Rapid video tracking and locking method based on substation field plane gridding

Abstract

The invention discloses a rapid video tracking and locking method based on substation field plane gridding. The method comprises the following steps: selecting and arranging cameras; deploying a video stream transmission network; training a personnel feature multi-target tracking model, and deploying the personnel feature multi-target tracking model to a central server; predicting a possible position of a target in a current frame by using a personnel feature multi-target tracking model, and generating a candidate area around the position; matching the features of the candidate region with target features extracted from the initial frame by using a matching algorithm; a substation is divided into a plurality of grid areas, a deployment scheme of equipment is designed, and the state of the equipment is monitored in real time. According to the invention, image processing, target detection and tracking technologies are introduced, all-around, all-weather and automatic monitoring of a substation site can be realized, the requirements of a modern substation for efficient, real-time and accurate monitoring are met, the complex substation site is divided into a plurality of areas easy to manage, and optimal configuration and fine management of resources are facilitated.

Description

Technical Field

[0001] The invention relates to the technical field of video fast tracking, and in particular to a video fast tracking and locking method based on on-site plane gridding of a transformer substation. Background Art

[0002] In modern power systems, substations are the core nodes for power conversion and distribution. Their safety, stability and operating efficiency are directly related to the reliability of power supply. However, with the continuous expansion of the scale of power grids and the improvement of their intelligence level, the operating environment and monitoring requirements of substations have become increasingly complex. Traditional substation monitoring methods mainly rely on manual inspections and fixed camera monitoring modes. This method has significant technical bottlenecks and is difficult to meet the modern power grid's requirements for real-time, accuracy and efficiency.

[0003] Manual inspection was the main means of substation monitoring in the early days. Inspectors discovered problems by regularly inspecting equipment and sites. However, manual inspection has obvious defects: first, the inspection efficiency is low. Due to the number of personnel and inspection frequency, many problems may be ignored or delayed in the inspection intervals; second, the inspection is highly subjective and relies on the experience and judgment of personnel. There may be cognitive biases between different inspectors, resulting in the omission of hidden dangers; third, when responding to emergencies, manual inspection cannot achieve rapid response and cannot meet the needs of efficient and real-time problem handling.

[0004] With the development of monitoring technology, fixed cameras have gradually become an important means of auxiliary monitoring. Fixed cameras can monitor substation scenes uninterruptedly and retain historical data for analysis through video recording. However, traditional fixed camera monitoring technology still has the following problems: First, it is difficult to completely eliminate monitoring blind spots. Due to the limited installation position, viewing angle and monitoring range of the camera, there may still be blind spots in the monitoring area; second, fixed cameras lack intelligent analysis capabilities and can only provide video images, but cannot perform in-depth identification or behavior analysis of the targets in the images; third, when the monitored target moves, it is difficult for fixed cameras to continuously track the dynamics of the target, especially when the target is out of the monitoring range, which can easily cause information faults. In addition, the data transmission and processing capabilities of traditional video surveillance systems are limited. When faced with large-scale video stream data, transmission delays and analysis lags may occur.

[0005] In recent years, with the rapid development of computer vision technology, artificial intelligence algorithms and edge computing capabilities, intelligent video surveillance has gradually become a mainstream solution to solve the defects of traditional monitoring. Some video surveillance technologies based on target detection and tracking algorithms have been applied to actual scenarios. For example, deep learning models are used to detect and classify real-time targets in video streams, and multi-target tracking algorithms are combined to achieve continuous tracking of targets. However, these technologies still have some shortcomings when applied to substation monitoring. Traditional target detection algorithms may be interfered with in complex environments. For example, background clutter or target occlusion can significantly reduce the accuracy of detection. Although multi-target tracking algorithms can alleviate this problem to a certain extent, they have high requirements for computing resources and are difficult to achieve efficient computing in resource-constrained environments. In addition, these technologies usually lack scenario-based optimization, such as customized support for the characteristics of equipment distribution and abnormal behavior patterns in substation scenarios, resulting in unsatisfactory results in actual applications.

