High-altitude cross operation safety supervision method and device using unmanned aerial vehicle

Abstract

The embodiment of the invention provides a high-place cross operation safety supervision method and device using an unmanned aerial vehicle, and the method comprises the steps: obtaining safety supervision task information, and transmitting the safety supervision task information to the unmanned aerial vehicle, the safety supervision task information comprising three-dimensional space coordinates of a high-place operation site; according to the three-dimensional space coordinates and the shooting performance data of the unmanned aerial vehicle camera, determining a hovering position of unmanned aerial vehicle safety supervision; acquiring safety supervision image data according to the hovering position; performing image detection on the safety supervision image data; and according to an image detection result, determining whether a high-altitude cross operation risk exists or not. According to the method, the unmanned aerial vehicle is used for shooting safety supervision image data to carry out safety supervision, all high-place operation sites can be subjected to all-around and continuous safety supervision, and the safety of high-place operation is ensured; and through an image analysis technology, timely and automatic judgment of high-place cross operation risks is realized, manual misjudgment is avoided, and the accuracy of judgment of possible safety problems is improved.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of safety supervision technology, and in particular to a method and device for safety supervision of high-altitude cross-operation using unmanned aerial vehicles. Background Art

[0002] Working at heights refers to working at a height of 2 meters or more from the falling reference plane where there is a possibility of falling, including aerial movement such as climbing up and down. This type of work is particularly common in the fields of construction and equipment installation, and is a high-risk work. If it is not managed or operated properly, safety accidents are very likely to occur, especially when the work at heights involves cross-operation in the vertical direction, there is a greater risk that the upper-level construction workers will fall and cause injuries to the lower-level construction workers at the same time. Therefore, in principle, cross-operation at heights should be eliminated; in construction sites where cross-operation at heights must be carried out, special safety protection and control measures must be set up.

[0003] Traditional safety supervision methods for high-altitude cross-operation mainly adopt manual on-site supervision, which has shortcomings such as limited supervision coverage, weak continuity, and high labor intensity. With the development of Internet of Things technology and video intelligent analysis technology, the commonly used supervision methods in the existing technology are mainly divided into two types: one is the method of using sensors, but due to the large space of production and construction sites and the limitation of calculation, the real-time detection accuracy is low, and the application effect cannot meet the requirements of rapid response of on-site safety control; the other is the method of automatically identifying abnormal conditions during high-altitude operations with the help of fixed cameras. This method is limited by the distribution and field of view of fixed cameras, and it is difficult to flexibly and automatically monitor any high-altitude operation position within the construction site.

[0004] In view of this, the embodiments of this specification aim to provide a method and device for safety supervision of high-altitude cross-operations using unmanned aerial vehicles. Summary of the invention

[0005] In view of the above-mentioned problems in the prior art, the purpose of the embodiments of this specification is to provide a method and device for safe supervision of high-altitude cross-operations using unmanned aerial vehicles, so as to solve the problems of imperfect, inaccurate and inefficient supervision of high-altitude cross-operations in the prior art.

[0006] In order to solve the above technical problems, the specific technical solutions of the embodiments of this specification are as follows:

[0007] In a first aspect, an embodiment of the present specification provides a method for safety supervision of high-altitude cross operations using a drone, the method comprising:

[0008] Obtaining safety supervision task information and sending it to the drone, the safety supervision task information including the three-dimensional spatial coordinates of the high-altitude operation site;

[0009] Determine the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera;

[0010] Acquiring safety supervision image data according to the hovering position;

[0011] Performing image detection on the security supervision image data;

[0012] Based on the image detection results, determine whether there is a risk of cross-operation at height.

[0013] Furthermore, the shooting performance data includes horizontal field of view angle data and vertical field of view angle data, and determining the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera includes:

[0014] Determine the coordinates of the hovering position of the drone in the height direction according to the falling reference plane of the high-altitude work site, the height coordinates of the three-dimensional space coordinates and the preset reference height of the detection object;

[0015] Determine the hovering distance between the UAV and the high working surface according to the falling reference plane, the height coordinate of the three-dimensional space coordinate, the preset reference height of the detection object and the vertical field of view angle data;

[0016] Determine the coordinates of the hovering position of the drone in the width direction according to the hovering distance and the width coordinate of the three-dimensional space coordinates;

[0017] The coordinates of the hovering position of the UAV in the length direction are determined according to the length coordinates of the three-dimensional space coordinates.

[0018] Specifically, the coordinates of the hovering position of the drone in the height direction are:

[0019] z=(H0+Z+D max ) / 2;

[0020] Among them, H0 is the height of the falling reference plane, Z is the height coordinate of the three-dimensional space coordinate, D max It is the preset reference height of the detection object;

[0021] The coordinates of the hovering position of the drone in the width direction are:

[0022] x = x + d;

[0023] Among them, X is the width coordinate of the three-dimensional space coordinate, and d is the hovering distance between the UAV and the high working surface;

[0024]

[0025] Among them, ω 垂直is the vertical field of view angle data;

[0026] The coordinates of the hovering position of the drone in the length direction are:

[0027] y=Y;

[0028] Wherein, Y is the length coordinate of the three-dimensional space coordinate.

