Sound-guided Spatial Object Search System, Storage Medium and Device for Visually Impaired People

Abstract

A spatial object-finding system, storage medium, and device for visually impaired people based on sound guidance belong to the joint technical field of sound guidance and path planning. The present invention solves the problems of low object-finding efficiency and lack of guarantee for object-finding safety for currently visually impaired people. The present invention proposes a spatial object-finding system for visually impaired people based on sound guidance. The system fully considers the global information of the traveling space and reserves a circular no-go area around obstacles to ensure the safety of the user during the traveling process as much as possible. First, a global shortest path that avoids the no-go area is planned, and then the local end point of the local path planning is determined based on the obtained global shortest path, which can avoid the problem of getting stuck in local dead ends and requiring re-planning while ensuring the shortest traveling path, that is, the efficiency of the user's object-finding is ensured through dual technologies. The method of the present invention can be applied to the joint technical field of sound guidance and path planning.

Description

Technical Field

[0001] The present invention belongs to the technical field of combined sound guidance and path planning, and particularly relates to a spatial object searching system, a storage medium and a device for visually impaired people. Background Art

[0002] According to the latest census data, the population of our country has exceeded 1.4 billion, among which the visually impaired population also accounts for a considerable proportion, and the number of blind people alone exceeds 17.3 million. For visually impaired people, since the process of searching for objects mainly relies on hearing, touch, etc. to assist. Therefore, many difficulties will inevitably be encountered in daily life. For example, when it is necessary to find an object located at a specific position indoors, due to the visual defects of visually impaired people (severely visually impaired people), they are unable to accurately locate and identify directions relying on visual memory, so there are difficulties in range identification and difficulties in obtaining objects at specific positions. Especially when visually impaired people enter a new environment or a relatively new environment, such as a community, a shopping mall, etc., this problem will be more prominent.

[0003] Existing methods can first plan the path to find the object, and then give travel tips to visually impaired people based on the results of the path planning. However, the current conventional path planning methods mainly include global path planning and local path planning. Among them, the global path planning method is not applicable to the path planning of visually impaired people; the local path planning method is to perform local path planning according to the current position of the visually impaired person. This method does not fully consider global information and is prone to leading to local dead ends, and then re-planning, resulting in a long path to find the object and low efficiency in finding the object. Moreover, existing methods do not fully consider the danger of collision with obstacles, and the safety during the process of finding objects is relatively low.

[0004] In summary, the current efficiency of visually impaired people in finding objects is still low, and the safety during the process of finding objects cannot be effectively guaranteed. How to solve the problem of object searching for visually impaired people in daily life and facilitate their daily life is an urgent problem to be solved at present. Summary of the Invention

[0005] The purpose of the present invention is to solve the problems of low efficiency of visually impaired people in finding objects and lack of guarantee of safety during the process of finding objects, and to propose a spatial object searching system for visually impaired people based on sound guidance.

[0006] The technical solution adopted by the present invention to solve the above technical problems is as follows: a spatial object searching system for visually impaired people based on sound guidance, the system comprising a position acquisition module, a task acquisition module, an obstacle geographical position acquisition module, a passage area acquisition module, a path planning module and a sound prompt module;

[0007] The user position acquisition module: is used to acquire the user's position in real time;

[0008] The task acquisition module: is used to acquire the user's voice and recognize the target object to be searched input by the user through voice;

[0009] The obstacle geographical position acquisition module: is used to acquire the positions of all obstacles in the area where the user and the target object are located;

[0010] The passage area acquisition module: is used to determine the passage area from the user to the target object according to the obstacle positions and the target object position;

[0011] The path planning module: is used to plan the optimal path within the determined passage area according to the user position;

[0012] The sound prompt module: is used to give sound prompts according to the planned optimal path to provide guidance for the user's traveling direction; and is also used to judge whether the user is outside the passage area according to the real-time user position, and if the user is outside the passage area, a danger prompt is given through sound.

[0013] A computer storage medium, in which at least one instruction is stored, and the at least one instruction is loaded and run by a processor to run the above-mentioned spatial object searching system for visually impaired people based on sound guidance.

[0014] A spatial object searching device for visually impaired people based on sound guidance, the device comprising a processor and a memory, and at least one instruction is stored in the memory, and the at least one instruction is loaded and run by the processor to run the above-mentioned spatial object searching system for visually impaired people based on sound guidance.

