of the environmental information are improved, and the blind user is helped to sense the surrounding environment better;
the data integration and verification are realized through the sharing and interaction of the equipment, the integration and verification of the sensor data are realized, the information of the data source is comprehensively operated, the data intercommunication mechanism can improve the comprehensiveness and consistency of the system to the environmental information, reduce the error and noise, and improve the performance and the credibility of the system;
the real-time road condition updating and verification is carried out through the authenticity verification of the road condition information provided by other normal users, and the acquisition and updating mechanism of the real-time road condition is increased, so that the blind guiding system can timely acquire accurate road condition information, and provide corresponding prompt and adjustment advice according to real-time change, thereby enabling blind users to navigate more safely and conveniently;
the comprehensive technology solves the problems: by means of comprehensive operation, data intercommunication and road condition information verification, the problems of incomplete information, unreliable data and lack of real-time road condition information caused by a single data source are solved, the accuracy and reliability of environment information are improved through comprehensive operation and data integration, and the perception and coping capacity of a system to real-time road conditions are enhanced through road condition information verification.
Working principle:
firstly, environmental data are collected in real time, secondly, reliability assessment is carried out on each data source, corresponding weight is distributed to each data source according to assessment results, further, a weighted average method is utilized to carry out comprehensive operation on the value and the weight of each data source, comprehensive environmental assessment values are obtained, whether the current environment is safe or not is judged according to a preset threshold value, further, a unique optimal path selection method is designed based on special requirements and safety consideration of blind users, a plurality of factors such as slope avoidance, steps and other obstacles are considered, user feedback and personalized adjustment are combined, then, each path is assessed, a mathematical formula is used to calculate optimal path assessment value of each path, the assessment values are ordered according to the weight distribution of safety, feasibility and personalized indexes and specific calculation values of corresponding indexes, then, the path with the highest assessment value is selected as the optimal path, if the optimal path assessment values do not accord with the preset threshold value, the path is required to be re-planned or other measures are taken to ensure navigation safety, finally, a blind user is provided with navigation guidance system based on the selected optimal path, navigation system is provided to the user, navigation environment is continuously provided with navigation information is required to be monitored, and the path information is continuously adjusted in real time according to the navigation information, and the navigation information is required to be continuously monitored in real time.
Drawings
FIG. 1 is a block diagram of a blind guiding system according to an embodiment of the present invention;
fig. 2 is a block diagram of steps of a blind guiding method according to an embodiment of the present invention.
Detailed Description
In order that the objects and advantages of the invention will become more apparent, the invention will be further described with reference to the following examples; it should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present invention, and are not intended to limit the scope of the present invention.
It should be noted that, in the description of the present invention, terms such as "upper," "lower," "left," "right," "inner," "outer," and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, which are merely for convenience of description, and do not indicate or imply that the apparatus or elements must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention.
Furthermore, it should be noted that, in the description of the present invention, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention can be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1-2, a blind guiding system and method includes: the blind guiding system comprises a data acquisition module, a credibility evaluation and weight configuration module, an operation and environment evaluation module, a path planning and evaluation module and an optimal path selection and navigation execution module;
the data acquisition module is connected with the credibility evaluation and weight configuration module and is used for acquiring environment data in real time and transmitting the acquired data to the credibility evaluation and weight configuration module;
the credibility evaluation and weight configuration module is connected with the data acquisition module and the operation and environment evaluation module and is used for carrying out credibility evaluation on each data source according to the acquired environment data, distributing corresponding weight for each data source and then transmitting an evaluation result and weight information to the comprehensive operation and environment evaluation module;
the operation and environment assessment module is connected with the credibility assessment and weight configuration module and the path planning and assessment module, and is used for receiving the assessment result and weight information transmitted by the credibility assessment and weight configuration module, carrying out comprehensive operation on the value and weight of each data source by using a weighted average method to obtain a comprehensive environment assessment value, simultaneously comparing the comprehensive environment assessment value with a preset threshold value to judge whether the current environment is safe or not, and triggering the path planning module to re-plan the path if the environment assessment result is unsafe;
the path planning and evaluating module is connected with the operation and environment evaluating module and the optimal path selecting and navigating executing module, and is used for designing a unique optimal path selecting method according to the special requirements and safety consideration of blind users under the instruction of the operation and environment evaluating module, wherein the module can consider a plurality of factors, such as avoiding obstacles such as slopes and steps, combining user feedback and personalized adjustment, and transmitting optimal path information to the optimal path selecting and navigating executing module after the planning is completed;
the optimal path selection and navigation execution module is connected with the path planning and evaluation module and is used for receiving the optimal path information transmitted by the path planning and evaluation module, sorting according to the optimal path evaluation value, selecting the path with the highest evaluation value as the optimal path, providing navigation guidance for blind users, continuously monitoring environment change, acquiring data source information in real time, recalculating the path evaluation value, and adjusting the path or giving an alarm according to the requirement so as to adapt to the real-time situation.
