A high-speed binocular camera inspection method and system based on VR

Abstract

The present application provides a VR-based high-speed binocular camera inspection method and system, the method comprising: when a target user is located in a preset area of ​​a coal mine, obtaining first attribute information of the target user; determining the current position and target orientation of the target user; collecting a first VR image corresponding to the current position and target orientation by a VR-based high-speed binocular camera; marking m dangerous targets and m dangerous positions in the first VR image, each dangerous target corresponding to a dangerous position and second attribute information of the dangerous target; m is a positive integer; detecting dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range, and obtaining n dangerous targets; determining a danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets, and the second attribute information, and obtaining n danger coefficients; performing an early warning operation according to the n danger coefficients.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a high-speed binocular camera inspection method and system based on VR. Background Art

[0002] In practical applications, safety issues are always of paramount importance in the collection of minerals in coal mines. Usually, the underground environment of coal mines is complex, the light is dim, and there are often many dangers. How to improve the safety of coal mine operations needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application provide a VR-based high-speed binocular camera inspection method and system, which can improve the operation safety of coal mines based on VR-based high-speed binocular camera inspection.

[0004] In a first aspect, an embodiment of the present application provides a VR-based high-speed binocular camera inspection method, which is applied to an electronic device, wherein the electronic device is communicatively connected to a VR-based high-speed binocular camera, and the VR-based high-speed binocular camera is worn on a smart helmet or smart glasses of a target user, and the method comprises:

[0005] When the target user is located in a preset area of ​​a coal mine, obtaining first attribute information of the target user;

[0006] Determine the current location and target position of the target user;

[0007] Acquiring a first VR image corresponding to the current position and the target orientation by the VR-based high-speed binocular camera;

[0008] Marking m dangerous targets and m dangerous positions in the first VR image, each dangerous target corresponds to a dangerous position and second attribute information of the dangerous target; m is a positive integer;

[0009] Detecting dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range, to obtain n dangerous targets;

[0010] Determine a risk factor of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets, and the second attribute information to obtain n risk factors;

[0011] An early warning operation is performed according to the n risk factors.

[0012] In a second aspect, an embodiment of the present application provides a VR-based high-speed binocular camera inspection system, which is applied to an electronic device, wherein the electronic device is communicatively connected to a VR-based high-speed binocular camera, and the VR-based high-speed binocular camera is worn on a smart helmet or smart glasses of a target user, and the system includes: an acquisition unit, a determination unit, a collection unit, a marking unit, a detection unit, and an early warning unit, wherein:

[0013] The acquisition unit is used to acquire the first attribute information of the target user when the target user is located in a preset area of ​​the coal mine;

[0014] The determining unit is used to determine the current position and target orientation of the target user;

[0015] The acquisition unit is used to acquire a first VR image corresponding to the current position and the target orientation through the VR-based high-speed binocular camera;

[0016] The marking unit is used to mark m dangerous targets and m dangerous positions in the first VR image, each dangerous target corresponds to a dangerous position and second attribute information of the dangerous target; m is a positive integer;

[0017] The detection unit is used to detect dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range, and obtain n dangerous targets;

[0018] The determining unit is further used to determine a danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets and the second attribute information to obtain n danger coefficients;

[0019] The early warning unit is used to perform early warning operations according to the n risk factors.

[0020] The implementation of the embodiments of the present application has the following beneficial effects:

[0021] It can be seen that the VR-based high-speed binocular camera inspection method and system described in the embodiments of the present application are applied to an electronic device, wherein the electronic device is communicatively connected to a VR-based high-speed binocular camera, and the VR-based high-speed binocular camera is worn on a smart helmet or smart glasses of a target user, and when the target user is located in a preset area of ​​a coal mine, the first attribute information of the target user is obtained; the current position and the target orientation of the target user are determined; a first VR image corresponding to the current position and the target orientation is collected by the VR-based high-speed binocular camera; m dangerous targets and m dangerous positions are marked in the first VR image, and each dangerous target corresponds to a dangerous position and the second attribute information of the dangerous target; m is a positive integer; dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range are detected to obtain n dangerous targets; and according to the first attribute information, the dangerous positions of the n dangerous targets are The first VR image can not only reflect the actual scene, but also enhance the image of the actual scene, thereby making the actual scene more perceptual and intelligent. Secondly, it can accurately mark dangerous targets that are potentially dangerous to users, accurately evaluate the risk factor of each dangerous target based on the user's own attributes, the characteristics of the dangerous target, and the relative position relationship between the dangerous target and the user, so that the risk assessment is more in line with the user himself, the characteristics of the dangerous target and the actual environment. Thirdly, on the basis of accurately evaluating the risk factor, it helps to ensure the accuracy of the early warning operation and the safety of coal mine operations, and can realize high-speed binocular camera inspection based on VR to improve the safety of coal mine operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 It is a flow chart of a high-speed binocular camera inspection method based on VR provided in an embodiment of the present application;

[0024] Figure 2 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application;

[0025] Figure 3This is a block diagram of the functional units of a high-speed binocular camera inspection system based on VR provided in an embodiment of the present application. DETAILED DESCRIPTION

[0026] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but in a possible example also includes steps or units that are not listed, or in a possible example also includes other steps or units inherent to these processes, methods, products or devices.

[0027] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0029] In the embodiment of the present application, the VR-based high-speed binocular camera uses virtual reality technology (VR) to achieve VR imaging. Virtual reality technology mainly includes aspects such as simulated environment, perception, natural skills and sensor equipment.

[0030] The simulated environment can be understood as a real-time dynamic three-dimensional realistic image generated by a computer.

[0031] Perception can be understood as the perception that an ideal VR may have all the perceptions that people have. Perception can include at least one of the following: visual perception, auditory perception, force perception, motion perception, tactile perception, olfactory perception, taste perception, etc.

[0032] Among them, natural skills can be understood as head movements, eyes, gestures, or other human behavioral movements. The processor can process data corresponding to the participant's movements, respond to the user's input in real time, and then feed back to the user's five senses respectively.

