Fitness equipment safety visual identification method based on deep learning

Abstract

The invention discloses a deep learning-based fitness equipment safety visual identification method, which relates to the technical field of regional safety monitoring, and comprises the following steps: collecting basic parameters of each fitness equipment, and setting a corresponding equipment region for each fitness equipment according to the basic parameters of the fitness equipment; arranging a video acquisition terminal, performing image acquisition on each instrument area through the video acquisition terminal, and processing the acquired images to obtain a to-be-identified image of each instrument area; performing safety identification on each instrument area according to the obtained to-be-identified image, and judging whether potential safety hazards exist in the instrument areas or not; different fitness equipment in the fitness area is divided into different equipment areas, and risk analysis is performed on each equipment area according to the defined picture data source, so that safety identification can be performed on each equipment area, and when safety risks exist, corresponding early warning can be given out in time, and occurrence of dangers or potential safety hazards is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of regional safety monitoring, and in particular to a safety visual recognition method for fitness equipment based on deep learning. Background Art

[0002] Gyms are places where a large number of people gather. Users and employees may face potential risks when using and managing gym facilities, such as equipment failure. Therefore, raising safety awareness and taking corresponding preventive measures are crucial to ensuring gym safety. The gym safety risk early warning system is a technical solution designed to improve the safety of gym users and employees. This system is designed to identify and mitigate potential safety risks to ensure the normal operation of the gym and the health and safety of users.

[0003] How to monitor different fitness equipment in the fitness area separately so that when there are people in the fitness area, we can promptly warn of possible risks is a problem we need to solve. To this end, a fitness equipment safety visual recognition method based on deep learning is provided. Summary of the invention

[0004] The purpose of the present invention is to provide a fitness equipment safety visual recognition method based on deep learning.

[0005] The purpose of the present invention can be achieved by the following technical solution: A method for visually identifying fitness equipment based on deep learning, comprising the following steps:

[0006] Step S1: collecting basic parameters of each fitness equipment, and setting a corresponding equipment area for each fitness equipment according to the basic parameters of the fitness equipment;

[0007] Step S2: arranging a video acquisition terminal, acquiring images of each device area through the video acquisition terminal, and processing the acquired images to obtain images to be identified of each device area;

[0008] Step S3: Perform safety identification on each device area according to the obtained image to be identified, and determine whether there is a safety hazard in the device area.

[0009] Furthermore, the process of collecting basic parameters of each fitness equipment and setting a corresponding equipment area for each fitness equipment according to the basic parameters of the fitness equipment includes:

[0010] Construct a corresponding regional plan according to the fitness area;

[0011] According to the location of each fitness equipment in the fitness area, a corresponding equipment icon is generated at the corresponding location in the area plan;

[0012] Obtaining basic parameters of each fitness equipment, wherein the basic parameters of the fitness equipment include weight, length, width and height;

[0013] According to the basic parameters of each fitness equipment, the corresponding equipment influence coefficient is obtained;

[0014] According to the obtained length and width of the fitness equipment, the floor area of ​​the corresponding fitness equipment is obtained;

[0015] Then, according to the floor area of ​​each fitness equipment and the equipment influence coefficient, a corresponding equipment area is set for each fitness equipment, and the area of ​​the equipment area is obtained;

[0016] Mapping the obtained instrument area to the corresponding instrument icon in the regional plan, and obtaining the relative position relationship of each instrument area in the regional plan according to the mapping result, wherein the relative position relationship includes an intersection relationship, a containment relationship and a separation relationship;

[0017] The fitness equipment corresponding to the equipment areas with inclusion relationships are summarized to obtain a corresponding equipment set, and the equipment area with the largest area is marked as a merged area corresponding to the equipment set.

[0018] Furthermore, a video acquisition terminal is arranged, and a process of acquiring images of each device area through the video acquisition terminal includes:

[0019] Several video acquisition terminals are arranged in the fitness area. Each video acquisition terminal adjusts the shooting range according to the location of the equipment area, so that the shooting range of each video acquisition terminal covers at least one equipment area. In the picture of each equipment area, each equipment area is marked as a picture data source.

[0020] Get the attention Gz of the merged area;

[0021] According to the attention degree of each merged area, the image sampling frequency f1 of the picture data source in the video acquisition terminal whose shooting range covers the merged area is set;

[0022] For the device areas whose relative position relationship is a separated relationship, the image sampling frequency of the picture data source in the video acquisition terminal whose shooting range covers the corresponding device area is set to f2;

[0023] For the device areas whose relative position relationship is an intersection relationship, the image sampling frequency of the picture data source in the video acquisition terminal whose shooting range covers the corresponding device area is set to f3;

[0024] The image data of each device area is acquired in real time through each video acquisition terminal.