[0015] The beneficial effects of the present invention are as follows:

[0016] The present invention proposes a spatial object searching system for visually impaired people based on sound guidance. The system fully considers the global information of the traveling space and reserves an annular no-passage area around the obstacles to ensure the safety of the user during the traveling process as much as possible. First, a global shortest path avoiding the no-passage area is planned, and then the local end point of the local path planning is determined based on the obtained global shortest path, so that while ensuring the shortest traveling path, the problem of getting stuck in a local dead end and requiring re-planning can be avoided, that is, the efficiency of the user's object searching is ensured through dual technologies. Description of the Drawings

[0017] Figure 1 This is a block diagram of the spatial object-finding system for visually impaired people based on sound guidance of the present invention. Detailed implementation manners

[0018] Before making a specific description, it should be noted first that the visually impaired people targeted by the present invention are severely visually impaired people, who can be regarded as "blind people" to a certain extent, rather than the general visually impaired people, that is, not including amblyopia.

[0019] Detailed implementation manner 1: In combination with Figure 1 Describe this implementation manner.

[0020] A spatial object-finding system for visually impaired people based on sound guidance described in this implementation manner, the system includes a user position acquisition module, a task acquisition module, an obstacle geographical position acquisition module, a passage area acquisition module, a path planning module and a sound prompt module;

[0021] The user position acquisition module: is used to acquire the position of the user in real time;

[0022] The task acquisition module: is used to acquire the voice of the user and recognize the target object to be searched input by the user through voice; after the user inputs the target object to be searched through voice, it guides the next operation of the system;

[0023] The obstacle geographical position acquisition module: is used to acquire the positions of all obstacles in the area where the user and the target object are located;

[0024] The passage area acquisition module: is used to determine the passage area from the user to the target object according to the obstacle position and the target object position;

[0025] The path planning module: is used to plan the best path in the determined passage area according to the user position;

[0026] The sound prompt module: is used to give a sound prompt according to the planned best path to provide guidance for the user's moving direction; it is also used to judge whether the user is outside the passage area according to the real-time user position, if the user is outside the passage area, a danger prompt is given through sound.

[0027] That is, if the user moves into the prohibited passage area, the sound prompt module is used to give a risk prompt to the user. In particular, when the user moves to a position very close to the target object, a specific prompt can be given.

[0028] The present invention takes the position where the target item is located as the end point of the global path planning, so that when the user moves to the end point, the user also reaches the position where the target item is located.

[0029] Embodiment 2: The difference between this embodiment and Embodiment 1 is that the working process of the passage area acquisition module is as follows:

[0030] Step 1: Determine the extension length r around the obstacle.

[0031] Step 2: Cluster the obstacles according to the obtained central positions of the obstacles. Each position clustering result is recorded as a cluster. For any cluster, determine the no-go area corresponding to the obstacles in this cluster according to the central positions of the obstacles included in the cluster and the extension length r.

[0032] The method for determining the no-go area is as follows:

[0033] For any cluster, make the smallest circumscribed circle that contains all the obstacles in this cluster. Then the no-go area is a circular area with the center of the smallest circumscribed circle as the center and a radius of r1; where r1 = r + the radius of the smallest circumscribed circle.

[0034] Similarly, perform the same processing on each cluster respectively to obtain the corresponding no-go areas; all the no-go areas are all the no-go areas within the area where the user and the target object are located.

[0035] Step 3: Use the RRT* algorithm to plan M passage paths from the user to the target object (the planned passage paths all avoid the no-go areas), and then select the passage path with the shortest path length from the M passage paths. The passage areas passed by the selected passage path are used as the passage areas from the user to the target object.

[0036] By bypassing each no-go area in the global map, several paths can be obtained. For visually impaired people, since they cannot walk along the planned path, deviations will occur at all times, and even the deviations will gradually accumulate, and they will not walk out of the shortest path. Therefore, planning the shortest path seems meaningless. However, through research, it is found that although the planned shortest path has no meaning in terms of "shortest distance" for visually impaired people, because the present invention is a "deviation correction" scheme at all times. The present invention first determines the "shortest distance" and corrects the generated deviations at all times. Therefore, even if the visually impaired person cannot walk out of the "shortest distance" path, walking according to the deviation of this path can still play a role in shortening the travel time, thereby improving the efficiency of finding objects; more importantly, the scheme of the present invention is actually a "global orientation" + "local departure" scheme, thus avoiding the problems of long search path and low search efficiency caused by the possibility of walking into local dead ends in "local departure" and then re-planning.