[0033] Among them, the sensing device can be understood as a three-dimensional interactive device.

[0034] See also Figure 1 , Figure 1 This is a flow chart of a high-speed binocular camera inspection method based on VR provided in an embodiment of the present application. As shown in the figure, the electronic device is connected to the high-speed binocular camera based on VR for communication. The high-speed binocular camera based on VR is worn on a smart helmet or smart glasses of a target user. The method includes:

[0035] 101. When the target user is located in a preset area of ​​a coal mine, obtain first attribute information of the target user.

[0036] In an embodiment of the present application, the electronic device is connected to a high-speed binocular camera based on VR for communication, and the high-speed binocular camera based on VR is worn on a smart helmet or smart glasses of a target user. The high-speed binocular camera based on VR can be used for shooting, and VR imaging is realized based on the shot images. For example, the electronic device can be smart glasses, and the two lenses of the smart glasses can correspond to a high-speed camera respectively.

[0037] Among them, the electronic device may include at least one of the following: a smart helmet, smart glasses, a server, etc., which are not limited here.

[0038] Among them, the first attribute information includes at least one of the following: the height of the target user, the weight of the target user, the vision parameters of the target user, the posture parameters of the target user, the movement parameters of the target user, the body shape of the target user, the age of the target user, the physical condition of the target user, the waist circumference of the target user, the lung capacity of the target user, etc., which are not limited here.

[0039] In the embodiment of the present application, the preset area can be pre-set or system default.

[0040] In a specific implementation, when the target user is located in a preset area of ​​a coal mine, the first attribute information of the target user can be obtained. The first attribute information reflects the user's own characteristics. Furthermore, a danger warning can be issued based on the user's own characteristics to ensure the accuracy and safety of the warning.

[0041] 102. Determine the current location and target position of the target user.

[0042] In the embodiment of the present application, an indoor positioning system or camera can be set up in the coal mine, and the indoor positioning system or camera is used for positioning to determine the current position and target orientation of the target user. The target orientation can be understood as the user orientation, the user orientation, or the direction of the user's navigation route.

[0043] 103. Collect a first VR image corresponding to the current position and the target orientation through the VR-based high-speed binocular camera.

[0044] In a specific implementation, a first VR image corresponding to the current position and the target orientation can be collected by a VR-based high-speed binocular camera. Specifically, an actual scene image corresponding to the current position and the target orientation can be collected by a VR-based high-speed binocular camera, and a historical VR image corresponding to the current position and the target orientation can be obtained. The historical VR image and the actual scene image are fused to obtain the first VR image.

[0045] Optionally, the target position is the forward position of the target user, or the direction of the target user. In the above step 103, the first VR image corresponding to the current position and the target position is collected by the VR-based high-speed binocular camera, and the following steps may be performed:

[0046] 31. Determine the visual field of the current position and the target orientation;

[0047] 32. The VR-based high-speed binocular camera is used to shoot according to the field of view to obtain the first VR image.

[0048] In an embodiment of the present application, the target orientation is the forward orientation of the target user, or the direction of the target user, and the field of view area of ​​the current position and the target orientation can be determined. In a specific implementation, different positions and orientations can correspond to different field of view areas, and the mapping relationship between the position, orientation and field of view area can be pre-set. Then, the field of view area of ​​the current position and the target orientation can be determined based on the mapping relationship, and then a high-speed binocular camera based on VR is used to shoot according to the field of view to obtain a first VR image. Since the first VR image can not only reflect the actual scene, but also enhance the image of the actual scene, the actual scene can be made more perceptual and more intelligent.

[0049] 104. Mark a dangerous targets and a dangerous positions in the first VR image, where each dangerous target corresponds to a dangerous position and second attribute information of the dangerous target.

[0050] Among them, the second attribute information of the dangerous target may include at least one of the following: the type of dangerous target, the volume of the dangerous target, the area of ​​the dangerous target, the height of the dangerous target, the thickness of the dangerous target, the width of the dangerous target, the length of the dangerous target, the color of the dangerous target, the smell of the dangerous target, the smoothness of the dangerous target, etc., without limitation here.

[0051] Among them, dangerous targets may include at least one of the following: stones, coal slag, puddles, rockfall areas, narrow areas, designated gas areas, blasting areas, landslide areas, collapsed areas, rocky areas, soft ground areas, etc., without limitation here.

[0052] In a specific implementation, a dangerous targets and a dangerous positions can be marked in the first VR image by using image recognition technology, and each dangerous target corresponds to a dangerous position and the second attribute information of the dangerous target.

[0053] 105. Detect dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range, and obtain n dangerous targets.

[0054] The preset distance range may be preset or set by the system by default. N is a positive integer less than or equal to m.

[0055] In a specific implementation, since usually only dangerous targets near the user will pose a danger to the user, m dangerous targets whose distances from the target user are within a preset distance range can be detected to obtain n dangerous targets. In this way, dangerous targets with potential dangers can be further identified.

[0056] 106. Determine a danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets and the second attribute information to obtain n danger coefficients.

[0057] In the embodiment of the present application, since the first attribute information reflects the attributes of the user himself, the second attribute information reflects the inherent characteristics of the dangerous target, and the dangerous positions of the n dangerous targets reflect the relative position relationship between the dangerous target and the user, then the danger coefficient of each dangerous target can be accurately evaluated based on the user's own attributes, the inherent characteristics of the dangerous target, and the relative position relationship between the dangerous target and the user, so that the danger assessment is more in line with the user himself, the characteristics of the dangerous target and the actual environment, which helps to ensure the accuracy of the early warning operation and the safety of coal mine operations. Therefore, high-speed binocular camera inspection based on VR can be realized to improve the safety of coal mine operations.

