Old people safe travel auxiliary equipment based on intelligent obstacle avoidance bracelet

Abstract

The utility model discloses an old people safe travel auxiliary device based on intelligent obstacle avoidance bracelet, including charging stand, bracelet and badge, the top of charging stand is provided with bracelet charging pile and badge charging pile, the side of bracelet charging pile is connected with a first charging line, the top of badge charging pile is provided with a groove, the obverse side of badge is embedded with a camera, and the camera is connected with the first charging line. Pin structures are arranged on the two sides of the back face of the badge, a magnetic attraction charging contact is arranged in the middle of the back face of the badge, a storage bin is arranged at the bottom end of the badge, a second charging wire is installed in the storage bin, a rubber dustproof pad is installed at an opening of the storage bin, and the bracelet and the badge are connected with the mobile phone end in a wireless mode. The bracelet and the badge are small in size and convenient to wear, meanwhile, the bracelet and the badge are matched with each other to recognize surrounding environment sounds and front obstacles, measure distances, monitor and recognize dangerous sounds and obstacles, a user is reminded in time to avoid potential dangers, and therefore the problem that old people are difficult to go out is solved.

Description

Technical Field

[0001] This utility model relates to the field of smart wearable devices, and in particular to a safety travel assistance device for the elderly based on a smart obstacle avoidance bracelet. Background Technology

[0002] The main problems with safe travel for the elderly include: As people age, their physical functions gradually decline, such as vision, hearing, and reaction time, making it difficult for them to react quickly to emergencies and increasing the risks of travel. In addition, some elderly people lack sufficient knowledge of traffic rules and safety regulations, making them prone to violating traffic rules and creating safety hazards.

[0003] Smartwatches and smart glasses already exist to assist the elderly with their travel, providing timely rescue services by monitoring their physical condition and location in real time. However, current technology focuses primarily on processing human voice information, neglecting related environmental sounds, and the sound recognition model structure is relatively complex. This results in an inability to effectively identify obstacles ahead, compromising the safety of elderly travelers. Utility Model Content

[0004] The technical problem to be solved by this utility model is to overcome the defects of the prior art and provide an auxiliary device for safe travel of the elderly based on a smart obstacle avoidance wristband.

[0005] To solve the above-mentioned technical problems, this utility model provides the following technical solution:

[0006] This utility model relates to an assistive device for elderly people's safe travel based on a smart obstacle avoidance wristband, comprising a charging base, a wristband, and a badge. The charging base has a wristband charging dock and a badge charging dock on its top. A first charging cable is connected to the side of the wristband charging dock. The top of the badge charging dock has a groove, and a magnetic charging head is embedded in the surface of the groove. A charging interface is provided on the side of the wristband. A camera is embedded in the front of the badge. Pin structures are provided on both sides of the back of the badge. A magnetic charging contact is located in the center of the back of the badge. A storage compartment is provided at the bottom of the badge, and a first charging cable is installed inside the storage compartment. The two charging cables are equipped with a rubber dustproof pad at the opening of the storage compartment. Both the wristband and the badge are wirelessly connected to the mobile phone. The wristband contains a microcontroller, a ranging module, a sound module, and an alert module. The badge contains a photosensor, an image acquisition module, and a storage module. The camera is an OV5640 camera. The microcontroller processes the data obtained by the ranging module, the sound module, the photosensor, and the image acquisition module. The sound module is used to collect ambient sounds and issue voice alerts to the user. The alert module is used to control the wristband to vibrate and alert the user.

[0007] As a preferred technical solution of this utility model, the pin structure includes a bottom block, a top block and a pin. The bottom block and the top block are on the same vertical line. The outer periphery of the pin is provided with an external thread that connects to the top block, and the diameter of the external thread is larger than that of the bottom end. The pin passes through the top block and abuts against the bottom block.

[0008] As a preferred embodiment of this utility model, a rotating head is installed at the top of the pin, and a slot for accommodating the pin tip is provided at the top of the base block.

[0009] As a preferred embodiment of this utility model, the storage compartment is provided with a cable groove that matches the size of the second charging cable, and a locking head is provided at the edge of the cable groove.