[0025] Furthermore, the process of processing the collected images to obtain the images to be identified in each device area includes:

[0026] Construct corresponding video data storage spaces according to the fitness equipment corresponding to each equipment area, and import image data obtained by the video acquisition terminal where the picture data source corresponding to the equipment area of ​​each fitness equipment is located into the corresponding video data storage spaces;

[0027] Construct a corresponding time axis for each device area, and map the image data obtained in the video data storage space to the time axis;

[0028] The image data mapped to the time axis is sampled at an image sampling frequency f3, a corresponding image frame is obtained according to the sampling result, the obtained image frame is rasterized, and the rasterized image frame is gray-scaled to obtain a corresponding gray-scale image;

[0029] The obtained grayscale image is intercepted according to the screen data source, and only the image portion corresponding to the screen data source is retained and recorded as the image to be recognized.

[0030] Furthermore, the process of safely identifying each device area according to the obtained image to be identified includes:

[0031] Input the obtained image to be identified into a trained convolutional neural network model, perform feature extraction on the image to be identified through the convolutional neural network model, identify the fitness equipment in the image to be identified based on the feature extraction result, and determine whether there is a person entering the equipment area;

[0032] If no one enters, the image sampling frequency of the corresponding screen data source defaults to f3;

[0033] If a person enters, the image sampling frequency of the corresponding screen data source is reset according to the relative position relationship of the device area;

[0034] According to the changes of the identified fitness equipment in the image to be identified, each equipment area is safely identified.

[0035] Furthermore, according to the changes of the identified fitness equipment in the image to be identified, the process of performing security identification on each equipment area includes:

[0036] Binarization is performed on the obtained image to be identified to obtain a corresponding binary image;

[0037] Mark the pixels of the binary image, determine the pixels belonging to the fitness equipment and summarize them as the equipment connected area;

[0038] Constructing a corresponding circumscribed rectangular area according to the determined device connectivity area;

[0039] Setting boundary endpoints for the boundary of the determined circumscribed rectangular area;

[0040] According to the shooting time corresponding to the image to be identified, the boundary endpoints at the same position of the circumscribed rectangular area of ​​the device connected area in the adjacent images to be identified are associated, and the displacement deviations of the associated boundary endpoints are compared;

[0041] Obtain the regional safety factor Qa of the equipment area when there are people entering and when there are no people entering;

[0042] Set a corresponding risk warning coefficient Q for each equipment area;

[0043] Compare the obtained regional risk coefficient with the set risk warning coefficient;

[0044] When Qa≥Q and a person enters the equipment area, it means that there is a potential safety hazard in the equipment area, and a safety warning message is generated and sent to the management terminal;

[0045] When Qa≥Q and no personnel enter the equipment area, it means that there are equipment safety hazards in the equipment area, and equipment maintenance warning information is generated and sent to the management personnel terminal;

[0046] When Qa<Q, it means there is no safety hazard in the equipment area.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] Different fitness equipment in the fitness area is divided into different equipment areas, and the picture data source of the image data obtained by the video acquisition terminal is defined according to the divided equipment areas. According to the defined picture data source, risk analysis is performed separately for different situations in which there are people entering and no people entering each equipment area, thereby making it possible to safely identify each equipment area and to issue corresponding warnings in time when there are safety risks, thereby reducing the occurrence of danger or safety hazards, and greatly improving the safety level of the fitness area. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0050] Figure 1The present invention is a flow chart of the method. DETAILED DESCRIPTION

[0051] like Figure 1 As shown, a fitness equipment safety visual recognition method based on deep learning includes the following steps:

[0052] Step S1: collecting basic parameters of each fitness equipment, and setting a corresponding equipment area for each fitness equipment according to the basic parameters of the fitness equipment;

[0053] Step S2: arranging a video acquisition terminal, acquiring images of each device area through the video acquisition terminal, and processing the acquired images to obtain images to be identified of each device area;

[0054] Step S3: Perform safety identification on each device area according to the obtained image to be identified, and determine whether there is a safety hazard in the device area;

[0055] It should be further explained that, in the specific implementation process, the process of collecting the basic parameters of each fitness equipment and setting the corresponding equipment area for each fitness equipment according to the basic parameters of the fitness equipment includes:

[0056] Construct a corresponding regional plan according to the fitness area;

[0057] According to the location of each fitness equipment in the fitness area, a corresponding equipment icon is generated at the corresponding location in the regional plan, and each fitness equipment is labeled as i, where i=1, 2, ..., n, and n is an integer;

[0058] Obtaining basic parameters of each fitness equipment, wherein the basic parameters of the fitness equipment include weight, length, width and height;

[0059] The weight of the fitness equipment labeled i is recorded as D i , the length is L i , the width is denoted as S i , the height is denoted as H i ;

[0060] According to the basic parameters of each fitness equipment, the corresponding equipment influence coefficient is obtained, which is recorded as Qy i ;

[0061] in,

[0062] Where a1 and a2 are weight coefficients respectively;

[0063] According to the obtained length and width of the fitness equipment, the area occupied by the corresponding fitness equipment is obtained, which is recorded as Zs i , Zs i=L i ×S i ;

[0064] According to the floor area of ​​each fitness equipment and the equipment influence coefficient, a corresponding equipment area is set for each fitness equipment, and the area of ​​the equipment area is recorded as Qs i ;

[0065] Among them, Qs i =(1+Qy i )×Zs i ;

[0066] Map the obtained instrument area to the corresponding instrument icon in the regional plan, and obtain the relative position relationship of each instrument area in the regional plan according to the mapping result, wherein the relative position relationship includes an intersection relationship, a containment relationship, and a separation relationship; wherein the intersection relationship means that two instrument areas partially overlap, the containment relationship means that one instrument area is completely within the range of another instrument area, and the separation relationship means that there is no overlap between the two instrument areas;

[0067] The fitness equipment corresponding to the equipment areas with inclusion relationships are summarized to obtain a corresponding equipment set, and the equipment area with the largest area is marked as a merged area corresponding to the equipment set.

[0068] It should be further explained that, in the specific implementation process, the process of arranging the video acquisition terminal and acquiring images of each device area through the video acquisition terminal includes:

[0069] Several video acquisition terminals are arranged in the fitness area. Each video acquisition terminal adjusts the shooting range according to the location of the equipment area, so that the shooting range of each video acquisition terminal covers at least one equipment area, so that each equipment area is monitored in all directions. In the picture of each equipment area being photographed, each equipment area is marked with a frame and recorded as the picture data source;

[0070] The device areas contained in each merged area are labeled as j, where j = 1, 2, ..., m, and m is an integer;

[0071] The area of ​​the device region labeled j is recorded as Qs j ;

[0072] The equipment influence coefficient of the fitness equipment corresponding to the equipment area labeled j is recorded as Qy j ;

[0073] Then the attention degree of the merged area is obtained, which is recorded as Gz;

[0074] in,

[0075] Among them, Qs max is the area of ​​the merged region;

[0076] According to the attention degree of each merged area, the image sampling frequency of the picture data source in the video acquisition terminal whose shooting range covers the merged area is set, which is recorded as f1;

[0077] For the device areas whose relative position relationship is a separated relationship, the image sampling frequency of the picture data source in the video acquisition terminal whose shooting range covers the corresponding device area is set to f2;

[0078] For the device areas whose relative position relationship is an intersection relationship, the image sampling frequency of the picture data source in the video acquisition terminal whose shooting range covers the corresponding device area is set to f3;

[0079] Where f1>f3>f2;

[0080] The image data of each device area is acquired in real time through each video acquisition terminal.

[0081] It should be further explained that, in the specific implementation process, the process of processing the collected images to obtain the images to be identified in each device area includes:

[0082] Construct corresponding video data storage spaces according to the fitness equipment corresponding to each equipment area, and import image data obtained by the video acquisition terminal where the picture data source corresponding to the equipment area of ​​each fitness equipment is located into the corresponding video data storage spaces;

[0083] Construct a corresponding time axis for each device area, and map the image data obtained in the video data storage space to the time axis;

[0084] The image data mapped to the time axis is sampled at an image sampling frequency f3, a corresponding image frame is obtained according to the sampling result, the obtained image frame is rasterized, and the rasterized image frame is gray-scaled to obtain a corresponding gray-scale image;

[0085] The obtained grayscale image is intercepted according to the screen data source, and only the image portion corresponding to the screen data source is retained, which is recorded as the image to be recognized;

[0086] By pre-cutting the image part of the picture data source in the grayscale image, the computational complexity of feature extraction in the subsequent image recognition process is greatly reduced, thereby improving the efficiency of image recognition;