[0058] Optionally, the first attribute information includes at least one of the following: the height of the target user, the weight of the target user, the vision parameter of the target user, the posture parameter of the target user, and the motion parameter of the target user; the above step 106, determining the danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets and the second attribute information to obtain n danger coefficients, may include the following steps:

[0059] 61. Determine the target travel route of the target user;

[0060] 62. Divide the visual field into m areas according to the target travel route, where m is an integer greater than 1;

[0061] 63. Determine a danger distribution density according to the m areas, the n dangerous targets, and the second attribute information of each dangerous target, to obtain m danger distribution densities;

[0062] 64. Determine an adjustment parameter for each of the m hazard distribution densities to obtain m adjustment parameters;

[0063] 65. Determine an initial risk coefficient of each of the m areas according to the second attribute information of the dangerous target in each of the m areas, to obtain m initial risk coefficients;

[0064] 66. Adjust corresponding initial risk coefficients among the m initial risk coefficients according to the m adjustment parameters to obtain m first risk coefficients;

[0065] 67. Determine the risk coefficient of each of the n risk targets based on the m first risk coefficients and the first attribute information to obtain n risk coefficients.

[0066] In an embodiment of the present application, the target route of the target user can be determined. Specifically, the destination corresponding to the target user can be set first, and a navigation route between the current location and the destination can be generated. A certain width can be set for the navigation route, thereby obtaining the target route. The width can accommodate the normal walking figure of the target user. The width can be preset or set by the system default. For example, the width is related to the body shape of the target user or the walking style of the target user. Different walking styles will result in different widths between the legs.

[0067] In a specific implementation, the field of view is divided into a regions according to the target route, where a is an integer greater than 1, the area of ​​each of the a regions can be equal or different, and the a regions can each contain a navigation route.

[0068] Next, the danger distribution density can be determined based on a areas, n dangerous targets and the second attribute information of each dangerous target, and a danger distribution densities can be obtained, that is, the ratio between the dangerous target area corresponding to each area and the area between each area can be determined, and this ratio is the danger distribution density, wherein the mapping relationship between the preset danger distribution density and the adjustment parameter can be pre-stored, and then, the adjustment parameter of each danger distribution density in the a danger distribution density can be determined based on the mapping relationship, and a adjustment parameters can be obtained.

[0069] In a specific implementation, since different dangerous targets correspond to different dangers, for example, the danger of a stone is different from that of a puddle, the mapping relationship between the preset second attribute information and the danger coefficient can be pre-stored, and the danger coefficient of each dangerous target in each area can be determined based on the mapping relationship, and the weight of each dangerous target can be determined. Based on these weights and the corresponding danger coefficient of each dangerous target, a weighted operation is performed to obtain the initial danger coefficient of each area in a areas, and a initial danger coefficients are obtained. The weight can be related to the area of ​​the dangerous target and the smoothness of the dangerous target.

[0070] Next, the corresponding initial risk coefficients among the a initial risk coefficients can be adjusted according to a adjustment parameters to obtain a first risk coefficients, that is, the first risk coefficient = (1 + adjustment parameter) * initial risk coefficient. Finally, the risk coefficient of each of the n risk targets can be determined according to the a first risk coefficients and the first attribute information to obtain n risk coefficients. In this way, based on the target route of the target user, the risk coefficient corresponding to the own characteristics (second attribute information) of the dangerous target on the user's path can be determined, and the risk coefficient can be adjusted based on the risk characteristics of the relevant area on its path, so that the adjusted risk coefficient is deeply consistent with the user's behavior and the actual environment, and then the risk coefficient is deeply optimized in combination with the user's own characteristics, so that the risk assessment is more consistent with the user himself, the characteristics of the dangerous target itself and the actual environment, which helps to ensure the accuracy of the early warning operation and the safety of coal mine operations. Therefore, it is possible to realize VR-based high-speed binocular camera inspection to improve the safety of coal mine operations.

[0071] Optionally, the above step 67, determining the risk factor of each of the n risk targets according to the m first risk factors and the first attribute information to obtain n risk factors, may include the following steps:

[0072] 671. Determine a first distance between a dangerous position of a first dangerous target and the target travel route, wherein the first dangerous target is any dangerous target among the n dangerous targets;

[0073] 672. Determine a reference first risk coefficient corresponding to the first risk target;

[0074] 673. Determine a second distance between the target user and the first dangerous target according to the first attribute information;

[0075] 674. Obtain target environment parameters corresponding to the first dangerous target;

[0076] 675. Determine a target optimization parameter corresponding to the target environmental parameter;

[0077] 676. Optimize the second distance according to the target optimization parameter to obtain a target second distance;

[0078] 677. Determine a first feedback adjustment parameter corresponding to the first distance;

[0079] 678. Determine a second feedback adjustment parameter corresponding to the second target distance;

[0080] 679. Perform feedback adjustment on the reference first risk factor according to the first feedback adjustment parameter and the second feedback adjustment parameter to obtain the risk factor corresponding to the first risk target.

[0081] In an embodiment of the present application, taking the first dangerous target as an example, the first dangerous target is any dangerous target among n dangerous targets. The target route can be displayed in the first VR image, and the first distance between the dangerous position of the first dangerous target and the target route can also be determined.

[0082] Among them, the danger coefficient of the first dangerous target corresponds to the corresponding area among the m areas corresponding to the first dangerous target, and then the reference first danger coefficient corresponding to the first dangerous target can be determined.

[0083] Among them, since the first attribute information reflects the user's habits, for example, the tendency, height change, and body shape change during walking, then, based on the user's actions, the second distance between the target user and the first dangerous target can be predicted under the first attribute information, and the second distance can be understood as the shortest distance between the possible target user and the first dangerous target. Since the user's behavior is known, the target route is known, and the user's habits are also known, the first attribute information can be used to predict the process of the user walking from the current position along the target route, and then the second distance can be determined based on the process.

[0084] In a specific implementation, the target environmental parameters corresponding to the first dangerous target can also be obtained. The target environmental parameters can be environmental parameters within a certain range near the first dangerous target. The environmental parameters can include at least one of the following: ambient temperature, ambient humidity, topography, geological structure, atmospheric pressure, ambient light brightness, ground smoothness, ambient images, etc., which are not limited here.

