Safety warning device and control method thereof

Abstract

This invention discloses a safety warning device and its control method. The safety warning device includes an image acquisition unit, a sound generation unit, a warning light unit, a blocking unit, and a controller unit. The controller unit is connected to the control terminals of the image acquisition unit, the sound generation unit, the warning light unit, and the blocking unit, respectively. The controller unit and the image acquisition unit are connected via a communication unit and a remote terminal, respectively. The control method includes: acquiring on-site images or videos through the image acquisition unit and performing image recognition; calculating the height H of the target object; if H is greater than a first preset value and less than or equal to a second preset value, enabling the sound generation unit and the warning light unit through the controller unit and saving the on-site images or videos; if H is greater than the second preset value, enabling the sound generation unit, the warning light unit, and the blocking unit through the controller unit and saving the on-site images or videos. This invention can provide timely warnings and blocking, thereby ensuring the safe and stable operation of power grid equipment.

Description

Technical Field

[0001] This invention relates to power grid auxiliary equipment, and more particularly to a safety warning device and its control method. Background Technology

[0002] A power transmission and distribution network refers to a power grid that receives electrical energy from transmission networks or regional power plants and distributes it locally or in stages according to voltage to various users through distribution facilities. To ensure personal and grid safety, installing safety warning signs on grid equipment is a common practice for power grid companies.

[0003] Traditional power safety warning signs are mostly static, resulting in ineffective warnings. In severe cases, they may cause personnel, vehicles, or other facilities to accidentally touch or come into contact with live equipment, thereby affecting the safe and stable operation of the power grid and equipment, and even causing power grid and personal safety accidents. Therefore, it is essential to develop a more intelligent and proactive power safety warning device. Summary of the Invention

[0004] The technical problem to be solved by this invention is: in view of the technical problems existing in the prior art, this invention provides a safety warning device and its control method, which can collect image information of the on-site environment in real time and can promptly issue warnings and block the operation, thereby ensuring the safe and stable operation of power grid equipment and avoiding the occurrence of safety accidents.

[0005] To solve the above-mentioned technical problems, the technical solution proposed by this invention is as follows:

[0006] A safety warning device includes a main body and an execution component. The main body includes an image acquisition unit and a controller unit. The execution component includes a sound-emitting unit, a warning light unit, and a blocking unit. The controller unit is connected to the control terminals of the image acquisition unit, the sound-emitting unit, the warning light unit, and the blocking unit, respectively. The controller unit and the image acquisition unit are connected to a communication unit and a remote terminal, respectively.

[0007] Furthermore, the main body also includes a power supply unit, which is connected to the power supply terminals of the image acquisition unit and the controller unit, respectively.

[0008] Furthermore, the power supply unit includes a solar photovoltaic panel, the image acquisition unit includes a camera, the camera housing is provided with an angle-adjustable bracket, and the solar photovoltaic panel is disposed at the end of the bracket.

[0009] Furthermore, the housing of the controller unit is located at the rear of the camera housing, and the housing has first mounting holes on both sides for screws to pass through, so that the housing is mounted to the wall through the first mounting holes.

[0010] Furthermore, the bottom of the housing is provided with a second mounting hole for inserting the top of the tripod.

[0011] Furthermore, the power supply unit includes a solar photovoltaic panel, the image acquisition unit includes a camera, the camera housing is connected to a first clamp, the solar photovoltaic panel is connected to a second clamp, and the controller unit housing is provided with a third clamp.

[0012] Furthermore, the main body also includes a positioning unit, the control terminal of which is connected to the controller unit, and the positioning unit is connected to a remote terminal via a communication unit.

[0013] The present invention also proposes a control method for a safety warning device, applicable to any of the aforementioned safety warning devices, comprising the following steps:

[0014] S1) Acquire the current scene image or video through the image acquisition unit and perform image recognition. If the target object is identified, proceed to step S2). If the target object is not identified, acquire the next scene image or video through the image acquisition unit and perform image recognition until the target object is identified.

[0015] S2) Calculate the height H of the target object. If the height H of the target object is less than or equal to the first preset value, return to step S1. If the height H of the target object is greater than the first preset value and less than or equal to the second preset value, enable the sound unit and the warning light unit through the controller unit, and save the current scene image or video. If the height H of the target object is greater than the second preset value, enable the sound unit, the warning light unit and the blocking unit through the controller unit, and save the current scene image or video.