[0006] In order to solve the above problems, some studies have proposed the concept of grid management, that is, by dividing the monitoring area into several grid units, in order to achieve refined management of the target. However, the application of existing grid technology is relatively limited, mainly reflected in the following aspects: first, the grid division method is relatively static and cannot be dynamically adjusted to adapt to the real-time movement of the target and the changes in monitoring needs; second, the linkage between grid and video monitoring in the existing technology is poor, and it is impossible to achieve dynamic matching between the camera and the grid; third, grid management technology is mostly used for regional division and resource allocation, lacking in-depth integration with video target tracking technology, and it is difficult to achieve accurate positioning and seamless tracking of targets in substation scenarios.

[0007] In summary, the current substation monitoring technology has certain technical defects in terms of efficient coverage, intelligent analysis and dynamic response, mainly manifested in many monitoring blind spots, low intelligence level, insufficient data processing capabilities and poor adaptability to substation scenarios. These defects directly affect the efficiency and safety of substation monitoring, and a new solution is urgently needed to make up for the shortcomings of existing technologies. Summary of the invention

[0008] One object of the present invention is to propose a video rapid tracking and locking method based on the grid-based substation site. The present invention integrates video analysis, deep learning, grid management and multi-device collaborative technology to achieve comprehensive coverage, precise positioning and rapid response of substation monitoring, thereby effectively improving the operation management level and safety assurance capability of the substation.

[0009] A video fast tracking and locking method based on grid-based substation site plane according to an embodiment of the present invention comprises the following steps: S1, select and arrange cameras to monitor key equipment, entrances and exits, and walled areas, and associate and match cameras with segmented grids; S2. Deploy a video stream transmission network. The camera transmits the video stream to the central server. The video streaming platform service is configured on the central server to operate the received video stream and output it into a video protocol stream. S3. Train a multi-target tracking model based on personnel characteristics, deploy it on a central server, analyze the video stream obtained from the grid video surveillance system in real time, extract feature values, compare them with the pre-stored feature library, and optimize the multi-target tracking model based on the comparison results; S4, draw the overall bounding box of the substation site and the coordinate area responsible for each video device, predict the possible position of the target in the current frame using the multi-target tracking model with human features based on the position and motion information of the target in the previous frame, and generate a candidate area around the position; S5. Use a matching algorithm to match the features of the candidate area with the target features extracted from the initial frame. According to the matching results, select the best candidate area as the target position in the current frame, and share the feature results recognized by multiple devices to achieve continuous target tracking. S6. Divide the substation into multiple grid areas according to the substation site layout, equipment distribution and monitoring requirements. Assign a unique identifier to each grid area, mark it on the map, design the equipment deployment plan, and monitor the equipment status in real time.

[0010] Optionally, the S1 specifically includes: S11. Identify the specific areas that need to be monitored and understand the size, shape and key areas of the monitoring area; S12, dividing and laying out the on-site environment in geometrically proportioned grids, marking and numbering the divided on-site layout grids; S13. Clarify the purpose of monitoring and the requirements for monitoring images; S14, selecting a camera type according to the monitoring area and monitoring requirements, and calculating the required number of cameras according to the area and shape of the monitoring area and the field of view of the camera; S15. According to the monitoring requirements and environmental characteristics, the height and angle of the camera are reasonably adjusted, and the monitoring grid number set that each camera is responsible for is bound according to the monitoring area and the optimal monitoring range of the camera; S16, installing the camera according to the predetermined installation position; S17. After the installation is completed, configure and test the monitoring system parameters.

[0011] Optionally, the key areas mainly include: entrances, exits, and dangerous construction areas.

[0012] Optionally, the camera types include: for short-distance monitoring, selecting a hemispherical camera or an infrared integrated camera; for medium- and long-distance monitoring, selecting a gun-type camera or a ball camera.

[0013] Optionally, the parameter configuration and testing include: camera resolution and frame rate, camera viewing angle and focal length, and test system stability and picture quality.

[0014] Optionally, the S3 specifically includes: S31, the monitoring terminal or video streaming media provides a video stream in RTSP protocol; S32, the data processing unit accesses the standard video stream, and extracts the video frame images according to the configured recognition speed parameters and the rules; S33, using a convolutional neural network to extract pedestrian-related features from the preprocessed image, input the image into the network, and obtain a series of feature maps containing image semantic information and spatial structure through multi-layer convolution, pooling and other operations; S34, using the labeled personnel data set to train the personnel feature multi-target tracking model; S35, using the personnel feature multi-target tracking model to detect pedestrians, and output position information, and further adjust the position and size of the bounding box according to the bounding box regression operation; S36. Evaluate the detection results, including detection accuracy, recall rate, and false positive rate indicators, and optimize the model based on the evaluation results.