[0085] In a specific implementation, a mapping relationship between preset environmental parameters and optimization parameters can be pre-stored, and then the target optimization parameters corresponding to the target environmental parameters can be determined based on the mapping relationship. Then, the second distance can be optimized based on the target optimization parameters to obtain the target second distance, that is, the target second distance = (1 + target optimization parameter) * second distance.

[0086] In a specific implementation, a mapping relationship between a preset first distance and a feedback adjustment parameter can be pre-stored, and then, a first feedback adjustment parameter corresponding to the first distance can be determined based on the mapping relationship. A mapping relationship between a preset second distance and a feedback adjustment parameter can also be pre-stored, and then, a second feedback adjustment parameter corresponding to the second distance of the target can be determined based on the mapping relationship. Finally, feedback adjustment can be performed on the reference first risk factor according to the first feedback adjustment parameter and the second feedback adjustment parameter to obtain the risk factor corresponding to the first risk target. The risk factor corresponding to the first risk target = (1 + first feedback adjustment parameter) * (1 + second feedback adjustment parameter) * reference first risk factor. First, a preliminarily determined risk factor can be obtained for the area where each risk target is located in combination with the regional characteristics of the risk target. A danger coefficient. Secondly, since the first distance between the dangerous position of the first dangerous target and the target's travel route reflects to a certain extent the contact probability between the user and the danger, the second distance reflects to a certain extent the contact probability between the user's behavior and the danger, as well as the environmental parameters of the dangerous target, the deep impact of the dangerous target on the user is extended to consider. Based on the contact probability between the user and the danger, the contact probability between the user's behavior and the danger, and the environmental impact of the dangerous target, the danger coefficient of each dangerous target is deeply evaluated, so that the danger assessment is more in line with the user's own characteristics, the dangerous target's own characteristics and the actual environment, which helps to ensure the accuracy of the early warning operation and the safety of coal mine operations. Therefore, high-speed binocular camera inspection based on VR can be realized to improve the safety of coal mine operations.

[0087] 107. Perform early warning operations according to the n risk factors.

[0088] In the specific implementation, different risk factors indicate that the risks faced by users are different. Therefore, different early warning operations can be performed based on different risk factors, thereby achieving targeted early warning operations and realizing VR-based high-speed binocular camera inspections to improve the safety of coal mine operations.

[0089] Optionally, the above step 107, performing a warning operation according to the n risk factors, may include the following steps:

[0090] 71. When there is a target risk factor greater than the first preset risk factor among the n risk factors, determine a first early warning operation parameter corresponding to the target risk factor;

[0091] 72. Perform an early warning operation according to the first early warning operation parameter;

[0092] 73. When there are k risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, determine the second warning operation parameter corresponding to the target risk factor; the second preset risk factor is less than the first preset risk factor; k is a positive integer less than or equal to n, and the ratio between k and n is greater than 0.5,

[0093] 74. Perform an early warning operation according to the second early warning operation parameter;

[0094] 75. When there are x risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, determine a third early warning operation parameter corresponding to the target risk factor; x is a positive integer less than or equal to n, and the ratio of x to n is less than or equal to 0.5;

[0095] 76. Perform a warning operation according to the third warning operation parameter;

[0096] 77. When each of the n risk factors is smaller than the second preset risk factor, no warning operation is performed.

[0097] Among them, the first preset risk factor and the second preset risk factor can be preset or set by system default, and the first preset risk factor is greater than the second preset risk factor.

[0098] Among them, the first warning operation parameter may include at least one of the following: warning method, warning level, warning type, etc., which are not limited here. The warning method may include at least one of the following: sending text messages to management personnel, sounding an alarm, voice prompts, displaying warning content on VR devices, etc., which are not limited here.

[0099] In a specific implementation, when there is a target risk factor greater than the first preset risk factor among the n risk factors, it means that there is a particularly dangerous target, and the first warning operation parameter corresponding to the target risk factor can be determined. The first warning operation parameter can be related to the target risk factor, or can be related to the second attribute information of the dangerous target corresponding to the target risk factor. Performing the warning operation according to the first warning operation parameter helps to ensure the accuracy of the warning operation and the safety of coal mine operations, so that high-speed binocular camera inspection based on VR can be realized to improve the safety of coal mine operations.

[0100] Among them, the second warning operation parameter may include at least one of the following: warning method, warning level, warning type, etc., which are not limited here. The warning method may include at least one of the following: sending text messages to management personnel, sounding an alarm, voice prompts, displaying warning content on VR devices, etc., which are not limited here.

[0101] In the specific implementation, when there are k hazard factors among the n hazard factors that are greater than the second preset hazard factor and less than or equal to the first preset hazard factor, it means that there is a dangerous target with moderate danger, and the second warning operation parameter corresponding to the target hazard factor is determined. The second warning operation parameter can be related to the k hazard factors, or it can be related to the second attribute information of the dangerous target corresponding to the k hazard factors. The warning operation is performed according to the second warning operation parameter, the second preset hazard factor is less than the first preset hazard factor; k is a positive integer less than or equal to n, and the ratio between k and n is greater than 0.5, which helps to ensure the accuracy of the warning operation and the safety of coal mine operations, so that the high-speed binocular camera inspection based on VR can be realized to improve the safety of coal mine operations.

[0102] Among them, the third warning operation parameter may include at least one of the following: warning method, warning level, warning type, etc., which are not limited here. The warning method may include at least one of the following: sending text messages to management personnel, sounding an alarm, voice prompts, displaying warning content on VR devices, etc., which are not limited here.

[0103] In the specific implementation, when there are x risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, it means that there is a dangerous target with a slight risk, and the third warning operation parameter corresponding to the target risk factor is determined. The third warning operation parameter can be related to the x risk factors, or it can be related to the second attribute information of the dangerous target corresponding to the x risk factors. x is a positive integer less than or equal to n, and the ratio between x and n is less than or equal to 0.5. The warning operation is performed according to the third warning operation parameter, thereby helping to ensure the accuracy of the warning operation and the safety of coal mine operations, so that the high-speed binocular camera inspection based on VR can be realized to improve the safety of coal mine operations.