[0016] Furthermore, step S2, calculating the target object height H, includes:

[0017] Transform the target object from the world coordinate system to the image pixel coordinate system;

[0018] Calculate the target position vector length d1 of the target object and the target position vector length d2 of the preset reference object under the same reference plane in the image pixel coordinate system. Multiply the actual height h of the preset reference object by the ratio of vector lengths d1 and d2 to calculate the actual height H of the object to be measured.

[0019] Furthermore, after transforming the target object from the world coordinate system to the image pixel coordinate system, the process also includes a step of determining whether the target object and the preset reference object are on the same reference plane in the image pixel coordinate system. Specifically, this includes:

[0020] Two images of the target object are obtained by zooming using the image acquisition unit (1). Taking the image pixel coordinate system as the reference system, the optical center at the smaller focal length as the origin, and the optical axis as the z-axis, corresponding image points Q1 and Q2 at the two focal lengths are obtained on the image plane. The distance z from the object point plane to the origin is calculated based on the coordinates of image points Q1 and Q2, and is used as the value of the reference plane in the image pixel coordinate system. The expression is as follows:

[0021]

[0022] Where f1 and f2 are the values ​​of the smaller focal length and the larger focal length, respectively, and r1 and r2 are the distances between the intersection point O of the principal optical axis and the image plane and the image points Q1(x1, y1) and Q2(x2, y2), respectively.

[0023] If the z-value of the target object is the same as the z-value of the preset reference object, then the target object and the preset reference object are on the same reference plane in the image pixel coordinate system.

[0024] Compared with the prior art, the advantages of the present invention are as follows:

[0025] The image acquisition unit of the safety warning device of the present invention is connected to a remote terminal through a communication unit, enabling the operator of the remote terminal to obtain real-time images and videos of the scene to understand the situation. The present invention also includes a blocking unit, which can block the advance of high-risk targets while warning them, thereby improving the effect of power safety warnings, ensuring the safe and stable operation of power grid equipment, and avoiding the occurrence of safety accidents.

[0026] In the control method of this invention, warning behaviors are set for different situations according to actual needs to meet different safety requirements. Furthermore, this invention can also record the behavior of the warned object for subsequent safety management. Attached Figure Description

[0027] Figure 1 This is a schematic diagram of Embodiment 1 of the present invention.

[0028] Figure 2 This is a block diagram showing the connection relationships in Embodiment 1 of the present invention.

[0029] Figure 3 This is a structural diagram of the main body of the device in Embodiment 1 of the present invention.

[0030] Figure 4 This is a schematic diagram of the main body of the device mounted on a tripod in Embodiment 1 of the present invention.

[0031] Figure 5 This is a schematic diagram of the installation position of the main body of the device in Embodiment 2 of the present invention.

[0032] Figure 6This is a flowchart of Embodiment 3 of the present invention.

[0033] Figure 7 This is a schematic diagram of coordinate system transformation in Embodiment 3 of the present invention.

[0034] Figure 8 This is a schematic diagram of zoom image imaging matching in Embodiment 3 of the present invention.

[0035] Legend: 1-Image acquisition unit, 2-Sound unit, 3-Warning light unit, 4-Blocking unit, 5-Controller unit, 6-Communication unit, 7-Power supply unit, 8-Positioning unit, 101-Bracket, 102-Housing shell, 103-First mounting hole. Detailed Implementation

[0036] The present invention will be further described below with reference to the accompanying drawings and specific preferred embodiments, but this does not limit the scope of protection of the present invention.

[0037] Example 1

[0038] To address the issue of unsatisfactory warning effectiveness of current power safety warning signs, this embodiment proposes a safety warning device, such as... Figure 1 and Figure 2 As shown, the system includes an image acquisition unit 1, a sound generation unit 2, a warning light unit 3, a blocking unit 4, a controller unit 5, a communication unit 6, a power supply unit 7, and a positioning unit 8. The controller unit 5 is connected to the control terminals of the image acquisition unit 1, the sound generation unit 2, the warning light unit 3, the blocking unit 4, and the positioning unit 8. The controller unit 5, the positioning unit 8, and the image acquisition unit 1 are connected to a remote terminal via the communication unit 6. The power supply unit 7 is connected to the power supply terminals of the image acquisition unit 1, the controller unit 5, the communication unit 6, and the positioning unit 8. The image acquisition unit 1, the controller unit 5, the communication unit 6, the power supply unit 7, and the positioning unit 8 are integrated together and referred to as the main body. The sound generation unit 2, the warning light unit 3, and the blocking unit 4 are referred to as the execution components.