[0015] Optionally, the candidate region is generated in a manner that depends on a prediction result and a search strategy of a personnel feature multi-target tracking model.

[0016] Optionally, the matching algorithm includes: cosine similarity based on similarity measurement, and a classifier based on machine learning.

[0017] Optionally, S6 also includes: when an abnormal target is detected, the grid where the target is located will be automatically locked; when the target moves to an adjacent grid, the system will automatically dispatch the camera of the adjacent grid for relay tracking. The system will also predict its possible future position based on the target's movement trajectory and speed, and adjust the camera's viewing angle and focal length in advance.

[0018] Optionally, the steps also include: using machine learning algorithms to analyze and learn the fused data, identify abnormal behavior patterns, and monitor the target's behavior in real time; designing an alarm mechanism, and selecting an alarm method and alarm level based on the severity and urgency of the abnormal behavior; recording and processing the triggered alarm information, and promptly feeding back the alarm information to relevant personnel for processing and response.

[0019] The beneficial effects of the present invention specifically include: Grid positioning divides the space into multiple grid units to achieve accurate tracking and positioning of the target object. This positioning method can still maintain high accuracy in complex environments, which helps to improve the overall performance of the system. Grid positioning is usually combined with a real-time monitoring system to provide instant feedback on the location information of the target object, which helps to quickly respond to abnormal situations.

[0020] Through grid management, resources can be reasonably allocated and dispatched to avoid waste and duplication of resources. For example, in substation management, inspection and maintenance plans can be arranged according to the actual situation of equipment in the grid to improve work efficiency. Once an abnormal situation occurs, grid positioning can quickly determine the location and scope of the abnormality, providing strong support for subsequent troubleshooting and processing, thereby shortening the fault processing time.

[0021] The construction and deployment of a grid positioning system requires a certain amount of initial investment, including the cost of hardware equipment, software systems, and system integration. However, as the technology continues to mature and become more popular, these costs are gradually decreasing. In the long run, grid positioning can improve the operating efficiency and reliability of the system, reduce the probability of failure and maintenance costs, and thus bring significant long-term benefits.

[0022] The grid positioning system has good scalability, and the grid can be divided and adjusted according to actual needs to adapt to different scenarios and application requirements. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 The invention proposes a video fast tracking and locking method based on the grid-based substation site plan.

[0024] Figure 2 This is a structural block diagram of the training and real-time analysis of a personnel feature multi-target tracking model for a video fast tracking and locking method based on plane gridding of a substation site proposed by the present invention. DETAILED DESCRIPTION

[0025] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0026] refer to Figure 1 , a video fast tracking and locking method based on the grid-based substation site plane, comprising the following steps: S1, select and arrange cameras to monitor key equipment, entrances and exits, and walled areas, and associate and match cameras with segmented grids; S2. Deploy a video stream transmission network. The camera transmits the video stream to the central server. The video streaming platform service is configured on the central server to operate the received video stream and output it into a video protocol stream. S3. Train a multi-target tracking model based on personnel characteristics, deploy it on a central server, analyze the video stream obtained from the grid video surveillance system in real time, extract feature values, compare them with the pre-stored feature library, and optimize the multi-target tracking model based on the comparison results; S4, draw the overall bounding box of the substation site and the coordinate area responsible for each video device, predict the possible position of the target in the current frame using the multi-target tracking model with human features based on the position and motion information of the target in the previous frame, and generate a candidate area around the position; S5. Use a matching algorithm to match the features of the candidate area with the target features extracted from the initial frame. According to the matching results, select the best candidate area as the target position in the current frame, and share the feature results recognized by multiple devices to achieve continuous target tracking. S6. Divide the substation into multiple grid areas according to the substation site layout, equipment distribution and monitoring requirements. Assign a unique identifier to each grid area, mark it on the map, design the equipment deployment plan, and monitor the equipment status in real time.

