Method, device and electronic equipment for detecting wearing of safety helmets in working areas
Through camera image processing and object detection algorithms, workers who are not wearing safety helmets in the hoisting operation area are identified in real time and alarms are sent, which solves the problem of not wearing safety helmets in hoisting operation to increase the risk of accidents and improves safety.
Patent Information
- Application Number
- CN202410897632.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-05
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-07-05
AI Technical Summary
During the lifting operation of the aircraft production workshop, it is common for staff to not wear safety helmets, which increases the risk of accidents and makes it difficult for existing technology to effectively detect and call the police in real time.
Images are collected through the camera, and the target detection box is generated to determine whether the target object is carrying out lifting operations. The detection box is adjusted according to the operation method, to identify whether there is a target object not wearing a safety helmet in the detection box, and to send alarm information to the relevant areas.
Real-time detection of the wearing status of the safety helmet in the hoist area is achieved, which significantly reduces the risk of safety accidents and improves the safety of the operation site.
Smart Images

Figure CN118429599B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of industrial production safety technology, and in particular to a method, device and electronic equipment for detecting the wearing of safety helmets in a work area. Background Art
[0002] During the lifting operation of aircraft sections in the aircraft production workshop, the aircraft sections are suspended in the air with slings to complete the moving operation. In order to prevent accidental injuries caused by falling objects from high altitude, the workers in the lifting area are required to wear safety helmets.
[0003] However, in actual operations, workers in the lifting area may not wear helmets due to reasons such as movement of the lifting area, forgetting to wear helmets, damage to the helmets, etc., which greatly increases the risk of accidents.
[0004] Based on this, there is an urgent need for a method for real-time detection and alarm of the wearing status of safety helmets at the lifting site to reduce the risk of accidents. Summary of the invention
[0005] The purpose of this application is to provide a method, device and electronic equipment for detecting the wearing of safety helmets in the working area, which are used to realize real-time detection of the situation where safety helmets are not worn in the lifting area, so as to reduce the risk of safety accidents.
[0006] The present application provides a method for detecting the wearing of a safety helmet in a work area, comprising:
[0007] Acquire the image to be identified that is currently captured by the camera, and generate a first target detection frame of the first target object within the field of view of the camera based on the image to be identified; determine whether a hoisting operation is being performed on the first target object based on the target feature points corresponding to the first target detection frame, and determine the operation mode for the first target object; the operation mode for the first target object includes any one of the following: translation operation, rotation operation; when it is determined that a hoisting operation is being performed on the first target object, adjust the first target detection frame based on the operation mode for the first target object to obtain a second target detection frame; identify whether there is a second target object who is not wearing a safety helmet within the target coverage range of the second target detection frame.
[0008] Optionally, generating a first target detection frame of a first target object within the field of view of a camera based on the image to be identified includes: obtaining a minimum circumscribed rectangular frame of the first target object, and determining the minimum circumscribed rectangular frame as the first target detection frame of the first target object.
[0009] Optionally, the target feature points include: at least two vertices on the first target detection frame; the determination of whether a lifting operation is being performed on the first target object based on the target feature points corresponding to the first target detection frame includes: comparing the position information of the target feature points with the position information of the target feature points corresponding to the image to be matched captured by the camera at least one moment before the current moment, and calculating the position change information of the target feature points; if the position change information indicates that the displacement of at least one point among the target feature points exceeds a preset distance threshold, it is determined that a lifting operation is being performed on the first target object.
[0010] Optionally, determining the operation mode for the first target object includes: if the position change information indicates that the rotation angle of the first target detection frame exceeds a preset angle threshold, determining that the operation mode for the first target object is a rotation operation; otherwise, determining that the operation mode for the first target object is a translation operation.
[0011] Optionally, based on the operation mode for the first target object, the first target detection frame is adjusted to obtain the second target detection frame, including: when the operation mode for the first target object is the rotation operation, the rotation center point of the first target detection frame and the distance between the rotation center point and each vertex of the first target detection frame are obtained, and the distance between the rotation center point and the target vertex is determined as the target radius; the target vertex is the vertex with the largest distance from the rotation center among the vertices of the first target detection frame; based on the rotation center point and the target radius, a circular detection frame is generated, and the circular detection frame is determined as the second target detection frame.
[0012] Optionally, based on the operation mode for the first target object, the first target detection frame is adjusted to obtain the second target detection frame, including: when the operation mode for the first target object is the translation operation, determining the translation direction of the first target detection frame, and expanding the boundary of the first target detection frame in the translation direction to obtain the second target detection frame.