[0087] It should be further explained that, in the specific implementation process, the process of safely identifying each device area according to the obtained image to be identified includes:

[0088] Input the obtained image to be identified into a trained convolutional neural network model, perform feature extraction on the image to be identified through the convolutional neural network model, identify the fitness equipment in the image to be identified based on the feature extraction result, and determine whether there is a person entering the equipment area;

[0089] If no one enters, the image sampling frequency of the corresponding screen data source defaults to f3;

[0090] If a person enters, the image sampling frequency of the corresponding screen data source is reset according to the relative position relationship of the device area; it should be further explained that in the specific implementation process, if the relative position relationship of the device area is a separation relationship, no modification is required; if the relative position relationship of the device area is an inclusion relationship, the image sampling frequency of the corresponding screen data source is modified to f1; if the relative position relationship of the device area is an intersection relationship, the image sampling frequency of the corresponding screen data source is modified to f2;

[0091] According to the changes of the identified fitness equipment in the image to be identified, each equipment area is safely identified.

[0092] It should be further explained that, in the specific implementation process, according to the changes of the fitness equipment in the image to be identified, the process of performing security identification on each equipment area includes:

[0093] Binarization is performed on the obtained image to be identified to obtain a corresponding binary image;

[0094] Mark the pixels of the binary image, determine the pixels belonging to the fitness equipment and summarize them as the equipment connected area;

[0095] Constructing a corresponding circumscribed rectangular area according to the determined device connectivity area;

[0096] Setting boundary endpoints for the determined circumscribed rectangular area, and labeling each of the set boundary endpoints as k, where k=1, 2, ..., s, where s is an integer;

[0097] According to the shooting time corresponding to the image to be identified, the boundary endpoints at the same position of the circumscribed rectangular area of ​​the device connected area in the adjacent images to be identified are associated, and the displacement deviation of the associated boundary endpoints is compared, which is recorded as Wp k It should be further explained that, in the specific implementation process, the displacement deviation is the displacement change of the same boundary endpoints of two same positions in adjacent images to be identified;

[0098] Obtain the corresponding regional safety factor, and record the obtained regional risk factor as Qa;

[0099] When no one enters the equipment area,

[0100]

[0101] Where f is the image sampling frequency of the screen data source corresponding to the device area, Gz is the attention level of the merged area where the device area is located, and if the device area is not in any merged area, Gz=1;

[0102] When someone enters the equipment area,

[0103]

[0104] Where R is the number of people entering the equipment area, and α is the personnel interference coefficient;

[0105] A corresponding risk warning coefficient Q is set for each equipment area. It should be further explained that in the specific implementation process, the risk warning coefficient of each equipment area is different.

[0106] Compare the obtained regional risk coefficient with the set risk warning coefficient;

[0107] When Qa≥Q and a person enters the equipment area, it means that there is a potential safety hazard in the equipment area, and a safety warning message is generated and sent to the management terminal;

[0108] When Qa≥Q and no personnel enter the equipment area, it means that there are equipment safety hazards in the equipment area, and equipment maintenance warning information is generated and sent to the management personnel terminal;

[0109] When Qa<Q, it means there is no safety hazard in the equipment area.

[0110] The above is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any modification or equivalent replacement of the above embodiments made according to the technical essence of the present invention without departing from the content of the technical solution of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. A fitness equipment safety visual recognition method based on deep learning, characterized in that: The following steps are involved: Step S1: collecting basic parameters of each fitness equipment, and setting a corresponding equipment area for each fitness equipment according to the basic parameters of the fitness equipment; Step S2: arranging a video acquisition terminal, acquiring images of each device area through the video acquisition terminal, and processing the acquired images to obtain images to be identified of each device area; Step S3: Perform safety identification on each device area according to the obtained image to be identified, and determine whether there is a safety hazard in the device area.

2. A fitness equipment safety visual recognition method based on deep learning according to claim 1, characterized in that: The process of collecting basic parameters of each fitness equipment and setting corresponding equipment areas for each fitness equipment according to the basic parameters of the fitness equipment includes: Construct a corresponding regional plan according to the fitness area; According to the location of each fitness equipment in the fitness area, a corresponding equipment icon is generated at the corresponding location in the area plan; Obtaining basic parameters of each fitness equipment, wherein the basic parameters of the fitness equipment include weight, length, width and height; According to the basic parameters of each fitness equipment, the corresponding equipment influence coefficient is obtained; According to the obtained length and width of the fitness equipment, the floor area of ​​the corresponding fitness equipment is obtained; Then, according to the floor area of ​​each fitness equipment and the equipment influence coefficient, a corresponding equipment area is set for each fitness equipment, and the area of ​​the equipment area is obtained; Mapping the obtained instrument area to the corresponding instrument icon in the regional plan, and obtaining the relative position relationship of each instrument area in the regional plan according to the mapping result, wherein the relative position relationship includes an intersection relationship, a containment relationship and a separation relationship; The fitness equipment corresponding to the equipment areas with inclusion relationships are summarized to obtain a corresponding equipment set, and the equipment area with the largest area is marked as a merged area corresponding to the equipment set.

