Environment identification method and system for assisting blind person to go out

Abstract

The invention provides an environment identification method and system for assisting a blind person in going out, and relates to the technical field of environment identification, an environment monitoring image and object information are acquired, and the object information comprises a target position and a current position of an object; determining a local action track of the object through the environment monitoring image and the object information; the object moves according to the local action track; acquiring an obstacle on the local action track from the environment monitoring image; acquiring information of obstacles in real time to obtain obstacle information; determining a risk value of the obstacle relative to the object through the object information and the obstacle information; and when the risk value is equal to or greater than a preset risk threshold value, generating a risk avoiding strategy executed by the object. And measures are taken in advance before the danger occurs, so that the blind person is helped to actively avoid the obstacle instead of passively dealing with the danger after the danger occurs, and the probability of accidents in the traveling process of the blind person is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental recognition, and particularly to an environmental recognition method and system for assisting blind people to travel. Background Art

[0002] Although the coverage rate of urban blind paths is high, the actual utilization rate is insufficient. The main reasons are that objects such as shared bicycles, motor vehicles, and trash cans occupy the blind paths for a long time.

[0003] When blind people are walking, they not only need to deal with static obstacles, but also need to deal with dynamic environments, such as pedestrians, vehicles, and temporary construction. Traditional guiding devices (such as blind canes) can only sense local static obstacles and cannot give early warnings of fast-moving objects. For example, when a motor vehicle starts and a blind person is in the driver's blind spot, a collision accident may occur. Summary of the Invention

[0004] The purpose of the present invention is to provide an environmental recognition method and system for assisting blind people to travel, and the technical problem to be solved is how to assist blind people to travel and reduce the travel risks of blind people.

[0005] The present invention is achieved through the following technical solutions:

[0006] In the first aspect, an environmental recognition method for assisting blind people to travel is provided, including the following steps:

[0007] Obtain an environmental monitoring image and object information, where the object information includes the target position and the current position of the object;

[0008] Determine the local movement trajectory of the object based on the environmental monitoring image and the object information; the object moves according to the local movement trajectory;

[0009] Obtain the obstacles on the local movement trajectory from the environmental monitoring image;

[0010] Obtain the information of the obstacles in real time to obtain obstacle information;

[0011] Determine the risk value of the obstacle relative to the object based on the object information and the obstacle information;

[0012] When the risk value is equal to or greater than a preset risk threshold, generate an avoidance strategy to be executed by the object.

[0013] By obtaining environmental monitoring images and object information including the target position and the current position of the object, the specific position of the blind person in the environment is determined, providing basic data for subsequent action trajectory planning and obstacle avoidance; based on the actual environment, a local action trajectory is planned to guide the blind person to avoid known dangerous areas (such as walls, ditches, motor vehicle lanes, etc.), providing preliminary safety protection for the blind person when traveling; obstacles on the local action trajectory are obtained from the environmental monitoring images, and the obstacle information is obtained in real time, enabling the blind person to know the situation of the obstacles ahead in time and avoid dangers such as collisions when suddenly encountering obstacles during movement. For example, if there is a moving vehicle or pedestrian in front of the blind person, update its information in time so that the blind person can understand the latest dynamics of the obstacle and thus take corresponding countermeasures. By comprehensively considering various factors such as the position of the blind person, the moving speed, and the distance from the obstacle, the risks that are difficult to intuitively judge are quantified to obtain a risk value, and a risk avoidance plan is formulated according to different risk situations. For example, guiding the blind person to change the moving direction, slow down or stop moving, etc., improving the blind person's ability to respond to sudden dangers and effectively reducing the travel risk.

[0014] In summary, the above method takes measures in advance before the danger occurs to help the blind person actively avoid obstacles, rather than passively coping after the danger occurs, thereby reducing the probability of accidents during the blind person's travel.

[0015] Furthermore, through the above environmental monitoring images and object information, the local action trajectory of the object is determined. The specific steps include:

[0016] Generate a global action trajectory through the current position and the target position of the above object information;

[0017] Determine the monitoring area through the above environmental monitoring images;

[0018] Intercept the action trajectory passing through the monitoring area from the above global action trajectory to obtain the local action trajectory.