[0013] Optionally, after identifying whether there is a second target object who is not wearing a safety helmet within the target coverage range of the second target detection frame, the method further includes: when it is identified that the second target object exists within the target coverage range, sending an alarm prompt information to the target device, and issuing an alarm reminder to the area where the second target object is located.
[0014] The present application also provides a working area safety helmet wearing detection device, comprising:
[0015] An image acquisition module is used to acquire an image to be identified that is currently captured by a camera; an image processing module is used to generate a first target detection frame of a first target object within the field of view of the camera based on the image to be identified; an image recognition module is used to determine whether a hoisting operation is being performed on the first target object based on target feature points corresponding to the first target detection frame, and to determine an operation mode for the first target object; the operation mode for the first target object includes any one of the following: translation operation, rotation operation; the image processing module is also used to adjust the first target detection frame based on the operation mode for the first target object to obtain a second target detection frame when it is determined that a hoisting operation is being performed on the first target object; the image recognition module is also used to identify whether there is a second target object who is not wearing a safety helmet within the target coverage range of the second target detection frame.
[0016] Optionally, the image processing module is specifically configured to obtain a minimum bounding rectangular frame of the first target object, and determine the minimum bounding rectangular frame as a first target detection frame of the first target object.
[0017] Optionally, the target feature point includes: at least two vertices on the first target detection frame; the image recognition module is specifically used to compare the position information of the target feature point with the position information of the target feature point corresponding to the image to be matched collected by the camera at least one moment before the current moment, and calculate the position change information of the target feature point; the image recognition module is also specifically used to determine that a lifting operation is being performed on the first target object when the position change information indicates that the displacement of at least one point among the target feature points exceeds a preset distance threshold.
[0018] Optionally, the image recognition module is specifically used to determine that the operation mode for the first target object is a rotation operation if the position change information indicates that the rotation angle of the first target detection frame exceeds a preset angle threshold; otherwise, determine that the operation mode for the first target object is a translation operation.
[0019] Optionally, the image processing module is specifically used to obtain the rotation center point of the first target detection frame and the distance between the rotation center point and each vertex of the first target detection frame when the operation mode for the first target object is the rotation operation, and determine the distance between the rotation center point and the target vertex as the target radius; the target vertex is the vertex with the largest distance from the rotation center among the vertices of the first target detection frame; the image processing module is also specifically used to generate a circular detection frame based on the rotation center point and the target radius, and determine the circular detection frame as the second target detection frame.
[0020] Optionally, the image processing module is specifically used to determine the translation direction of the first target detection frame when the operation mode for the first target object is the translation operation, and to expand the boundary of the first target detection frame in the translation direction to obtain the second target detection frame.
[0021] Optionally, the apparatus further includes: an alarm module; the alarm module is configured to send an alarm prompt message to the target device and issue an alarm reminder to the area where the second target object is located when the second target object is identified to exist within the target coverage range.
[0022] The present application also provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of any of the above-mentioned methods for detecting the wearing of a safety helmet in a work area.
[0023] The present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-mentioned methods for detecting the wearing of a safety helmet in a work area are implemented.
[0024] The present application also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of any of the above-mentioned methods for detecting the wearing of a safety helmet in a work area are implemented.
[0025] The present application provides a method, device and electronic device for detecting the wearing of safety helmets in the working area. First, the image to be identified collected by the camera at the current moment is obtained, and a first target detection frame of the first target object within the field of view of the camera is generated based on the image to be identified; then, based on the target feature points corresponding to the first target detection frame, it is determined whether a hoisting operation is being performed on the first target object, and the operation mode for the first target object is determined; the operation mode for the first target object includes any of the following: translation operation, rotation operation; in the case of determining that a hoisting operation is being performed on the first target object, the first target detection frame is adjusted based on the operation mode for the first target object to obtain a second target detection frame; finally, it is identified whether there is a second target object without a safety helmet within the target coverage range of the second target detection frame. In this way, not only the real-time detection of the non-wearing of safety helmets in the hoisting area is achieved, but also the risk of safety accidents can be greatly reduced. BRIEF DESCRIPTION OF THE DRAWINGS
[0026] In order to more clearly illustrate the technical solutions in the present application or 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 some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0027] Figure 1 It is a schematic diagram of the architecture of the work area safety helmet wearing detection system provided by the present application;
[0028] Figure 2 It is one of the flow diagrams of the method for detecting the wearing of safety helmets in the working area provided by this application;
[0029] Figure 3 It is a schematic diagram of the detection frame adjustment method provided by this application;
[0030] Figure 4 This is the second flow chart of the method for detecting the wearing of safety helmets in the working area provided by the present application;
[0031] Figure 5 This is a schematic diagram of an example of safety helmet wearing detection in a work area provided by this application;
[0032] Figure 6 It is a structural schematic diagram of a working area safety helmet wearing detection device provided by the present application;
[0033] Figure 7 It is a structural schematic diagram of the electronic device provided by this application. DETAILED DESCRIPTION
[0034] In order to make the purpose, technical solutions and advantages of this application clearer, the technical solutions in this application will be clearly and completely described below in conjunction with the drawings in this application. Obviously, the described embodiments are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0035] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.