[0029] Further, determining the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera includes:

[0030] The coordinates of the hovering position in the height direction, the width direction, and the length direction are corrected using the preset hovering error to obtain the hovering coordinate range of the drone during safety supervision:

[0031]

[0032] Among them, x, y, z are the coordinates of the drone's hovering position in the width direction, length direction and height direction respectively; X, Y, Z are the width coordinate, length coordinate and height coordinate of the three-dimensional space coordinate respectively, d is the distance between the drone and the high working surface; R is the preset hovering error, H0 is the height of the falling reference surface, D max It is the preset reference height of the detection object.

[0033] Furthermore, performing image detection on each of the security supervision image data includes:

[0034] Performing image analysis on the security monitoring image data to identify each detection object in the security monitoring image data;

[0035] The identified detection objects are marked with marking frames, and the coordinate information of the center position of each marking frame is marked.

[0036] Furthermore, based on the image detection results, determine whether there is a risk of cross-operation at height, including:

[0037] Calculate the horizontal coordinate distance and the vertical coordinate distance between any two detected objects according to the coordinate information corresponding to each of the marking frames;

[0038] Determine whether there is a danger of cross-operation at height based on the horizontal coordinate distance and the height coordinate distance.

[0039] Furthermore, determining whether there is a risk of high-altitude cross-operation based on the horizontal coordinate distance and the vertical coordinate distance includes:

[0040] Determine whether the horizontal coordinate distance is less than a preset first safety distance;

[0041] If yes, determining whether the vertical coordinate distance is greater than the first safety distance;

[0042] If yes, it is determined that there is a risk of cross-operation at height;

[0043] Otherwise, it is determined that there is no risk of cross-operation at height.

[0044] Furthermore, before marking the identified detection objects with the marking frames and marking the coordinate information of the center positions of the marking frames, the method further includes:

[0045] converting the size of the security supervision image data according to the security supervision area corresponding to the security supervision image data and the shooting performance data;

[0046] The coordinate information of the center position of each marking frame is obtained according to the converted safety supervision image data.

[0047] Furthermore, the shooting performance data includes the width and height of the size of the drone camera sensor, and the size of the safety supervision image data is converted according to the safety supervision area corresponding to the safety supervision image data and the shooting performance data, including:

[0048] Determining whether a width-to-height ratio of the drone camera sensor size is less than a width-to-height ratio of the safety supervision image data;

[0049] If yes, the ratio of the width of the safety supervision image data to the distance of the safety supervision area in the horizontal direction is used as the conversion ratio;

[0050] Otherwise, the ratio of the width of the safety supervision image data to the distance of the safety supervision area in the vertical direction is used as the conversion ratio;

[0051] The security supervision image data is multiplied by the conversion ratio to obtain the security supervision image data after size conversion.

[0052] Preferably, the safety supervision task information also includes operation categories, which at least include scaffolding installation, equipment installation and wall decoration; and determining whether there is a risk of cross-operation at height according to the image detection result includes:

[0053] Determine whether there is a risk of cross-operation at height based on the image detection results and the type of operation described

[0054] Specifically, the safety supervision task information also includes the start time and stop time of the high-altitude operation, and the method further includes:

[0055] Calculate the power warning value of the drone according to the start time, the stop time and the operation location;

[0056] Monitoring the remaining power of the drone;

[0057] When the remaining power is less than the power warning value, the UAV is controlled to return from the work site and a replacement UAV is controlled to go to the work site.

[0058] Specifically, obtaining safety supervision task information and sending it to the drone may include:

[0059] Generate work permits corresponding to each safety supervision task based on the daily updated risk work announcements;

[0060] The operation permit certificate is scanned, and the drone is bound to the operation permit certificate to send information about the safety supervision task to the drone.

[0061] In a second aspect, an embodiment of the present specification provides a high-altitude cross-operation safety supervision device using a drone, the device comprising:

[0062] A safety supervision task information acquisition module is used to acquire safety supervision task information and send it to the drone, wherein the safety supervision task information includes the three-dimensional spatial coordinates of the high-altitude operation site;

[0063] A hovering position determination module, used to determine the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera;

[0064] A safety supervision image data acquisition module, used to acquire safety supervision image data according to the hovering position;

[0065] An image detection module, used to perform image detection on the safety supervision image data;

[0066] The operation risk determination module is used to determine whether there is a risk of cross-operation at height based on the image detection results.

[0067] In a third aspect, an embodiment of the present specification also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided by the above technical solution when executing the computer program.

[0068] In a fourth aspect, an embodiment of the present specification further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method provided by the above technical solution is implemented.

[0069] By adopting the above-mentioned technical scheme, the embodiment of this specification provides a method and device for safety supervision of cross-operations at heights using drones, which utilizes drones to capture safety supervision image data for safety supervision. This can achieve all-round and continuous safety supervision of all high-altitude work sites, enhance the intensity of safety supervision of high-altitude operations, and thus ensure the safety of high-altitude operations; and through image analysis technology, timely and automatic judgment of the risks of cross-operations at heights is achieved, thus avoiding manual misjudgment, improving the accuracy of judging possible safety issues, and facilitating back-end management personnel to take timely intervention measures.