[0039] The following is a detailed explanation of each unit:

[0040] The image acquisition unit 1 in this embodiment is used to acquire video and image information of the scene in real time. In this embodiment, a panoramic camera is used. The camera can achieve 360° and 180° monitoring effects by means of hanging and wall mounting, respectively, and can independently realize large-area monitoring without blind spots.

[0041] The sound-emitting unit 2 in this embodiment is used to play sound, and a speaker or loudspeaker is used in this embodiment.

[0042] The warning light unit 3 in this embodiment is used to mark and remind the location of the power grid equipment at night or in low visibility conditions. In this embodiment, an LED warning light is used, which has a long service life and high brightness. In this embodiment, the LED warning light is installed near the power grid equipment.

[0043] The blocking unit 4 in this embodiment is used to block excessively tall objects that may damage the power grid equipment. In this embodiment, an electric barrier is used, which is installed at the end of the road near the power grid equipment. The controller unit 5 outputs a first level (such as a high level) to control the electric barrier to rise (e.g., ...). Figure 1 (As shown by the dashed line) allows objects below the safe height to pass through, and the controller unit 5 outputs a second level (such as a low level) to control the electric barrier to descend (as shown by the dashed line). Figure 1 (As shown by the solid line) This prevents objects above the safe height from being blocked.

[0044] In this embodiment, the controller unit 5 is used to control the stop or operation of other functional modules after receiving signals from the remote terminal through the communication unit 6. In this embodiment, the controller unit 5 adopts an MCU (microcontroller) to reduce the size of the device. The MCU of the controller unit 5 is bidirectionally connected to the communication unit 6, and the MCU of the controller unit 5 is connected to the control terminals of the image acquisition unit 1, the sound unit 2, the warning light unit 3, the blocking unit 4, and the positioning unit 8 respectively. Thus, the MCU of the controller unit 5 can output a first level (such as a high level) or a second level (such as a low level) to the control terminals of other functional modules according to the remote terminal signal, and the other functional modules are controlled to stop or run.

[0045] like Figure 2As shown, in this embodiment, the MCU of the controller unit 5 is also provided with IO interfaces corresponding one-to-one with the image acquisition unit 1, the sound unit 2, the warning light unit 3, the blocking unit 4, the communication unit 6, and the positioning unit 8. The data input / output terminals of these functional units are respectively connected to the corresponding IO interfaces. The IO interface corresponding to the communication unit 6 is connected to the IO interfaces corresponding to the image acquisition unit 1, the sound unit 2, the warning light unit 3, the blocking unit 4, and the positioning unit 8, respectively. Furthermore, an uplink channel is provided between the IO interfaces corresponding to the image acquisition unit 1 and the positioning unit 8 and the IO interface corresponding to the communication unit 6, thereby enabling the image acquisition unit 1 and the positioning unit 8 to communicate with each other. Yuan 8 can upload the collected data to the remote terminal in real time through the communication unit 6. In addition, the IO interfaces corresponding to the sound unit 2, warning light unit 3, and barrier unit 4 are provided with a downlink channel between the IO interface corresponding to the communication unit 6, so that the remote terminal can update the data of related functional units through the downlink channel. For example, new voice data can be sent to the sound unit 2 for playback, new light combination data can be sent to the warning light unit 3 for display, new barrier lifting speed data can be sent to the barrier unit 4 to adjust the lifting speed next time, or the software firmware can be sent to the sound unit 2, warning light unit 3, and barrier unit 4 for firmware update.

[0046] The communication unit 6 in this embodiment is used to forward data between the controller unit 5 and the remote terminal. In this embodiment, a 4G or 5G communication module is used, which has a faster upload and download speed in the case of wireless transmission.

[0047] In this embodiment, the power supply unit 7 is used to supply power to the image acquisition unit 1, the controller unit 5, the communication unit 6, and the positioning unit 8, so as to ensure that the installation position of the main body will not be affected by the cables when the equipment is running for a long time. In this embodiment, a solar photovoltaic panel or a wind turbine is used.

[0048] In this embodiment, the positioning unit 8 is used to collect the coordinate information of the installation location of the main body in real time, so as to understand the location of objects above the safe height. In this embodiment, a GPS or Beidou positioning module is used to provide high positioning accuracy.