A blind guiding method comprises the following steps:
s1, acquiring environmental data by using an infrared sensor, an ultrasonic sensor and image recognition camera equipment;
s2, evaluating and assigning the credibility of each data source according to the sensor performance and the historical accuracy factors;
s3, giving weight to the comprehensive operation according to the credibility, and carrying out the comprehensive operation on the data of the three data sources:
comprehensive environmental assessment= (w) 1 *d 1 +w 2 *d 2 +w 3 *d 3 )/(w 1 +w 2 +w 3 )
Wherein w is 1 、w 2 、w 3 Weights representing infrared, ultrasonic and image data sources, respectively, d 1 、d 2 、d 3 Respectively represent the values of the corresponding data sources
S4, comparing the environment evaluation judgment with a preset threshold value according to the comprehensive environment evaluation result, and judging whether the current environment is safe or not;
if the comprehensive environment evaluation is more than or equal to the threshold value, the environment is relatively safe, and navigation can be continued;
if the comprehensive environment evaluation is less than the threshold value, the situation that the obstacle or the dangerous situation exists is indicated, and corresponding measures such as stopping or changing the navigation path are needed to be taken;
s5, designing a unique optimal path selection method according to the special requirements and safety requirements of the blind, and evaluating each path by considering factors such as safety, feasibility, individuation and the like;
s6, calculating an optimal path evaluation value of each path according to the path planning result by path evaluation calculation:
optimal path evaluation=w s *s+w_f*f+w_p*p
Wherein w is s W_f and w_p respectively represent weights of safety, feasibility and individualization indexes, and s, f and p respectively represent values of corresponding indexes;
s7, selecting optimal paths, sorting according to the optimal path evaluation values, and selecting a path with the highest evaluation value as the optimal path:
if the optimal path evaluation value is more than or equal to a threshold value, selecting the path as an optimal path, and navigating the blind user;
and if the optimal path evaluation value is less than the threshold value, the path needs to be re-planned or other measures are taken, so that the navigation safety is ensured.
Specifically, the data acquisition in the S1 stage uses an infrared sensor, an ultrasonic sensor and an image recognition camera device, environmental data are collected through the sensors, the infrared sensor can detect the distance and heat distribution condition of surrounding objects, the ultrasonic sensor can emit ultrasonic waves and receive reflected signals thereof for measuring the distance and shape of the objects, and the image recognition camera can capture image information in the environment;
in the S2 stage, the credibility evaluation of each data source is performed according to the sensor performance and the historical accuracy factors, and the evaluation process comprises the following steps:
sensor performance evaluation: testing and evaluating the performance of each sensor, including precision, sensitivity and stability aspects, such as the measurement range and precision of the infrared sensor and the distance measurement precision of the ultrasonic sensor;
historical accuracy assessment: evaluating the accuracy of each sensor according to previous data collection, wherein the accuracy comprises the matching degree and the error range with the actual environmental conditions;
confidence assignment: based on the sensor performance and the historical accuracy assessment results, assigning a corresponding confidence value to each data source, the confidence typically being represented by a number between 0 and 1, higher values representing higher confidence for the data source;
after the reliability evaluation of the data source is completed in the step S2, the evaluation result can be further transmitted to a subsequent module (S3) for the comprehensive operation of the weighted average method and the calculation of the comprehensive environment evaluation.