[0010] Compared with the prior art, the beneficial effects of this utility model are as follows:

[0011] This utility model features a small and convenient wristband and badge that are easy to wear. The wristband and badge work together to identify and measure the distance to ambient sounds and obstacles in front of the user, monitor and identify dangerous sounds and obstacles, and promptly remind the user to avoid potential dangers, thereby solving the problem of travel difficulties for the elderly. Attached Figure Description

[0012] The accompanying drawings are provided to further illustrate the present invention and form part of the specification. They are used together with the embodiments of the present invention to explain the present invention, but do not constitute a limitation thereof. In the drawings:

[0013] Figure 1 This is a front view of the overall structure of this utility model;

[0014] Figure 2 This is a schematic diagram of the structure of the badge of this utility model;

[0015] Figure 3 This is a rear view of the badge of this utility model;

[0016] Figure 4 This is an exploded view of the pin structure of this utility model;

[0017] Figure 5 This is a top view of the overall structure of this utility model;

[0018] Figure 6 This is a structural diagram of the internal structure of the storage compartment of this utility model;

[0019] Figure 7 This is a flowchart used in the embodiments;

[0020] Figure 8 This is a flowchart of the identification process in the embodiment;

[0021] In the diagram: 1. Charging dock; 2. Wristband; 3. Badge; 11. Wristband charging station; 12. Badge charging station; 13. First charging cable; 14. Groove; 15. Magnetic charging head; 31. Camera; 32. Pin structure; 33. Magnetic charging contact; 34. Storage compartment; 35. Second charging cable; 36. Rubber dustproof pad; 321. Base block; 322. Top block; 323. Pin. Detailed Implementation

[0022] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0023] In the attached diagram, all identical reference numerals refer to the same components.

[0024] Example 1

[0025] like Figure 1-8 As shown, this utility model provides an elderly safety travel assistance device based on a smart obstacle avoidance wristband, including a charging base 1, a wristband 2, and a badge 3. The charging base 1 has a wristband charging post 11 and a badge charging post 12 on its top. A first charging cable 13 is connected to the side of the wristband charging post 11. The top of the badge charging post 12 has a groove 14, and a magnetic charging head 15 is embedded in the surface of the groove 14. A charging interface is provided on the side of the wristband 2. A camera 31 is embedded in the front of the badge 3. Pin structures 32 are provided on both sides of the back of the badge 3. A magnetic charging contact 33 is provided in the middle of the back of the badge 3. A storage compartment 34 is provided at the bottom of the badge 3. The storage compartment 34 houses a second charging cable 35, and a rubber dustproof pad 36 is installed at the opening of the storage compartment 34. Both the wristband 2 and the badge 3 are wirelessly connected to the mobile phone. The wristband 2 contains a microcontroller, a ranging module, a sound module, and an alert module. The badge 3 contains a light sensor, an image acquisition module, and a storage module. The camera 31 is an OV5640 camera. The microcontroller processes the data obtained by the ranging module, the sound module, the light sensor, and the image acquisition module. The sound module is used to collect ambient sounds and issue voice reminders to the user. The alert module is used to control the wristband 2 to vibrate and remind the user.

[0026] Furthermore, the pin structure 32 includes a bottom block 321, a top block 322, and a pin 323. The bottom block 321 and the top block 322 are on the same vertical line. The outer periphery of the pin 323 is provided with an external thread that connects to the top block 322. The diameter of the external thread is larger than that of the bottom end. The pin 323 passes through the top block 322 and abuts against the bottom block 321.

[0027] Furthermore, a rotating head is mounted on the top of the pin 323, and a slot is provided on the top of the base block 321 to accommodate the tip of the pin 323.

[0028] Furthermore, the storage compartment 34 has a cable groove inside that matches the size of the second charging cable 35, and a locking head is provided at the edge of the cable groove.

[0029] Specifically, the first charging cable 13 on the wristband charging station 11 on the charging base 1 charges the wristband 2, and the magnetic charging head 15 in the groove 14 on the badge charging station 12 connects with the magnetic charging contact 33 on the back of the badge 3 to charge the badge 3. At the same time, when using it outside, if the wristband 2 is low on power, the second charging cable 35 can be taken out from the rubber dustproof pad 36 of the storage compartment 34 at the bottom of the badge 3 to charge the wristband 2.