3. A fitness equipment safety visual recognition method based on deep learning according to claim 2, characterized in that: The process of arranging a video acquisition terminal and acquiring images of each device area through the video acquisition terminal includes: Several video acquisition terminals are arranged in the fitness area. Each video acquisition terminal adjusts the shooting range according to the location of the equipment area, so that the shooting range of each video acquisition terminal covers at least one equipment area. In the picture of each equipment area, each equipment area is marked as a picture data source. Get the attention Gz of the merged area; According to the attention degree of each merged area, the image sampling frequency f1 of the picture data source in the video acquisition terminal whose shooting range covers the merged area is set; For the device areas whose relative position relationship is a separated relationship, the image sampling frequency of the picture data source in the video acquisition terminal whose shooting range covers the corresponding device area is set to f2; For the device areas whose relative position relationship is an intersection relationship, the image sampling frequency of the picture data source in the video acquisition terminal whose shooting range covers the corresponding device area is set to f3; The image data of each device area is acquired in real time through each video acquisition terminal.

4. The method for safety visual recognition of fitness equipment based on deep learning according to claim 3, characterized in that: The process of processing the acquired images to obtain the images to be identified in each device area includes: Construct corresponding video data storage spaces according to the fitness equipment corresponding to each equipment area, and import image data obtained by the video acquisition terminal where the picture data source corresponding to the equipment area of ​​each fitness equipment is located into the corresponding video data storage spaces; Construct a corresponding time axis for each device area, and map the image data obtained in the video data storage space to the time axis; The image data mapped to the time axis is sampled at an image sampling frequency f3, a corresponding image frame is obtained according to the sampling result, the obtained image frame is rasterized, and the rasterized image frame is gray-scaled to obtain a corresponding gray-scale image; The obtained grayscale image is intercepted according to the screen data source, and only the image portion corresponding to the screen data source is retained and recorded as the image to be recognized.

5. A fitness equipment safety visual recognition method based on deep learning according to claim 4, characterized in that: The process of safely identifying each device area based on the obtained image to be identified includes: Input the obtained image to be identified into a trained convolutional neural network model, perform feature extraction on the image to be identified through the convolutional neural network model, identify the fitness equipment in the image to be identified based on the feature extraction result, and determine whether there is a person entering the equipment area; If no one enters, the image sampling frequency of the corresponding screen data source defaults to f3; If a person enters, the image sampling frequency of the corresponding screen data source is reset according to the relative position relationship of the device area; According to the changes of the identified fitness equipment in the image to be identified, each equipment area is safely identified.

6. A fitness equipment safety visual recognition method based on deep learning according to claim 5, characterized in that: According to the changes of the fitness equipment in the image to be identified, the process of safely identifying each equipment area includes: Binarization is performed on the obtained image to be identified to obtain a corresponding binary image; Mark the pixels of the binary image, determine the pixels belonging to the fitness equipment and summarize them as the equipment connected area; Constructing a corresponding circumscribed rectangular area according to the determined device connectivity area; Setting boundary endpoints for the boundary of the determined circumscribed rectangular area; According to the shooting time corresponding to the image to be identified, the boundary endpoints at the same position of the circumscribed rectangular area of ​​the device connected area in the adjacent images to be identified are associated, and the displacement deviations of the associated boundary endpoints are compared; Obtain the regional safety factor Qa of the equipment area when there are people entering and when there are no people entering; Set a corresponding risk warning coefficient Q for each equipment area; Compare the obtained regional risk coefficient with the set risk warning coefficient; When Qa≥Q and a person enters the equipment area, it means that there is a potential safety hazard in the equipment area, and a safety warning message is generated and sent to the management terminal; When Qa≥Q and no personnel enter the equipment area, it means that there are equipment safety hazards in the equipment area, and equipment maintenance warning information is generated and sent to the management personnel terminal; When Qa<Q, it means there is no safety hazard in the equipment area.

Images