Specifically, in the step S3, a corresponding confidence value is allocated to each data source according to the confidence evaluation result, and these confidence values will now be used to perform a comprehensive operation and calculate a comprehensive environmental evaluation:
the preset infrared sensor (I R), the Ultrasonic Sensor (US) and the image recognition camera (Cam) are respectively distributed with reliability values of w1, w2 and w3;
and (3) comprehensive operation: the comprehensive environmental assessment is calculated by the following formula: comprehensive environmental assessment= (w1×d1+w2×d2+w3×d3)/(w1+w2+w3);
wherein d1, d2 and d3 represent values of the corresponding data sources, respectively, which are the distances measured by the sensor, the results of the image processing;
weighted average method: in the comprehensive operation, by multiplying corresponding weights and carrying out weighted average on all data sources, the higher the weights are, the greater the contribution of the data sources to the comprehensive environment evaluation is indicated, so that the reliability difference of different data sources is considered;
preset, the reliability value of the infrared sensor (I R) is w1=0.8, the reliability value of the Ultrasonic Sensor (US) is w2=0.9, the reliability value of the image recognition camera (Cam) is w3=0.7, meanwhile, the distance measured by the ultrasonic sensor is d1=2 meters, the distance measured by the ultrasonic sensor is d2=3 meters, and the image recognition camera detects an object and estimates the distance to be d3=2.5 meters;
the calculation of the comprehensive environmental assessment is as follows:
comprehensive environmental assessment= (0.8×2+0.9×3+0.7×2.5)/(0.8+0.9+0.7)
=(1.6+2.7+1.75)/2.4
=6.05/2.4
=2.52
And obtaining a comprehensive environment evaluation result, namely, a comprehensive environment evaluation value is 2.52, and comparing the comprehensive environment evaluation value with a threshold value according to a specific application scene and a preset threshold value to judge the safety of the current environment.
Specifically, in the step S4, according to the preset data in step S3, there are three data sources: an infrared sensor (I R), an Ultrasonic Sensor (US) and an image recognition camera (Cam), each data source being assigned a respective confidence value and weight;
the preset data are as follows:
the reliability value of the infrared sensor (I R) is w1=0.8;
the confidence value of the Ultrasonic Sensor (US) is w2=0.9;
the credibility value of the image recognition camera (Cam) is w3=0.7;
the values acquired by the data sources are preset as follows:
the value of the infrared sensor (I R) is d1=2 meters;
the value of the Ultrasonic Sensor (US) is d2=3 meters;
the value of the image recognition camera (Cam) is d3=2.5 meters;
the comprehensive operation formula is as follows:
comprehensive environmental assessment= (w1+w2+d2+w3+d3)/(w1+w2+w3)
Substituting preset data for calculation:
comprehensive environmental assessment= (0.8×2+0.9×3+0.7×2.5)/(0.8+0.9+0.7)
=(1.6+2.7+1.75)/2.4
=6.05/2.4
=2.52
Based on the calculation result, the comprehensive environment evaluation value is 2.52;
in the S4 stage, the comprehensive environmental assessment value is compared with a preset threshold value to determine the safety of the current environment, and the specific operation is as follows:
if the comprehensive environment evaluation value is larger than or equal to a preset threshold value, the comprehensive environment evaluation value is larger than or equal to the threshold value, namely 2.52 is larger than or equal to the threshold value, the current environment is relatively safe, and the blind user can be continuously navigated;
if the comprehensive environmental assessment value is smaller than the preset threshold value, the comprehensive environmental assessment < threshold value, namely 2.52< threshold value, indicates that the current environment has an obstacle or dangerous condition, and corresponding measures such as stopping navigation, changing a navigation path or giving an alarm need to be taken to ensure the safety of navigation.
Specifically, the following preset data are obtained by substituting the preset data of S3 into the actual calculation in the steps S6-S7:
security weight: ws=0.5
The feasibility weight: w_f=0.3
Personalized weights: w_p=0.2
For each path, the following index values are preset:
safety index of path 1: s1=0.8
Path 1 feasibility index: f1 =0.7
Personalized index for path 1: p1=0.9
Path 2 security index: s2=0.6
Path 2 feasibility index: f2 =0.8
Personalized index of path 2: p2=0.7
Next, an optimal path evaluation value for each path is calculated according to an optimal path evaluation formula:
optimal path evaluation 1=ws_s1+w_f_f1+w_p_p1
=0.5*0.8+0.3*0.7+0.2*0.9
=0.4+0.21+0.18
=0.79
Optimal path evaluation 2=ws_s2+w_f_f2+w_p_p2
=0.5*0.6+0.3*0.8+0.2*0.7
=0.3+0.24+0.14
=0.68
In the S7 stage, sorting the optimal path evaluation values, selecting the path with the highest evaluation value as the optimal path, and according to the calculation result, the optimal path evaluation 1 is 0.79, and the optimal path evaluation 2 is 0.68, so that the path 1 with the highest optimal path evaluation value is selected as the optimal path, and the blind person user is continuously navigated;
through the steps of S6 and S7, we evaluate each path and rank and select according to the optimal path evaluation value.