[0037] It should be noted here that global planning refers to pre-planning the path for the starting point and the ending point to obtain a path considering the overall area of the starting point and the ending point, which is generally the shortest-distance path, and then proceeding along the path. However, it should be noted that global planning is not applicable to visually impaired persons because visually impaired persons cannot strictly follow the planned path.

[0038] In fact, visually impaired persons "grope" in an "unfamiliar" environment, that is, they get to know and familiarize themselves with the environment through continuous attempts. Each process of continuous attempt is a process of "local departure". "Local departure" starts from the current point and expands in multiple directions around, which is actually equivalent to each step in the heuristic algorithm (each step in the enumeration process), that is, without knowing the direction of the ending point in advance, and finally reaching the ending point through continuous attempts. For a computer, the heuristic algorithm can be used to complete task planning. However, for visually impaired persons, "local departure" not only has low efficiency, but may even occur the situation of "feasible at the beginning, but impassable after a certain number of steps", similar to walking in a maze. A certain path can be walked at the beginning, but it may become impassable after walking for a while.

[0039] To avoid the above problems, after research, in view of the connectivity of the passable area and the characteristics of visually impaired persons, the present invention first adopts a method similar to global planning. First, a path is planned. However, this path is not regarded as the planned path, but regarded as the result of discretization and used as the selection range for each "local departure". Or rather, the planned path is not used as a path, but used as "orientation", and this "orientation" is a "global orientation" with connectivity between the starting point and the ending point. Therefore, the present invention is actually a scheme of "global orientation" + "local departure", which not only avoids the problem that "local departure" may not be able to reach the ending point, but also can shorten the travel time and improve the efficiency of finding things.

[0040] Other steps and parameters are the same as those in the first specific implementation manner.

[0041] Specific implementation manner three: The difference between this implementation manner and the first or second specific implementation manner is that the extension length r is determined by the following method:

[0042] Set a test starting point and a test ending point, and take the straight-line distance between the test starting point and the test ending point as 1-2 meters; then set a test ending line, and the test ending line passes through the test ending point and is perpendicular to the line connecting the test starting point and the test ending point; the tester is located at the test starting point and faces the test ending point, and proceeds towards the test ending point;

[0043] Until the tester reaches the test ending line, take the straight-line distance between the position of the tester and the test ending point as the extension length r.

[0044] Other steps and parameters are the same as those in the first or second specific implementation manner.

[0045] In this implementation manner, the tester is a person with visual impairment. Since a person with visual impairment cannot walk in a straight line, when a person with visual impairment walks towards the test end point, there will be an offset from the test end point during the walking process. Let the tester continue to walk until reaching the test end line, and take the straight-line distance lr between the end position where the tester walks to and the test end point as the extension length r.

[0046] It should be noted that in this method, after only one test, the corresponding lr or r is input into the system, and then the system will use lr or r as the default parameter.

[0047] Specific implementation manner four: The difference between this implementation manner and one of the first to third specific implementation manners is that the extension length r is determined by the following method:

[0048] Set a test start point and a test end point, and take the straight-line distance between the test start point and the test end point as 1 - 2 meters; then set a test end line, the test end line passes through the test end point and is perpendicular to the connection line between the test start point and the test end point; the tester is located at the test start point and faces the test end point, and walks towards the test end point;

[0049] When the tester reaches the test end line, record the straight-line distance between the position of the tester and the test end point as lr;

[0050] Select the maximum value from all the distances lr corresponding to the testers, and take the selected maximum value as the extension length r:

[0051] r = max(lr i ), i = 1, 2, …, N

[0052] where lr i is the distance corresponding to the i-th tester, and N is the total number of testers.

[0053] Other steps and parameters are the same as those in one of the first to third specific implementation manners.

[0054] In this implementation manner, the extension length r is the maximum value of the distances lr statistically obtained from a certain number of users as the extension length r. It can also be determined by other methods, such as directly setting it artificially according to experience.

