Barrier-free and aging-suitable intelligent passage control method in building

Abstract

The invention discloses a barrier-free and aging-suitable intelligent traffic control method in a building, and relates to the technical field of intelligent travel, and the method comprises the control steps: S1, a user obtains an intelligent wheelchair at a barrier-free entrance of the building, recognizes and judges the type of the current user based on a camera module, and carries out the recognition of the type of the current user for different types of users; the intelligent wheelchair gives a corresponding use means, inputs a destination instruction and advances, and a barrier-free aging service facility is arranged in the building; and S2, identifying whether obstacles exist around the barrier-free traffic flow line on the ground or not through barrier-free channel magnetic induction and a camera module of the ground navigation magnetic strip. On the basis of combination of the ground navigation magnetic strip and the camera, obstacles are recognized, service personnel are reminded to clean when obstacles exist, the intelligent wheelchair automatically judges elevator time for preparation in advance, a safe and reliable passing environment is provided, the response time is shortened, convenience and efficiency are improved, and special requirements of the old and the disabled are fully considered.

Description

Technical Field

[0001] The present invention relates to the field of intelligent travel technology, and in particular to a barrier-free and aging-friendly intelligent passage control method in a building. Background Art

[0002] With the development of society and the acceleration of the aging process, barrier-free and aging-friendly design in buildings has become increasingly important. At present, although many buildings have considered the construction of barrier-free facilities to a certain extent, on the one hand, the traditional barrier-free passage design is relatively simple, usually simply setting up basic facilities such as ramps and handrails, lacking intelligent guidance and control. When using these facilities, the elderly and people with mobility difficulties often need to rely on the help of others or grope on their own, which makes them prone to getting lost and misoperating. In addition, for some complex building structures, traditional barrier-free passages may not meet the needs of users, resulting in their passage in the building being restricted. In this regard, we propose a barrier-free and aging-friendly intelligent passage control method in buildings. Summary of the invention

[0003] In order to solve the above technical problems, a barrier-free and aging-friendly intelligent passage control method is provided in a building. This technical solution solves the above-mentioned problem of not being able to meet the needs of users.

[0004] In order to achieve the above objectives, the technical solution adopted by the present invention is: a barrier-free and aging-friendly intelligent passage control method in a building, the control steps are:

[0005] S1. The user obtains a smart wheelchair at the barrier-free entrance of the building. The camera module identifies the type of the current user. The smart wheelchair gives the corresponding usage method for different types of users. The user enters the destination command and moves forward. The building is equipped with barrier-free facilities for the elderly.

[0006] S2. The barrier-free passage magnetic induction and camera module of the ground navigation magnetic strip identify whether there are obstacles around the barrier-free passage flow line on the ground. If there are no obstacles, the user is automatically carried to the destination. At the same time, the corresponding service facilities at the destination give voice prompts to remind the service personnel to prepare for the service. When obstacles are found around the barrier-free passage flow line, the service personnel are reminded by voice playback to clear the obstacles for the aisle;

[0007] S3: The smart wheelchair automatically determines the time it takes to reach other floors through the barrier-free elevator and ramp, automatically controls the barrier-free elevator in advance to prepare, and sends the elderly to the corresponding barrier-free elderly-friendly service facilities on the corresponding floor after the smart wheelchair arrives;

[0008] S4. After use, the user takes the smart wheelchair and presses the one-touch return button to return to the starting point. The wheelchair automatically charges when it returns to the nearest charging point or the starting point.

[0009] Preferably, in step S1, the smart wheelchair includes a gravity sensing module, an AGV navigation module, an electromagnetic recognition module, a camera module and a Braille button module, wherein the gravity sensing module is used to sense whether there is someone riding in the smart wheelchair, the AGV navigation module is used to locate and navigate the smart wheelchair, the electromagnetic recognition module is used to sense the navigation magnetic strip on the ground, the camera module is used to photograph the process of travel and identify the user, and the Braille button module is used for the blind to identify the button text information; the barrier-free and aging-friendly service facilities in the building include barrier-free toilets, low-level water dispensers, barrier-free ramps and barrier-free service centers.

