CN114558279A - Safety control method of running machine and running machine - Google Patents

Abstract

The invention relates to a safety control method for a treadmill and a treadmill. The safety control method for the treadmill comprises: acquiring a face image captured by a first camera device; wherein, the first camera device is arranged on the treadmill of the treadmill. The upper end of the front side of the fuselage; the rotation speed of the treadmill is controlled according to the proportion of the human face in the face image and the preset positive correlation between the proportion of the human face and the rotational speed of the treadmill. Compared with the prior art, the present application can effectively avoid the occurrence of unexpected situations, improve the safety of the treadmill, and the method of prejudging the user's position based on the face image and then controlling the rotation speed of the treadmill is more suitable for the actual use scenario of the user, higher accuracy.

Description

Safety control method of treadmill and treadmill

technical field

The embodiments of the present application relate to the technical field of treadmills, and in particular, to a safety control method for a treadmill and a treadmill.

Background technique

At present, the safety control of treadmills on the market is mainly based on optical sensors. By setting an optical sensor on the treadmill, it can detect whether an object appears in a designated area of the treadmill.

However, this kind of safety control method based on optical sensors, on the one hand, cannot judge the type of the object, and on the other hand, it can only suspend the treadmill when the object is not in the designated area. Therefore, the safety of the treadmill cannot be guaranteed. , and it cannot be applied to the actual usage scenarios of users.

SUMMARY OF THE INVENTION

The embodiment of the present application provides a safety control method and treadmill of a treadmill, which can effectively avoid the occurrence of unexpected situations and improve the safety of the treadmill. The technical scheme is as follows:

In a first aspect, an embodiment of the present application provides a security control method for a treadmill, comprising the steps of:

acquiring a face image captured by a first camera device; wherein, the first camera device is arranged on the upper end of the front side of the treadmill;

The rotation speed of the treadmill is controlled according to the proportion of the human face in the human face image and the preset positive correlation between the proportion of the human face and the rotational speed of the treadmill.

Optionally, after obtaining the face image captured by the first camera, the steps include:

Inputting the face image into a preset face recognition model to obtain the pixels of the face region in the face image;

According to the ratio of the number of pixels in the face area to the total number of pixels in the face image, the proportion of the face in the face image is obtained.

Optionally, controlling the rotation speed of the treadmill according to the proportion of the human face in the human face image and the preset positive correlation between the proportion of the human face and the rotational speed of the treadmill includes the steps:

When the proportion of the human face in the human face image is higher, the rotation speed of the treadmill is controlled to be higher;

When the proportion of the human face in the human face image is lower, the rotation speed of the treadmill is controlled to be lower.

Optionally, controlling the rotation speed of the treadmill according to the proportion of the human face in the face image and the preset positive correlation between the proportion of the human face and the rotational speed of the treadmill, also includes the steps:

When the proportion of the human face in the human face image is lower than the first threshold, the treadmill is controlled to stop rotating.

Optionally, controlling the rotation speed of the treadmill according to the proportion of the human face in the human face image and the preset positive correlation between the proportion of the human face and the rotational speed of the treadmill includes the steps:

Obtain the target scale interval where the scale of the face in the face image is located;

obtaining the target rotational speed according to the target proportional interval and the corresponding relationship between the preset proportional interval and several stages of rotational speeds;

The treadmill is controlled to rotate at the target rotational speed.

Optionally, obtaining the target-level rotation speed and controlling the treadmill to rotate at the target rotation speed includes the steps of:

When the duration of the proportion of the human face in the human face image in the target proportion interval is greater than a preset time threshold, the treadmill is controlled to rotate at the target rotation speed.

Optionally, before acquiring the face image captured by the first camera device, the method further includes the steps:

When receiving a treadmill start-up instruction, it is detected whether a user enters the shooting area of the first camera device; if yes, the treadmill is controlled to start; if not, the treadmill is controlled not to start.

Optionally, the method further includes the steps:

acquiring an image of the treadmill area photographed by a second camera; wherein, the second camera is arranged at the lower end of the front side of the treadmill;

When an abnormal object is identified from the treadmill area image, the treadmill is controlled to stop rotating.

Optionally, after acquiring the image of the running belt area captured by the second camera device, the following steps are included:

Input the image of the treadmill area into a preset abnormal object recognition model to confirm whether there is an abnormal object in the image of the treadmill area.