[0036] In the related art, it mainly relies on the personnel's own safety awareness and arranges special personnel to supervise on site, but this solution is manpower-consuming and the effect is not ideal. In response to the above-mentioned technical problems existing in the related art, the embodiment of the present application provides a method for detecting the wearing of safety helmets in the working area, which collects real-time image information of the hoisting site through a network camera and a sky eye system. By processing the image information and combining it with the target detection algorithm, the area range of the hoisting operation is determined, and it is determined whether the personnel within the area are wearing safety helmets, and an alarm is pushed to the personnel who are not wearing safety helmets. This method can timely, accurately and efficiently identify the phenomenon of not wearing safety helmets and issue an alarm reminder, which can effectively improve the safety factor of the hoisting site and promote the implementation of standardized operations at the hoisting site.
[0037] like Figure 1 As shown, it is a schematic diagram of the architecture of the detection system used in the method for detecting the wearing of safety helmets in the working area provided in the embodiment of the present application. The system includes: cameras distributed in various areas of the workshop, a sky eye system for identifying and processing images collected by the cameras, and an APP terminal for receiving alarm information sent by the sky eye system.
[0038] The following, in conjunction with the accompanying drawings, describes in detail the method for detecting safety helmet wearing in the work area provided by the embodiment of the present application through specific embodiments and their application scenarios.
[0039] like Figure 2 As shown, an embodiment of the present application provides a method for detecting the wearing of a safety helmet in a work area, and the method may include the following steps 201 to 204:
[0040] Step 201: obtain an image to be identified that is currently captured by a camera, and generate a first target detection frame of a first target object within a field of view of the camera based on the image to be identified.
[0041] Exemplarily, the camera is any one of a plurality of cameras installed in a workshop, and the camera may be a camera with a fixed viewing angle or a rotating camera with a rotatable viewing angle. The camera may collect real-time images of the hoisting operation site, obtain the image to be identified, and send the collected image to be identified to the Sky Eye system.
[0042] Exemplarily, the first target object may be an aircraft section, or other components, such as a work vehicle, a stamping die, a robotic arm, etc.
[0043] Specifically, in the above step 201, the step of generating a first target detection frame of the first target object within the field of view of the camera based on the image to be recognized may include the following steps 201a:
[0044] Step 201a: Obtain a minimum bounding rectangular frame of the first target object, and determine the minimum bounding rectangular frame as a first target detection frame of the first target object.
[0045] Exemplarily, in an embodiment of the present application, the minimum circumscribed rectangular frame of the aircraft section may be obtained, and the minimum circumscribed rectangular frame may be used as the detection frame of the aircraft section, that is, the first target detection frame mentioned above.
[0046] It is understood that the bounding box, also known as the enclosing rectangle, is the smallest rectangle that can completely contain a target object. In computational geometry, it is often associated with the convex hull, which is the smallest convex polygon formed by a set of points that can contain all these points. The minimum enclosing rectangle is the boundary of this convex polygon, whose sides are parallel to the coordinate axes. This concept is very important in image processing, computer vision, and geographic information systems for tasks such as spatial analysis and object recognition. For example, in image recognition, the enclosing rectangle can be used to determine the position and size of an object.
[0047] Step 202: Based on the target feature points corresponding to the first target detection frame, determine whether a hoisting operation is being performed on the first target object, and determine an operation method for the first target object.
[0048] The operation mode for the first target object includes any one of the following: translation operation and rotation operation.
[0049] Exemplarily, after the first target detection frame of the first target object is acquired, the operation status of the first target object can be determined based on the first target detection frame, that is, whether to perform an operation on the first target object.