[0049] The following description uses a solar photovoltaic panel as an example to illustrate the main body of this embodiment:

[0050] like Figure 3As shown, in this embodiment, the camera housing of the image acquisition unit 1 is provided with an angle-adjustable bracket 101. The bracket 101 includes a first bracket arm and a second bracket arm that are hinged to each other. A solar photovoltaic panel is disposed at the end of the first bracket arm or the second bracket arm in the bracket 101. Correspondingly, the second bracket arm or the first bracket arm is connected to the camera housing of the image acquisition unit 1, so that the solar photovoltaic panel can be adjusted 180° to receive the best light.

[0051] In this embodiment, the controller unit 5 includes a housing 102 and an MCU (microcontroller) disposed within the housing 102. Furthermore, the communication unit 6 and the positioning unit 8 are both disposed within the housing 102. Figure 3 As shown, in this embodiment, the outer casing 102 is disposed at the rear of the camera housing, and the outer casing 102 has first mounting holes 103 on both sides for screws to pass through, so that the outer casing 102 is mounted on the wall through the first mounting holes 103.

[0052] Furthermore, to facilitate installation at emergency repair, power supply, and temporary construction sites, this embodiment includes a second mounting hole at the bottom of the outer casing 102 for inserting the top of a tripod, allowing the main body to be mounted on a tripod. Figure 4 As shown.

[0053] like Figure 1 As shown, the main body and the execution components are installed in different positions. The working principle of the safety warning device in this embodiment is as follows:

[0054] The image acquisition unit 1 acquires on-site video or images and sends them to the remote terminal via the communication unit 6. When the staff at the remote terminal discovers an object in the video or image that is higher than the safe height, they obtain the location information sent by the positioning unit 8 through the communication unit 6 and send an enable message to the communication unit 6, so that the controller unit 5 controls the sound unit 2, the warning light unit 3, and the barrier unit 4 to work, thereby realizing remote control.

[0055] Example 2

[0056] This embodiment is basically the same as Embodiment 1, except that, in order for the main body to be installed in application sites such as cement poles and steel pipes, such as... Figure 5 As shown, in this embodiment, the camera of the image acquisition unit 1, the solar photovoltaic panel of the power supply unit 7, and the housing 102 of the controller unit 5 are respectively installed on the same cement pole or steel pipe. The housing of the camera of the image acquisition unit 1 is connected to a first clamp, the solar photovoltaic panel of the power supply unit 7 is connected to a second clamp, and the housing 102 of the controller unit 5 is provided with a third clamp.

[0057] Example 3

[0058] This embodiment proposes a control method for a safety warning device, which is applied to the safety warning device described in Embodiment 1. It can accurately and effectively identify objects that exceed the safe height, and the device can actively warn and block them. Different warning levels can be set according to actual needs to meet different safety requirements. It can also record the behavior of the warned objects for subsequent safety management.

[0059] like Figure 6 As shown, in this embodiment, the remote terminal or controller unit 5 is programmed or configured to perform the following steps:

[0060] S1) Acquire the current scene image or video through image acquisition unit 1 and perform image recognition. If the target object is identified, proceed to step S2). If the target object is not identified, acquire the next scene image or video through image acquisition unit 1 and perform image recognition until the target object is identified.

[0061] S2) Calculate the height H of the target object. If the height H of the target object is less than or equal to the first preset value Hi, return to step S1. If the height H of the target object is greater than the first preset value Hi and less than or equal to the second preset value Hii, enable the sound unit 2 and the warning light unit 3 through the controller unit 5, and save the current scene image or video to start the second-level warning. If the height H of the target object is greater than the second preset value Hii, enable the sound unit 2, the warning light unit 3 and the blocking unit 4 through the controller unit 5, and save the current scene image or video to start the first-level warning.

[0062] In step S1 of this embodiment, the panoramic camera of the image acquisition unit 1 patrols within a preset detection range to detect whether a moving object has entered. If so, it actively zooms to track and capture images to obtain clear images. The specific implementation process is currently disclosed technology and is not the focus of this embodiment, so it will not be described in detail here.

[0063] In step S1 of this embodiment, when acquiring the current scene image or video and performing image recognition, a trained artificial intelligence model is invoked for recognition. In this embodiment, the artificial intelligence model presets three types of high-risk objects as target objects: the first type is a crane, the second type is an excavator, and the third type is humans. If the identified object belongs to any of the above three high-risk objects, then step S2 is initiated to calculate the height of the target object. The specific implementation process of target recognition in the image is currently disclosed technology and is not the focus of this embodiment, so it will not be described in detail here.