In a second aspect, an embodiment of the present application provides a treadmill, comprising: a body, a treadmill arranged on the body, a first camera device arranged at the upper end of the front side of the body, and a treadmill connected to the body. A control device for establishing a data connection for the first camera device, the control device includes a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes The computer program implements the steps of the treadmill safety control method according to the first aspect.

In the embodiment of the present application, a first camera device is arranged on the upper end of the front side of the treadmill to obtain a face image captured by the first camera device, and the proportion of the face in the face image and the preset The positive correlation between the proportion of the face and the rotation speed of the treadmill realizes the real-time control of the rotation speed of the treadmill, which can effectively avoid the occurrence of unexpected situations, improve the safety of the treadmill, and predict the user based on the face image. The position of the treadmill, and then the method of controlling the speed of the treadmill is more suitable for the actual use of the user, and the accuracy is higher.

For better understanding and implementation, the technical solutions of the present application are described in detail below with reference to the accompanying drawings.

Description of drawings

1 is a schematic flowchart of a security control method for a treadmill provided by an embodiment of the present application;

2 is a schematic structural diagram of a treadmill provided by an embodiment of the present application;

3 is a schematic flowchart of S102 in the security control method for a treadmill provided by an embodiment of the present application;

4 is a schematic flowchart of S102 in the safety control method for a treadmill provided by another embodiment of the present application;

5 is a schematic flowchart of a security control method for a treadmill provided by another embodiment of the present application;

6 is a schematic flowchart of a security control method for a treadmill provided by other embodiments of the present application;

FIG. 7 is a schematic structural diagram of a control device of a treadmill provided by an embodiment of the present application.

Detailed ways

Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, the same numerals in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the illustrative examples below are not intended to represent all implementations consistent with this application. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present application as recited in the appended claims.

The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this application and the appended claims, the singular forms "a," "the," and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It will also be understood that the term "and/or" as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

It should be understood that although the terms first, second, third, etc. may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information without departing from the scope of the present application. Depending on the context, the words "if"/"if" as used herein can be interpreted as "at the time of" or "when" or "in response to determining".

Please refer to FIG. 1, which is a schematic flowchart of a security control method for a treadmill provided by an embodiment of the present application. The method includes the following steps:

S101: Acquire a face image captured by a first camera device; wherein, the first camera device is disposed at the upper end of the front side of the treadmill.

In an optional embodiment, the execution subject of the safety control method of the treadmill may be a treadmill, or may be a component in the treadmill, for example: a control device, a processor or a microprocessor inside the treadmill. In another optional embodiment, the executive body of the security control method of the treadmill may be an external device that establishes a data connection with the treadmill, or may be a component in the external device; In other optional embodiments, the execution body of the security control method for the treadmill may be a server that establishes a data connection with the treadmill.

In the embodiment of the present application, the execution subject of the safety control method of the treadmill may be a control device in the treadmill.

The control device acquires the face image captured by the first capturing device.

Wherein, the first camera device is arranged on the upper end of the front side of the body of the treadmill. In an optional embodiment, the first camera device may be a self-contained camera device of the treadmill; in another optional embodiment, the first camera device may also be a camera independent of the treadmill device.

In the embodiment of the present application, the first camera device is a camera device that comes with the treadmill, the first camera device is arranged on the display screen of the treadmill, and the display screen of the treadmill is arranged on the front side of the fuselage the upper end of .

The vertical distance between the first photographing device and the treadmill plane of the treadmill needs to be within a preset first range.

The preset first range is a range in which the shooting angle of the first shooting device can cover the face of the user.

In an optional embodiment, please refer to FIG. 2 , which is a schematic structural diagram of a treadmill provided by an embodiment of the present application. In FIG. 2 , the optimal position between the first photographing device and the treadmill plane of the treadmill is marked. The vertical distance is 1445mm. When the vertical distance between the first shooting device and the treadmill plane of the treadmill is 1445mm, the shooting angle of the first shooting device can better cover the faces of users of different heights.

It should be noted that the optimal vertical distance is not limiting, and the vertical distance between the first photographing device and the treadmill plane of the treadmill can be rationally adjusted in different usage scenarios.

In this embodiment of the present application, the first shooting device may be a video shooting device, or an image shooting device. The specific models and performance parameters are not limited here.

If the first shooting device is a video shooting device, the control device needs to obtain the video captured by the first shooting device, and perform frame-by-frame processing on the video to obtain a face image.

If the first photographing device is an image photographing device, a photographing frequency is preset in the control device, and a face image is acquired based on the photographing frequency.

Wherein, the face image does not mean that the image must include a human face, but refers to an image used to detect whether there is a human face and the proportion of the human face in the image.