[0050] Exemplarily, the target feature points include: at least two vertices on the first target detection frame. For example, the target feature points may include two, three or four vertices on the first target detection frame, and the target feature points may also include the center point of two diagonal vertices of the first target detection frame. That is, in the embodiment of the present application, the judgment of the subsequent steps can be performed through the three points of the upper left corner vertex, the lower right corner vertex and the intersection of the diagonal lines connecting the four vertices of the aircraft section detection frame (i.e., the first target detection frame).
[0051] Specifically, in the above step 202, the step of determining whether a hoisting operation is being performed on the first target object based on the target feature points corresponding to the first target detection frame may further include the following steps 202a1 and 202a2:
[0052] Step 202a1, compare the position information of the target feature point with the position information of the target feature point corresponding to the image to be matched collected by the camera at least one time before the current time, and calculate the position change information of the target feature point.
[0053] Step 202a2: When the position change information indicates that the displacement of at least one point among the target feature points exceeds a preset distance threshold, it is determined that a hoisting operation is being performed on the first target object.
[0054] For example, taking the above target feature points including two diagonal vertices and the intersection of diagonal lines as an example, the coordinates of the upper left vertex, lower right vertex and the intersection of diagonal lines of the aircraft section detection frame are obtained, and the current coordinate position is compared with that 4 seconds ago and 8 seconds ago to obtain the moving distance and displacement direction of the three points, and then judge the action being taken by the aircraft section. For example: if the moving directions of the three points are consistent and the moving distance exceeds the threshold, it is judged that the target aircraft section is undergoing a moving hoisting operation; if the moving directions of the three points are inconsistent and the moving distance exceeds the threshold, it is judged that the target aircraft section is undergoing a rotating hoisting operation; if the moving distance of the three points does not exceed the threshold, it is judged that the aircraft section has not moved.
[0055] Specifically, in the above step 202, the step of determining the operation mode for the first target object may further include the following step 202b:
[0056] Step 202b: if the position change information indicates that the rotation angle of the first target detection frame exceeds a preset angle threshold, determine that the operation mode for the first target object is a rotation operation; otherwise, determine that the operation mode for the first target object is a translation operation.
[0057] Exemplarily, when it is determined that the first target object is rotating based on the position change information of the target feature point, the operation mode for the first target object is determined to be a rotation operation; otherwise, the operation mode for the first target object is determined to be a translation operation.
[0058] Step 203: When it is determined that a hoisting operation is being performed on the first target object, the first target detection frame is adjusted based on the operation mode for the first target object to obtain a second target detection frame.
[0059] For example, after determining the operation mode for the first target object, the first target detection frame can be adjusted to obtain an adjusted second target detection frame to expand the detection range and improve the safety of the operation.
[0060] Illustratively, with respect to the above two different operation modes, the embodiments of the present application provide two different target detection frame adjustment modes.
[0061] Method 1:
[0062] In method 1, for the rotation operation, considering the expansion of the operation area due to the rotation, a circular area with the rotation center as the center and covering the coverage range of the first object detection frame can be used as the detection area.
[0063] Specifically, the above step 203 may further include the following steps 203a1 and 203a2:
[0064] Step 203a1, when the operation mode for the first target object is the rotation operation, obtain the rotation center point of the first target detection frame, and the distance between the rotation center point and each vertex of the first target detection frame, and determine the distance between the rotation center point and the target vertex as the target radius.
[0065] The target vertex is the vertex with the largest distance from the rotation center among the vertices of the first target detection frame.
[0066] Step 203a2: Generate a circular detection frame based on the rotation center point and the target radius, and determine the circular detection frame as the second target detection frame.
[0067] For example, after the circular area is used as the detection area, the operation area can be predicted in advance, which greatly improves the safety of the operation.
[0068] For example, Figure 3 As shown in (A), when performing rotating operations, the detection area can be adjusted to a circular area to increase the coverage of the detection area and improve the safety of the operation.
[0069] Method 2:
[0070] In method 2, for translation operations, the expansion of the operating area caused by translation is also taken into consideration, and the detection area can be expanded in the moving direction to provide early warning.
[0071] Specifically, the above step 203 may further include the following step 203b:
[0072] Step 203b: when the operation mode for the first target object is the translation operation, determine the translation direction of the first target detection frame, and expand the boundary of the first target detection frame in the translation direction to obtain the second target detection frame.
[0073] For example, Figure 3 As shown in (B), when performing translation operations, the detection area can be expanded in the moving direction to increase the coverage of the detection area and improve the safety of the operation.
[0074] Step 204: Identify whether there is a second target object who is not wearing a helmet within the target coverage range of the second target detection frame.