[0070] In order to make the above and other purposes, features and advantages of the embodiments of this specification more obvious and easy to understand, the following specifically cites preferred embodiments and describes them in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the embodiments of this specification 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 this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0072] Figure 1 A schematic diagram of the steps of a method for safety supervision of high-altitude cross operations using a drone provided in an embodiment of this specification is shown;

[0073] Figure 2 A schematic diagram of an application scenario of a method for safety supervision of high-altitude cross operations using a drone provided in an embodiment of this specification is shown;

[0074] Figure 3 A schematic diagram of the steps for determining the hovering position of a drone for safety supervision in an embodiment of this specification is shown;

[0075] Figure 4 A schematic diagram showing the steps of performing image detection on each security supervision image data in an embodiment of this specification is shown;

[0076] Figure 5 A schematic diagram of a safety supervision image in which a detection object is marked;

[0077] Figure 6 A schematic diagram of the steps of determining whether there is a risk of cross-operation at height according to the image detection results in an embodiment of this specification is shown;

[0078] Figure 7 A schematic diagram showing the steps of calculating the coordinate information of the center position of each marking frame in an embodiment of this specification is shown;

[0079] Figure 8 A schematic diagram of the steps of determining whether there is a danger of high-altitude cross-operation according to the horizontal coordinate distance and the height coordinate distance in an embodiment of this specification is shown;

[0080] Fig. 9 Another schematic diagram of the steps of the method for safety supervision of high-altitude cross operations using a drone provided in an embodiment of this specification is shown;

[0081] Fig.10 A schematic diagram of the structure of a high-altitude cross-operation safety monitoring device using a drone provided in an embodiment of this specification is shown;

[0082] Fig.11 A schematic diagram of the structure of a computer device provided in an embodiment of this specification is shown.

[0083] Description of the accompanying symbols:

[0084] 1010. Safety supervision task information acquisition module;

[0085] 1020. Hover position determination module;

[0086] 1030. Safety supervision image data acquisition module;

[0087] 1040. Image detection module;

[0088] 1050. Operational risk determination module;

[0089] 1102. Computer equipment;

[0090] 1104. Processor;

[0091] 1106. Memory;

[0092] 1108, driving mechanism;

[0093] 1110, input / output module;

[0094] 1112. Input device;

[0095] 1114. Output device;

[0096] 1116. Presentation equipment;

[0097] 1118. Graphical user interface;

[0098] 1120. Network interface;

[0099] 1122. Communication link;

[0100] 1124. Communication bus. DETAILED DESCRIPTION

[0101] The following will be combined with the drawings in the embodiments of this specification to clearly and completely describe the technical solutions in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this specification.

[0102] It should be noted that the terms "first", "second", etc. in this specification and claims and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of this specification described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product or equipment that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0103] Cross-operation at height refers to the situation where there are multiple operations at height in the same vertical direction. To ensure the safety of the operation, the operation at the bottom must be outside the possible falling range of the operation at the top. However, in the prior art, the safety supervision method for cross-operation at height is inefficient and difficult to meet the accuracy and flexibility of supervision.

[0104] In order to solve the above problems, the embodiments of this specification provide a method, device and computer equipment for safety supervision of high-altitude cross operations using drones. Figure 1 This is a schematic diagram of the steps of a method for safely supervising high-altitude cross-operations using drones provided in an embodiment of this specification. This specification provides method operation steps as described in the embodiment or flow chart, but more or fewer operation steps may be included based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many, and does not represent the only execution order. When the actual system or device product is executed, it can be executed in the order or in parallel according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 1 As shown, the method may include:

[0105] S110: Obtain safety supervision task information and send it to the drone, wherein the safety supervision task information includes the three-dimensional spatial coordinates of the high-altitude work site.

[0106] In the embodiments of the present specification, there may be multiple safety supervision tasks at a construction site, and the multiple safety supervision tasks will be sent to multiple drones respectively, so that each safety supervision task has a corresponding drone, and each safety supervision task corresponds to a three-dimensional space coordinate, so that each drone corresponds to a three-dimensional space coordinate and goes to the three-dimensional space coordinate to perform the safety supervision task.

[0107] S120: Determine a hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera.

[0108] S130: Acquire safety supervision image data according to the hovering position.

[0109] That is Figure 2 As shown, it is a schematic diagram of an application scenario of a method for safety supervision of high-altitude cross operations using a drone, wherein the drone hovers at the hovering position and performs safety supervision on high-altitude operations including three-dimensional space coordinates in the safety supervision task, and obtains safety image data during the safety supervision process. The safety supervision image data may include picture data and video data.

[0110] S140: Performing image detection on the security supervision image data.

[0111] In the embodiments of the present specification, since a construction scene may include multiple high-altitude work sites that require safety supervision, multiple safety supervision image data may be acquired from multiple drones, and image detection may be performed on each of these multiple safety supervision image data.

[0112] S150: Determine whether there is a risk of cross-operation at height based on the image detection result.

[0113] It should be noted that in the embodiments of the present specification, when determining whether there is a risk of cross-operation at height based on the image detection results, not only the image detection results of each safety supervision image data are analyzed, but also the image detection results of multiple safety supervision image data are compared and analyzed.

[0114] The embodiments of this specification provide a method for safety supervision of high-altitude cross-operations using drones. The drones are used to go to high-altitude operations to capture safety supervision image data for safety supervision, which can achieve continuous safety supervision of all high-altitude operation sites, avoid the problem of inadequate supervision, reduce the workload of manual supervision, improve the intensity of safety supervision of high-altitude operations, and ensure the safety of high-altitude operations; and through image analysis technology, timely and automatic judgment of the risks of high-altitude cross-operations can be achieved, avoiding manual misjudgment and improving the accuracy of judging possible safety problems.