[0019] Generating a global action trajectory through the current position and the target position of the object information provides a complete path planning for the blind person from the starting point to the end point; determining the monitoring area through the environmental monitoring images focuses on the local area of the specific environment where the blind person is currently located. The monitoring area changes according to the movement of the blind person and the changes in the environment, and obstacles and potential risks (uncovered sewage wells, bicycles, electric vehicles, etc.) around the blind person are perceived in the monitoring area; the interception of the local action trajectory enables the blind person to focus more on the movement path within the current monitoring area, avoiding being interfered by other irrelevant parts in the global trajectory, improving the pertinence and safety of the action; the local action trajectory can be dynamically adjusted according to the real-time changes in the monitoring area (i.e., the risk avoidance strategy) to ensure that the blind person moves forward along a safe and reasonable path during movement, effectively avoiding suddenly emerging obstacles or risks.

[0020] Further, the obstacles on the above local movement trajectory include animals and still objects; among them, the above animals move relative to the object, and the still objects are stationary relative to the object.

[0021] Since the animals move relative to the object, their movement directions and speeds are uncertain, and the risks posed to the blind are relatively complex; while the still objects are stationary relative to the object, their movement directions and speeds are the same as those of the object and will not pose a danger to the object, so the still objects are not considered when calculating the risk value.

[0022] Further, based on the above object information and obstacle information, determine the risk value of the obstacle relative to the object. The specific steps include:

[0023] The above obstacle information includes the moving direction, moving speed and current position of the obstacle; the above object information also includes the moving direction, moving speed and current position of the object;

[0024] Determine the interval distance between the obstacle and the object based on the current positions of the above obstacle and the object;

[0025] Predict the probability of collision between the obstacle and the object based on the current positions and moving directions of the above obstacle and the object; the above probability is the risk value.

[0026] Risk assessment is carried out based on real-time object information and obstacle information. Therefore, the risk value can be dynamically adjusted as the environment and object state change, and can reflect the current risk situation in real time, providing timely and accurate safety tips and risk avoidance guidance for the blind, and ensuring that the blind are always in a relatively safe state during travel.

[0027] Further, when the above risk value is greater than the preset risk threshold, generate an avoidance strategy executed by the object. The specific steps include:

[0028] Determine the collision position between the obstacle and the object based on the moving directions, moving speeds and interval distance of the above obstacle and the object;

[0029] Determine the collision area based on the above collision position and the preset collision increment;

[0030] Determine the avoidance duration based on the above collision position, the current position of the obstacle and the moving speed of the obstacle;

[0031] Move in a direction away from the collision area based on the above avoidance duration, the current position of the object and the moving speed of the object, and determine the avoidance position of the object.

[0032] Based on the relative motion trends of obstacles and objects in space, potential dangerous situations are predicted. When the risk value is greater than the risk threshold, the collision position, collision area, and safety area are determined. Taking the collision position as a reference, an avoidance strategy is formulated. The avoidance strategy can be: when the object is in the safety area, the object waits for the obstacle to pass and then moves; when the object is in the collision area, the moving direction of the object is changed to make the object enter the safety area or leave the center of the collision area, reducing the severity of injury.

[0033] Furthermore, based on the above-mentioned collision position and a preset collision increment, the collision area is determined. The specific steps include:

[0034] Obtain the front-end point, rear-end point, left-end point, and right-end point of the above-mentioned obstacle. Based on the positions of the front-end point, rear-end point, left-end point, and right-end point respectively, the collision increment is superimposed to obtain the width and length of the collision area; taking the collision position as the midpoint, the calculated width and length are amplified to obtain the collision area; the other areas except the collision area are the safety areas.

[0035] Consider the range that the obstacle may pose a threat to the blind in all directions. The obstacle is not just a point or a simple geometric shape, and there may be potential risks in all directions. Ensure that the blind can be effectively protected within a certain safety area around the obstacle, avoiding missing risk areas due to incomplete definition of the safety area. The safety area provides a clear safety boundary for the blind. The blind can adjust their movement paths and speeds according to the safety area to avoid entering dangerous areas where collisions may occur. For example, when the blind approach an obstacle, by understanding the range of the safety area, they can plan a detour route in advance to ensure passing within the safety area, effectively reducing the risk of collision with the obstacle.