[0030] When in use, first fix the badge to the front of the shirt using the pin structure 32, rotate and lift the pin 323, then pass it through the shirt and insert the bottom end of the pin 323 into the slot of the bottom block 321, and then rotate the pin 323 to make it threadedly connect with the top block 322 to complete the fixing of the badge 3.

[0031] like Figure 7 As shown, during the walking process, the camera 31 on the badge 3 captures images of the road ahead. The captured images are processed by a microcontroller using algorithms to identify objects and determine obstacles. The camera 31 uses an OV5640 sensor with 5 megapixels, sufficient for the obstacle avoidance device to acquire road information. Utilizing OmniBSI technology, the camera boasts high sensitivity, low noise, and low crosstalk, along with automatic image control algorithms such as automatic white balance and automatic exposure. These technologies eliminate interference from external factors (light, shadow) on the camera's recognition accuracy, significantly improving obstacle recognition and making the identified objects clearer and more accurate. Simultaneously, to accurately identify image features, a convolutional network using the SSD algorithm is established and trained. The neural network acts as a feature extractor, extracting image features. Based on the extracted features, convolution is used to generate candidate boxes containing object location and category information. The extracted candidate boxes are then decoded and filtered (NMS). When performing label matching on a default box, the object information labels of the input image are traversed. If the IOU between the object and the default box exceeds a certain threshold, the default box is considered valid. The box is used to identify the object and output the final candidate box. It finds matching obstacles and provides a reminder. A convolutional network is built by transferring the label to the default box. The cost function is divided into localization accuracy and classification accuracy. The training task is labeled.

[0032] The ranging module in the wristband 2 uses ultrasonic ranging. The ultrasonic ranging sensor emits ultrasonic waves according to the trigger pulse output by the microprocessor and detects the reflected waves. The time between the emission and detection of the ultrasonic waves is output to the microprocessor as pulse width data. The distance to the obstacle is calculated based on the speed of sound and the time difference. The device can detect the distance between the user and the obstacle and send a signal when the distance between the user and the obstacle reaches a certain value.

[0033] Using the MultiRseponsed-GMM-CNN structure, the Mel-Cepson feature extraction results and spectrograms, which contain essentially the same amount of information, are processed by a relatively simple Gaussian mixture model and a relatively lightweight 6-layer convolutional neural network, respectively. The final result is determined by both. This approach can achieve good results with a small model size.

[0034] like Figure 8 As shown, the recognition process is as follows: For the vision system, the ultrasonic detector in the wristband 2 detects the distance to obstacles. When the distance is less than 5m, a high-level signal is triggered, controlling the image acquisition module in the badge 3 to acquire an image of the suspected obstacle. The image is first stored, then sent to the mobile app's intelligent processing module. The acquired image is analyzed and processed, extracting features from the image using Haar features. Furthermore, a neural network dataset is used in the cloud database to identify objects and feature point detection to determine the type of obstacle. The results are fed back to the voice module of the app's intelligent processing platform for voice prompts. For the hearing system, air vibrations drive the portable wristband and fixed sound... The magnetic coil on the sound acquisition device vibrates to generate a corresponding analog signal. To better process the signal, it needs to be sampled. The human ear's hearing frequency is between 20Hz and 20000Hz. According to the Nyquist-Shannon sampling theorem, the sampling frequency fc > 2fm, that is, a sampling frequency of 40000Hz is sufficient. The wristband collects sound data, performs preprocessing, and then transmits it to the mobile APP. The mobile APP classifies and identifies the sound data. On one hand, it feeds back the identification results to the wristband 2, and the sound module on the wristband 2 reminds the elderly to avoid obstacles. At the same time, the wristband 2 vibrates to remind them. On the other hand, it feeds back unidentified data to the cloud self-learning module to expand the database.