[0115] Specifically, the shooting performance data of the drone camera includes horizontal field of view angle data and vertical field of view angle data. In the embodiment of this specification, Figure 3 As shown, step S120: determining the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera further includes:

[0116] S310: Determine the coordinates of the hovering position of the drone in the height direction according to the falling reference plane of the high-altitude work site, the height coordinates of the three-dimensional space coordinates and the preset reference height of the detection object.

[0117] When there is a protective device such as a protective net under the high-altitude work site, the plane where the protective device is located is used as the fall reference plane of the high-altitude work site. When there is no protective device under the high-altitude work site, the fall reference plane is the ground plane. The detection object is generally a worker engaged in high-altitude work, so the maximum height of the high-altitude worker (here the value is 2 meters) is taken as the reference height of the detection object.

[0118] The coordinates of the hovering position of the drone in the height direction can be determined by the following steps:

[0119] Step 1: Determine the vertical range height affected by the high-altitude operation based on the height coordinates of the three-dimensional space coordinates and the preset reference height of the detection object:

[0120] H1=Z+D max ;

[0121] Among them, H1 is the vertical range height of the high-altitude operation; Z is the height coordinate of the three-dimensional space coordinate; D max The reference height of the detected object (here set to 2 meters).

[0122] Step 2: Calculate the height difference between the vertical range of the height of the work at height and the reference plane of the fall:

[0123] Δh=H1-H0;

[0124] Among them, Δh is the height difference; H0 is the falling reference surface;

[0125] Step 3: Calculate the drone's hovering height:

[0126] h0=H0+Δh / 2;

[0127] Among them, h0 is the hovering height of the drone;

[0128] Then the coordinates of the hovering position of the UAV in the height direction are:

[0129] z=h0;

[0130] That is, z=(H0+Z+D max ) / 2.

[0131] S320: Determine a hovering distance between the UAV and a high working surface according to the falling reference plane, the height coordinate of the three-dimensional space coordinate, a preset reference height of the detection object and the vertical field of view angle data.

[0132] Specifically, in the embodiments of this specification, according to the field of view data of the drone camera, the falling reference plane and the top of the high-altitude operation (i.e., the sum of the height coordinates of the three-dimensional space coordinates and the preset reference height of the detection object) are respectively located at the lower and upper boundaries of the drone safety supervision area in the vertical direction. The safety supervision area is the range of the actual construction site corresponding to the safety supervision image data captured by the drone camera. The hovering distance d between the drone and the high-altitude operation surface is determined according to the upper and lower boundaries:

[0133]

[0134] Right now

[0135]

[0136] Among them, ω 垂直 is the vertical field of view angle data;

[0137] S330: Determine the coordinates of the hovering position of the drone in the width direction according to the hovering distance and the width coordinate of the three-dimensional space coordinates.

[0138] The coordinates of the drone's hovering position in the width direction are:

[0139] x = x + d;

[0140] Among them, X is the width coordinate of the three-dimensional space coordinate, and d is the hovering distance between the UAV and the high working surface.

[0141] S340: Determine the coordinates of the hovering position of the UAV in the length direction according to the length coordinates of the three-dimensional space coordinates.

[0142] The coordinates of the hovering position of the drone in the length direction are:

[0143] y=Y;

[0144] Wherein, Y is the length coordinate of the three-dimensional space coordinate.

[0145] In summary, the coordinates of the drone's hovering position in three-dimensional space are:

[0146]

[0147] The coordinates of the hovering position of the UAV in three-dimensional space are obtained by the above method, and Figure 2 As shown, the UAV is in its hovering position with a vertical distance of Δh and a horizontal distance of The safety supervision area is supervised by the tilt sensor configured on the drone, and the drone camera is kept facing the high working surface, and the lens plane is opposite to the high working surface, so as to obtain safety supervision image data. By setting the parameters such as the flight altitude of the drone, the horizontal distance from the high working surface, and the focal length of the camera, it is helpful to improve the accuracy and coverage of the capture of safety supervision image data, and improve the picture quality used for image analysis of safety supervision image data.

[0148] The method for safety supervision of high-altitude cross-operation using drones provided in the embodiments of this specification enables the safety supervision area of ​​the safety supervision image data obtained by the drone camera to extend from the top of the high-altitude operation to the falling reference plane below it, thereby judging whether the detection object at the high-altitude operation site has a risk of cross-operation for other detection objects located below it. By combining the safety supervision image data obtained by multiple drone cameras, it is possible to judge whether there is a risk of high-altitude cross-operation for all high-altitude operations at the construction site, thereby ensuring the safety of high-altitude operations at the construction site.

[0149] In the embodiment of this specification, the horizontal field of view angle is calculated by the following formula:

[0150] ω 水平 =2*arctan(w / 2f)

[0151] Among them, ω 水平 is the horizontal field of view angle, f is the focal length of the drone camera, and w is the width of the drone camera sensor size;

[0152] The vertical field of view angle is calculated by the following formula:

[0153] ω 垂直 =2*arctan(h / 2f)

[0154] Among them, ω 垂直 is the vertical field of view angle data, and h is the height of the drone camera sensor size.