[0075] Exemplarily, after adjusting the first target detection frame to obtain the second target detection frame, the situation where the helmet is not worn can be detected based on the second target detection frame.
[0076] In the embodiment of the present application, the hoisting operation performs feature recognition of the wearing of safety helmets in the area. Identify the safety helmets in the image, and obtain the overall head features of all personnel in the hoisting area. Based on the target detection algorithm, obtain the minimum circumscribed rectangular frame of all personnel in the hoisting area, recorded as the "personnel detection frame". Using target detection algorithms such as YOLOY7, identify the "head of a person wearing a safety helmet" and the "head of a person not wearing a safety helmet" in the image, and obtain their minimum circumscribed rectangular frame, recorded as the "safety helmet detection frame".
[0077] Illustratively, after the above step 204, the method for detecting the wearing of a safety helmet in a work area provided in the embodiment of the present application may further include the following step 205:
[0078] Step 205: When it is identified that the second target object exists within the target coverage area, an alarm prompt message is sent to the target device, and an alarm reminder is issued to the area where the second target object is located.
[0079] For example, if the feature of "a person's head not wearing a helmet" is identified in the area where the lifting operation is carried out, the intersection and union ratio of the helmet detection frame and the person detection frame is used to determine which person detection frame the "person's head not wearing a helmet" detection frame is located in, and the person information in the person detection frame is obtained, and an alarm is sent through the Sky Eye system.
[0080] For example, data storage and alarm push after detecting that a person is not wearing a helmet. After the system detects that a person is not wearing a helmet, it will automatically save real-time image information, personnel information, alarm video, time information and other data to facilitate subsequent accountability. According to the danger level of the incident, relevant personnel will be notified to handle it in a timely manner through information push, sound and light alarm, interface display, etc.
[0081] For example, Figure 4 As shown, it is a flow chart of the method for detecting the wearing of safety helmets in the working area provided by the embodiment of the present application. First, the network camera collects real-time data, and the Sky Eye system determines whether the lifting operation is in progress based on the three-point coordinates in the aircraft section detection frame, and defines the lifting operation area by adjusting the detection frame. After that, the Sky Eye system identifies the features of "safety helmet", "head of a person wearing a safety helmet" and "head of a person not wearing a safety helmet" in the area, and when the feature of "head of a person not wearing a safety helmet" is detected, the Sky Eye system automatically saves real-time image information, personnel information, time information and other data, and issues an abnormal event alarm, and uses information push, sound and light alarm, interface display and other methods through terminal devices such as personal computers (PC), mobile phones, and on-site alarms, so that relevant personnel can handle it in time.
[0082] For example, Figure 5 As shown, it is a flow chart of the method for detecting the wearing of helmets in the working area provided by the embodiment of the present application. It includes: a camera monitoring area 501, an aircraft section detection frame 502, a hoisting area 503, a personnel detection frame 504, and a head of a person not wearing a helmet 505a and a head of a person wearing a helmet 505b. The example of a scene in which a hoisting operation is being performed and there are both people wearing helmets and people not wearing helmets in the hoisting operation area 503 is used for explanation.
[0083] The camera monitoring area 501 at the hoisting operation site is captured in real time through a network camera. The camera captures the hoisting status of the aircraft section, and obtains the minimum circumscribed rectangle of the aircraft section through image processing technology, such as edge detection or target recognition. This rectangular frame is the aircraft section detection frame 502.
[0084] Determine the state of the lifting operation: In the figure, the aircraft section is in the process of lifting. By comparing continuous image frames, it can be detected whether the aircraft section has moved. If displacement occurs, it can be determined that the lifting operation is in progress. Define the lifting operation area: For the aircraft section being lifted in the figure, the left and right borders of its detection frame extend to the bottom edge of the image, and the area inside the frame is the lifting operation area 503. Personnel and location identification: Combined with the Sky Eye system, identify and mark the personnel appearing in the operation area.
[0085] At the same time, based on the previous information, the specific location and related information of the aircraft section can be detected. Safety helmet wearing detection: Using image recognition technology, the system can identify the safety helmet wearing of personnel in the lifting operation area. Figure 5 In the figure, the system simultaneously identifies the features of “the head of a person not wearing a safety helmet 505a” and “the head of a person wearing a safety helmet 505b” through the person detection frame 504, wherein the appearance of the feature of “the head of a person not wearing a safety helmet 505a” will trigger a system alarm.
[0086] Alarm push and data storage: When the system detects that someone is not wearing a helmet, it will immediately match the head position with the previous personnel identification information to determine which worker is not wearing a helmet. The background will immediately send an alarm to notify the relevant personnel, and store the data of the event (such as time, personnel information, etc.) for subsequent analysis.