After the face image is acquired, a preprocessing operation can be performed on the face image, so as to improve the accuracy of the proportion of the face in the subsequently acquired face image. The preprocessing method is not limited here, and all existing preprocessing methods that can improve the clarity of the face image, effectively remove noise pixels, or smooth the edge of the face are within the protection scope of the embodiments of the present application.

In an optional embodiment, before the control device executes step S101, the start-up of the treadmill can be controlled to avoid the occurrence of the treadmill idling without a user on the treadmill. Specifically, the following steps need to be performed. step:

When the control device receives the treadmill start command, it needs to detect whether a user enters the shooting area of the first camera device; if so, control the treadmill to start; if not, control the treadmill not to start.

There are many ways to detect whether a user enters the shooting area of the first camera device. In this embodiment of the present application, the first camera device can be used to detect whether there is a human face in the shooting area, and then control the treadmill to start when a human face appears. , otherwise it will not start; in other optional embodiments, a sensing device can also be set on the treadmill, and the sensing device can detect whether there is an object obstructing the sensing signal in the shooting area, and then control the treadmill to start, otherwise it will not start .

S102: Control the rotation speed of the treadmill according to the proportion of the human face in the human face image and the preset positive correlation between the proportion of the human face and the rotational speed of the treadmill.

The proportion of the face in the face image can reflect the distance between the treadmill user and the first camera device, and can also reflect the treadmill user's position on the treadmill. The closer the distance to the first camera device is, that is, the more forward the user is on the treadmill.

Usually, if the user's position on the treadmill can be relatively centered, the safety of the running process will be improved. Therefore, in the embodiment of the present application, the user's position on the treadmill is estimated according to the proportion of the face in the face image. In turn, the speed of the treadmill is controlled, and the user's position on the treadmill is indirectly adjusted.

Specifically, a positive correlation between the proportion of the human face and the rotational speed of the treadmill is preset in the control device, and the rotation speed of the treadmill is controlled according to the proportion of the human face in the face image and the positive correlation, thereby Indirect adjustment of the user's position on the treadmill.

In the embodiment of the present application, a first camera device is arranged on the upper end of the front side of the treadmill to obtain a face image captured by the first camera device, and the proportion of the face in the face image and the preset The positive correlation between the proportion of the face and the rotation speed of the treadmill realizes the real-time control of the rotation speed of the treadmill, which can effectively avoid the occurrence of unexpected situations, improve the safety of the treadmill, and predict the user based on the face image. The position of the treadmill, and then the method of controlling the speed of the treadmill is more suitable for the actual use of the user, and the accuracy is higher.

In an optional embodiment, please refer to FIG. 3, step S102 includes steps S1021-S1023, which are as follows:

S1021: When the proportion of the human face in the human face image is higher, control the rotation speed of the treadmill to be higher.

When the proportion of the human face in the face image is higher, the user's position on the treadmill is further forward, so it is necessary to control the treadmill to increase the rotation speed to drive the runner to move backward.

S1022: When the proportion of the human face in the human face image is lower, control the rotation speed of the treadmill to be lower.

When the proportion of the face in the face image is lower, the user's position on the treadmill is further back, so the treadmill needs to be controlled to reduce the rotation speed to drive the runner to move forward.

S1023: When the proportion of the human face in the human face image is lower than a first threshold, control the treadmill to stop rotating.

When the proportion of the face in the face image is lower than the first threshold, an unexpected situation may occur, and at this time, the treadmill needs to be controlled to stop rotating, so as to avoid secondary injury.

The first threshold can be rationally set according to the age and physical condition of the user, which is not limited here.

In this embodiment, not only can the rotation speed of the treadmill be controlled to be higher when the proportion of human faces is higher, and the rotation speed of the treadmill can be controlled to be lower when the proportion of human faces is lower, but also When the proportion of the face in the face image is lower than the first threshold, the treadmill is controlled to stop rotating, thereby ensuring the safety of the treadmill to the greatest extent.

In another optional embodiment, please refer to FIG. 4 , in order to be more suitable for practical application scenarios, and to avoid too high frequency of rotation speed adjustment, which affects the user's sense of use, step S102 includes steps S1024 to S1026, which are as follows:

S1024: Acquire a target scale interval where the scale of the face in the face image is located.

In the embodiment of the present application, several proportional intervals are preset in the control device.