[0010] Preferably, in step S1, the user inputs the destination instruction based on voice and touch input text to input the destination; the camera module analyzes and judges the wheelchair user based on image recognition technology. For elderly people with weak bodies and limited mobility, the camera recognizes their slower movements and specific body characteristics; for people who temporarily need to use wheelchairs due to injuries, they are distinguished according to the location of their injuries and the stage of rehabilitation; the disabled are judged based on the behavior and movement characteristics of the photos taken; and different operation methods are given to different types of users.

[0011] Preferably, when analyzing the wheelchair user, the camera module pre-processes the image, including denoising and contrast enhancement operations, to improve the image quality, extract various features of the user, including body posture, facial expression and movement amplitude, and determine the type of the wheelchair user through comprehensive analysis of these features;

[0012] Assume that the wheelchair user is U, and calculate the image feature vector to obtain the image feature vector F'=(F1, F2, F3), where F1 represents the body posture feature value, F2 represents the body posture feature value, and F3 represents the movement amplitude feature value. Based on the obtained vector, the type of the current wheelchair user is judged, and a threshold range is established for each type of person. The obtained image feature vector is compared with the established threshold, and the currently identified user is divided into the corresponding type of person according to the corresponding threshold range.

[0013] Preferably, in step S2, when the ground navigation magnetic strip is in effect, it releases a magnetic field signal, and the signal is received by the electromagnetic recognition module. When an object approaches or is near the barrier-free traffic flow line, the electromagnetic recognition module responds to detect changes in the magnetic field and determine whether there are obstacles around that may affect barrier-free traffic. The camera module captures the images around the barrier-free traffic flow line in real time, analyzes and judges the objects in the image based on image recognition technology, and issues an alarm when an object that hinders barrier-free traffic is found, and the service personnel take corresponding measures.

[0014] Preferably, the method of judging obstacles by image recognition technology collects various image samples of objects that hinder traffic in advance, extracts feature vectors, and establishes an obstacle feature model. Assuming that there are N types of obstacles, the feature vector of each type of obstacle is M = (M1, M2, ... M n ), trained based on machine learning algorithms, and obtained a classifier to determine whether the object in the input image is an obstacle. The currently shot video is input for judgment. The classifier calculation formula is:

[0015] y=sign(w*g+b)

[0016] Where y is the output result of the classifier, w is the weight vector, b is the bias term, and g is the input image. When y is 1, it means that the object in the image is an obstacle, and when y is 0, it means that the object in the image is not an obstacle.

[0017] Preferably, in step S3, when the smart wheelchair receives an instruction to go to other floors, it evaluates the ramp between the current position and the target floor, measures the length and slope of the ramp and the speed of the wheelchair on the ramp in the current state, calculates the time required to pass the ramp, then communicates with the elevator control system of the building, obtains the current position, running speed and estimated time to arrive at the current floor of the elevator, calculates the time required to reach the elevator by taking into account the distance from the current position to the elevator entrance and the moving speed of the wheelchair, and calculates the time required to reach the elevator by combining the running speed of the elevator and the height of the target floor.

[0018] Preferably, after obtaining the total time to reach other floors via the barrier-free elevator and ramp, the smart wheelchair automatically controls the barrier-free elevator in advance to prepare, sends a signal to the elevator control system, and requests the elevator to open the door and wait within the estimated time. After entering the elevator, the elevator runs smoothly to the target floor. After reaching the target floor, the smart wheelchair continues to move towards the corresponding barrier-free and elderly-friendly service facilities.

[0019] Preferably, in step S4, when the user finishes using the smart wheelchair, he / she presses a return button, determines the current location based on the built-in AGV navigation module, compares it with the pre-stored departure information, and calculates the shortest return route based on the path planning algorithm. During the return process, the smart wheelchair continuously monitors the surrounding environment, automatically adjusts the speed, and avoids obstacles.