Specifically, the index value obtaining method in the steps S6 to S7 is as follows: sensor data: acquiring environmental information, such as measuring obstacle distance, detecting traffic conditions, identifying road conditions, by using infrared sensors, ultrasonic sensors, camera sensor devices;
based on the processing and analysis of the sensor data, specific values of safety, feasibility and personalized indexes can be obtained;
map and path information: the map data and the path planning algorithm are utilized to obtain the information of the path, such as the path length, traffic condition and congestion degree;
these information are used as part of the feasibility index;
database and history data: the safety and feasibility of the path are measured by collecting and analyzing historical data and accident record information;
these data are used as part of an evaluation index to predict the risk and feasibility of the path.
Specifically, the working principle of the steps S1-S7 is as follows: firstly, environmental data are collected in real time, secondly, reliability assessment is carried out on each data source, corresponding weight is distributed to each data source according to assessment results, further, a weighted average method is utilized to carry out comprehensive operation on the value and the weight of each data source, comprehensive environmental assessment values are obtained, whether the current environment is safe or not is judged according to a preset threshold value, further, a unique optimal path selection method is designed based on special requirements and safety consideration of blind users, a plurality of factors such as slope avoidance, steps and other obstacles are considered, user feedback and personalized adjustment are combined, then, each path is assessed, a mathematical formula is used to calculate optimal path assessment value of each path, the assessment values are ordered according to the weight distribution of safety, feasibility and personalized indexes and specific calculation values of corresponding indexes, then, the path with the highest assessment value is selected as the optimal path, if the optimal path assessment values do not accord with the preset threshold value, the path is required to be re-planned or other measures are taken to ensure navigation safety, finally, a blind user is provided with navigation guidance system based on the selected optimal path, navigation system is provided to the user, navigation environment is continuously provided with navigation information is required to be monitored, and the path information is continuously adjusted in real time according to the navigation information, and the navigation information is required to be continuously monitored in real time.
1-2, the present invention is operated in the scene of giving a higher weight (0.6) to a safety index to emphasize the attention of safety to the blind user, and simultaneously, carrying out comprehensive operation on infrared, ultrasonic and image data sources and improving the accuracy and reliability of environmental information by combining reliability assessment, wherein the following steps are as follows:
in path evaluation calculation, the accuracy and the reliability of environmental information are improved by comprehensively calculating infrared, ultrasonic and image data sources and combining with credibility weight configuration;
through data integration and verification, the system can reduce errors and noise, improves the comprehensiveness and consistency of environmental information, and further improves the accuracy and reliability of path evaluation;
in the aspect of updating and verifying real-time road conditions, the system can acquire real road condition information provided by other normal users and verify the credibility of the real road condition information, so that the sensing and coping capacity of the system on the real-time road conditions is enhanced;
the calculation process comprises the following steps:
the security weight (ws) is set to 0.6, the feasibility weight (w_f) is set to 0.3, and the individualization weight (w_p) is set to 0.1;
assuming that the safety index(s) of the path A is 0.8, the feasibility index (f) is 0.7, and the individuation index (p) is 0.9;
calculating an optimal path evaluation value: optimal path evaluation = ws + w_f + w_p =0.60.8+0.30.7+0.1 =0.48+0.21+0.09=0.78.