[0087] Through the above steps, we can realize a system for real-time monitoring of the hoisting operation site. The system can not only detect the status of the hoisting operation, but also monitor the wearing of safety helmets by personnel in the operation area, greatly improving the safety of the operation.
[0088] The method for detecting the wearing of a safety helmet in a work area provided in an embodiment of the present application first obtains the image to be identified collected by the camera at the current moment, and generates a first target detection frame of the first target object within the field of view of the camera based on the image to be identified; then, based on the target feature points corresponding to the first target detection frame, determines whether a hoisting operation is being performed on the first target object, and determines the operation mode for the first target object; the operation mode for the first target object includes any one of the following: translation operation, rotation operation; in the case of determining that a hoisting operation is being performed on the first target object, based on the operation mode for the first target object, adjusts the first target detection frame to obtain a second target detection frame; finally, identifies whether there is a second target object that is not wearing a safety helmet within the target coverage range of the second target detection frame. In this way, not only is real-time detection of the non-wearing of safety helmets in the hoisting area achieved, but the risk of safety accidents can also be reduced to a great extent.
[0089] It should be noted that the working area safety helmet wearing detection method provided in the embodiment of the present application can be executed by a working area safety helmet wearing detection device, or a control module in the working area safety helmet wearing detection device for executing the working area safety helmet wearing detection method. In the embodiment of the present application, the working area safety helmet wearing detection method is executed by a working area safety helmet wearing detection device as an example to illustrate the working area safety helmet wearing detection device provided in the embodiment of the present application.
[0090] It should be noted that, in the embodiments of the present application, the above-mentioned methods shown in the drawings. The working area safety helmet wearing detection method is illustrated by combining one of the drawings in the embodiments of the present application as an example. In specific implementation, the working area safety helmet wearing detection method shown in the above-mentioned method drawings can also be implemented in combination with any other drawings that can be combined as shown in the above-mentioned embodiments, which will not be repeated here.
[0091] The following is a description of the work area safety helmet wearing detection device provided by the present application. The work area safety helmet wearing detection method described below and described above can be referenced to each other.
[0092] Figure 6 A schematic diagram of the structure of a safety helmet wearing detection device for a work area provided in an embodiment of the present application, as shown in FIG. Figure 6 As shown, specifically including:
[0093] The image acquisition module 601 is used to acquire the image to be identified collected by the camera at the current moment; the image processing module 602 is used to generate a first target detection frame of the first target object within the field of view of the camera based on the image to be identified; the image recognition module 603 is used to determine whether a hoisting operation is being performed on the first target object based on the target feature points corresponding to the first target detection frame, and determine the operation mode for the first target object; the operation mode for the first target object includes any one of the following: translation operation, rotation operation; the image processing module 602 is also used to adjust the first target detection frame based on the operation mode for the first target object to obtain a second target detection frame when it is determined that a hoisting operation is being performed on the first target object; the image recognition module 603 is also used to identify whether there is a second target object who is not wearing a safety helmet within the target coverage range of the second target detection frame.
[0094] Optionally, the image processing module 602 is specifically configured to obtain a minimum bounding rectangular frame of the first target object, and determine the minimum bounding rectangular frame as a first target detection frame of the first target object.
[0095] Optionally, the target feature point includes: at least two vertices on the first target detection frame; the image recognition module 603 is specifically used to compare the position information of the target feature point with the position information of the target feature point corresponding to the image to be matched collected by the camera at least one moment before the current moment, and calculate the position change information of the target feature point; the image recognition module 603 is also specifically used to determine that a lifting operation is being performed on the first target object when the position change information indicates that the displacement of at least one point among the target feature points exceeds a preset distance threshold.
[0096] Optionally, the image recognition module 603 is specifically used to determine that the operation mode for the first target object is a rotation operation if the position change information indicates that the rotation angle of the first target detection frame exceeds a preset angle threshold; otherwise, determine that the operation mode for the first target object is a translation operation.
[0097] Optionally, the image processing module 602 is specifically used to obtain the rotation center point of the first target detection frame and the distance between the rotation center point and each vertex of the first target detection frame when the operation mode for the first target object is the rotation operation, and determine the distance between the rotation center point and the target vertex as the target radius; the target vertex is the vertex with the largest distance from the rotation center among the vertices of the first target detection frame; the image processing module 602 is also specifically used to generate a circular detection frame based on the rotation center point and the target radius, and determine the circular detection frame as the second target detection frame.