[0064] In step S2 of this embodiment, calculating the height H of the target object includes:

[0065] S201) Transform the target object from the world coordinate system to the image pixel coordinate system, specifically:

[0066] The process of coordinate system transformation for objects in the three-dimensional world is shown in the attached figure. Figure 7 As shown. The world coordinate system is the coordinate P(X) of an object in the real world. w Y w Z w The coordinate system of the image acquisition unit is centered at optical center O. c With the origin as the Z-axis, and the optical axis as the Z-axis c The axis, and perpendicular to the imaging plane, X c ,Y c The axis is parallel to the x and y axes of the image's physical coordinate system, and O c O represents the focal length f of the image acquisition unit. The image physical coordinate system has its origin at the intersection point O of the principal optical axis and the image plane, with the x and y directions parallel to the two sides of the image plane, respectively. The image pixel coordinate system has its origin at the top left corner of the image, with the u and v directions parallel to the x and y directions, respectively.

[0067] When transforming from the world coordinate system to the image acquisition unit coordinate system, we first add one dimension and represent it using homogeneous coordinates. R is the rotation matrix, T is the translation matrix, and the two together form a 3×4 extrinsic parameter matrix M. k .

[0068]

[0069] The coordinate system of the image acquisition unit is transformed to the physical coordinate system of the image using a focal length diagonal matrix. Based on the principles of perspective transformation and similarity, we can obtain...

[0070]

[0071] The image physical coordinate system is transformed to the image pixel coordinate system through a pixel transformation matrix, where d x and d y This represents the physical size of each pixel in the x and y directions, where u0 and v0 represent the horizontal and vertical pixel differences between the center pixel coordinates and the origin pixel coordinates. This can be expressed by the formula:

[0072]

[0073] Therefore, the general formula for the transformation process between the world coordinate system and the image pixel coordinate system is shown below. The focal length diagonal matrix and the pixel transformation matrix together form the intrinsic parameter matrix M of the image acquisition unit. c .

[0074]

[0075] S202) Calculate the vector length d1 of the target object's position and the vector length d2 of the preset reference object's position under the same reference plane in the image pixel coordinate system. Multiply the actual height h of the preset reference object by the ratio of vector lengths d1 and d2 to calculate the actual height H of the object to be measured. Specifically:

[0076] To determine the size of the object in the image, we use a ruler of fixed height h as a reference object, with the point where the ruler's center is projected onto the ground as the origin of the world coordinate system. A calibration plate is placed on a horizontal surface, and its world coordinates and pixel coordinates in the image are recorded. Then, by mapping the three-dimensional geometric positions of points on the surface of the spatial object to their corresponding points in the image, a geometric model of the image acquisition unit is established, and the intrinsic and extrinsic parameters of the image acquisition unit are calculated.

[0077] Two images were obtained by zooming in using image acquisition unit 1. Feature extraction and matching were performed using the SIFT feature matching algorithm, resulting in:

[0078] Using the image acquisition unit coordinate system as the reference system, the optical center at the small focal length as the origin, and the optical axis as the z-axis, corresponding image points at the two focal lengths are obtained on the image plane. The imaging matching results are shown in the appendix. Figure 8 As shown in the figure. R is the distance from the spatial object point to the camera's principal axis, z is the distance from the object point plane to the origin, f1 and f2 are the smaller and larger focal lengths, respectively, and r1 and r2 are the distances from the intersection point O of the principal optical axis and the image plane to image points Q1(x1, y1) and Q2(x2, y2), respectively. and

[0079] From the similarity relationship, we can obtain:

[0080]

[0081] Therefore, z can be obtained:

[0082]

[0083] When the object under test and the reference object are on the same reference plane, i.e., when their z values ​​are equal, the pixel coordinates of the reference object and the object under test are compared, and the vector lengths of the center pixel coordinates (u1, v1) and (u2, v2) of the two short sides of the rectangular detection box of the object under test are calculated. The vector lengths of the pixel coordinates (u3, v3) and (u4, v4) of the center points of the two shorter sides of the reference object. Finally, the actual height of the object to be measured was calculated by combining the actual height of the reference object.

