Highway worker dangerous behavior identification method capable of quickly adapting to weather change

Abstract

The invention discloses an expressway worker dangerous behavior identification method capable of rapidly adapting to weather changes, and belongs to the technical field of expressway worker labor protection safety early warning, and the method comprises the steps: laying a camera and a laser radar at the edge position of a to-be-monitored road section; acquiring image data and point cloud data of a road section to be monitored by using a camera and a laser radar; three-dimensional space coordinates of the positions of the cones in the road section to be monitored are recognized based on the collected data, the three-dimensional space coordinates of the cones are connected in sequence, and a safety boundary line is constructed; recognizing three-dimensional space coordinates of the position where the construction worker is located based on the collected data; and the distance between the construction worker and the safety boundary line is calculated, if the distance reaches a safety threshold value, an alarm is given, and image data at the moment are recorded. According to the method, parameters can be automatically adjusted according to weather changes, the accurate positions of the workers are obtained, and therefore dangerous behavior recognition, alarm and recording of the workers on the expressway are conveniently and efficiently achieved in real time.

Description

Technical Field

[0001] This invention relates to the field of occupational safety early warning technology for highway workers, and in particular to a method for identifying dangerous behaviors of highway workers that can quickly adapt to weather changes. Background Technology

[0002] In highway maintenance projects, the unauthorized movement of some maintenance personnel outside designated work areas is a significant cause of safety accidents during highway maintenance construction. Traditional management models, relying primarily on manual patrols and physical fencing warnings, suffer from insufficient management efficiency, limited technical means, and a lack of data support. For example, traditional management models struggle to achieve 24-hour continuous monitoring, are slow to respond to sudden incidents such as personnel crossing boundaries or entering dangerous areas, and cannot provide real-time feedback on changes in the boundary status of the work area. They also lack digital records such as personnel tracking and behavioral pattern analysis, making it difficult to trace responsibility for accidents. Therefore, traditional management models are no longer sufficient to meet the needs of modern construction safety management.

[0003] In recent years, breakthroughs in computer vision, the Internet of Things, and edge computing technologies have provided new pathways for construction safety management. Intelligent monitoring equipment enables 24-hour real-time monitoring of construction and maintenance areas. Simultaneously, image recognition technology automatically delineates the safety boundaries of the construction site in the monitoring images, intelligently identifies the activities of construction personnel, uses edge distance algorithms to identify dangerous behaviors of personnel, and provides on-site safety reminders and post-event accountability through on-site audible and visual alarms and video screenshots of dangerous behaviors.

[0004] However, for purely visual worker safety monitoring and early warning systems, the clarity is highly correlated with weather conditions, often affected by factors such as light intensity, air quality (fog or haze), and dappled sunlight. Deteriorating weather conditions can lead to decreased target recognition capabilities and reduced ranging accuracy, consequently lower detection rates for hazardous behaviors and increased risk of accidents. Therefore, addressing the issues of decreased target recognition capabilities and reduced ranging accuracy in purely visual systems during weather changes is an important research objective. Summary of the Invention

[0005] This invention provides a method for identifying hazardous behaviors of highway workers that can quickly adapt to weather changes, in order to solve the technical problem that pure visual safety monitoring and early warning schemes suffer from decreased target recognition ability and deteriorated ranging accuracy when the weather changes, resulting in a decrease in the detection and recognition rate of hazardous behaviors and an increase in the risk of safety accidents.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: On one hand, the present invention provides a method for identifying hazardous behaviors of highway workers that rapidly adapt to weather changes, the method comprising: Cameras and lidar are deployed at the edge of the road section to be monitored; the road section to be monitored includes construction workers and multiple traffic cones used to separate safe and dangerous areas; The system uses cameras to collect image data of the road section to be monitored, and simultaneously uses lidar to collect point cloud data of the road section to be monitored. Based on image data and point cloud data, the three-dimensional spatial coordinates of the location of each traffic cone in the road section to be monitored are identified, and the three-dimensional spatial coordinates of the location of each traffic cone are connected in sequence to construct a safety boundary line; The three-dimensional spatial coordinates of the construction worker's location were identified based on image data and point cloud data. Based on the three-dimensional spatial coordinates of the construction worker's location, the distance between the construction worker and the safety boundary line is calculated. If the distance reaches the safety threshold, an alarm is triggered, and the image data at this time is recorded.

[0007] Furthermore, the deployment of cameras and lidar at the edge of the road segment to be monitored includes: The cameras and lidar are deployed at the edge of the road section to be monitored; the wide-angle lenses of the cameras and lidar are the same. Adjust the placement angle and height of the camera and LiDAR to achieve the best field of view for both.