[0055] Specific implementation manner five: The difference between this implementation manner and one of the first to fourth specific implementation manners is that clustering the obstacles according to the obtained obstacle center positions; specifically:

[0056] Step 2-1: Initialize the number of clusters as k, and randomly initialize the central positions of k obstacles as the centers of the k clusters respectively;

[0057] Step 2-2: For any non-central obstacle, calculate the distances between the central position of this obstacle and the centers of each cluster respectively. Then, this obstacle belongs to the cluster corresponding to the minimum distance;

[0058] Similarly, after processing each non-central obstacle respectively, the clustering result of this iteration is obtained;

[0059] Step 2-3: For any cluster in the clustering result of Step 2-2, calculate a new center according to the central positions of all the obstacles in this cluster. Similarly, process each cluster in the clustering result of Step 2-2;

[0060] Step 2-4: Use the new centers obtained in Step 2-3 to return and execute Step 2-2; stop the iteration until the centers obtained in two consecutive iterations are exactly the same, and the final obstacle clustering result is obtained.

[0061] Other steps and parameters are the same as those in any one of the specific embodiments 1 to 4.

[0062] After obtaining the positions of all the obstacles in the area where the user and the target object are located, initialize the number of clusters according to the position distribution of the obstacles. For example, when the obstacles are concentrated in a certain local area, a cluster can be initialized for the obstacles in the current area. Similarly, the number of clusters to be clustered can be initialized according to the position distribution of the obstacles. Finally, the present invention clusters the obstacles that are relatively close in spatial position into one cluster, which can prevent the user from entering the prohibited area, thus avoiding the user from repeatedly trying to walk between two very adjacent prohibited areas and improving the object searching efficiency.

[0063] Specific Embodiment 6: The difference between this embodiment and any one of the specific embodiments 1 to 5 is that the specific process of Step 2-3 is as follows:

[0064] Step 2-3-1: If there is only one obstacle in the current cluster, the central position of the obstacle is the new center of the current cluster;

[0065] If there are two obstacles in the current cluster, execute Step 2-3-2;

[0066] If there are a obstacles in the current cluster and a ≥ 3, execute Step 2-3-3;

[0067] Step 2-3-2: The calculation method of the new center C new is as follows: Denote the center of one obstacle as P1, denote the center of the other obstacle as P2, and take the midpoint of the line segment P1P2 as the new center C new ;

[0068] Step 233: Randomly number the a obstacles in the current cluster, and denote the centers of the a obstacles as P1, P2, …, P a ;

[0069] Step (1): Calculate the midpoint of the line segment P1P2;

[0070] Step (2): Connect the midpoint calculated in step (1) with P3 to form a line segment, and then obtain the midpoint of the line segment; and so on until P a is traversed, and the midpoint of the last calculated line segment is used as the new center C new .

[0071] Other steps and parameters are the same as those in any one of the first to fifth specific embodiments.

[0072] Specific Embodiment 7: The difference between this embodiment and any one of the first to sixth specific embodiments is that the working process of the path planning module is as follows:

[0073] Step 1: Take the user's current position as the center O, draw a circle with a radius of length l to obtain a circular curve, and then obtain the arc part located in the passage area according to the circular curve (here, taking the user's position on the ground as the center and drawing a circle with a certain radius to obtain the circular curve on the ground), and select the end point (x, y) of the local path planning on the arc by maximizing the objective function value S(x, y);

[0074]

[0075] Among them, set A is the set of points located on the arc, q is the number of prohibited passage areas included in the prohibited passage area set Q, j = 1, 2, …, q, d j is the distance between the point (x, y) and the jth prohibited passage area in set Q, d j = R j - r1, R j is the distance between the point (x, y) and the center of the jth prohibited passage area in set Q, and α is the included angle between the line connecting the user's current position and the target object position and the line connecting the user's current position and the point (x, y);

[0076] Step 2: Use the RRT* algorithm to perform path planning between the user's current position and the point (x, y), and give a voice prompt to the user according to the planned path. Under the voice prompt, the user moves towards the end point (x, y);

[0077] Step 3: Take the new position (when the user travels to any point in set A, the position about to be traveled to is used as the new position) as the current position, and return to execute step 1; until the user reaches the end position and obtains the target object.

[0078] Other steps and parameters are the same as those in any one of the first to sixth specific embodiments.

[0079] The present invention sets the length l of the local path planning. The local path refers to the straight-line distance that the user needs to travel in each small segment. Since the user cannot travel along the planned path and will definitely deviate, the present invention adopts a segment-by-segment travel, and deviation correction is performed for each segment, that is, deviation correction; generally, the value of l is 1-2 meters.

[0080] The present invention comprehensively considers the distance between the local end point and each no-go area and the deviation angle of the line connecting the user and the local end point relative to the line connecting the user and the target object, and can effectively balance the safety of travel and the efficiency of travel.