[0084] Based on the above derivation process, in this embodiment, after transforming the target object from the world coordinate system to the image pixel coordinate system, the method further includes a step of determining whether the target object and the preset reference object are on the same reference plane in the image pixel coordinate system, specifically including:

[0085] Two images of the target object are obtained by zooming using the image acquisition unit 1. The image pixel coordinate system is used as the reference system, the optical center at the smaller focal length is used as the origin, and the optical axis is used as the z-axis. The corresponding image points Q1 and Q2 at the two focal lengths are obtained on the image plane. According to Equation (6), the distance z from the object point plane to the origin is calculated based on the coordinates of the image points Q1 and Q2, and is used as the value of the reference surface in the image pixel coordinate system.

[0086] If the z-value of the target object is the same as the z-value of the preset reference object, then the target object and the preset reference object are on the same reference plane in the image pixel coordinate system.

[0087] In step S2 of this embodiment, when saving the current scene image or video, the coordinate information obtained by the positioning unit 8 is also saved.

[0088] In step S2 of this embodiment, the first preset value Hi and the second preset value Hii are set as follows:

[0089] Hi = Height of the lowest point of the power grid equipment line from the ground - Safety distance specified by national standards - 0.5 meters;

[0090] Hii = Height of the lowest point of the power grid equipment line from the ground - Safety distance specified by national standards + 0.5 meters.

[0091] Correspondingly, when the height H of the target object is greater than the first preset value Hi and less than or equal to the second preset value Hii, the warning method of the second-level warning is as follows: the LED warning light of the warning light unit 3 flashes to display the warning information, and at the same time the sound unit 2 plays the pre-stored first voice warning information, which reads "Extremely high danger, do not approach!", and transmits image, video information and coordinate information to the remote terminal through the communication unit 6;

[0092] When the height H of the target object is greater than the second preset value Hii, the first-level warning is triggered as follows: the LED warning light of the warning light unit 3 flashes to display the warning information, and at the same time, the sound unit 2 plays the pre-stored second voice warning information, which reads "Extremely dangerous, stop immediately!", the blocking unit 4 lowers the barrier to block the dangerous behavior, and at the same time, the communication unit 6 transmits image, video and coordinate information to the remote terminal.

[0093] In summary, this invention can accurately and effectively identify unsafe behaviors, proactively warn and block them, improving the effectiveness of power safety warnings and thus ensuring the safe and stable operation of power grid equipment and preventing safety accidents. This invention can also set different warning levels according to actual needs to meet different safety requirements. Furthermore, this invention can record the behavior of the warned object for subsequent safety management. This invention is simple to install and easy to operate, effectively improving the effectiveness of power safety warnings and preventing safety accidents.

[0094] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the invention. Therefore, any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention should fall within the protection scope of the present invention.

Claims

1. A safety warning device, characterized in that, The application relates to a kind of intelligent height measurement systems, including main body and execution component, the main body includes image acquisition unit (1) and controller unit (5), the execution component includes sounding unit (2), warning light unit (3), blocking unit (4), the control end of the controller unit (5) and image acquisition unit (1), sounding unit (2), warning light unit (3), blocking unit (4) are connected respectively, the controller unit (5) and image acquisition unit (1) are connected by communication unit (6) and remote terminal respectively, the controller unit (5) is programmed or configured to execute the following steps: S1) by image acquisition unit (1) obtains the live image or video at the current time and carries out image recognition, if the target object is identified, step S2) is executed, if the target object is not identified, by image acquisition unit (1) obtains the live image or video at the next time and carries out image recognition until the target object is identified; S2) the height H of target object is calculated, if the height H of target object is less than or equal to the first preset value, return to step S1, if the height H of target object is greater than the first preset value and less than or equal to the second preset value, enable sounding unit (2) and warning light unit (3) by controller unit (5), and save the live image or video at the current time, if the height H of target object is greater than the second preset value, enable sounding unit (2), warning light unit (3) and blocking unit (4) by controller unit (5), and save the live image or video at the current time, the height H of target object includes: Convert the target object from the world coordinate system to the image pixel coordinate system; Determine whether the target object and the preset reference are on the same reference surface in the image pixel coordinate system, specifically including: Use image acquisition unit (1) to obtain two images of the target object by zooming, take the image pixel coordinate system as the reference system, take the optical center at smaller focal length as the origin, take the optical axis as the z axis, obtain corresponding image points Q1 and Q2 on the image plane at two focal lengths, calculate the distance z of the object point plane to the origin as the value of the reference surface in the image pixel coordinate system according to the coordinates of image points Q1 and Q2, the expression is as follows: Wherein, f1 and f2 are the values of smaller focal length and larger focal length respectively, r1 and r2 are the distances of the intersection O of the principal optical axis and the image plane and image points Q1 (x1, y1) and Q2 (x2, y2) respectively; If the z value of the target object is the same as the z value of the preset reference, then the target object and the preset reference are on the same reference surface in the image pixel coordinate system; Calculate the length d1 of the target position vector of the target object and the length d2 of the target position vector of the preset reference on the same reference surface in the image pixel coordinate system respectively, multiply the actual height h of the preset reference by the ratio of the lengths d1 and d2 of the vector, and calculate the actual height H of the object to be measured.