[0020] Preferably, the smart wheelchair uses wireless communication technology to interact with surrounding charging facilities to obtain the location and usage status information of each charging point. When the smart wheelchair successfully returns to the starting point, it will automatically prepare for charging. During the charging process, the control system of the wheelchair will monitor the charging status in real time.

[0021] Compared with the prior art, the present invention has the following beneficial effects:

[0022] The present invention combines ground navigation magnetic strips with cameras to identify obstacles, remind service personnel to clear obstacles when there are obstacles, and the smart wheelchair automatically determines the elevator time and prepares in advance, providing a safe and reliable passage environment, shortening the response time, improving convenience and efficiency, fully considering the special needs of the elderly and people with mobility difficulties, providing all-round services, embodying care and concern, and intelligent design and management to meet physiological and psychological needs and improve the quality of life. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a flow chart of the control steps of the present invention;

[0024] Figure 2 This is a block diagram of the internal structure of the intelligent wheelchair of the present invention;

[0025] Figure 3 This is a flow chart of the time determination steps of the intelligent wheelchair of the present invention;

[0026] Figure 4 This is a schematic diagram of the magnetic strip guidance for ground navigation in an indoor barrier-free passage of a building according to the present invention. DETAILED DESCRIPTION

[0027] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0028] Reference Figures 1 to 3 As shown, a barrier-free and aging-friendly intelligent traffic control method in a building, the control steps are:

[0029] S1. The user obtains a smart wheelchair at the barrier-free entrance of the building. The camera module identifies the type of the current user. The smart wheelchair gives the corresponding usage method for different types of users. The user enters the destination command and moves forward. The building is equipped with barrier-free facilities for the elderly.

[0030] S2. The barrier-free passage magnetic induction and camera module of the ground navigation magnetic strip identify whether there are obstacles around the barrier-free passage flow line on the ground. If there are no obstacles, the user is automatically carried to the destination. At the same time, the corresponding service facilities at the destination give voice prompts to remind the service personnel to prepare for the service. When obstacles are found around the barrier-free passage flow line, the service personnel are reminded by voice playback to clear the obstacles for the aisle;

[0031] S3: The smart wheelchair automatically determines the time it takes to reach other floors through the barrier-free elevator and ramp, automatically controls the barrier-free elevator in advance to prepare, and sends the elderly to the corresponding barrier-free elderly-friendly service facilities on the corresponding floor after the smart wheelchair arrives;

[0032] S4. After use, the user takes the smart wheelchair and presses the one-touch return button to return to the starting point. The wheelchair automatically charges when it returns to the nearest charging point or the starting point.

[0033] The present application identifies the type of user through the camera module and gives the corresponding means of use, which can meet the personalized needs of different users. After entering the destination command, the vehicle can move forward automatically without complicated operations, making it easier to use. The barrier-free magnetic induction of the ground navigation magnetic strip is combined with the camera module to identify in real time and accurately whether there are obstacles around the barrier-free flow line on the ground. When there are no obstacles, the smart wheelchair automatically carries the user to the destination, ensuring safety during driving. When obstacles are found, the service personnel are reminded to clear the obstacles through voice playback and eliminate safety hazards in time. The corresponding service facilities at the destination will give voice prompts to remind the service personnel to prepare for the service. After the user has finished using the smart wheelchair, he can return to the departure point by pressing the one-touch return button and return to the nearest charging point or the departure point for automatic charging. This intelligent access control method fully considers the special needs of the elderly and people with mobility difficulties, and provides them with a full range of barrier-free and aging-friendly services.

[0034] Reference Figure 2As shown, in step S1, the smart wheelchair includes a gravity sensing module, an AGV navigation module, an electromagnetic recognition module, a camera module and a Braille button module, wherein the gravity sensing module is used to sense whether there is someone riding in the smart wheelchair, the AGV navigation module is used to locate and navigate the smart wheelchair, the electromagnetic recognition module is used to sense the navigation magnetic strip on the ground, the camera module is used to photograph the process of travel and identify the user, and the Braille button module is used for the blind to identify the button text information; the barrier-free and aging-friendly service facilities in the building include barrier-free toilets, low-level water dispensers, barrier-free ramps and barrier-free service centers.