[0155] Preferably, in the embodiment of this specification, step S120: determining the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera further includes:

[0156] The coordinates of the hovering position in the height direction, the width direction, and the length direction are corrected using the preset hovering error to obtain the hovering coordinate range of the drone during safety supervision:

[0157] The corrected hovering coordinate range is as follows:

[0158]

[0159] Among them, x, y, and z are the coordinates of the drone's hovering position in the width direction, length direction, and height direction, respectively; X is the width coordinate of the three-dimensional space coordinate, d is the distance between the drone and the high working surface; R is the preset hovering error (for example, its value can be set to 0.5 meters), Y is the length coordinate of the three-dimensional space coordinate, h0 is the hovering height of the drone, H0 is the height of the falling reference plane, Z is the height coordinate of the three-dimensional space coordinate, and D max It is the preset reference height of the detection object.

[0160] By correcting the hovering coordinates of the drone, it can be made more consistent with the actual working conditions of the drone. At the same time, the hovering coordinate range can be used to verify the safety supervision operation of the drone.

[0161] When the hovering coordinates of the drone are not within the hovering coordinate range, the drone camera can be controlled not to work, or the safety supervision image data captured by the drone camera at this time can be not image detected until the drone adjusts its hovering position to be within the hovering coordinate range. This is conducive to improving the efficiency of subsequent image detection of safety supervision image data, and the accuracy of using image detection results to determine whether there is a risk of cross-interaction at high altitude.

[0162] like Figure 4 As shown, in the embodiment of this specification, step S140: performing image detection on each of the security supervision image data may further include:

[0163] S410: Perform image analysis on the security monitoring image data to identify each detection object in the security monitoring image data.

[0164] Image analysis technology is used to identify various detection objects in safety supervision image data, where the detection objects are workers working at heights.

[0165] S420: Mark the identified detection objects with a marking frame, and mark the coordinate information of the center position of each marking frame.

[0166] like Figure 5 As shown in FIG. , it is a schematic diagram of a safety supervision image marking each detection object. Figure 5 As shown in the figure, two detection objects are identified in the safety supervision image captured by a drone camera. The coordinate information of the center position of the detection frame of the two detection objects is recorded as (A i , Bi ) and (A j , B j ). It should be noted that, since the safety supervision image data captured by the drone camera is a two-dimensional plane image, the coordinates corresponding to each marked detection object are two-dimensional coordinates.

[0167] In other feasible embodiments, the detection objects may also include equipment such as air-conditioning outdoor units that have not been installed, scaffolding, etc.; and also include safety equipment such as safety belts and safety helmets. It can also be determined whether the workers are wearing the safety equipment correctly based on the identified detection objects.

[0168] Furthermore, if Figure 6 As shown, step S150: determining whether there is a risk of cross-operation at height according to the image detection result, further includes:

[0169] S610: Calculate the horizontal coordinate distance and the vertical coordinate distance between any two detected objects according to the coordinate information corresponding to each of the marking boxes.

[0170] Assuming that a certain safety supervision image data only identifies a detection object at its left or right boundary, if only this safety supervision image data is used to judge the risk of high-altitude cross-operation, it will be determined that the detection object does not have the risk of high-altitude cross-operation. However, in actual construction scenarios, there may be other high-altitude work sites that require safety supervision on the left or right side of the actual high-altitude work site corresponding to the safety supervision image data, so the detection object may have a high-altitude cross-operation risk for the detection objects at other adjacent high-altitude work sites.

[0171] Therefore, in the embodiments of the present specification, not only the distances between multiple detection objects identified from the same safety supervision image data are calculated, but also the distances between multiple detection objects identified from different safety supervision image data are calculated, which greatly improves the comprehensiveness and accuracy of risk assessment of cross-operations at heights.

[0172] S620: Determine whether there is a danger of cross-operation at height based on the horizontal coordinate distance and the height coordinate distance.

[0173] The safety supervision method provided in the embodiments of this specification utilizes the distance between each detection object to determine whether there is a risk of cross-operation at height, which not only ensures the accuracy of risk determination, but also is convenient and efficient.

[0174] like Figure 7 As shown, further, in the embodiment of this specification, before step S610: calculating the horizontal coordinate distance and the vertical coordinate distance between any two detection objects according to the coordinate information corresponding to each of the marking boxes, the method further includes:

[0175] S710: Convert the size of the safety supervision image data according to the safety supervision area corresponding to the safety supervision image data and the shooting performance data.

[0176] In the embodiment of this specification, the size of the safety supervision image data includes the width and height of the safety supervision image data, which is the size of the pixel level of the safety supervision image data. Because different drones select different upper and lower boundaries for different safety supervision areas when performing safety supervision, the vertical distance Δh, Therefore, before calculating the distance between the detection objects identified from different security monitoring image data, the size of the security monitoring image data needs to be converted.

[0177] In some feasible embodiments, the size conversion can be achieved through the following steps:

[0178] Determine whether the ratio of the width (w) to the height (h) of the drone camera sensor size is less than the width of the safety supervision image data (denoted as w j ) and height (denoted as h j ), that is, to judge Is it less than

[0179] If yes, then the ratio of the width of the safety supervision image data to the horizontal distance of the safety supervision area is used as the conversion ratio; let the conversion ratio be k, then

[0180] Otherwise, the ratio of the width of the safety supervision image data to the vertical distance of the safety supervision area is used as the conversion ratio, that is,

[0181] The security supervision image data is multiplied by the conversion ratio to obtain the security supervision image data after size conversion.

[0182] Through the above-mentioned proportional conversion method, the influence of size conversion on the accuracy of distance calculation between any two detection objects can be minimized, the complexity of conversion can be reduced, and the efficiency of risk identification of high-altitude cross-operation can be improved.

[0183] S720: Obtaining coordinate information of the center position of each mark frame according to the converted safety supervision image data.