[0081] Specific embodiment eight: The difference between this embodiment and any one of the first to seventh specific embodiments is that the method for determining the no-go area set Q is as follows:

[0082] Calculate the shortest distance for the user to enter each no-go area respectively, and then select the no-go areas with the shortest distance less than or equal to l. The set composed of the selected no-go areas is the no-go area set Q.

[0083] Other steps and parameters are the same as those in any one of the first to seventh specific embodiments. Specific embodiment nine:

[0085] This embodiment is a computer storage medium, and at least one instruction is stored in the storage medium. The at least one instruction is loaded and run by a processor to implement a spatial object searching system for visually impaired people based on sound guidance.

[0086] It should be understood that the instruction includes a computer program product, software, or computerized method corresponding to any method described in the present invention; the instruction can be used to program a computer system or other electronic devices. The computer storage medium may include a readable medium on which the instruction is stored, and may include, but is not limited to, a magnetic storage medium, an optical storage medium; the magneto-optical storage medium includes a read-only memory ROM, a random access memory RAM, an erasable programmable memory (for example, EPROM and EEPROM), and a flash memory layer, or other types of media suitable for storing electronic instructions. Specific embodiment ten:

[0088] This embodiment is a spatial object searching device for visually impaired people based on sound guidance. The device includes a processor and a memory. It should be understood that it includes any device including a processor and a memory described in the present invention. The device may further include other units and modules for display, interaction, processing, control, etc. through signals or instructions, and other functions;

[0089] At least one instruction is stored in the memory, and the at least one instruction is loaded and run by a processor for a spatial object searching system for visually impaired people based on sound guidance.

[0090] The above examples of the present invention are only for explaining in detail the calculation model and calculation process of the present invention, rather than limiting the implementation manners of the present invention. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is impossible to enumerate all the implementation manners here. Any obvious changes or modifications derived from the technical solution of the present invention still fall within the protection scope of the present invention.

Claims

1. A method for visually impaired people to search for objects in space based on sound guidance, which is implemented based on a spatial object search system for visually impaired people. The system includes a user position acquisition module, a task acquisition module, an obstacle geographical position acquisition module, a passage area acquisition module, a path planning module, and a sound prompt module; the user position acquisition module: used to acquire the position of the user in real time; the task acquisition module: used to acquire the voice of the user and recognize the target object to be searched by the user through voice input; the obstacle geographical position acquisition module: used to acquire the positions of all obstacles in the area where the user and the target object are located; The passage area acquisition module: used to determine the passage area from the user to the target object according to the obstacle position and the target object position; The path planning module: used to plan the optimal path within the determined passage area according to the user position; The voice prompt module: used to give voice prompts according to the planned optimal path to provide guidance for the user's walking direction; It is also used to judge whether the user is outside the passage area according to the real-time user position. If the user is outside the passage area, a danger prompt is given through voice; It is characterized in that the working process of the path planning module is: Step 1: Taking the user's current position as the center O, draw a circle with a length l as the radius to obtain a circular curve. Then, based on the circular curve, obtain the arc part located within the passing area, and by maximizing the objective function value , select the end point of the local path planning on the arc ; Among them, the set A is the set of points located on the circular arc, q is the number of no-go areas included in the no-go area set , , is the distance between the point and the center of the th no-go area in the set ; , is the distance between the point and the center of the th no-go area in the set ; is the included angle between the line connecting the user's current position and the target object position and the line connecting the user's current position and the point ; Step 2: Use the RRT* algorithm to plan a path between the user's current position and the point and give voice prompts to the user according to the planned path. Under the voice prompts, the user moves towards the end point ; Step 3: Take the new position as the current position, and return to execute Step 1; until the user reaches the end position and obtains the target object.

2. The method for a visually impaired person to search for objects in space based on sound guidance according to claim 1, wherein, The working process of the passage area acquisition module is: Step 1: Determine the extension length r around the obstacle; Step 2: Cluster the obstacles according to the obtained obstacle center positions. Each position clustering result is recorded as a cluster. For any cluster, determine the no-go area corresponding to the obstacles in this cluster according to the center positions of the obstacles included in the cluster and the extension length r; The method for determining the no-go area is: For any cluster, make the smallest circumscribed circle containing all the obstacles in this cluster. Then the no-go area is a circular area with the center of the smallest circumscribed circle as the center and a radius of r1; where r1 = r + the radius of the smallest circumscribed circle; Similarly, perform the same processing on each cluster respectively to obtain their corresponding no-go areas; all the no-go areas are all the no-go areas within the area where the user and the target object are located; Step 3: Use the RRT* algorithm to plan M passage paths from the user to the target object, and then select the passage path with the shortest path length from the M passage paths. The passage area passed by the selected passage path is used as the passage area from the user to the target object.