[0008] Furthermore, the step of identifying the three-dimensional spatial coordinates of the locations of each traffic cone in the monitored road segment based on image data and point cloud data includes: The image data is processed using the YOLO-v5 algorithm to identify the three-dimensional spatial coordinates of each road cone in the monitored road segment, which are recorded as road cone coordinates based on the image data. The PointNet++ algorithm is used to process the point cloud data to identify the three-dimensional spatial coordinates of the location of each road cone in the road segment to be monitored, which are recorded as the road cone coordinates based on the point cloud data. For each road cone, a preset fusion strategy is adopted to fuse its road cone coordinates based on image data and its road cone coordinates based on point cloud data, and the fused coordinates are used as the three-dimensional spatial coordinates of the corresponding road cone.

[0009] Furthermore, the process of identifying the three-dimensional spatial coordinates of the construction worker's location based on image data and point cloud data includes: The image data is processed using the YOLO-v5 algorithm to identify the three-dimensional spatial coordinates of each construction worker in the monitored road section, which are recorded as worker coordinates based on the image data. The PointNet++ algorithm is used to process the point cloud data to identify the three-dimensional spatial coordinates of each construction worker in the road section to be monitored, which are recorded as worker coordinates based on the point cloud data. For each construction worker, a preset fusion strategy is adopted to fuse the worker coordinates based on image data and the worker coordinates based on point cloud data, and the fused coordinates are used as the three-dimensional spatial coordinates of the corresponding worker.

[0010] Furthermore, the formula for the fusion strategy is expressed as follows: ; In the formula, Indicates the merged coordinates; Represents the coordinates of the image-based data to be fused; Represents the coordinates of the point cloud data to be fused; Indicates visual positioning weight; This represents the point cloud localization weights.

[0011] Furthermore, the fusion strategy is as follows: Based on the changes in the sharpness of the same object in the image data within a preset time period, visual positioning weights and point cloud positioning weights are set to fuse the two coordinates. The greater the sharpness of the same object in the image data within the preset time period, the higher the visual positioning weight and the lower the point cloud positioning weight.

[0012] Furthermore, if the distance reaches a safety threshold, an alarm is triggered, including: If the distance reaches the safety threshold, an audible and visual alarm will be activated.

[0013] Furthermore, the alarm signal is a radio signal based on the LORA protocol.

[0014] In another aspect, the present invention also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above-described method.

[0015] In another aspect, the present invention also provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the above method.

[0016] The beneficial effects of the technical solution provided by this invention include at least the following: This invention employs a fusion of vision and lidar technologies, enabling automatic parameter adjustments based on weather changes to accurately pinpoint worker locations. This allows for real-time, convenient, and efficient identification, alarming, and recording of hazardous behaviors by highway workers. It reduces the impact of weather conditions on detection accuracy, overcoming the limitations of traditional purely visual methods for highway worker safety monitoring that are easily affected by weather. Furthermore, it enables the capture of hazardous worker behaviors, facilitating post-incident safety education, enhancing worker safety awareness, and reducing potential safety hazards. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the execution flow of the method for identifying hazardous behaviors of highway workers that can quickly adapt to weather changes, provided in an embodiment of the present invention. Figure 2 This is a simulation diagram of highway safety zone division provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of safety cone feature recognition based on image data provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of safety cone feature recognition based on lidar data provided in an embodiment of the present invention; Figure 5 This is a schematic diagram of weather discrimination based on image data provided in an embodiment of the present invention; Figure 6 This is an alarm screenshot of a dangerous boundary crossing provided in an embodiment of the present invention; Figure 7 This is a schematic diagram illustrating the actual implementation process of the method for identifying hazardous behaviors of highway workers that rapidly adapt to weather changes, provided in this embodiment of the invention. Figure 8 This is a system block diagram of the electronic device provided in the embodiments of the present invention. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0020] First, it should be noted that in the embodiments of the present invention, the words "exemplarily," "for example," etc., are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the term "exemplarily" is intended to present the concept in a specific manner. Furthermore, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either one or the other.

[0021] First Embodiment This embodiment provides a method for identifying hazardous behaviors of highway workers that rapidly adapts to weather changes, used for labor monitoring and safety early warning of highway maintenance workers. This method can be implemented using electronic devices, such as terminals or servers. The execution flow of this method is as follows: Figure 1 As shown, it includes the following steps:

[0022] S1, cameras and lidar are deployed at the edge of the road section to be monitored; the road section to be monitored includes construction workers and multiple traffic cones used to separate safe and dangerous areas; Specifically, in this embodiment, the implementation process of S1 is as follows: S11, obtain the content of the construction site, construction methods and construction scope.