[0098] Optionally, the image processing module 602 is specifically used to determine the translation direction of the first target detection frame when the operation mode for the first target object is the translation operation, and to expand the boundary of the first target detection frame in the translation direction to obtain the second target detection frame.
[0099] Optionally, the apparatus further includes: an alarm module; the alarm module is configured to send an alarm prompt message to the target device and issue an alarm reminder to the area where the second target object is located when the second target object is identified to exist within the target coverage range.
[0100] The device for detecting the wearing of safety helmets in the working area provided by the present application first obtains the image to be identified collected by the camera at the current moment, and generates a first target detection frame of the first target object within the field of view of the camera based on the image to be identified; then, based on the target feature points corresponding to the first target detection frame, it is determined whether a hoisting operation is being performed on the first target object, and the operation mode for the first target object is determined; the operation mode for the first target object includes any one of the following: translation operation, rotation operation; in the case of determining that a hoisting operation is being performed on the first target object, the first target detection frame is adjusted based on the operation mode for the first target object to obtain a second target detection frame; finally, it is identified whether there is a second target object that is not wearing a safety helmet within the target coverage range of the second target detection frame. In this way, not only the real-time detection of the non-wearing of safety helmets in the hoisting area is realized, but also the risk of safety accidents can be reduced to a great extent.
[0101] Figure 7 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 7 As shown, the electronic device may include: a processor 710, a communication interface 720, a memory 730 and a communication bus 740, wherein the processor 710, the communication interface 720 and the memory 730 communicate with each other through the communication bus 740. The processor 710 may call the logic instructions in the memory 730 to execute the method for detecting the wearing of a safety helmet in the working area, the method comprising: obtaining the image to be identified collected by the camera at the current moment, and generating a first target detection frame of the first target object within the field of view of the camera based on the image to be identified; judging whether a hoisting operation is being performed on the first target object based on the target feature points corresponding to the first target detection frame, and determining the operation mode for the first target object; the operation mode for the first target object includes any one of the following: translation operation, rotation operation; in the case of determining that a hoisting operation is being performed on the first target object, adjusting the first target detection frame based on the operation mode for the first target object to obtain a second target detection frame; identifying whether there is a second target object without a safety helmet within the target coverage range of the second target detection frame.
[0102] In addition, the logic instructions in the above-mentioned memory 730 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several 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 the present application. 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, etc. Various media that can store program codes.
[0103] On the other hand, the present application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the work area safety helmet wearing detection method provided by the above methods, the method including: obtaining an image to be identified collected by a camera at a current moment, and generating a first target detection frame of a first target object within the field of view of the camera based on the image to be identified; based on the target feature points corresponding to the first target detection frame, judging whether a hoisting operation is being performed on the first target object, and determining an operation mode for the first target object; the operation mode for the first target object includes any one of the following: translation operation, rotation operation; when it is determined that a hoisting operation is being performed on the first target object, adjusting the first target detection frame based on the operation mode for the first target object to obtain a second target detection frame; identifying whether there is a second target object who is not wearing a safety helmet within the target coverage range of the second target detection frame.
[0104] On the other hand, the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the above-mentioned work area safety helmet wearing detection method, the method comprising: obtaining an image to be identified captured by the camera at a current moment, and generating a first target detection frame of a first target object within the field of view of the camera based on the image to be identified; judging whether a hoisting operation is being performed on the first target object based on target feature points corresponding to the first target detection frame, and determining an operation mode for the first target object; the operation mode for the first target object comprises any one of the following: translation operation, rotation operation; in the case of determining that a hoisting operation is being performed on the first target object, adjusting the first target detection frame based on the operation mode for the first target object to obtain a second target detection frame; identifying whether there is a second target object who is not wearing a safety helmet within the target coverage range of the second target detection frame.
[0105] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative effort.
[0106] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0107] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.