In the second embodiment, referring to fig. 1-2, the present invention gives a higher weight (0.5) to the feasibility index to emphasize consideration of convenience and comfort of navigation, and the data integration and verification mechanism helps to reduce errors and inconsistencies, so that the present invention works as follows in the context of improving the comprehensiveness and consistency of environmental information:
the blind guiding system can evaluate the environment state more comprehensively and provide more accurate feasibility and comfort indexes by carrying out comprehensive operation on infrared, ultrasonic and image data sources, so that the path planning is optimized and the optimal path is selected;
the data integration and verification mechanism ensures the consistency of the data, and reduces the influence of errors and inconsistencies on the assessment of the feasibility and the comfort;
the real-time road condition updating and verification enables the system to adjust the path selection according to the latest road condition information, and provides more convenient navigation experience;
the calculation process comprises the following steps:
the security weight (ws) is set to 0.4, the feasibility weight (w_f) is set to 0.5, and the individualization weight (w_p) is set to 0.1;
assuming that the safety index(s) of the path B is 0.6, the feasibility index (f) is 0.8, and the individuation index (p) is 0.7;
calculating an optimal path evaluation value: optimal path evaluation = ws + w_f + w_p =0.4 x 0.6+0.5 x 0.8+0.1 x 0.7 = 0.24+0.4+0.07 = 0.71.
In the third embodiment, referring to fig. 1-2, the present invention, in the case of giving a higher weight (0.5) to a personalized index to meet the personalized navigation requirements of different users, performs comprehensive operation on infrared, ultrasonic and image data sources, and performs weight configuration according to the reliability, so as to provide personalized navigation service scenarios for different users, works as follows:
the infrared, ultrasonic and image data sources are comprehensively operated, weight configuration is carried out according to the credibility, and the blind guiding system can provide personalized navigation service for different users;
the data integration and verification ensure that the data used in the comprehensive operation is accurate, reliable and consistent, thereby providing credibility for personalized navigation assessment;
the real-time road condition updating and verifying mechanism enables the system to adjust the path selection according to the road condition information which changes in real time, so that the personalized navigation requirement of the user is met;
the calculation process comprises the following steps:
the security weight (ws) is set to 0.3, the feasibility weight (w_f) is set to 0.2, and the individualization weight (w_p) is set to 0.5;
assuming that the safety index(s) of the path C is 0.7, the feasibility index (f) is 0.6, and the individuation index (p) is 0.8;
calculating an optimal path evaluation value: optimal path evaluation = ws + w_f + w_p =0.3 x 0.7+0.2 x 0.6+0.5 x 0.8 = 0.21+0.12+0.4 = 0.73.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will be within the scope of the present invention.
The foregoing description is only of the preferred embodiments of the invention and is not intended to limit the invention; various modifications and variations of the present invention will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and rules of the present invention should be included in the protection scope of the present invention.

Claims (6)

1. A method for guiding blind, characterized in that:
s1, acquiring environmental data by using an infrared sensor, an ultrasonic sensor and image recognition camera equipment;
s2, evaluating and assigning the credibility of each data source according to the sensor performance and the historical accuracy factors;
s3, giving weight to the comprehensive operation according to the credibility, and carrying out the comprehensive operation on the data of the three data sources:
comprehensive environmental assessment= (w) 1 *d 1 +w 2 *d 2 +w 3 *d 3 )/(w 1 +w 2 +w 3 )
Wherein w is 1 、w 2 、w 3 Weights representing infrared, ultrasonic and image data sources, respectively, d 1 、d 2 、d 3 Respectively represent the values of the corresponding data sources
S4, comparing the environment evaluation judgment with a preset threshold value according to the comprehensive environment evaluation result, and judging whether the current environment is safe or not;
if the comprehensive environment evaluation is more than or equal to the threshold value, the environment is relatively safe, and navigation can be continued;
if the comprehensive environment evaluation is less than the threshold value, the situation that the obstacle or the dangerous situation exists is indicated, and corresponding measures such as stopping or changing the navigation path are needed to be taken;
s5, designing a unique optimal path selection method according to the special requirements and the safety requirements of the blind, and evaluating each path;
s6, calculating an optimal path evaluation value of each path according to the path planning result by path evaluation calculation:
optimal path evaluation=w s *s+w_f*f+w_p*p
Wherein w is s W_f and w_p respectively represent weights of safety, feasibility and individualization indexes, and s, f and p respectively represent values of corresponding indexes;
s7, selecting optimal paths, sorting according to the optimal path evaluation values, and selecting a path with the highest evaluation value as the optimal path:
the optimal path evaluation value is more than or equal to a threshold value, and the path is selected as an optimal path;
the optimal path evaluation value < threshold value, the path needs to be re-planned.