[0023] S12 places cameras and lidar at the edge of the highway construction site.

[0024] S13, adjust the placement angle and height of the camera and LiDAR to achieve the optimal field of view. For example... Figure 2 As shown, Figure 2 The illustration shows a simulated highway construction site, where cameras and lidar need to be deployed in locations that maximize coverage of the construction area, depending on the actual construction conditions.

[0025] S2, turn on the camera and lidar to take pictures and scan the scene. Use the camera to collect image data of the road section to be monitored, and use the lidar to collect point cloud data of the road section to be monitored. S3 identifies the three-dimensional spatial coordinates of each traffic cone in the monitored road section based on image data and point cloud data, and connects the three-dimensional spatial coordinates of each traffic cone in sequence to construct a safety boundary line; S4 identifies the three-dimensional spatial coordinates of the construction worker's location based on image data and point cloud data; Specifically, in this embodiment, the method used to obtain the coordinates of the traffic cones and workers is as follows: Features are extracted from the image data Z and point cloud data Θ obtained from the camera and LiDAR based on pre-trained YOLO-v5 and PointNet++ algorithms. The three-dimensional spatial position of the identified safety traffic cones is calculated, and a complete three-dimensional spatial boundary line is constructed, such as... Figure 3 and Figure 4 As shown. The process calculates the worker's 3D positioning coordinates based on image data and the worker's 3D spatial coordinates based on point cloud data. The coordinate calculation method involves depth calculation based on a reference object and world coordinate calculation to calculate the worker's 3D positioning coordinates based on image data and the worker's 3D spatial coordinates based on point cloud data. Further, to improve accuracy, weather conditions are determined based on the changes in image sharpness of the same object within 10 minutes. Based on the weather conditions, a weighting factor for the worker's 3D coordinates is automatically set, and then the worker's positioning coordinates are fused, with the fused coordinates used as the corresponding worker's 3D coordinates. The image sharpness assessment indicators include contrast, brightness distribution, noise level, and edge sharpness, such as... Figure 5 As shown, the coordinate weighting factor changes according to the image sharpness. The sharper the image, the higher the coordinate weight based on the image and the lower the coordinate weight based on the LiDAR, and vice versa.

[0026] Based on the above, fusion of three-dimensional coordinates The mathematical representation of is: (1) In the formula, These are the coordinates of the image data to be fused. These are the coordinates of the point cloud data to be fused. It is the visual positioning weight. It refers to the point cloud localization weights.

[0027] When extracting features from the safety cones using image data Z and point cloud data Θ obtained from cameras and LiDAR based on the YOLO-v5 and PointNet++ algorithms, it is necessary to confirm whether the feature extraction is successful. If unsuccessful, the site needs to be photographed and scanned again. Then, based on the identified safety cones, their three-dimensional spatial positions are calculated, and the three-dimensional coordinates of the safety cones are connected to construct a complete three-dimensional spatial boundary line.

[0028] The training process of the Yolo-v5 algorithm consists of five steps: data acquisition, data annotation, training optimization, and model validation. The acquired data comes from videos of highway construction sites (daytime / nighttime / foggy days), supplemented by publicly available datasets. The annotation rules are: cones are labeled with a coverage area plus the reflective area at the top; pedestrians are labeled with a rectangle from the ankle to the top of the head. The mathematical principles of model training are:

[0029] 1. YOLOv5 transforms the detection task into a grid cell regression problem: (2) In the formula, It is the center coordinate offset. It is the width and height scaling factor. It is the sigmoid activation function. It is the intersection-union ratio (IUU) between the predicted bounding box and the ground truth bounding box.

[0030] 2. The total loss function under consideration is: (3) In the formula, For coordinate loss function, For confidence loss function, This is the classification loss function.

[0031] Coordinate loss function for: (4) In the formula, It is the Euclidean distance between the center points of the predicted bounding box and the ground truth bounding box. It is the length of the diagonal of the minimum bounding box. It is the aspect ratio consistency factor. Weighting coefficient Confidence loss function for: (5) In the formula, and It is a constant. It is the confidence prediction value.

[0032] Classification loss function for: (6) In the formula, It is the number of categories. These are real category labels. It is the predicted probability of the category.

[0033] During training, techniques such as perspective transformation to simulate slope, image blending enhancement, fog simulation, and dynamic blur can be used to further enhance the model's generalization ability.

[0034] After training, the matching degree between the preset anchor boxes and the real boxes is verified. A result of 0.85 or higher is considered reliable.