The division of the several proportion intervals is based on experimental data. During the experiment, a plurality of runners are respectively allowed to exercise on the treadmill to obtain the proportions of the faces in the face images corresponding to the runners, and the runners are running. The actual position on the stage, and then reasonably divide different scale intervals.

In an optional embodiment, four proportional intervals may be divided, which are a first proportional interval, a second proportional interval, a third proportional interval, and a fourth proportional interval.

The proportion of the human face in the face image in the first scale interval is too large, and the corresponding runner is in the front position on the treadmill, and the proportion of the human face in the face image in the second scale interval is moderate, The position of the corresponding runner on the treadmill is relatively centered, the proportion of the face in the face image in the third scale interval is small, and the position of the corresponding runner on the treadmill is behind, the fourth scale If the proportion of the faces in the face images in the interval is too small, the corresponding runners may experience unexpected situations on the treadmill.

The control device acquires a target ratio interval in which the proportion of the human face in the human face image is located according to the proportion of the human face in the human face image and several preset ratio intervals.

S1025: Acquire a target rotational speed according to the target proportional interval and the corresponding relationship between the preset proportional interval and several stages of rotational speeds.

The corresponding relationship between the proportional interval and several levels of rotational speeds is preset in the control device, and different proportional intervals correspond to different rotational speeds. When the proportion of the face in the acquired face image is within a proportional interval When it is floating, the control device will also control the treadmill to keep the corresponding rotation speed unchanged, so as to avoid excessively adjusting the rotation speed and improve the user's sense of use.

In the embodiment of the present application, the control device can obtain the target rotational speed according to the target proportional interval and the corresponding relationship between the preset proportional interval and several stages of rotational speeds.

S1026: Control the treadmill to rotate at the target rotation speed.

The control device controls the treadmill to rotate at the target rotation speed.

In an optional embodiment, the control device controls the treadmill to rotate at the target when the proportion of the human face in the face image is greater than the duration of the target proportion interval is greater than a preset time threshold speed rotation.

By judging the duration of the proportion of the human face in the face image in the target proportion interval, the proportion of the human face in the face image is in the duration of the target proportion interval, thereby further improving the treadmill's performance. safety.

In another embodiment, referring to FIG. 5, after step S101 and before step S102, in order to obtain the proportion of the face in the face image, the method includes steps S103-S104, which are as follows:

S103: Input the face image into a preset face recognition model, and obtain the pixels of the face region in the face image.

The preset face recognition model is a trained face recognition model. The training process of the face recognition model can be performed in the control device or in an external device.

Specifically, first obtain a training set, which includes several face images with marked face regions, and then input the training set into an initialized face recognition model to identify the face regions, and then identify the face regions according to the recognition results and The marked and accurate results are obtained, the recognition error is obtained, the face recognition model is reversely trained based on the recognition error, the model parameters are adjusted, and finally the training of the face recognition model is completed when the convergence conditions are met.

In an optional embodiment, the face recognition model may be a face recognition model based on a deep neural network.

In the embodiment of the present application, the trained face recognition model is pre-stored in the control device, and the control device inputs the face image into the preset face recognition model, and obtains the pixels of the face region in the face image. point. In other optional embodiments, the trained face recognition model may also be pre-stored in a server that has established a data connection with the control device, the control device sends the face image to the server, and the server inputs the face image to the server. The preset face recognition model acquires and sends the pixels of the face region in the face image to the control device.

S104: Obtain the proportion of the human face in the human face image according to the ratio between the number of pixels in the human face region and the total number of pixels in the human face image.

The control device acquires the proportion of the human face in the human face image according to the ratio of the number of pixels in the human face region to the total number of pixels in the human face image.

In other embodiments, in order to further improve the safety of the treadmill, please refer to FIG. 6 , and steps S105 to S106 are further included, as follows:

S105: Acquire an image of the treadmill area captured by a second camera device; wherein, the second camera device is disposed at the lower end of the front side of the treadmill.

The second camera device is arranged at the lower end of the front side of the body of the treadmill. The second camera device may be a self-contained camera device of the treadmill, or may be a camera device independent of the treadmill.

In the embodiment of the present application, the second camera device is a self-contained camera device of the treadmill, and the second camera device is arranged on the support device on the front side of the body of the treadmill.

The vertical distance between the first photographing device and the treadmill plane of the treadmill needs to be within a preset second range.

The preset second range is a range in which the shooting angle of the second shooting device can cover the treadmill area.