2. The safety warning device of claim 1, wherein, The main body further includes a power supply unit (7), and the power supply unit (7) is connected to the power supply ends of the image acquisition unit (1) and the controller unit (5).

3. The safety warning device of claim 2, wherein, The power supply unit (7) comprises a solar photovoltaic panel, the image acquisition unit (1) comprises a camera, an angle-adjustable support (101) is arranged on the shell of the camera, and the solar photovoltaic panel is arranged at the end of the support (101).

4. The safety warning device of claim 3, wherein, The shell (102) of the controller unit (5) is arranged at the rear of the shell of the camera, and first mounting holes (103) for screws to pass through are arranged on the two sides of the shell (102), so that the shell (102) is mounted on the wall through the first mounting holes (103).

5. The safety warning device of claim 4, wherein, The bottom of the shell (102) is also provided with a second mounting hole for the top end of a tripod to be inserted.

6. The safety warning device of claim 2, wherein, The power supply unit (7) comprises a solar photovoltaic panel, the image acquisition unit (1) comprises a camera, a first clamp is connected to the shell of the camera, a second clamp is connected to the solar photovoltaic panel, and a third clamp is arranged on the shell (102) of the controller unit (5).

7. The safety warning device of claim 1, wherein, The main body further comprises a positioning unit (8), the control end of the positioning unit (8) is connected to the controller unit (5), and the positioning unit (8) is connected to a remote terminal through the communication unit (6).

8. A control method of a safety warning device, applied to the safety warning device according to any one of claims 1 to 7, characterized in that, The method comprises the following steps: S1) acquiring live images or videos at the current moment through the image acquisition unit (1) and performing image recognition, if a target object is recognized, executing step S2), if no target object is recognized, acquiring live images or videos at the next moment through the image acquisition unit (1) and performing image recognition until a target object is recognized; S2) calculating the height H of the target object, if the height H of the target object is less than or equal to a first preset value, returning to step S1, if the height H of the target object is greater than the first preset value and less than or equal to a second preset value, enabling the sound generating unit (2) and the warning light unit (3) through the controller unit (5), and saving the live images or videos at the current moment, if the height H of the target object is greater than the second preset value, enabling the sound generating unit (2), the warning light unit (3) and the blocking unit (4) through the controller unit (5), and saving the live images or videos at the current moment, and the calculation of the height H of the target object comprises: converting the target object from a world coordinate system to an image pixel coordinate system; the step of judging whether the target object and a preset reference object are on the same reference surface in the image pixel coordinate system, specifically comprising: using the image acquisition unit (1) to perform zoom shooting to obtain two images of the target object, taking the image pixel coordinate system as a reference system, taking the optical center at a smaller focal length as an origin, and taking an optical axis as a z axis, obtaining corresponding image points Q1 and Q2 at two focal lengths on an image plane, calculating the distance z of an object point plane to the origin as a value of a reference surface in the image pixel coordinate system according to the coordinates of the image points Q1 and Q2, and the expression is as follows: wherein f1 and f2 are values of a smaller focal length and a larger focal length respectively, and r1 and r2 are distances from an intersection O of a principal optical axis and an image plane to image points Q1 (x1, y1) and Q2 (x2, y2); if the z value of the target object is the same as the z value of the preset reference object, the target object and the preset reference object are on the same reference surface in the image pixel coordinate system. The length of the target position vector d1 of the target object and the length of the target position vector d2 of the preset reference object in the image pixel coordinate system are calculated respectively, the actual height h of the preset reference object is multiplied by the ratio of the vector lengths d1 and d2, and the actual height H of the object to be measured is calculated.

Images