[0184] Through ratio conversion, the range of each safety supervision image data is adapted to the corresponding actual safety supervision area, thereby ensuring the accuracy of discriminating the high-altitude cross-operation risk existing between the detection objects identified from different safety supervision image data, and guaranteeing the comprehensiveness of the high-altitude cross-operation risk investigation at the construction site. It should be noted that since the three-dimensional coordinates of the high-altitude operation locations corresponding to each safety supervision image data are known, the two-dimensional plane coordinates in the three-dimensional coordinates of the high-altitude operation locations can be used as the reference coordinates for calculating the center position coordinates of the bounding boxes of each detection object. Therefore, the coordinate information of the center position of the bounding box of each detection object can be obtained by those skilled in the art.

[0185] As Figure 8 shown, in some feasible embodiments, step S620: determining whether there is a high-altitude cross-operation hazard according to the horizontal coordinate distance and the height coordinate distance may further include:

[0186] S810: Determine whether the horizontal coordinate distance is less than a preset first safety distance.

[0187] Denote the horizontal coordinate distance as D1. Exemplarily, the first safety distance can be set to 2 meters.

[0188] S820: If so, determine whether the vertical coordinate distance is greater than the first safety distance.

[0189] Denote the vertical coordinate distance as D2.

[0190] S830: If so, determine that there is a high-altitude cross-operation risk.

[0191] That is, when D1 < 2 meters and D2 > 2 meters, it is determined that there is a high-altitude cross-operation risk.

[0192] S840: Otherwise, determine that there is no high-altitude cross-operation risk.

[0193] In some preferred embodiments, after determining that there is a high-altitude cross-operation hazard, the method may further include:

[0194] Determine whether the vertical coordinate distance is greater than a preset second safety distance, and the second safety distance is greater than the first safety distance; exemplarily, the second safety distance can be set to 5 meters.

[0195] If not, determine that there is a high-altitude cross-operation risk and the risk level is level one, and issue a safety warning.

[0196] That is, when D1 < 2 meters and 2 meters < D2 ≤ 5 meters, it is determined that there is a high-altitude cross-operation risk at this time and the risk level is level one, and a drone can be used to shout to intervene and give a warning at the scene.

[0197] If yes, it is determined that the risk level of high-altitude cross-operation is level 2, and a safety warning is issued, and the risk level of level 2 is higher than the risk level of level 1;

[0198] That is, when D1<2 meters and D2>5 meters, it is determined that there is a risk of high-altitude cross-operation and the risk level is level 2. In addition to using drones to shout, the construction site alarm can also be sounded to warn the site. By shouting and sounding the alarm, high-altitude cross-operation with risks can be stopped in time, which has good practical application effects and broad promotion space.

[0199] In some other preferred embodiments, the safety supervision task information also includes a job category, and the job category includes at least scaffolding installation, equipment installation and wall decoration; the determining whether there is a risk of cross-operation at height based on the image detection result further includes:

[0200] Based on the image detection results and the type of operation, determine whether there is a risk of cross-operation at height.

[0201] For example, under the premise that the horizontal coordinate distance is less than the first safety distance (ie, D1<2 meters), the risk levels of different operation categories at different vertical coordinate distances are shown in Table 1:

[0202] Table 1

[0203]

[0204]

[0205] Furthermore, if Fig. 9 As shown, in the embodiment of this specification, the safety supervision task information also includes the start time and stop time of the high-altitude operation, and the method also includes:

[0206] S910: Calculate a power warning value of the UAV according to the start time, the stop time and the work location.

[0207] Exemplarily, in the embodiments of this specification, the power warning value is calculated by the following formula:

[0208] C min =P 飞行 *t1+P 悬停 *t2

[0209] Among them, C min The battery power limit of the drone is low; 飞行 P is the flight power of the UAV; 悬停is the hovering power of the UAV; t1 is the flight time required for the UAV to fly from the hangar to the location of the work site; t2 is the working time of the UAV for safety supervision at the work site, that is, the time interval between the start time and the stop time.

[0210] S920: Monitor the remaining power of the drone.

[0211] S930: When the remaining power is less than the power warning value, the UAV is controlled to return from the work site and a replacement UAV is controlled to go to the work site.

[0212] By calculating the drone's endurance and setting a low-battery alarm, when the drone's remaining battery is insufficient to complete safety supervision of the high-altitude work site, other drones can be used to relay alternately, ensuring the continuity of the high-altitude work.

[0213] The method may also include controlling the drone to arrive at the high-altitude work site during work start time, and to return from the high-altitude work site to the drone hangar during work stop time, so as to ensure the quality of the drone's safety supervision of the high-altitude work site.

[0214] Furthermore, in the embodiment of this specification, step S110: obtaining safety supervision task information and sending it to the drone may further include:

[0215] According to the daily updated risk operation announcement, an operation permit voucher corresponding to each safety supervision task is generated. The operation permit voucher can be a barcode or a QR code.

[0216] The operation permit certificate is scanned, and the drone is bound to the operation permit certificate to send information about the safety supervision task to the drone.