[0104] In the embodiment of the present application, when each of the n risk factors is less than the second preset risk factor, it means that there is no dangerous target, and the early warning operation may not be performed.

[0105] It can be seen that the VR-based high-speed binocular camera inspection method described in the embodiment of the present application is applied to an electronic device, wherein the electronic device is communicatively connected to a VR-based high-speed binocular camera, and the VR-based high-speed binocular camera is worn on a smart helmet or smart glasses of a target user, and when the target user is located in a preset area of ​​a coal mine, the first attribute information of the target user is obtained; the current position and the target orientation of the target user are determined; a first VR image corresponding to the current position and the target orientation is collected by the VR-based high-speed binocular camera; m dangerous targets and m dangerous positions are marked in the first VR image, and each dangerous target corresponds to a dangerous position and the second attribute information of the dangerous target; m is a positive integer; dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range are detected to obtain n dangerous targets; and according to the first attribute information, the dangerous positions and The second attribute information determines the danger coefficient of each of the n dangerous targets, and obtains n danger coefficients; performs early warning operations according to the n danger coefficients. First, a corresponding VR image can be generated based on the user's position and orientation. Since the first VR image can not only reflect the actual scene, but also perform image enhancement on the actual scene, the actual scene is made more perceptual and intelligent. Second, it can accurately mark dangerous targets that are potentially dangerous to users, and accurately evaluate the danger coefficient of each dangerous target based on the user's own attributes, the dangerous target's own characteristics, and the relative position relationship between the dangerous target and the user, so that the danger evaluation is more in line with the user himself, the characteristics of the dangerous target itself, and the actual environment. Third, on the basis of accurately evaluating the danger coefficient, it helps to ensure the accuracy of the early warning operation and the safety of coal mine operations, and can realize VR-based high-speed binocular camera inspections to improve the safety of coal mine operations.

[0106] In accordance with the above embodiment, please refer to Figure 2 , Figure 2 : is a structural schematic diagram of an electronic device provided in an embodiment of the present application. As shown in the figure, the electronic device includes a processor, a memory, a communication interface and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor. In the embodiment of the present application, the electronic device is connected to a high-speed binocular camera based on VR for communication, and the high-speed binocular camera based on VR is worn on a smart helmet or smart glasses of a target user. The program includes instructions for executing the following steps:

[0107] When the target user is located in a preset area of ​​a coal mine, obtaining first attribute information of the target user;

[0108] Determine the current location and target position of the target user;

[0109] Acquiring a first VR image corresponding to the current position and the target orientation by the VR-based high-speed binocular camera;

[0110] Marking m dangerous targets and m dangerous positions in the first VR image, each dangerous target corresponds to a dangerous position and second attribute information of the dangerous target; m is a positive integer;

[0111] Detecting dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range, to obtain n dangerous targets;

[0112] Determine a risk factor of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets, and the second attribute information to obtain n risk factors;

[0113] An early warning operation is performed according to the n risk factors.

[0114] Optionally, the target orientation is the forward orientation of the target user, or the orientation of the target user; in terms of acquiring a first VR image corresponding to the current position and the target orientation by the VR-based high-speed binocular camera, the program includes instructions for performing the following steps:

[0115] Determine the visual field of the current position and the target orientation;

[0116] The first VR image is obtained by shooting according to the field of view area through the VR-based high-speed binocular camera.

[0117] Optionally, the first attribute information includes at least one of the following: the height of the target user, the weight of the target user, the vision parameter of the target user, the posture parameter of the target user, and the motion parameter of the target user; and in determining the danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets, and the second attribute information to obtain the n danger coefficients, the program includes instructions for executing the following steps:

[0118] Determining a target travel route of the target user;

[0119] Dividing the visual field into a regions according to the target travel route, where a is an integer greater than 1;

[0120] Determine a danger distribution density according to the a areas, the n dangerous targets and the second attribute information of each dangerous target, to obtain a danger distribution densities;

[0121] Determine an adjustment parameter for each of the a hazard distribution densities to obtain a adjustment parameters;

[0122] Determine an initial risk coefficient of each of the a areas according to the second attribute information of the dangerous target in each of the a areas, and obtain a initial risk coefficients;

[0123] According to the a adjustment parameters, corresponding initial risk coefficients among the a initial risk coefficients are adjusted to obtain a first risk coefficients;

[0124] The risk coefficient of each of the n dangerous targets is determined according to the a first risk coefficients and the first attribute information to obtain n risk coefficients.

[0125] Optionally, in the aspect of determining the risk factor of each of the n risk targets according to the a first risk factors and the first attribute information to obtain the n risk factors, the program includes instructions for executing the following steps:

[0126] Determine a first distance between a dangerous position of a first dangerous target and the target travel route, wherein the first dangerous target is any dangerous target among the n dangerous targets;

[0127] Determine a reference first risk factor corresponding to the first risk target;

[0128] Determine a second distance between the target user and the first dangerous target according to the first attribute information;

[0129] Obtaining target environment parameters corresponding to the first dangerous target;

[0130] Determining target optimization parameters corresponding to the target environmental parameters;

[0131] Optimizing the second distance according to the target optimization parameter to obtain a target second distance;

[0132] determining a first feedback adjustment parameter corresponding to the first distance;

[0133] Determining a second feedback adjustment parameter corresponding to the second target distance;

[0134] Feedback adjustment is performed on the reference first risk factor according to the first feedback adjustment parameter and the second feedback adjustment parameter to obtain the risk factor corresponding to the first risk target.