[0036] In a second aspect, an environment recognition system for assisting the blind to travel is provided. This system adopts the above-mentioned environment recognition method;

[0037] This system includes: an image acquisition device, a positioning device, a processing device, and a voice device. The above-mentioned image acquisition device, positioning device, and voice device are connected to the processing device;

[0038] The above-mentioned image acquisition device is used to acquire environmental monitoring images;

[0039] The above-mentioned positioning device is used to obtain the current position of the object in real time;

[0040] The above-mentioned voice device is used to receive the target position input by the object and output voice information;

[0041] The above-mentioned processing device is used to perform the following operations:

[0042] Determine the local movement trajectory of the object based on the above environmental monitoring image and object information; transmit the above local movement trajectory to the object through a voice device;

[0043] Obtain the obstacles on the local movement trajectory from the above environmental monitoring image;

[0044] Obtain the information of the above obstacles in real time to obtain obstacle information;

[0045] Determine the risk value of the obstacle relative to the object based on the above object information and obstacle information;

[0046] When the above risk value is equal to or greater than the preset risk threshold, generate an avoidance strategy to be executed by the object; transmit the above avoidance strategy to the object through a voice device.

[0047] Furthermore, the above processing device is used to determine the local movement trajectory of the object based on the environmental monitoring image and object information. The specific steps include:

[0048] Generate a global movement trajectory based on the current position and target position of the above object information;

[0049] Determine the monitoring area through the above environmental monitoring image;

[0050] Intercept the movement trajectory passing through the monitoring area from the above global movement trajectory to obtain the local movement trajectory.

[0051] Furthermore, the above processing device is used to determine the risk value of the obstacle relative to the object based on the object information and obstacle information. The specific steps include:

[0052] The above obstacle information includes the moving direction, moving speed, and current position of the obstacle; the above object information also includes the moving direction, moving speed, and current position of the object;

[0053] Determine the distance between the obstacle and the object based on the current positions of the above obstacle and the object;

[0054] Predict the probability of collision between the obstacle and the object based on the current positions and moving directions of the above obstacle and the object; the above probability is the risk value.

[0055] Furthermore, when the above risk value is greater than the preset risk threshold, generate an avoidance strategy to be executed by the object. The specific steps include:

[0056] Determine the collision position between the obstacle and the object based on the moving directions, moving speeds, and distance between the above obstacle and the object;

[0057] Determine the collision area based on the above collision position and the preset collision increment;

[0058] Determine the risk avoidance duration based on the above collision position, the current position of the obstacle, and the moving speed of the obstacle;

[0059] Based on the above risk avoidance duration, the current position of the object, and the moving speed of the object, move in a direction away from the collision area to determine the risk avoidance position of the object.

[0060] Furthermore, obtain the front-end point, rear-end point, left-side point, and right-side point of the obstacle by the above image acquisition device. Based on the positions of the front-end point, rear-end point, left-side point, and right-side point respectively, superimpose the collision increment to obtain the width and length of the collision area; use the collision position as the midpoint and amplify the calculated width and length to obtain the collision area; the other areas except the collision area are safety areas.

[0061] A third aspect provides a computer-readable storage medium, on which computer program instructions are stored. When the above computer program instructions are executed by a processor, the above environment recognition method is implemented.

[0062] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0063] By obtaining the environmental monitoring image and the object information including the target position and the current position of the object, determine the specific position of the blind person in the environment, providing basic data for subsequent action trajectory planning and obstacle avoidance; plan the local action trajectory based on the actual environment to guide the blind person to avoid known dangerous areas (such as walls, ditches, motor vehicle lanes, etc.), providing preliminary safety protection for the blind person to travel; obtain the obstacles on the local action trajectory from the environmental monitoring image and obtain the obstacle information in real time, enabling the blind person to know the situation of the obstacles ahead in time and avoid dangers such as collisions when suddenly encountering obstacles during movement. For example, if there is a moving vehicle or pedestrian in front of the blind person, update its information in time to let the blind person understand the latest dynamics of the obstacle, so as to take corresponding countermeasures. Considering various factors such as the position of the blind person, the moving speed, and the distance from the obstacle comprehensively, quantify the risks that are difficult to intuitively judge originally to obtain a risk value, and formulate a risk avoidance plan according to different risk situations. For example: guide the blind person to change the moving direction, decelerate or stop moving, etc., improving the blind person's ability to cope with sudden dangers and effectively reducing the travel risk. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts. In the drawings:

[0065] Figure 1 is the main flow chart;