[0035] The gravity sensing module of the present application can accurately determine whether there is someone riding in the smart wheelchair, avoid misstart and waste of resources, and start the corresponding function only when someone is riding, improve energy utilization efficiency, ensure that navigation operations are performed only when someone is using it, and prevent accidents. The AGV navigation module realizes accurate positioning of the smart wheelchair, so that users can clearly understand their location and reduce the risk of getting lost. It provides efficient location navigation and helps users quickly reach their destination, especially for people who are not familiar with the environment, which greatly improves the convenience of travel. The electromagnetic recognition module accurately senses the navigation magnetic strip on the ground, provides reliable travel path guidance for the smart wheelchair, ensures that the wheelchair travels on the barrier-free passage, improves the accuracy and stability of driving, and cooperates with other modules to jointly ensure the safe driving of the wheelchair and avoid deviating from the barrier-free passage and encountering obstacles. The camera module shoots the process of travel. On the one hand, it can record the driving trajectory so that it can be queried and traced back when needed. On the other hand, it provides additional protection for safety, such as providing evidence in the event of an accident. The Braille button module provides a way for the blind to identify the text information of the button, so that the blind can also operate the smart wheelchair independently, greatly expanding the applicable population of the smart wheelchair.

[0036] In step S1, the user inputs the destination command by voice and touch input. The camera module analyzes and judges the wheelchair user based on image recognition technology. For the elderly who are weak and have limited mobility, the camera recognizes their slower movements and specific body characteristics. For those who temporarily need to use a wheelchair due to injuries, they are distinguished according to the location of their injury and the stage of rehabilitation. The disabled are judged based on the behavior and movement characteristics captured. Different operation methods are given for different types of users.

[0037] For users with limited mobility, especially those with limited hand movements, voice input does not require manual operation, greatly improving the convenience of inputting destinations. They can easily tell the smart wheelchair the destination through voice commands without the need for laborious touch operations. For users with poor eyesight, voice input can avoid the problem of them not being able to accurately input the destination because they cannot see the screen or buttons clearly. Just say the name of the destination, and the smart wheelchair can accurately identify and plan the route quickly and efficiently. Users can complete the destination input in a short time, saving time and improving travel efficiency.

[0038] When analyzing the wheelchair user, the camera module pre-processes the image, including denoising and contrast enhancement operations to improve the image quality and extract various features of the user, including body posture, facial expression and movement amplitude. Through comprehensive analysis of these features, the type of the wheelchair user is determined. Suppose the wheelchair user is U, and the image feature vector is calculated to obtain the image feature vector F'=(F1, F2, F3), where F1 represents the body posture feature value, F2 represents the body posture feature value, and F3 represents the movement amplitude feature value. Based on the obtained vector, the type of the current wheelchair user is determined, and a threshold range is established for each type of person. The obtained image feature vector is compared with the established threshold, and the currently identified user is divided into the corresponding type of person according to the corresponding threshold range.

[0039] The calculation of the image feature vector in this application is a prior art and will not be described in detail here. It provides a clear standard for judging the type of person. By establishing a threshold range for each type of person, the extracted image feature vector can be compared with these thresholds to accurately judge the type of the user. This avoids the uncertainty of subjective judgment and improves the accuracy and reliability of judgment.

[0040] In step S2, when the ground navigation magnetic strip is in effect, it releases a magnetic field signal, which is received by the electromagnetic recognition module. When an object approaches or is near the barrier-free flow line, the electromagnetic recognition module responds to detect changes in the magnetic field and determine whether there are obstacles around that may affect barrier-free passage. The camera module captures the images around the barrier-free flow line in real time, analyzes and judges the objects in the image based on image recognition technology, and issues an alarm when an object that hinders barrier-free passage is found, and the service personnel take corresponding measures.