[0135] Optionally, in the aspect of performing the early warning operation according to the n risk factors, the program includes instructions for executing the following steps:

[0136] When there is a target risk factor greater than a first preset risk factor among the n risk factors, determining a first early warning operation parameter corresponding to the target risk factor;

[0137] Execute the early warning operation according to the first early warning operation parameter;

[0138] When there are k risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, a second early warning operation parameter corresponding to the target risk factor is determined; the second preset risk factor is less than the first preset risk factor; k is a positive integer less than or equal to n, and the ratio between k and n is greater than 0.5,

[0139] Execute an early warning operation according to the second early warning operation parameter;

[0140] When there are x risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, determining a third early warning operation parameter corresponding to the target risk factor; x is a positive integer less than or equal to n, and the ratio of x to n is less than or equal to 0.5;

[0141] Execute the early warning operation according to the third early warning operation parameter;

[0142] When each of the n risk factors is smaller than the second preset risk factor, no warning operation is performed.

[0143] It can be seen that the electronic device described in the embodiment of the present application is communicatively connected with a VR-based high-speed binocular camera, and the VR-based high-speed binocular camera is worn on a smart helmet or smart glasses of a target user, and when the target user is located in a preset area of ​​a coal mine, the first attribute information of the target user is obtained; the current position and the target orientation of the target user are determined; a first VR image corresponding to the current position and the target orientation is collected by the VR-based high-speed binocular camera; m dangerous targets and m dangerous positions are marked in the first VR image, and each dangerous target corresponds to a dangerous position and second attribute information of the dangerous target; m is a positive integer; dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range are detected to obtain n dangerous targets; the dangerous positions of the n dangerous targets and the second attribute information are determined according to the first attribute information, the dangerous positions of the n dangerous targets and the second attribute information. The hazard coefficient of each dangerous target among n dangerous targets is obtained, and n hazard coefficients are obtained; according to the said n hazard coefficients, early warning operations are performed. First, a corresponding VR image can be generated based on the user's position and orientation. Since the first VR image can not only reflect the actual scene, but also perform image enhancement on the actual scene, the actual scene is made more perceptual and intelligent. Second, dangerous targets that are potentially dangerous to users can be accurately marked, and the hazard coefficient of each dangerous target can be accurately evaluated based on the user's own attributes, the dangerous target's own characteristics, and the relative position relationship between the dangerous target and the user, so that the hazard evaluation is more in line with the user himself, the characteristics of the dangerous target itself, and the actual environment. Third, on the basis of accurately evaluating the hazard coefficient, it helps to ensure the accuracy of the early warning operation and the safety of coal mine operations, and can realize VR-based high-speed binocular camera inspections to improve the safety of coal mine operations.

[0144] Figure 3 It is a functional unit composition block diagram of a high-speed binocular camera inspection system 300 based on VR involved in an embodiment of the present application. The high-speed binocular camera inspection system 300 based on VR is applied to an electronic device, and the electronic device is connected to a high-speed binocular camera based on VR for communication. The high-speed binocular camera based on VR is worn on a smart helmet or smart glasses of a target user. The high-speed binocular camera inspection system 300 based on VR includes: an acquisition unit 301, a determination unit 302, a collection unit 303, a marking unit 304, a detection unit 305 and an early warning unit 306, wherein,

[0145] The acquisition unit 301 is used to acquire the first attribute information of the target user when the target user is located in a preset area of ​​a coal mine;

[0146] The determination unit 302 is used to determine the current position and target orientation of the target user;

[0147] The acquisition unit 303 is used to acquire a first VR image corresponding to the current position and the target orientation through the VR-based high-speed binocular camera;

[0148] The marking unit 304 is used to mark m dangerous targets and m dangerous positions in the first VR image, each dangerous target corresponds to a dangerous position and second attribute information of the dangerous target; m is a positive integer;

[0149] The detection unit 305 is used to detect dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range, and obtain n dangerous targets;

[0150] The determining unit 302 is further configured to determine a risk factor of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets and the second attribute information, so as to obtain n risk factors;

[0151] The early warning unit 306 is used to perform early warning operations according to the n risk factors.

[0152] Optionally, the target orientation is the forward orientation of the target user, or the direction of the target user; in terms of acquiring the first VR image corresponding to the current position and the target orientation by the VR-based high-speed binocular camera, the acquisition unit 303 is specifically used to:

[0153] Determine the visual field of the current position and the target orientation;

[0154] The first VR image is obtained by shooting according to the field of view area through the VR-based high-speed binocular camera.

[0155] Optionally, the first attribute information includes at least one of the following: the height of the target user, the weight of the target user, the vision parameter of the target user, the posture parameter of the target user, and the motion parameter of the target user; in determining the danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets, and the second attribute information to obtain the n danger coefficients, the determining unit 302 is specifically used to:

[0156] Determining a target travel route of the target user;

[0157] Dividing the visual field into a regions according to the target travel route, where a is an integer greater than 1;

[0158] Determine a danger distribution density according to the a areas, the n dangerous targets and the second attribute information of each dangerous target, to obtain a danger distribution densities;

[0159] Determine an adjustment parameter for each of the a hazard distribution densities to obtain a adjustment parameters;

[0160] Determine an initial risk coefficient of each of the a areas according to the second attribute information of the dangerous target in each of the a areas, and obtain a initial risk coefficients;

[0161] According to the a adjustment parameters, corresponding initial risk coefficients among the a initial risk coefficients are adjusted to obtain a first risk coefficients;

[0162] The risk coefficient of each of the n dangerous targets is determined according to the a first risk coefficients and the first attribute information to obtain n risk coefficients.

[0163] Optionally, in determining the risk coefficient of each of the n risk targets according to the a first risk coefficients and the first attribute information to obtain the n risk coefficients, the determining unit 302 is specifically configured to:

[0164] Determine a first distance between a dangerous position of a first dangerous target and the target travel route, wherein the first dangerous target is any dangerous target among the n dangerous targets;

[0165] Determine a reference first risk factor corresponding to the first risk target;

[0166] Determine a second distance between the target user and the first dangerous target according to the first attribute information;

[0167] Obtaining target environment parameters corresponding to the first dangerous target;

[0168] Determining target optimization parameters corresponding to the target environmental parameters;

[0169] Optimizing the second distance according to the target optimization parameter to obtain a target second distance;

[0170] determining a first feedback adjustment parameter corresponding to the first distance;

[0171] Determining a second feedback adjustment parameter corresponding to the second target distance;

[0172] Feedback adjustment is performed on the reference first risk factor according to the first feedback adjustment parameter and the second feedback adjustment parameter to obtain the risk factor corresponding to the first risk target.