[0066] Figure 2 is a schematic diagram when a blind person and an obstacle are in relative motion;

[0067] Figure 3 is a schematic diagram of the collision area, safety area, and before and after the object's risk avoidance;

[0068] Figure 4 is Figure 3 a partial enlarged view of A in Specific Embodiment

[0069] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in combination with embodiments and drawings. The illustrative embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0070] First Embodiment:

[0071] Combined with Figure 1 , an environment recognition method for assisting blind people to travel includes the following steps:

[0072] Obtain environmental monitoring images and object information, where the above object information includes the target position and current position of the object;

[0073] Determine the local movement trajectory of the object through the above environmental monitoring images and object information; the above object moves according to the local movement trajectory;

[0074] Obtain obstacles on the local movement trajectory from the above environmental monitoring images; the above obstacles include animals and static objects; among them, the above animals are in relative motion with the object, and the static objects are in relative static with the object; due to the relative motion of the animals and the object, their movement directions and speeds are uncertain, and the risks posed to blind people are relatively complex; while the static objects are in relative static with the object, their movement directions and speeds are the same as those of the object and will not pose a danger to the object, and the static objects are not considered when calculating the risk value.

[0075] Obtain the information of the above obstacles in real time to obtain obstacle information;

[0076] Determine the risk value of the obstacle relative to the object through the above object information and obstacle information;

[0077] When the above risk value is equal to or greater than a preset risk threshold, generate a risk avoidance strategy to be executed by the object.

[0078] Considering the privacy of pedestrians, the collected images can neither identify their identities nor be transmitted over the network, ensuring a reasonable viewing range of the images and avoiding the risk of privacy leakage.

[0079] By obtaining environmental monitoring images and object information including the target position and the current position of the object, the specific position of the blind person in the environment is determined, providing basic data for subsequent action trajectory planning and obstacle avoidance; based on the actual environment, a local action trajectory is planned to guide the blind person to avoid known dangerous areas (such as walls, ditches, motor vehicle lanes, etc.), providing preliminary safety protection for the blind person to travel; obstacles on the local action trajectory are obtained from the environmental monitoring images, and obstacle information is obtained in real time, enabling the blind person to know the situation of obstacles ahead in a timely manner and avoid dangers such as collisions when suddenly encountering obstacles during movement. For example, if there is a moving vehicle or pedestrian in front of the blind person, its information is updated in a timely manner to let the blind person understand the latest dynamics of the obstacle, so as to take corresponding countermeasures. By comprehensively considering various factors such as the position of the blind person, the moving speed, and the distance from the obstacle, the risks that are difficult to intuitively judge are quantified to obtain a risk value, and an avoidance plan is formulated according to different risk situations. For example: guiding the blind person to change the moving direction, decelerate or stop moving, etc., improving the blind person's ability to respond to sudden dangers and effectively reducing the travel risk.

[0080] In summary, the above method takes measures in advance before the danger occurs to help the blind person actively avoid obstacles, rather than passively coping after the danger occurs, thereby reducing the probability of accidents during the blind person's travel.

[0081] For reference, assume that a blind person is walking on a park path using a blind stick equipped with an environmental monitoring camera and a navigation system. The environmental image of the park path is captured in real time through the camera, and the current position of the blind person is obtained through GPS. Based on the current position of the blind person (the center of the park, coordinates (0, 0)) and the target position (the park exit, coordinates (100, 0)), a global action trajectory is planned, and the current local action trajectory is intercepted; through image recognition technology, a dog, a pedestrian, and a bench are detected on the local action trajectory. The dog is moving towards the blind person (as Figure 2 shown), getting closer gradually. The pedestrian and the blind person are moving in the same direction at the same speed. When the blind person moves towards the exit, he passes by the bench. Therefore, the dog and the bench are animals, and the pedestrian is a static object. At this time, the pedestrian poses no threat to the blind person and is not included in the risk consideration (this example is in an ideal state).

[0082] Second Embodiment:

[0083] On the basis of the first embodiment, through the above-mentioned environmental monitoring images and object information, the local action trajectory of the object is determined. The specific steps include:

[0084] Generate a global action trajectory through the current position and the target position of the above-mentioned object information;

[0085] Determine the monitoring area through the above-mentioned environmental monitoring images;

[0086] Intercept the action trajectory passing through the monitoring area from the above-mentioned global action trajectory to obtain the local action trajectory.