2. A method of blind guiding according to claim 1, wherein: in the S2 stage, the credibility evaluation of each data source is performed according to the sensor performance and the historical accuracy factors, and the evaluation process comprises the following steps:
sensor performance evaluation: testing and evaluating the performance of each sensor, including precision, sensitivity and stability aspects, such as the measurement range and precision of the infrared sensor and the distance measurement precision of the ultrasonic sensor;
historical accuracy assessment: evaluating the accuracy of each sensor according to previous data collection, wherein the accuracy comprises the matching degree and the error range with the actual environmental conditions;
confidence assignment: based on the sensor performance and the historical accuracy assessment results, a corresponding confidence value is assigned to each data source, the confidence being represented by a number between 0 and 1, with higher values representing higher confidence for that data source.
3. A method of blind guiding according to claim 1, wherein: in the step S3, corresponding reliability values are allocated to each data source according to the reliability evaluation result, and these reliability values are used to perform comprehensive operation and calculate comprehensive environment evaluation:
the preset infrared sensor (IR), the Ultrasonic Sensor (US) and the image recognition camera (Cam) are respectively distributed with reliability values of w1, w2 and w3;
and (3) comprehensive operation: the comprehensive environmental assessment is calculated by the following formula: comprehensive environmental assessment= (w1×d1+w2×d2+w3×d3)/(w1+w2+w3);
wherein d1, d2 and d3 represent values of the corresponding data sources, respectively, which are the distances measured by the sensor, the results of the image processing;
weighted average method: in the comprehensive operation, multiplying corresponding weights and carrying out weighted average on all data sources;
preset, the reliability value of the infrared sensor (IR) is w1=0.8, the reliability value of the Ultrasonic Sensor (US) is w2=0.9, the reliability value of the image recognition camera (Cam) is w3=0.7, meanwhile, the distance measured by the ultrasonic sensor is d1=2 meters, the distance measured by the ultrasonic sensor is d2=3 meters, and the image recognition camera detects an object and estimates the distance thereof to be d3=2.5 meters;
the calculation of the comprehensive environmental assessment is as follows:
comprehensive environmental assessment= (0.8×2+0.9×3+0.7×2.5)/(0.8+0.9+0.7)
=(1.6+2.7+1.75)/2.4
=6.05/2.4
=2.52
The result of the comprehensive environmental evaluation, that is, the comprehensive environmental evaluation value was 2.52.
4. A method of blind guiding according to claim 3, wherein: in the S4 stage, the comprehensive environmental assessment value is compared with a preset threshold value to determine the safety of the current environment, and the specific operation is as follows:
if the comprehensive environment evaluation value is larger than or equal to a preset threshold value, the comprehensive environment evaluation value is larger than or equal to the threshold value, namely 2.52 is larger than or equal to the threshold value, the current environment is relatively safe, and the blind user can be continuously navigated;
if the comprehensive environmental assessment value is smaller than the preset threshold value, the comprehensive environmental assessment < threshold value, namely 2.52< threshold value, indicates that the current environment has an obstacle or dangerous condition, and corresponding measures such as stopping navigation, changing a navigation path or giving an alarm need to be taken to ensure the safety of navigation.
5. A method of blind guiding according to claim 1, wherein: the index value obtaining mode in the S6-S7 steps is as follows: sensor data: acquiring environmental information, such as measuring obstacle distance, detecting traffic conditions, identifying road conditions, by using infrared sensors, ultrasonic sensors, camera sensor devices;
based on the processing and analysis of the sensor data, specific values of safety, feasibility and personalized indexes can be obtained;
map and path information: the map data and the path planning algorithm are utilized to obtain the information of the path, such as the path length, traffic condition and congestion degree;
these information are used as part of the feasibility index;
database and history data: the safety and feasibility of the path are measured by collecting and analyzing historical data and accident record information;
these data are used as part of the evaluation index.