[0173] Optionally, in the aspect of performing the early warning operation according to the n risk factors, the early warning unit 306 is specifically used for:

[0174] When there is a target risk factor greater than a first preset risk factor among the n risk factors, determining a first early warning operation parameter corresponding to the target risk factor;

[0175] Execute the early warning operation according to the first early warning operation parameter;

[0176] When there are k risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, a second early warning operation parameter corresponding to the target risk factor is determined; the second preset risk factor is less than the first preset risk factor; k is a positive integer less than or equal to n, and the ratio between k and n is greater than 0.5,

[0177] Execute an early warning operation according to the second early warning operation parameter;

[0178] When there are x risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, determining a third early warning operation parameter corresponding to the target risk factor; x is a positive integer less than or equal to n, and the ratio of x to n is less than or equal to 0.5;

[0179] Execute the early warning operation according to the third early warning operation parameter;

[0180] When each of the n risk factors is smaller than the second preset risk factor, no warning operation is performed.

[0181] It can be seen that the VR-based high-speed binocular camera inspection system described in the embodiment of the present application is applied to an electronic device, and the electronic device is communicatively connected to the VR-based high-speed binocular camera, and the VR-based high-speed binocular camera is worn on a smart helmet or smart glasses of a target user, and when the target user is located in a preset area of ​​a coal mine, the first attribute information of the target user is obtained; the current position and the target orientation of the target user are determined; a first VR image corresponding to the current position and the target orientation is collected by the VR-based high-speed binocular camera; m dangerous targets and m dangerous positions are marked in the first VR image, and each dangerous target corresponds to a dangerous position and the second attribute information of the dangerous target; m is a positive integer; dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range are detected to obtain n dangerous targets; according to the first attribute information, the dangerous positions and The second attribute information determines the danger coefficient of each of the n dangerous targets, and obtains n danger coefficients; performs early warning operations according to the n danger coefficients. First, a corresponding VR image can be generated based on the user's position and orientation. Since the first VR image can not only reflect the actual scene, but also perform image enhancement on the actual scene, the actual scene is made more perceptual and intelligent. Second, it can accurately mark dangerous targets that are potentially dangerous to users, and accurately evaluate the danger coefficient of each dangerous target based on the user's own attributes, the dangerous target's own characteristics, and the relative position relationship between the dangerous target and the user, so that the danger evaluation is more in line with the user himself, the characteristics of the dangerous target itself, and the actual environment. Third, on the basis of accurately evaluating the danger coefficient, it helps to ensure the accuracy of the early warning operation and the safety of coal mine operations, and can realize VR-based high-speed binocular camera inspections to improve the safety of coal mine operations.

[0182] It can be understood that the functions of each program module of the VR-based high-speed binocular camera inspection system of this embodiment can be specifically implemented according to the method in the above-mentioned method embodiment, and its specific implementation process can refer to the relevant description of the above-mentioned method embodiment, which will not be repeated here.

[0183] An embodiment of the present application also provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute part or all of the steps of any method described in the above method embodiments, and the above computer includes an electronic device.

[0184] The embodiment of the present application also provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, the computer program is operable to cause a computer to execute some or all of the steps of any method described in the method embodiment. The computer program product may be a software installation package, and the computer includes an electronic device.

[0185] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0186] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0187] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0188] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0190] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0191] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0192] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method and core idea of ​​the present application. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A high-speed binocular camera inspection method based on VR, characterized in that: Applied to an electronic device, the electronic device is communicatively connected to a VR-based high-speed binocular camera, the VR-based high-speed binocular camera is worn on a smart helmet or smart glasses of a target user, the method comprising: When the target user is located in a preset area of ​​a coal mine, obtaining first attribute information of the target user; Determine the current location and target position of the target user; Acquiring a first VR image corresponding to the current position and the target orientation by the VR-based high-speed binocular camera; Marking m dangerous targets and m dangerous positions in the first VR image, each dangerous target corresponds to a dangerous position and second attribute information of the dangerous target; m is a positive integer; Detecting dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range, to obtain n dangerous targets; Determine a risk factor of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets, and the second attribute information to obtain n risk factors; Performing early warning operations according to the n risk factors; The target position is the forward position of the target user, or the direction of the target user; and the step of collecting a first VR image corresponding to the current position and the target position by the VR-based high-speed binocular camera includes: Determine the visual field of the current position and the target orientation; The VR-based high-speed binocular camera is used to shoot according to the field of view to obtain the first VR image; The first attribute information includes at least one of the following: the height of the target user, the weight of the target user, the vision parameter of the target user, the posture parameter of the target user, and the motion parameter of the target user; the step of determining the danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets, and the second attribute information to obtain the n danger coefficients includes: Determining a target travel route of the target user; Dividing the visual field into a regions according to the target travel route, where a is an integer greater than 1; Determine a danger distribution density according to the a areas, the n dangerous targets and the second attribute information of each dangerous target, to obtain a danger distribution densities; Determine an adjustment parameter for each of the a hazard distribution densities to obtain a adjustment parameters; Determine an initial risk coefficient of each of the a areas according to the second attribute information of the dangerous target in each of the a areas, and obtain a initial risk coefficients; According to the a adjustment parameters, corresponding initial risk coefficients among the a initial risk coefficients are adjusted to obtain a first risk coefficients; The risk coefficient of each of the n dangerous targets is determined according to the a first risk coefficients and the first attribute information to obtain n risk coefficients.