[0035] Furthermore, the aforementioned SSD can be replaced by the CNN algorithm. The CNN algorithm is also a candidate box-based object detection algorithm. CNN can integrate candidate region selection, image feature extraction, object classification, and box regression into the same network framework. In the candidate box selection stage, CNN proposes a Region Proposal Network (RPN) to replace the selective search algorithm in CNN, in order to filter candidate regions in the image that may contain objects. The RPN network introduces the concept of anchor points to generate initial candidate boxes. In terms of feature extraction, CNN uses the convolutional part of the VGG-16 model. In the object classification and box regression stages, CNN trains a fully connected classification and location refinement network to classify and confirm the location of the candidate regions. In order to solve the problem of inconsistent feature map sizes generated by candidate regions of different scales, CNN proposes the region of interest pooling method, which unifies the candidate regions to the same dimension through 7×7 grid pooling. Then, two fully connected branches are trained for object classification and location regression respectively.

[0036] The ranging module in the bracelet 2 can also use an infrared sensor to achieve ranging functionality. The basic principle of infrared sensor ranging is that the light-emitting diode emits infrared light, and the photosensitive receiver receives the reflected light from objects in front, thereby measuring the distance between the two ends. The infrared sensor's ranging method is specular reflection. The light-emitting diode emits infrared light, and the photosensitive receiver receives the reflected light from objects in front, thereby measuring the distance between the two ends. The infrared rangefinder consists of two parts: a transmitter and a receiver. The transmitter continuously emits infrared light with a frequency of 40kHz. When it encounters a reflected wave signal, the receiver receives the signal and converts it into an electrical signal.

[0037] In summary, the wristband and badge of this utility model are small and easy to wear. At the same time, the wristband and badge work together to identify and measure the distance of surrounding ambient sounds and obstacles in front, monitor and identify dangerous sounds and obstacles, and promptly remind users to avoid potential dangers, thereby solving the problem of travel difficulties for the elderly.

[0038] Finally, it should be noted that the above description is merely a preferred embodiment of this utility model and is not intended to limit the utility model. Although the utility model has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this utility model should be included within the protection scope of this utility model.

Claims

1. A safety assistance device for elderly people based on a smart obstacle avoidance wristband, comprising a charging base (1), a wristband (2), and a badge (3), characterized in that, The charging base (1) is equipped with a wristband charging station (11) and a badge charging station (12) on its top. The wristband charging station (11) is connected to a first charging cable (13) on its side. The badge charging station (12) has a groove (14) at its top, and a magnetic charging head (15) is embedded in the surface of the groove (14). The wristband (2) is equipped with a charging interface on its side. The badge (3) has a camera (31) embedded in its front. The badge (3) has pin structures (32) on both sides of its back. The badge (3) has a magnetic charging contact (33) in the middle of its back. The badge (3) has a storage compartment (34) at its bottom. The storage compartment (34) contains a second charging cable. The charging cable (35) and the opening of the storage compartment (34) are equipped with a rubber dustproof pad (36). The wristband (2) and the badge (3) are both wirelessly connected to the mobile phone. The wristband (2) contains a microcontroller, a ranging module, a sound module and an alert module. The badge (3) contains a photosensitive sensor, an image acquisition module and a storage module. The camera (31) is an OV5640 camera. The microcontroller processes the data obtained by the ranging module, the sound module, the photosensitive sensor and the image acquisition module. The sound module is used to collect the sound of the surrounding environment and issue a voice reminder to the user. The alert module is used to control the wristband (2) to vibrate to remind the user.

2. The elderly safety travel assistance device based on a smart obstacle avoidance wristband according to claim 1, characterized in that, The pin structure (32) includes a bottom block (321), a top block (322), and a pin (323). The bottom block (321) and the top block (322) are on the same vertical line. The pin (323) has an external thread at its outer periphery top end that connects to the top block (322), and the diameter of the external thread is larger than that of the bottom end. The pin (323) passes through the top block (322) and abuts against the bottom block (321).

3. The elderly safety travel assistance device based on a smart obstacle avoidance wristband according to claim 2, characterized in that, The top of the pin (323) is equipped with a rotating head, and the top of the base block (321) is provided with a slot for accommodating the tip of the pin (323).

4. The elderly safety travel assistance device based on a smart obstacle avoidance wristband according to claim 1, characterized in that, The storage compartment (34) has a cable groove inside that matches the size of the second charging cable (35), and a locking head is provided at the edge of the cable groove.

Images