[0035] The PointNet++ algorithm training process consists of five steps: point cloud data acquisition, point cloud preprocessing, data annotation, loss function optimization, and model deployment. The annotation methods include: annotating the geometric center and highly reflective features of the cones, and annotating the head, feet, and velocity vectors of pedestrians. Preprocessing includes dataset augmentation, including rotation around the Z-axis, scaling, and Gaussian noise.

[0036] The joint loss function of the PointNet++ network is: (7) In the formula, The classification loss function; This is the location loss function.

[0037] Classification loss function The formula is: (8) In the formula, It is the probability that the model predicts for that category. γ is the class weight, and γ is a constant that suppresses the contribution of class samples to the loss.

[0038] Location loss function The formula is: (9) In the formula, δ is the error threshold. These are the actual coordinates. These are the predicted coordinates.

[0039] After training, the algorithm is validated. If the algorithm's accuracy reaches 95% or higher, recall reaches 96% or higher, and localization error does not exceed 0.08m, then the model is considered usable.

[0040] S5. Based on the three-dimensional spatial coordinates of the construction worker's location, calculate the distance between the construction worker and the safety boundary line. If the distance reaches the safety threshold, issue an alarm and record the image data at this time.

[0041] The safety boundary distance threshold can be determined on-site.

[0042] The alarm mechanism is as follows: if the distance between the worker and the safety boundary line reaches the safety threshold, such as... Figure 6 As shown, an alarm signal is output. After the alarm signal is output, the audible and visual alarm will automatically sound, and the camera will automatically take pictures to record the data. The alarm signal is a radio signal based on the LoRa protocol. If the worker's distance from the safety boundary does not reach the safety threshold, safety monitoring and data processing will continue.

[0043] In summary, this embodiment provides a method for identifying hazardous behaviors of highway workers that can quickly adapt to weather changes. The implementation process is as follows: Figure 7 As shown in the diagram, this method enables automatic parameter adjustment based on weather changes, accurate worker location acquisition, and real-time, convenient, and efficient identification, alarm, and recording of hazardous behaviors of highway workers. It reduces the impact of weather factors on detection accuracy, overcomes the limitations of traditional purely visual methods for highway worker safety monitoring that are easily affected by weather, and simultaneously enables the capture of hazardous worker behaviors, facilitating post-incident safety education, improving worker safety awareness, and reducing safety hazards.

[0044] Second Embodiment This embodiment provides an electronic device, such as... Figure 8 As shown, the electronic device includes a processor and a memory; wherein the processor and the memory can be connected via a communication bus; the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment described above. Furthermore, the electronic device may also include a transceiver, the processor and the transceiver can be connected via a communication bus, and the transceiver is used to communicate with other devices.

[0045] Below, in conjunction with Figure 8 A detailed introduction to each component of this electronic device is provided below: The processor is the control center of the electronic device. The electronic device may include multiple processors, each of which can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The term "processor" can refer to a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), other general-purpose processors, application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), one or more field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor can perform various functions of the electronic device by running or executing software programs stored in memory and by calling data stored in memory.

[0046] In a specific implementation, as one example, the processor may include one or more CPUs, for example... Figure 8 CPU0 and CPU1 shown are, of course, merely illustrative examples.

[0047] The memory is used to store the software program that executes the solution of the present invention, and the processor controls its execution. For specific implementation methods, please refer to the above method embodiments, which will not be repeated here.

[0048] Optionally, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may be integrated with the processor or exist independently, and may be accessed through the interface circuit of the electronic device ( Figure 8 (Not shown in the image) is coupled to the processor; however, this embodiment of the invention does not impose specific limitations on this.

[0049] The transceiver may include a receiver and a transmitter. Figure 8 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function. The transceiver can be integrated with the processor or exist independently, and can be connected through the interface circuit of the electronic device (…). Figure 8 (Not shown in the image) is coupled to the processor, and this embodiment of the invention does not specifically limit this.

[0050] In addition, it should be noted that, Figure 8 The structure of the electronic device shown is not intended to limit the device. Actual devices may include more or fewer components than shown, or combine certain components, or have different component arrangements. Furthermore, the technical effects achieved by this electronic device when performing the method of the first embodiment described above can be referenced to the technical effects described in the first embodiment; therefore, they will not be repeated here.

[0051] Third Embodiment This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc. The instruction stored therein can be loaded and executed by a processor in a terminal.

[0052] Furthermore, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of a completely or partially hardware embodiment, a completely or partially software embodiment, or an embodiment combining software and hardware aspects. Moreover, when implemented in software, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any usable medium accessible to a computer or a data storage device such as a server or data center containing one or more sets of usable media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive (SSD).