6. A blind guiding system, characterized by: the system comprises a data acquisition module, a credibility evaluation and weight configuration module, an operation and environment evaluation module, a path planning and evaluation module and an optimal path selection and navigation execution module;
the data acquisition module is connected with the credibility evaluation and weight configuration module and is used for acquiring environment data in real time and transmitting the acquired data to the credibility evaluation and weight configuration module;
the credibility evaluation and weight configuration module is connected with the data acquisition module and the operation and environment evaluation module and is used for carrying out credibility evaluation on each data source according to the acquired environment data, distributing corresponding weight for each data source and then transmitting an evaluation result and weight information to the comprehensive operation and environment evaluation module;
the operation and environment assessment module is connected with the credibility assessment and weight configuration module and the path planning and assessment module, and is used for receiving the assessment result and weight information transmitted by the credibility assessment and weight configuration module, carrying out comprehensive operation on the value and weight of each data source by using a weighted average method to obtain a comprehensive environment assessment value, simultaneously comparing the comprehensive environment assessment value with a preset threshold value to judge whether the current environment is safe or not, and triggering the path planning module to re-plan the path if the environment assessment result is unsafe;
the path planning and evaluating module is connected with the operation and environment evaluating module and the optimal path selecting and navigating executing module, and is used for designing a unique optimal path selecting method according to the special requirements and safety consideration of blind users under the instruction of the operation and environment evaluating module, wherein the module can consider a plurality of factors, such as avoiding obstacles such as slopes and steps, combining user feedback and personalized adjustment, and transmitting optimal path information to the optimal path selecting and navigating executing module after the planning is completed;
the optimal path selection and navigation execution module is connected with the path planning and evaluation module and is used for receiving the optimal path information transmitted by the path planning and evaluation module, sorting according to the optimal path evaluation value, selecting the path with the highest evaluation value as the optimal path, providing navigation guidance for blind users, continuously monitoring environment change, acquiring data source information in real time, recalculating the path evaluation value, and adjusting the path or giving an alarm according to the requirement so as to adapt to the real-time situation.
CN202311399467.3A 2023-10-25 2023-10-25 Blind guiding system and method Pending CN117452515A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202311399467.3A CN117452515A (en) 2023-10-25 2023-10-25 Blind guiding system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202311399467.3A CN117452515A (en) 2023-10-25 2023-10-25 Blind guiding system and method

Publications (1)

Publication Number Publication Date
CN117452515A true CN117452515A (en) 2024-01-26

Family

ID=89582899

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202311399467.3A Pending CN117452515A (en) 2023-10-25 2023-10-25 Blind guiding system and method

Country Status (1)

Country Link
CN (1) CN117452515A (en)

Similar Documents

Publication Publication Date Title
WO2018181974A1 (en) Determination device, determination method, and program
CN110889455B (en) Fault detection positioning and safety assessment method for chemical engineering garden inspection robot
CN105676251A (en) Vehicle passenger identification
CN111947644B (en) Outdoor mobile robot positioning method and system and electronic equipment thereof
CN112650825A (en) Method and device for determining abnormal drive receiving behavior, storage medium and electronic equipment
CN114485968A (en) Vision laser calibration platform system
CN112598932A (en) Automobile anti-collision early warning model based on vehicle-road cooperation technology
KR102217422B1 (en) Driving license test processing device
JPH11326520A (en) Personal radiation exposure dose control system
KR20230137439A (en) A computer-implemented method for assessing the accuracy of swarm trajectory locations.
CN111024431A (en) Bridge rapid detection vehicle based on multi-sensor unmanned driving
CN117452515A (en) Blind guiding system and method
CN116311775B (en) Wearable near-electricity alarm equipment and monitoring system
KR102585557B1 (en) Apparatus and method for evaluating obstacle recognition performance of autonomous vehicle
JP7359388B2 (en) Ground fault point location system, ground fault point location device, location method and program for ground fault point location device
CN116295508A (en) Road side sensor calibration method, device and system based on high-precision map
CN113408916A (en) Fire-fighting equipment detection and on-site acceptance evaluation system based on intelligent AI and mobile APP
CN116929373B (en) Path generation method and system of fire control reconnaissance robot
CN116721512B (en) Autonomous navigation robot environment perception control method and system
CN114252013B (en) AGV visual identification accurate positioning system based on wired communication mode
KR20070106273A (en) Server, system, and method for creating and providing traffic information
JP7359386B2 (en) Ground fault point location system, ground fault point location device, location method and program for ground fault point location device
Totev et al. An Approach to Skid Detection Using Optical Flow and IMU Sensor
JP7359387B2 (en) Ground fault point location system, ground fault point location device, location method and program for ground fault point location device
CN116216530A (en) Crane auxiliary boom length identification system and method based on differential positioning

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