[0041] The magnetic field signal released by the ground navigation magnetic strip of the present application can provide a clear route for the smart wheelchair, ensuring that it travels within the barrier-free traffic flow line, improving the accuracy and reliability of navigation. When an object approaches or is near the barrier-free traffic flow line, the electromagnetic recognition module can quickly detect the magnetic field changes and promptly determine whether there are obstacles around that may affect barrier-free traffic. This provides users with early warning and increases driving safety.

[0042] The method of judging obstacles by image recognition technology is to collect various image samples of objects that hinder traffic in advance, extract feature vectors, and establish an obstacle feature model. Assuming that there are N types of obstacles, the feature vector of each type of obstacle is M = (M1, M2, ... M n ), trained based on machine learning algorithms, and obtained a classifier to determine whether the object in the input image is an obstacle. The currently shot video is input for judgment. The classifier calculation formula is:

[0043] y=sign(w*g+b)

[0044] Where y is the output result of the classifier, w is the weight vector, b is the bias term, and g is the input image. When y is 1, it means that the object in the image is an obstacle, and when y is 0, it means that the object in the image is not an obstacle.

[0045] Reference Figure 3 As shown, in step S3, when the smart wheelchair receives an instruction to go to other floors, it evaluates the ramp between the current position and the target floor, measures the length and slope of the ramp and the speed of the wheelchair on the ramp in the current state, calculates the time required to pass the ramp, and then communicates with the elevator control system of the building to obtain the current position, running speed and estimated time to reach the current floor of the elevator, considers the distance from the current position to the elevator entrance and the moving speed of the wheelchair, calculates the time required to reach the elevator, and combines the running speed of the elevator and the height of the target floor to calculate the time required to reach the target floor by the elevator.

[0046] The smart wheelchair of the present application can select the optimal path and time arrangement by calculating the time of ramps and elevators. If the waiting time for the elevator is long and the ramp is relatively smooth, the wheelchair can adjust the route according to the actual situation, and give priority to reaching the target floor via the ramp and then waiting for the elevator, thereby improving the overall travel efficiency. By communicating with the elevator control system, it can coordinate the operation of the elevator in advance to ensure that the elevator can respond in time when the smart wheelchair arrives, which can reduce the waiting time for the elevator, improve the efficiency of elevator use, and avoid waste of elevator resources.

[0047] After calculating the total time to reach other floors via the barrier-free elevator and ramp, the smart wheelchair automatically controls the barrier-free elevator in advance to prepare, sends a signal to the elevator control system, requesting the elevator to open the door and wait within the estimated time. After entering the elevator, the elevator runs smoothly to the target floor. After reaching the target floor, the smart wheelchair continues to move towards the corresponding barrier-free and elderly-friendly service facilities.

[0048] This application controls the elevator to prepare in advance, saving users' waiting time for the elevator. For elderly and disabled people with limited mobility, reducing waiting time can reduce their fatigue and anxiety and improve travel comfort and convenience.

[0049] In step S4, when the user finishes using the smart wheelchair, he / she presses the one-touch return button. Based on the built-in AGV navigation module, the current location is determined and compared with the pre-stored departure information. Based on the path planning algorithm, the shortest return route is calculated. During the return process, the smart wheelchair continuously monitors the surrounding environment, automatically adjusts the speed, and avoids obstacles.

[0050] During the return process of this application, the smart wheelchair continuously monitors the surrounding environment and can detect potential obstacles in time, which helps to avoid collisions and accidents and ensure the safety of users.

[0051] The smart wheelchair uses wireless communication technology to interact with the surrounding charging facilities to obtain the location and usage status information of each charging point. When the smart wheelchair returns to the starting point smoothly, it will automatically prepare for charging. During the charging process, the wheelchair's control system will monitor the charging status in real time.

[0052] The real-time monitoring of charging status in this application can ensure the safety and efficiency of the charging process. The control system can promptly detect abnormal charging conditions, such as overcharging and overheating, and take corresponding measures to protect them, thereby extending battery life and reducing safety risks.