[0217] Based on the above-mentioned method for safety supervision of high-altitude cross-operations using unmanned aerial vehicles, the embodiments of this specification also provide a corresponding device for safety supervision of high-altitude cross-operations using unmanned aerial vehicles. The device may include software (applications), modules, components, servers, clients, etc. that use the method described in the embodiments of this specification and are combined with necessary implementation hardware. Based on the same innovative concept, the devices in one or more embodiments provided in the embodiments of this specification are as described in the following embodiments. As used below, the terms "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0218] like Fig.10 As shown, the high-altitude cross-operation safety supervision device using a drone provided in the embodiment of this specification includes:

[0219] A safety supervision task information acquisition module 1010 is used to acquire safety supervision task information and send it to the drone, wherein the safety supervision task information includes the three-dimensional spatial coordinates of the high-altitude operation site;

[0220] A hovering position determination module 1020, configured to determine a hovering position for safety supervision of the drone according to the three-dimensional space coordinates and the shooting performance data of the drone camera;

[0221] A safety supervision image data acquisition module 1030 is used to acquire safety supervision image data according to the hovering position;

[0222] An image detection module 1040 is used to perform image detection on the security supervision image data;

[0223] The operation risk determination module 1050 is used to determine whether there is a risk of cross-operation at height based on the image detection results.

[0224] The beneficial effects obtained by the device provided in the embodiments of this specification are consistent with the beneficial effects obtained by the above method, and will not be repeated here.

[0225] like Fig.11 As shown, a computer device provided in an embodiment of this specification is provided. The high-altitude cross-operation safety supervision device using a drone in this specification can be a computer device in this embodiment, executing the above method of this specification. The computer device 1102 may include one or more processors 1104, such as one or more central processing units (CPUs), and each processing unit may implement one or more hardware threads. The computer device 1102 may also include any memory 1106, which is used to store any kind of information such as code, settings, data, etc. Non-limiting, for example, the memory 1106 may include any one or more combinations of the following: any type of RAM, any type of ROM, flash memory device, hard disk, optical disk, etc. More generally, any memory can use any technology to store information. Further, any memory can provide volatile or non-volatile retention of information. Further, any memory can represent a fixed or removable component of the computer device 1102. In one case, when the processor 1104 executes an associated instruction stored in any memory or combination of memories, the computer device 1102 can perform any operation of the associated instruction. The computer device 1102 also includes one or more drive mechanisms 1108 for interacting with any storage, such as a hard disk drive mechanism, an optical disk drive mechanism, etc.

[0226] The computer device 1102 may also include an input / output module 1110 (I / O) for receiving various inputs (via input devices 1112) and for providing various outputs (via output devices 1114). A specific output mechanism may include a presentation device 1116 and an associated graphical user interface (GUI) 1118. In other embodiments, the input / output module 1110 (I / O), input device 1112, and output device 1114 may not be included, and the computer device 1102 may be used as a computer device in a network. The computer device 1102 may also include one or more network interfaces 1120 for exchanging data with other devices via one or more communication links 1122. One or more communication buses 1124 couple the components described above together.

[0227] The communication link 1122 may be implemented in any manner, for example, through a local area network, a wide area network (e.g., the Internet), a point-to-point connection, etc., or any combination thereof. The communication link 1122 may include any combination of hardwired links, wireless links, routers, gateway functions, name servers, etc. governed by any protocol or combination of protocols.

[0228] Corresponding to Figure 1 , Figure 3 to Figure 4 , Figures 6 to 9 In addition to the method shown, an embodiment of the specification also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above method are executed.

[0229] The embodiment of the present specification also provides a computer-readable instruction, wherein when the processor executes the instruction, the program therein causes the processor to execute the following Figure 1 , Figure 3 to Figure 4 , Figures 6 to 9 The method shown.

[0230] The embodiments of the present specification also provide a computer program product, including at least one instruction or at least one program, wherein the at least one instruction or the at least one program is loaded and executed by a processor to implement the following Figure 1 , Figure 3 to Figure 4 , Figures 6 to 9 The method shown.

[0231] It should be understood that in the various embodiments of this specification, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this specification.

[0232] It should also be understood that in the embodiments of this specification, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this specification generally indicates that the associated objects before and after are in an "or" relationship.

[0233] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this specification can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this specification.

[0234] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0235] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, or it can be an electrical, mechanical or other form of connection.

[0236] The units described 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 embodiments of this specification.

[0237] In addition, each functional unit in each embodiment of this specification 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 integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0238] If the 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 storage medium. Based on this understanding, the technical solution of this specification 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 storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0239] Specific embodiments are used in this specification to illustrate the principles and implementation methods of this specification. The description of the above embodiments is only used to help understand the methods and core ideas of this specification. At the same time, for those skilled in the art, according to the ideas of this specification, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on this specification.

Claims

1. A method for safety supervision of high-altitude cross-operation using unmanned aerial vehicles, characterized in that: include: Obtaining safety supervision task information and sending it to the drone, the safety supervision task information including the three-dimensional spatial coordinates of the high-altitude operation site; Determine the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera; Acquiring safety supervision image data according to the hovering position; Performing image detection on the security supervision image data; Based on the image detection results, determine whether there is a risk of cross-operation at height.

2. The method according to claim 1, characterized in that The shooting performance data includes horizontal field of view angle data and vertical field of view angle data. According to the three-dimensional space coordinates and the shooting performance data of the drone camera, the hovering position of the drone for safety supervision is determined, further comprising: Determine the coordinates of the hovering position of the drone in the height direction according to the falling reference plane of the high-altitude work site, the height coordinates of the three-dimensional space coordinates and the preset reference height of the detection object; Determine the hovering distance between the UAV and the high working surface according to the falling reference plane, the height coordinate of the three-dimensional space coordinate, the preset reference height of the detection object and the vertical field of view angle data; Determine the coordinates of the hovering position of the drone in the width direction according to the hovering distance and the width coordinate of the three-dimensional space coordinates; The coordinates of the hovering position of the UAV in the length direction are determined according to the length coordinates of the three-dimensional space coordinates.