2. The method according to claim 1, characterized in that The step of determining the risk coefficient of each of the n risk targets according to the a first risk coefficients and the first attribute information to obtain n risk coefficients includes: Determine a first distance between a dangerous position of a first dangerous target and the target travel route, wherein the first dangerous target is any dangerous target among the n dangerous targets; Determine a reference first risk factor corresponding to the first risk target; Determine a second distance between the target user and the first dangerous target according to the first attribute information; Obtaining target environment parameters corresponding to the first dangerous target; Determining target optimization parameters corresponding to the target environmental parameters; Optimizing the second distance according to the target optimization parameter to obtain a target second distance; determining a first feedback adjustment parameter corresponding to the first distance; Determining a second feedback adjustment parameter corresponding to the second target distance; Feedback adjustment is performed on the reference first risk factor according to the first feedback adjustment parameter and the second feedback adjustment parameter to obtain the risk factor corresponding to the first risk target.

3. The method according to claim 1 or 2, characterized in that: The early warning operation according to the n risk factors includes: When there is a target risk factor greater than a first preset risk factor among the n risk factors, determining a first early warning operation parameter corresponding to the target risk factor; Execute the early warning operation according to the first early warning operation parameter; When there are k risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, a second early warning operation parameter corresponding to the target risk factor is determined; the second preset risk factor is less than the first preset risk factor; k is a positive integer less than or equal to n, and the ratio between k and n is greater than 0.5, Execute an early warning operation according to the second early warning operation parameter; When there are x risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, determining a third early warning operation parameter corresponding to the target risk factor; x is a positive integer less than or equal to n, and the ratio of x to n is less than or equal to 0.5; Execute the early warning operation according to the third early warning operation parameter; When each of the n risk factors is smaller than the second preset risk factor, no warning operation is performed.

4. A high-speed binocular camera inspection system based on VR, characterized in that: Applied to an electronic device, the electronic device is connected to a high-speed binocular camera based on VR for communication, the high-speed binocular camera based on VR is worn on a smart helmet or smart glasses of a target user, the system comprises: an acquisition unit, a determination unit, a collection unit, a marking unit, a detection unit and an early warning unit, wherein: The acquisition unit is used to acquire the first attribute information of the target user when the target user is located in a preset area of ​​the coal mine; The determining unit is used to determine the current position and target orientation of the target user; The acquisition unit is used to acquire a first VR image corresponding to the current position and the target orientation through the VR-based high-speed binocular camera; The marking unit is used to mark m dangerous targets and m dangerous positions in the first VR image, each dangerous target corresponds to a dangerous position and second attribute information of the dangerous target; m is a positive integer; The detection unit is used to detect dangerous targets whose distances from the m dangerous targets to the target user are within a preset distance range, and obtain n dangerous targets; The determining unit is further used to determine a danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets and the second attribute information to obtain n danger coefficients; The early warning unit is used to perform early warning operations according to the n risk factors; The target orientation is the forward orientation of the target user, or the orientation of the target user; in acquiring the first VR image corresponding to the current position and the target orientation by the VR-based high-speed binocular camera, the acquisition unit is specifically used for: Determine the visual field of the current position and the target orientation; The VR-based high-speed binocular camera is used to shoot according to the field of view to obtain the first VR image; The first attribute information includes at least one of the following: the height of the target user, the weight of the target user, the vision parameter of the target user, the posture parameter of the target user, and the motion parameter of the target user; in determining the danger coefficient of each of the n dangerous targets according to the first attribute information, the dangerous positions of the n dangerous targets, and the second attribute information to obtain the n danger coefficients, the determining unit is specifically used to: Determining a target travel route of the target user; Dividing the visual field into a regions according to the target travel route, where a is an integer greater than 1; Determine a danger distribution density according to the a areas, the n dangerous targets and the second attribute information of each dangerous target, to obtain a danger distribution densities; Determine an adjustment parameter for each of the a hazard distribution densities to obtain a adjustment parameters; Determine an initial risk coefficient of each of the a areas according to the second attribute information of the dangerous target in each of the a areas, and obtain a initial risk coefficients; According to the a adjustment parameters, corresponding initial risk coefficients among the a initial risk coefficients are adjusted to obtain a first risk coefficients; The risk coefficient of each of the n dangerous targets is determined according to the a first risk coefficients and the first attribute information to obtain n risk coefficients.

5. The system according to claim 4, characterized in that In the aspect of determining the risk coefficient of each of the n risk targets according to the a first risk coefficients and the first attribute information to obtain the n risk coefficients, the determining unit is specifically used to: Determine a first distance between a dangerous position of a first dangerous target and the target travel route, wherein the first dangerous target is any dangerous target among the n dangerous targets; Determine a reference first risk factor corresponding to the first risk target; Determine a second distance between the target user and the first dangerous target according to the first attribute information; Obtaining target environment parameters corresponding to the first dangerous target; Determining target optimization parameters corresponding to the target environmental parameters; Optimizing the second distance according to the target optimization parameter to obtain a target second distance; determining a first feedback adjustment parameter corresponding to the first distance; Determining a second feedback adjustment parameter corresponding to the second target distance; Feedback adjustment is performed on the reference first risk factor according to the first feedback adjustment parameter and the second feedback adjustment parameter to obtain the risk factor corresponding to the first risk target.

6. The system according to claim 4 or 5, characterized in that: In the aspect of performing the early warning operation according to the n risk factors, the early warning unit is specifically used for: When there is a target risk factor greater than a first preset risk factor among the n risk factors, determining a first early warning operation parameter corresponding to the target risk factor; Execute the early warning operation according to the first early warning operation parameter; When there are k risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, determining a second early warning operation parameter corresponding to the target risk factor; The second preset risk factor is less than the first preset risk factor; k is a positive integer less than or equal to n, and the ratio between k and n is greater than 0.5, Execute an early warning operation according to the second early warning operation parameter; When there are x risk factors among the n risk factors that are greater than the second preset risk factor and less than or equal to the first preset risk factor, determining a third early warning operation parameter corresponding to the target risk factor; x is a positive integer less than or equal to n, and the ratio of x to n is less than or equal to 0.5; Execute the early warning operation according to the third early warning operation parameter; When each of the n risk factors is smaller than the second preset risk factor, no warning operation is performed.

Images