[0053] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0054] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0055] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element. Furthermore, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Additionally, the character " / " in this text generally indicates an "or" relationship between the preceding and following objects, but it can also indicate an "AND / OR" relationship. Please refer to the context for specific interpretations. "At least one" refers to one or more items, while "more than" refers to two or more items. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can be represented as: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0056] Furthermore, it is understood that in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0057] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0058] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of functional modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs. Additionally, the functional units in the various embodiments of this invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0059] If the method is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0060] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention. It should be pointed out that although preferred embodiments of the present invention have been described, those skilled in the art, once they understand the basic inventive concept of the present invention, can make several improvements and modifications without departing from the principles described herein. These improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A method for identifying dangerous behavior of a highway worker in rapid adaptation to weather changes, characterized in that, The method for identifying dangerous behaviors of highway workers rapidly adapting to weather changes comprises the following steps: A camera and a laser radar are arranged at the edge of a to-be-monitored road section, wherein the to-be-monitored road section includes construction workers and a plurality of road cones for separating a safe area from a dangerous area; Image data of the to-be-monitored road section is collected by the camera, and point cloud data of the to-be-monitored road section is collected by the laser radar; Three-dimensional spatial coordinates of positions of the road cones in the to-be-monitored road section are identified based on the image data and the point cloud data, and the three-dimensional spatial coordinates of the positions of the road cones are sequentially connected to construct a safety boundary line; Three-dimensional spatial coordinates of positions of the construction workers are identified based on the image data and the point cloud data; A distance between the construction workers and the safety boundary line is calculated based on the three-dimensional spatial coordinates of the positions of the construction workers, and if the distance reaches a safety threshold, an alarm is given, and image data at this time is recorded.

2. The highway worker hazard behavior recognition method that quickly adapts to weather changes of claim 1, wherein, The camera and the laser radar are arranged at the edge of the to-be-monitored road section, and the wide angles of the camera and the laser radar are consistent. The placement angle and height of the camera and the laser radar are adjusted to achieve an optimal field of view. The Yolo-v5 algorithm is used to process the image data to identify the three-dimensional spatial coordinates of the positions of the road cones in the to-be-monitored road section, which are denoted as road cone coordinates based on image data. 3.The highway worker hazard behavior recognition method of quickly adapting to weather changes according to claim 1, characterized in that, The PointNet++ algorithm is used to process the point cloud data to identify the three-dimensional spatial coordinates of the positions of the road cones in the to-be-monitored road section, which are denoted as road cone coordinates based on point cloud data. For each road cone, a preset fusion strategy is used to fuse the road cone coordinates based on image data and the road cone coordinates based on point cloud data, and the fused coordinates are used as the three-dimensional spatial coordinates of the corresponding road cone. The Yolo-v5 algorithm is used to process the image data to identify the three-dimensional spatial coordinates of the positions of the construction workers in the to-be-monitored road section, which are denoted as worker coordinates based on image data. The PointNet++ algorithm is used to process the point cloud data to identify the three-dimensional spatial coordinates of the positions of the construction workers in the to-be-monitored road section, which are denoted as worker coordinates based on point cloud data.

4. The method of claim 1, wherein the method is characterized by, For each construction worker, a preset fusion strategy is used to fuse the worker coordinates based on image data and the worker coordinates based on point cloud data, and the fused coordinates are used as the three-dimensional spatial coordinates of the corresponding worker. The formula of the fusion strategy is: The fusion strategy is: Based on the change of the clarity of the same object in the image data within a preset time period, a visual positioning weight and a point cloud positioning weight are set to fuse the two coordinates, wherein the greater the clarity of the same object in the image data within the preset time period, the higher the visual positioning weight, and the lower the point cloud positioning weight.

5. The method of claim 3 or 4, wherein the method is characterized by, If the distance reaches the safety threshold, an alarm is given, which comprises the following steps: ； wherein denotes the fused coordinate; denotes the image data based coordinate to be fused; denotes the point cloud data based coordinate to be fused; denotes the visual localization weight; denotes the point cloud localization weight. 6.The highway worker hazard behavior recognition method of quickly adapting to weather changes according to claim 5, wherein, ​ ​ 7. The method of claim 1, wherein the method is characterized by, ​ If the distance reaches a safety threshold, an audible and visual alarm is activated. 8.The highway worker hazard behavior recognition method of quickly adapting to weather changes according to claim 7, characterized in that, The alarm signal is a radio signal based on LORA protocol.

Images