3. The method according to claim 2, characterized in that The coordinates of the hovering position of the drone in the height direction are: from=(H0+Z+D max ) / 2; Among them, H0 is the height of the falling reference plane, Z is the height coordinate of the three-dimensional space coordinate, D max It is the preset reference height of the detection object; The coordinates of the hovering position of the drone in the width direction are: x = x + d; Among them, X is the width coordinate of the three-dimensional space coordinate, and d is the hovering distance between the UAV and the high working surface; Among them, ω 垂直 is the vertical field of view angle data; The coordinates of the hovering position of the drone in the length direction are: y=Y; Wherein, Y is the length coordinate of the three-dimensional space coordinate.

4. The method according to claim 3, characterized in that Determining the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera further includes: The coordinates of the hovering position in the height direction, the width direction, and the length direction are corrected using the preset hovering error to obtain the hovering coordinate range of the drone during safety supervision: Among them, x, y, z are the coordinates of the drone's hovering position in the width direction, length direction and height direction respectively; X, Y, Z are the width coordinate, length coordinate and height coordinate of the three-dimensional space coordinate respectively, d is the distance between the drone and the high working surface; R is the preset hovering error, H0 is the height of the falling reference surface, D max It is the preset reference height of the detection object.

5. The method according to claim 1, characterized in that Performing image detection on each of the safety supervision image data further includes: Performing image analysis on the security monitoring image data to identify each detection object in the security monitoring image data; The identified detection objects are marked with marking frames, and the coordinate information of the center position of each marking frame is marked.

6. The method according to claim 5, characterized in that Based on the image detection results, determine whether there is a risk of cross-operation at height, further including: Calculate the horizontal coordinate distance and the vertical coordinate distance between any two detected objects according to the coordinate information corresponding to each of the marking frames; Determine whether there is a danger of cross-operation at height based on the horizontal coordinate distance and the height coordinate distance.

7. The method according to claim 6, characterized in that The determining whether there is a risk of high-altitude cross-operation according to the horizontal coordinate distance and the vertical coordinate distance further includes: Determine whether the horizontal coordinate distance is less than a preset first safety distance; If yes, determining whether the vertical coordinate distance is greater than the first safety distance; If yes, it is determined that there is a risk of cross-operation at height; Otherwise, it is determined that there is no risk of cross-operation at height.

8. The method according to claim 5, characterized in that Before marking the identified detection objects with the marking frames and marking the coordinate information of the center positions of the marking frames, the method further includes: converting the size of the security supervision image data according to the security supervision area corresponding to the security supervision image data and the shooting performance data; The coordinate information of the center position of each marking frame is obtained according to the converted safety supervision image data.

9. The method according to claim 8, characterized in that The shooting performance data includes the width and height of the size of the drone camera sensor, and converting the size of the safety supervision image data according to the safety supervision area corresponding to the safety supervision image data and the shooting performance data, further comprising: Determining whether a width-to-height ratio of the drone camera sensor size is less than a width-to-height ratio of the safety supervision image data; If yes, the ratio of the width of the safety supervision image data to the distance of the safety supervision area in the horizontal direction is used as the conversion ratio; Otherwise, the ratio of the width of the safety supervision image data to the distance of the safety supervision area in the vertical direction is used as the conversion ratio; The security supervision image data is multiplied by the conversion ratio to obtain the security supervision image data after size conversion.

10. The method according to claim 6, characterized in that The safety supervision task information also includes the operation category, which includes at least scaffolding installation, equipment installation and wall decoration; the determining whether there is a risk of cross-operation at height based on the image detection result further includes: Based on the image detection results and the type of operation, determine whether there is a risk of cross-operation at height.

11. The method according to claim 1, characterized in that: The safety supervision task information also includes the start time and stop time of the high-altitude operation, and the method also includes: Calculate the power warning value of the drone according to the start time, the stop time and the operation location; Monitoring the remaining power of the drone; When the remaining power is less than the power warning value, the UAV is controlled to return from the work site and a replacement UAV is controlled to go to the work site.

12. The method according to claim 1, characterized in that Obtaining safety supervision task information and sending it to the drone, further including: Generate work permits corresponding to each safety supervision task based on the daily updated risk work announcements; The operation permit certificate is scanned, and the drone is bound to the operation permit certificate to send information about the safety supervision task to the drone.

13. A high-altitude cross-operation safety monitoring device using an unmanned aerial vehicle, characterized in that: The device comprises: A safety supervision task information acquisition module is used to acquire safety supervision task information and send it to the drone, wherein the safety supervision task information includes the three-dimensional spatial coordinates of the high-altitude operation site; A hovering position determination module, used to determine the hovering position of the drone for safety supervision according to the three-dimensional space coordinates and the shooting performance data of the drone camera; A safety supervision image data acquisition module, used to acquire safety supervision image data according to the hovering position; An image detection module, used to perform image detection on the safety supervision image data; The operation risk determination module is used to determine whether there is a risk of cross-operation at height based on the image detection results.

14. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 12 is implemented.

15. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 12 is implemented.

Images