[0053] Reference Figure 4 As shown in the figure, different symbols and lines are used to represent various facilities and their connection paths.

[0054] The user enters from the "barrier-free entrance to the building", next to which is the "parking area for intelligent barrier-free wheelchairs". After entering from the entrance, there is a dotted line path leading to the "right-angle fork section", followed by the "straight section", and then to the "acute-angle fork section", and finally to the "barrier-free, aging-friendly facilities" area. On the right side of the figure, there is an "accessible passage" with a "navigation magnetic strip" next to it. The passage is connected to the "right-angle turn connection diagram" and the "acute-angle turn connection diagram". These turn connection diagrams are connected to the "barrier-free, aging-friendly facilities" area through dotted line paths. This area is also represented by a rectangle with a dotted border;

[0055] The figure also shows several “barrier-free, age-friendly facilities” areas, which are represented by rectangles with dashed borders and are located in different locations on the figure and connected to other facilities by dashed paths;

[0056] Overall, it shows the layout of barrier-free facilities and aging-friendly facilities, as well as the connecting paths between the various facilities, aiming to provide convenient navigation and usage guidance for people with limited mobility.

[0057] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments, and the above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention, and these changes and improvements fall within the scope of the present invention claimed.

Claims

1. A barrier-free and aging-friendly intelligent traffic control method in a building, characterized in that: The control steps are: S1. The user obtains a smart wheelchair at the barrier-free entrance of the building. The camera module identifies the type of the current user. The smart wheelchair gives the corresponding usage method for different types of users. The user enters the destination command and moves forward. The building is equipped with barrier-free facilities for the elderly. S2. The barrier-free passage magnetic induction and camera module of the ground navigation magnetic strip identify whether there are obstacles around the barrier-free passage flow line on the ground. If there are no obstacles, the user is automatically carried to the destination. At the same time, the corresponding service facilities at the destination give voice prompts to remind the service personnel to prepare for the service. When obstacles are found around the barrier-free passage flow line, the service personnel are reminded by voice playback to clear the obstacles for the aisle; S3: The smart wheelchair automatically determines the time it takes to reach other floors through the barrier-free elevator and ramp, automatically controls the barrier-free elevator in advance to prepare, and sends the elderly to the corresponding barrier-free elderly-friendly service facilities on the corresponding floor after the smart wheelchair arrives; S4. After use, the user takes the smart wheelchair and presses the one-touch return button to return to the starting point. The wheelchair automatically charges when it returns to the nearest charging point or the starting point.

2. According to claim 1, a barrier-free and aging-friendly intelligent traffic control method in a building is characterized in that: In step S1, the smart wheelchair includes a gravity sensing module, an AGV navigation module, an electromagnetic recognition module, a camera module and a Braille button module, wherein the gravity sensing module is used to sense whether there is someone riding in the smart wheelchair, the AGV navigation module is used to locate and navigate the smart wheelchair, the electromagnetic recognition module is used to sense the navigation magnetic strip on the ground, the camera module is used to photograph the process of movement and identify the user, and the Braille button module is used for the blind to identify the button text information; the barrier-free and aging-friendly service facilities in the building include barrier-free toilets, low-level water dispensers, barrier-free ramps and barrier-free service centers.

3. The barrier-free and aging-friendly intelligent traffic control method in a building according to claim 1 is characterized in that: In step S1, a person inputs a destination command by voice and touch input text to input the destination; The camera module uses image recognition technology to analyze and judge wheelchair users. For elderly people who are weak and have limited mobility, the camera can identify their slower movements and specific body characteristics. For people who temporarily need to use wheelchairs due to injuries, they are differentiated according to the location of their injuries and the stage of their recovery; the disabled are judged based on the behavior and movement characteristics of the filming; different operating methods are given for different types of users.