In an optional embodiment, please refer to FIG. 2. In FIG. 2, the optimal vertical distance between the second photographing device and the treadmill plane of the treadmill is marked, which is 290 mm. When the vertical distance of the treadmill plane is 290mm, the shooting angle of view of the second shooting device can better cover the treadmill area.

It should be noted that the optimal vertical distance is not limiting, and the vertical distance between the second photographing device and the treadmill plane of the treadmill can be rationally adjusted in different usage scenarios.

S106: When it is identified from the treadmill area image that there is an abnormal object, control the treadmill to stop rotating.

If the control device recognizes that there is an abnormal object from the image of the treadmill area, it controls the treadmill to stop rotating, thereby effectively avoiding the occurrence of injury.

Specifically, the method for the control device to identify whether there is an abnormal object in the image of the treadmill area is as follows:

The control device inputs the image of the treadmill area into a preset abnormal object recognition model, and confirms whether there is an abnormal object in the image of the treadmill area.

The preset abnormal object recognition model is a trained abnormal object recognition model. The training process of the abnormal object recognition model can be performed in the control device or in an external device, which is not limited herein.

Specifically, the training set is first obtained, and the training set for training the abnormal object recognition model is the images of objects such as children, toys and pets that have been marked, and then the training set is input into the initialized abnormal object recognition model, and the abnormal objects are recognized. The recognition result and the marked accurate result are obtained, the recognition error is obtained, the abnormal object recognition model is reversely trained based on the recognition error, the model parameters are adjusted, and finally when the convergence condition is satisfied, the training of the abnormal object model is completed.

In an optional embodiment, the abnormal object model may be an abnormal object model based on a deep neural network.

In the embodiment of the present application, the trained abnormal object recognition model is stored in the control device in advance, and the control device inputs the image of the treadmill area into the preset abnormal object recognition model to confirm whether there is an abnormal object in the image of the treadmill area. . In other optional embodiments, the trained abnormal object recognition model may also be pre-stored in a server that has established a data connection with the control device, the control device sends the image of the treadmill area to the server, and the server sends the treadmill area image to the server. The image is input into a preset abnormal object recognition model, and it is confirmed whether there is an abnormal object in the image of the treadmill area, and then the confirmation result is sent to the control device.

In this embodiment, a second camera device is provided at the lower end of the front side of the treadmill, and images of the treadmill area are captured by the second camera device, so that real-time monitoring of the treadmill area can be performed. When an abnormal object appears in the running machine, the treadmill is quickly controlled to stop rotating, so as to avoid the occurrence of injury to a great extent.

Please refer to FIG. 2 and FIG. 7 , FIG. 2 is a schematic structural diagram of a treadmill provided by an embodiment of the application, and FIG. 7 is a schematic structural diagram of a control device of a treadmill provided by an embodiment of the application.

The treadmill 2 includes a fuselage 21, a treadmill 22 arranged on the fuselage, a first camera device 23 arranged on the upper end of the front side of the fuselage, and establishes a data connection with the first camera device The control device 100 (not shown in FIG. 2 ).

In an optional embodiment, the treadmill 2 further includes a second camera device 24 disposed at the lower end of the front side of the fuselage.

The control device 100 includes: a processor 1001, a memory 1002, and a computer program 1003 stored in the memory 1002 and executable on the processor 1001, such as a safety control program for a treadmill; the processor 1001 executes The computer program 1003 implements the steps in the foregoing method embodiments, such as steps S101 to S102 shown in FIG. 1 .

The processor 1001 may include one or more processing cores. The processor 1001 uses various interfaces and lines to connect various parts in the treadmill 2, and executes running by running or executing the instructions, programs, code sets or instruction sets stored in the memory 141, and calling the data in the memory 1002. Various functions and processing data of the computer 2, optionally, the processor 1001 can use digital signal processing (Digital Signal Processing, DSP), Field-Programmable Gate Array (Field-Programmable Gate Array, FPGA), programmable logic array ( Programble LogicArray, PLA) in at least one hardware form. The processor 1001 may integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), a modem, and the like. Among them, the CPU mainly handles the operating system, user interface and application programs, etc.; the GPU is used for rendering and drawing the content that needs to be displayed on the touch screen; the modem is used to handle wireless communication. It can be understood that, the above-mentioned modem may not be integrated into the processor 1001, but is implemented by a single chip.

The memory 1002 may include a random access memory (Random Access Memory, RAM) or a read-only memory (Read-Only Memory). Optionally, the memory 1002 includes a non-transitory computer-readable storage medium. Memory 1002 may be used to store instructions, programs, codes, sets of codes, or sets of instructions. The memory 1002 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing the operating system, instructions for at least one function (such as touch control instructions, etc.), and for implementing the above method embodiments. The storage data area can store the data involved in the above method embodiments, etc. Optionally, the memory 1002 may also be at least one storage device located away from the aforementioned processor 1001 .