Claims
1. A method for detecting the wearing of safety helmets in a working area, characterized in that: include: Acquire an image to be identified that is currently captured by the camera, and generate a first target detection frame of a first target object within the field of view of the camera based on the image to be identified; Based on the target feature points corresponding to the first target detection frame, determining whether a hoisting operation is being performed on the first target object, and determining an operation method for the first target object; The operation mode for the first target object includes any one of the following: translation operation, rotation operation; When it is determined that a hoisting operation is being performed on the first target object, adjusting the first target detection frame based on the operation mode of the first target object to obtain a second target detection frame; Identify whether there is a second target object who is not wearing a helmet within the target coverage range of the second target detection frame; The target feature points include: at least two vertices on the first target detection frame; The determining, based on the target feature points corresponding to the first target detection frame, whether a hoisting operation is being performed on the first target object includes: Compare the position information of the target feature point with the position information of the target feature point corresponding to the image to be matched collected by the camera at least one time before the current time, and calculate the position change information of the target feature point; When the position change information indicates that the displacement of at least one point among the target feature points exceeds a preset distance threshold, it is determined that a hoisting operation is being performed on the first target object; The determining of the operation mode for the first target object includes: If the position change information indicates that the rotation angle of the first target detection frame exceeds a preset angle threshold, determining that the operation mode for the first target object is a rotation operation; otherwise, determining that the operation mode for the first target object is a translation operation; The adjusting the first target detection frame based on the operation mode for the first target object to obtain a second target detection frame includes: In the case where the operation mode for the first target object is the rotation operation, a rotation center point of the first target detection frame and distances between the rotation center point and each vertex of the first target detection frame are obtained, and the distance between the rotation center point and the target vertex is determined as a target radius; the target vertex is a vertex with the largest distance from the rotation center among the vertices of the first target detection frame; Based on the rotation center point and the target radius, a circular detection frame is generated, and the circular detection frame is determined as the second target detection frame; The adjusting the first target detection frame based on the operation mode for the first target object to obtain a second target detection frame includes: When the operation mode for the first target object is the translation operation, the translation direction of the first target detection frame is determined, and the boundary of the first target detection frame is expanded in the translation direction to obtain the second target detection frame.
2. The method according to claim 1, characterized in that The step of generating a first target detection frame of a first target object within the field of view of a camera based on the image to be recognized includes: A minimum bounding rectangular frame of the first target object is obtained, and the minimum bounding rectangular frame is determined as a first target detection frame of the first target object.
3. The method according to any one of claims 1 or 2, characterized in that After identifying whether there is a second target object not wearing a helmet within the target coverage range of the second target detection frame, the method further includes: When it is identified that the second target object exists within the target coverage area, an alarm prompt message is sent to the target device, and an alarm reminder is issued to the area where the second target object is located.
4. A device for detecting the wearing of a safety helmet in a working area, characterized in that: The device comprises: An image acquisition module is used to acquire the image to be recognized collected by the camera at the current moment; An image processing module, used for generating a first target detection frame of a first target object within the field of view of a camera based on the image to be recognized; An image recognition module, used to determine whether a hoisting operation is being performed on the first target object based on the target feature points corresponding to the first target detection frame, and determine an operation mode for the first target object; the operation mode for the first target object includes any one of the following: translation operation, rotation operation; The image processing module is further configured to, when it is determined that a hoisting operation is being performed on the first target object, adjust the first target detection frame based on an operation mode for the first target object to obtain a second target detection frame; The image recognition module is further used to identify whether there is a second target object who is not wearing a safety helmet within the target coverage range of the second target detection frame; The target feature point includes: at least two vertices on the first target detection frame; the image recognition module is specifically used to compare the position information of the target feature point with the position information of the target feature point corresponding to the image to be matched collected by the camera at least one time before the current time, and calculate the position change information of the target feature point; the image recognition module is specifically used to determine that a hoisting operation is being performed on the first target object when the position change information indicates that the displacement of at least one point among the target feature points exceeds a preset distance threshold; The image recognition module is specifically configured to determine that the operation mode for the first target object is a rotation operation if the position change information indicates that the rotation angle of the first target detection frame exceeds a preset angle threshold, and otherwise, determine that the operation mode for the first target object is a translation operation; The image processing module is specifically used to obtain the rotation center point of the first target detection frame and the distance between the rotation center point and each vertex of the first target detection frame when the operation mode for the first target object is the rotation operation, and determine the distance between the rotation center point and the target vertex as the target radius; the target vertex is the vertex with the largest distance from the rotation center among the vertices of the first target detection frame; the image processing module is also specifically used to generate a circular detection frame based on the rotation center point and the target radius, and determine the circular detection frame as the second target detection frame; The image processing module is specifically used to determine the translation direction of the first target detection frame when the operation mode for the first target object is the translation operation, and to expand the boundary of the first target detection frame in the translation direction to obtain the second target detection frame.
5. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method for detecting the wearing of a safety helmet in a working area as claimed in any one of claims 1 to 3 are implemented.
6. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps of the method for detecting the wearing of a safety helmet in a working area as claimed in any one of claims 1 to 3 are implemented.