[0087] Generate a global action trajectory through the current position and target position of the object information, providing a complete path planning for the blind from the starting point to the ending point; determine the monitoring area through the environmental monitoring image, focusing on the local area of the specific environment where the blind is currently located. The monitoring area changes according to the movement of the blind and the changes in the environment, and obstacles and potential risks (uncovered sewage wells, bicycles, electric vehicles, etc.) around the blind are perceived in the monitoring area; the interception of the local action trajectory enables the blind to focus more on the movement path within the current monitoring area, avoiding being disturbed by other irrelevant parts in the global trajectory, improving the pertinence and safety of the action; the local action trajectory can be dynamically adjusted according to the real-time changes in the monitoring area (i.e., the risk avoidance strategy) to ensure that the blind moves along a safe and reasonable path during the movement, effectively avoiding suddenly emerging obstacles or risks.

[0088] Third Embodiment:

[0089] Based on any of the above embodiments, determine the risk value of the obstacle relative to the object through the above-mentioned object information and obstacle information. The specific steps include:

[0090] The above-mentioned obstacle information includes the moving direction, moving speed, and current position of the obstacle; the above-mentioned object information also includes the moving direction, moving speed, and current position of the object;

[0091] Determine the interval distance between the obstacle and the object through the current positions of the above-mentioned obstacle and object;

[0092] Predict the probability of collision between the obstacle and the object through the current positions and moving directions of the above-mentioned obstacle and object; the above probability is the risk value.

[0093] For reference, the current coordinates of the blind and the dog are (0, 0) and (10, 0) respectively. If the blind and the dog move relatively in the same straight line, the collision probability is 100%; if the blind moves towards (-10, 0) and the dog moves towards (100, 0), the collision probability is 0%; if the blind moves towards (10, 10) and the dog moves towards (0, 10), and the moving speeds of the blind and the dog are the same, the collision probability is 100%.

[0094] In a specific embodiment, when the above risk value is greater than the preset risk threshold, generate a risk avoidance strategy executed by the object. The specific steps include:

[0095] Determine the collision position between the obstacle and the object through the moving directions, moving speeds, and interval distance of the above-mentioned obstacle and object;

[0096] Determine the collision area based on the above-mentioned collision position and the preset collision increment;

[0097] Determine the risk avoidance duration based on the above-mentioned collision position, the current position of the obstacle, and the moving speed of the obstacle;

[0098] Based on the above-mentioned risk avoidance duration, the current position of the object, and the moving speed of the object, move in a direction away from the collision area to determine the risk avoidance position of the object.

[0099] Output the risk avoidance position through voice information. When there is a moving object in the front and there is an empty space on the right, prompt the object to turn right to avoid the moving object in the front.

[0100] Based on the relative motion trend of the obstacle and the object in space, predict potential dangerous situations. When the risk value is greater than the risk threshold, determine the collision position, the collision area, and the safe area, and formulate a risk avoidance strategy based on the collision position. The risk avoidance strategy can be: when the object is in the safe area, the object waits for the obstacle to pass and then moves; when the object is in the collision area, change the moving direction of the object to make the object enter the safe area or leave the center of the collision area to reduce the severity of injury.

[0101] Since the risk assessment process is based on real-time object information and obstacle information, the risk value can be dynamically adjusted as the environment and the object state change, enabling the assistance system to reflect the current risk situation in real time, providing timely and accurate safety tips and risk avoidance guidance for the blind, and ensuring that the blind are always in a relatively safe state during travel.

[0102] In a specific embodiment, determine the collision area based on the above-mentioned collision position and the preset collision increment. The specific steps include:

[0103] Obtain the front end point, rear end point, left end point, and right end point of the above-mentioned obstacle. Based on the positions of the front end point, rear end point, left end point, and right end point respectively, superimpose the collision increment to obtain the width and length of the collision area; use the collision position as the midpoint and amplify the calculated width and length to obtain the collision area; the other areas except the collision area are safe areas.