In the embodiment of the present application, the upper end of the front side of the body of the treadmill is provided with a first camera, and by acquiring a face image captured by the first camera, based on the proportion of the face in the face image and the preset The positive correlation between the proportion of the face and the rotation speed of the treadmill can realize the real-time control of the rotation speed of the treadmill, so as to effectively avoid the occurrence of unexpected situations and improve the safety of the treadmill. The method of predicting the user's position and then controlling the speed of the treadmill is more suitable for the actual use of the user and has higher accuracy.

In the foregoing embodiments, the description of each embodiment has its own emphasis. For parts that are not described or described in detail in a certain embodiment, reference may be made to the relevant descriptions of other embodiments.

The present invention is not limited to the above-mentioned embodiments. If various changes or modifications of the present invention do not depart from the spirit and scope of the present invention, and if these changes and modifications belong to the claims of the present invention and the equivalent technical scope, then the present invention is also Intended to contain these alterations and variants.

Claims (10)

1. A safety control method of a treadmill is characterized by comprising the following steps:

acquiring a face image shot by a first camera device; the first camera device is arranged at the upper end of the front side of the body of the running machine;

and controlling the rotation speed of the running machine according to the proportion of the human face in the human face image and the positive correlation between the preset proportion of the human face and the rotation speed of the running machine.

2. The method for safely controlling a treadmill according to claim 1, wherein after said step of obtaining a human face image captured by a first camera, comprising the steps of:

inputting the face image into a preset face recognition model, and acquiring pixel points of a face area in the face image;

and acquiring the proportion of the face in the face image according to the ratio of the number of the pixel points in the face region to the total number of the pixel points in the face image.

3. The safety control method of a treadmill according to claim 1, wherein the step of controlling the rotation speed of the treadmill according to the proportion of the human face in the human face image and the positive correlation between the preset proportion of the human face and the treadmill rotation speed comprises the steps of:

when the proportion of the human face in the human face image is higher, controlling the running machine to rotate at a higher speed;

and controlling the running machine to rotate at a lower speed when the proportion of the face in the face image is lower.

4. The safety control method of a treadmill of claim 1, wherein the step of controlling the rotation speed of the treadmill according to the ratio of the human face in the human face image and the positive correlation between the preset ratio of the human face and the treadmill rotation speed further comprises the steps of:

and when the proportion of the face in the face image is lower than a first threshold value, controlling the running machine to stop rotating.

5. The safety control method of a treadmill according to claim 1, wherein the step of controlling the rotation speed of the treadmill according to the proportion of the human face in the human face image and the positive correlation between the preset proportion of the human face and the treadmill rotation speed comprises the steps of:

acquiring a target proportion interval in which the proportion of the face in the face image is located;

acquiring a target rotating speed according to the target proportion interval and the corresponding relation between a preset proportion interval and a plurality of levels of rotating speeds;

controlling the running machine to rotate at the target rotating speed.

6. The method of claim 5, wherein the step of obtaining a target level rotational speed and controlling the treadmill to rotate at the target rotational speed comprises the steps of:

and when the duration of the face proportion in the face image in the target proportion interval is greater than a preset time threshold, controlling the running machine to rotate at the target rotation speed.

7. The safety control method of a treadmill according to claim 1, further comprising, before acquiring the image of the human face captured by the first camera, the steps of:

when a running machine starting instruction is received, detecting whether a user enters a shooting area of the first camera device; if yes, controlling the running machine to start; if not, controlling the treadmill not to start.

8. The safety control method of a treadmill of claim 1, further comprising the steps of:

acquiring a running platform area image shot by a second camera device; the second camera device is arranged at the lower end of the front side of the body of the running machine;

and controlling the running machine to stop rotating when the abnormal object is identified from the running platform area image.

9. The safety control method of a treadmill according to claim 8, after acquiring the running zone image captured by the second camera, comprising the steps of:

and inputting the running area image into a preset abnormal object recognition model, and confirming whether an abnormal object exists in the running area image.

10. A treadmill, comprising: a body, a treadmill arranged on the body, a first camera arranged at the upper end of the front side of the body, and a control device for establishing a data connection with the first camera, the control device comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method as claimed in claims 1 to 9 when executing the computer program.

Images