4. The barrier-free and aging-friendly intelligent traffic control method in a building according to claim 3 is characterized in that: When analyzing the wheelchair user, the camera module pre-processes the image, including denoising and contrast enhancement operations to improve the image quality and extract various features of the user, including body posture, facial expression and movement amplitude. Through comprehensive analysis of these features, the type of the wheelchair user is determined. Suppose the wheelchair user is U, and the image feature vector is calculated to obtain the image feature vector F'=(F1, F2, F3), where F1 represents the body posture feature value, F2 represents the body posture feature value, and F3 represents the movement amplitude feature value. Based on the obtained vector, the type of the current wheelchair user is determined, and a threshold range is established for each type of person. The obtained image feature vector is compared with the established threshold, and the currently identified user is divided into the corresponding type of person according to the corresponding threshold range.

5. The barrier-free and aging-friendly intelligent traffic control method in a building according to claim 1 is characterized in that: In step S2, when the ground navigation magnetic strip is in effect, it releases a magnetic field signal, which is received by the electromagnetic recognition module. When an object approaches or is near the barrier-free flow line, the electromagnetic recognition module responds to detect changes in the magnetic field and determine whether there are obstacles around that may affect barrier-free passage. The camera module captures the images around the barrier-free flow line in real time, analyzes and judges the objects in the image based on image recognition technology, and issues an alarm when an object that hinders barrier-free passage is found, and the service personnel take corresponding measures.

6. The barrier-free and aging-friendly intelligent traffic control method in a building according to claim 5 is characterized in that: The method of judging obstacles by image recognition technology is to collect various image samples of objects that hinder traffic in advance, extract feature vectors, and establish an obstacle feature model. Assuming that there are N types of obstacles, the feature vector of each type of obstacle is M = (M1, M2, ... M n ), trained based on machine learning algorithms, and obtained a classifier to determine whether the object in the input image is an obstacle. The currently shot video is input for judgment. The classifier calculation formula is: y=sign(w*g+b) Where y is the output result of the classifier, w is the weight vector, b is the bias term, and g is the input image. When y is 1, it means that the object in the image is an obstacle, and when y is 0, it means that the object in the image is not an obstacle.

7. The barrier-free and aging-friendly intelligent traffic control method in a building according to claim 1 is characterized in that: In step S3, when the smart wheelchair receives an instruction to go to other floors, it evaluates the ramp between the current position and the target floor, measures the length and slope of the ramp, and the speed of the wheelchair on the ramp in the current state, and calculates the time required to pass the ramp. It then communicates with the building's elevator control system to obtain the elevator's current position, operating speed, and estimated time to reach the current floor. It calculates the time required to reach the elevator by taking into account the distance from the current position to the elevator entrance and the moving speed of the wheelchair. It then calculates the time required to reach the target floor by taking the elevator into account, combining the elevator's operating speed and the height of the target floor.

8. The barrier-free and aging-friendly intelligent traffic control method in a building according to claim 7, characterized in that: After calculating the total time to reach other floors via the barrier-free elevator and ramp, the smart wheelchair automatically controls the barrier-free elevator in advance to prepare, sends a signal to the elevator control system, requesting the elevator to open the door and wait within the estimated time. After entering the elevator, the elevator runs smoothly to the target floor. After reaching the target floor, the smart wheelchair continues to move towards the corresponding barrier-free and elderly-friendly service facilities.

9. The barrier-free and aging-friendly intelligent traffic control method in a building according to claim 1 is characterized in that: In step S4, when the user finishes using the smart wheelchair, he / she presses the one-touch return button. Based on the built-in AGV navigation module, the current location is determined and compared with the pre-stored departure information. Based on the path planning algorithm, the shortest return route is calculated. During the return process, the smart wheelchair continuously monitors the surrounding environment, automatically adjusts the speed, and avoids obstacles.

10. The barrier-free and aging-friendly intelligent traffic control method in a building according to claim 9, characterized in that: The smart wheelchair uses wireless communication technology to interact with the surrounding charging facilities to obtain the location and usage status information of each charging point. When the smart wheelchair returns to the starting point smoothly, it will automatically prepare for charging. During the charging process, the wheelchair's control system will monitor the charging status in real time.

Images