[0104] Consider the range in which obstacles may pose a threat to the blind in all directions. An obstacle is not just a point or a simple geometric shape, and there may be potential risks in all directions. Ensure that the blind can be effectively protected within a certain collision area around the obstacle, avoiding missing risk areas due to incomplete definition of the safe area. The safe area provides a clear safety boundary for the blind. The blind can adjust their movement path and speed according to the safe area to avoid entering dangerous areas where collisions may occur. For example, when the blind approach an obstacle, by understanding the range of the safe area, they can plan a detour route in advance to ensure passing within the safe area, effectively reducing the risk of collision with the obstacle.

[0105] For reference, track the movement trajectory of the dog, and obtain the current position (10, 0) and moving speed of 1.5 m / s of the dog in real time. The moving speed of the blind is 0.5 m / s. After calculation, the distance between the blind and the dog is 10 meters, and they meet at (2.5, 0) after 5 seconds. The preset collision increment is 0.5 meters; based on the four endpoints of the dog, it can be known that the width of the dog is 0.2 meters and the length of the dog is 0.6 meters. Taking the collision position as the base point, add the length of the dog in the length direction and the width of the dog in the width direction to obtain a rectangular area, and then superimpose the collision increment to obtain the collision area. The collision area expands 0.5 meters (i.e., the collision increment) outward based on the rectangular area. Other areas except the collision area are safe areas, as Figure 3 shown.

[0106] Since the collision position is (2.5, 0), the length of the dog is 0.6, the width of the dog is 0.2, and the collision increment is 0.5, the four endpoints of the collision area can be obtained as (2.2, 0.1), (2.2, -0.1), (2.8, 0.1), and (2.8, -0.1).

[0107] The blind move in a direction perpendicular to the obstacle, and the avoidance position (0, 2.5) is obtained by calculating the avoidance time of 5 seconds.

[0108] Fourth Embodiment:

[0109] An environmental recognition system for assisting the blind in traveling, which adopts the above environmental recognition method;

[0110] The system includes: an image acquisition device, a positioning device, a processing device, and a voice device. The above image acquisition device, positioning device, and voice device are connected to the processing device;

[0111] The above image acquisition device is used to acquire environmental monitoring images;

[0112] The above positioning device is used to obtain the current position of the object in real time;

[0113] The above voice device is used to receive the target position input by the object and output voice information;

[0114] The above processing device is used to perform the following operations:

[0115] Determine the local action trajectory of the object through the above environmental monitoring image and object information; the above local action trajectory is transmitted to the object through the voice device;

[0116] Obtain the obstacles on the local action trajectory from the above environmental monitoring image;

[0117] Obtain the information of the above obstacles in real time to obtain obstacle information;

[0118] Determine the risk value of the obstacle relative to the object through the above object information and obstacle information;

[0119] When the above risk value is equal to or greater than the preset risk threshold, generate an avoidance strategy to be executed by the object; the above avoidance strategy is transmitted to the object through the voice device.

[0120] Fifth Embodiment:

[0121] Based on the fourth embodiment, the above processing device is used to determine the local action trajectory of the object through the environmental monitoring image and object information. The specific steps include:

[0122] Generate a global action trajectory through the current position and target position of the above object information;

[0123] Determine the monitoring area through the above environmental monitoring image;

[0124] Intercept the action trajectory passing through the monitoring area from the above global action trajectory to obtain the local action trajectory.

[0125] Sixth Embodiment:

[0126] Based on the fourth or fifth embodiment, the above processing device is used to determine the risk value of the obstacle relative to the object through the object information and obstacle information. The specific steps include:

[0127] The above obstacle information includes the moving direction, moving speed and current position of the obstacle; the above object information also includes the moving direction, moving speed and current position of the object;

[0128] Determine the interval distance between the obstacle and the object through the current positions of the above obstacle and the object;

[0129] Predict the probability of collision between the obstacle and the object through the current positions and moving directions of the above obstacle and the object; the above probability is the risk value.

[0130] In a specific embodiment, when the above risk value is greater than a preset risk threshold, a risk avoidance strategy to be executed by the object is generated. The specific steps include:

[0131] Determine the collision position between the obstacle and the object based on the moving direction, moving speed, and spacing distance of the above obstacle and the object;

[0132] Determine the collision area based on the above collision position and a preset collision increment;

[0133] Determine the risk avoidance duration based on the above collision position, the current position of the obstacle, and the moving speed of the obstacle;

[0134] Determine the risk avoidance position of the object by moving in a direction away from the collision area based on the above risk avoidance duration, the current position of the object, and the moving speed of the object.