3. The method for visually impaired people to search for objects in space based on sound guidance according to claim 2, characterized in that, The extension length r is determined in the following way: Set a test starting point and a test ending point, and take the straight-line distance between the test starting point and the test ending point as 1 - 2 meters; then set a test end line, which passes through the test ending point and is perpendicular to the connection line between the test starting point and the test ending point; The tester is located at the test starting point and faces the test ending point, and walks towards the test ending point; Until the tester reaches the test end line, take the straight-line distance between the tester's position and the test ending point as the extension length r.

4. The method for visually impaired people to search for objects in space based on sound guidance according to claim 2, wherein, The extension length r is determined in the following way: Set a test starting point and a test ending point, and take the straight-line distance between the test starting point and the test ending point as 1 - 2 meters; then set a test end line, which passes through the test ending point and is perpendicular to the connection line between the test starting point and the test ending point; The tester is located at the test starting point and faces the test ending point, and walks towards the test ending point; When the tester reaches the test finish line, record the straight-line distance between the position of the tester and the test finish point as lr ; From the distances corresponding to all testers lr select the maximum value, and use the selected maximum value as the extension length r: Among them, is the distance corresponding to the i th tester, and is the total number of testers.

5. The method for visually impaired people to search for objects in space based on sound guidance according to any one of claims 2 to 4, characterized in that, The clustering of the obstacles according to the obtained obstacle center positions; specifically: Step 2-1: Initialize the number of clusters as k, and randomly initialize the center positions of k obstacles as the centers of k clusters respectively; Step 22: For any non - central obstacle, calculate the distances between the center position of the obstacle and the centers of each cluster respectively. Then, the obstacle belongs to the cluster corresponding to the minimum distance. Similarly, after processing each non - central obstacle respectively, the clustering result of this iteration is obtained. Step 23: For any cluster in the clustering result of Step 22, calculate a new center according to the center positions of all obstacles in the cluster. Similarly, process each cluster in the clustering result of Step 22. Step 24: Use the new centers obtained in Step 23 to return and execute Step 22 until the centers obtained in two consecutive iterations are exactly the same, then stop the iteration to obtain the final obstacle clustering result.

6. The method for visually impaired people to search for objects in space based on sound guidance according to claim 5, characterized in that The specific process of Step 23 is as follows: Step 231: If there is only one obstacle in the current cluster, the center position of the obstacle is the new center of the current cluster. If there are two obstacles in the current cluster, execute Step 232. If there are a obstacles in the current cluster and a≥3, execute Step 233. Step 232, New Center C new The calculation method is as follows: Denote the center of one obstacle as P 1, denote the center of another obstacle as P 2, and take the midpoint of the line segment P 1 P 2 as the new center C new ; Step 233: Randomly number the a obstacles in the current cluster, and denote the centers of the a obstacles as P 1, P 2, …, P a ; Step (1), calculate the midpoint of the line segment P 1 P 2; Step (2): Connect the midpoint calculated in step (1) with P 3 to form a line segment, and then obtain the midpoint of the line segment; and so on until P a is traversed. Take the midpoint of the last calculated line segment as the new center C new .

7. The method for visually impaired people to search for objects in space based on sound guidance according to claim 6, characterized in that, The set of prohibited passage areas The determination method is as follows: Calculate the shortest distance for the user to enter each no-go area respectively, and then select the no-go areas where the shortest distance is less than or equal to l . The set of no-go areas selected forms the no-go area set .

8. A computer storage medium, characterized in that, The storage medium stores at least one instruction, and the at least one instruction is loaded and run by a processor to execute the method for visually - impaired people to search for objects in space based on sound guidance according to any one of claims 1 to 7.

9. A spatial object-finding device for visually impaired people based on sound guidance, characterized in that, The device includes a processor and a memory. The memory stores at least one instruction, and the at least one instruction is loaded and run by a processor to execute the method for visually - impaired people to search for objects in space based on sound guidance according to any one of claims 1 to 7.

Images