[0135] In a specific embodiment, the front-end point, rear-end point, left-end point, and right-end point of the obstacle are obtained by the above image acquisition device. Based on the positions of the front-end point, rear-end point, left-end point, and right-end point respectively, the collision increment is superimposed to obtain the width and length of the collision area; with the collision position as the midpoint, the calculated width and length are amplified to obtain the collision area; the other areas except the collision area are safety areas.

[0136] Sixth Embodiment:

[0137] A computer-readable storage medium, on which computer program instructions are stored. When the above computer program instructions are executed by a processor, the above environment recognition method is implemented.

[0138] The above specific implementation manners further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific implementation manners of the present invention and are not used to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An environmental recognition method for assisting blind people to travel, characterized in that, It includes the following steps: Obtain an environmental monitoring image and object information, where the object information includes the target position and current position of the object; Determine the local movement trajectory of the object based on the environmental monitoring image and object information; the object moves according to the local movement trajectory; Obtain obstacles on the local movement trajectory from the environmental monitoring image; Obtain the information of the obstacles in real time to obtain obstacle information; Determine the risk value of the obstacle relative to the object based on the object information and obstacle information; When the risk value is equal to or greater than a preset risk threshold, generate an avoidance strategy to be executed by the object.

2. The environmental recognition method according to claim 1, characterized in that Determine the local movement trajectory of the object through the environmental monitoring image and object information. The specific steps include: Generate a global movement trajectory based on the current position and target position of the object information; Determine the monitoring area through the environmental monitoring image; Intercept the movement trajectory passing through the monitoring area from the global movement trajectory to obtain the local movement trajectory.

3. The environmental recognition method according to claim 1, characterized in that, The obstacles on the local movement trajectory include animals and static objects; among them, the animals move relative to the object, and the static objects are stationary relative to the object.

4. The environmental recognition method according to claim 1, characterized in that Determine the risk value of the obstacle relative to the object based on the object information and obstacle information. The specific steps include: The obstacle information includes the moving direction, moving speed and current position of the obstacle; the object information also includes the moving direction, moving speed and current position of the object; Determine the distance between the obstacle and the object based on the current positions of the obstacle and the object; Predict the probability of collision between the obstacle and the object based on the current positions and moving directions of the obstacle and the object; the probability is the risk value.

5. An environment recognition system for assisting blind people in traveling, characterized in that, This system adopts the environmental recognition method described in any one of claims 1 to 4; This system includes: an image acquisition device, a positioning device, a processing device and a voice device, and the image acquisition device, the positioning device and the voice device are connected to the processing device; The image acquisition device is used to acquire an environmental monitoring image; The positioning device is used to obtain the current position of the object in real time; The voice device is used to receive the target position input by the object and output voice information; The processing device is used to perform the following operations: Determine the local movement trajectory of the object through the environmental monitoring image and object information; the local movement trajectory is transmitted to the object through the voice device; Obtain obstacles on the local movement trajectory from the environmental monitoring image; Obtain the information of the obstacles in real time to obtain obstacle information; Determine the risk value of the obstacle relative to the object based on the object information and obstacle information; When the risk value is equal to or greater than a preset risk threshold, generate an avoidance strategy to be executed by the object; the avoidance strategy is transmitted to the object through the voice device.

6. The environmental recognition system according to claim 5, wherein The processing device is used to determine the local movement trajectory of the object through the environmental monitoring image and object information. The specific steps include: Generate a global movement trajectory based on the current position and target position of the object information; Determine the monitoring area through the environmental monitoring image; Intercept the movement trajectory passing through the monitoring area from the global movement trajectory to obtain the local movement trajectory.

7. The environmental recognition system according to claim 5, characterized in that, The processing device is used to determine the risk value of the obstacle relative to the object based on the object information and the obstacle information. The specific steps include: The obstacle information includes the moving direction, moving speed, and current position of the obstacle; the object information further includes the moving direction, moving speed, and current position of the object; Determine the distance between the obstacle and the object based on the current positions of the obstacle and the object; Predict the probability of collision between the obstacle and the object based on the current positions and moving directions of the obstacle and the object; the probability is the risk value.

8. A computer-readable storage medium having computer program instructions stored thereon, characterized in that, When the computer program instructions are executed by a processor, the environment recognition method described in any one of claims 1 to 4 is implemented.

Images