[0027] In this implementation, S1 specifically includes: S11. Identify the specific areas that need to be monitored and understand the size, shape and key areas of the monitoring area; S12, dividing and laying out the on-site environment in geometrically proportioned grids, marking and numbering the divided on-site layout grids; S13. Clarify the purpose of monitoring and the requirements for monitoring images; S14, selecting a camera type according to the monitoring area and monitoring requirements, and calculating the required number of cameras according to the area and shape of the monitoring area and the field of view of the camera; S15. According to the monitoring requirements and environmental characteristics, the height and angle of the camera are reasonably adjusted, and the monitoring grid number set that each camera is responsible for is bound according to the monitoring area and the optimal monitoring range of the camera; S16, installing the camera according to the predetermined installation position; S17. After the installation is completed, configure and test the monitoring system parameters.

[0028] In this implementation manner, the key areas mainly include: entrances, exits, and dangerous construction areas.

[0029] In this embodiment, the camera types include: for short-distance monitoring, a hemispherical camera or an infrared integrated camera is selected; for medium- and long-distance monitoring, a gun-type camera or a ball camera is selected.

[0030] In this implementation, the parameter configuration and testing include: the resolution and frame rate of the camera, the viewing angle and focal length of the camera, and the stability and picture quality of the test system.

[0031] In this implementation, S3 specifically includes: S31, the monitoring terminal or video streaming media provides a video stream in RTSP protocol; S32, the data processing unit accesses the standard video stream, and extracts the video frame images according to the configured recognition speed parameters and the rules; S33, using a convolutional neural network to extract pedestrian-related features from the preprocessed image, input the image into the network, and obtain a series of feature maps containing image semantic information and spatial structure through multi-layer convolution, pooling and other operations; S34, using the labeled personnel data set to train the personnel feature multi-target tracking model; S35, using the personnel feature multi-target tracking model to detect pedestrians, and output position information, and further adjust the position and size of the bounding box according to the bounding box regression operation; S36. Evaluate the detection results, including detection accuracy, recall rate, and false positive rate indicators, and optimize the model based on the evaluation results.

[0032] In this implementation manner, the candidate region is generated in a manner that depends on the prediction results and search strategy of the personnel feature multi-target tracking model.

[0033] In this implementation, the matching algorithm includes: cosine similarity based on similarity measurement, and a classifier based on machine learning.

[0034] In this embodiment, S6 also includes: when an abnormal target is detected, the grid where the target is located will be automatically locked; when the target moves to an adjacent grid, the system will automatically dispatch the camera of the adjacent grid for relay tracking. The system will also predict its possible future position based on the target's movement trajectory and speed, and adjust the camera's viewing angle and focal length in advance.

[0035] In this embodiment, the steps also include: using machine learning algorithms to analyze and learn the fused data, identify abnormal behavior patterns, and monitor the target's behavior in real time; designing an alarm mechanism, selecting an alarm method and alarm level based on the severity and urgency of the abnormal behavior; recording and processing the triggered alarm information, and promptly feeding back the alarm information to relevant personnel for processing and response. Example

[0036] This embodiment demonstrates a video fast tracking and locking method based on the grid-based substation site plan.

[0037] A large substation is located in a densely populated urban area and undertakes important power transmission tasks. With the advancement of urban construction, activities around the substation are frequent, personnel mobility is high, and the pressure on security management is increasing. In particular, at the entrance, exit and some construction areas of the substation, there have been many incidents of unauthorized entry, and even safety accidents caused by equipment theft and irregular construction. The existing video surveillance system is difficult to meet actual needs due to the lack of refined management and rapid response mechanism. For example, the layout of the camera is unreasonable and there are blind spots; video analysis relies on manual operation and is inefficient; the ability to continuously track the target has not been formed, resulting in difficulties in obtaining evidence afterwards. To this end, the substation introduced a video fast tracking and locking method based on on-site plane gridding to comprehensively improve the level of security management.

[0038] During the renovation process, the technical team first conducted detailed measurements and assessments of the actual site of the substation, and divided the site into multiple grid areas in equal proportions, with each grid area marked with a unique number. After the monitoring area was divided, the appropriate camera model was selected. For short-distance monitoring needs, hemispherical cameras and infrared integrated cameras were deployed to cover the entrance and exit areas; for medium and long-distance monitoring needs, dome cameras and gun cameras were deployed to cover walls and dangerous construction areas. After the camera was installed, the video stream was transmitted to the central server through the network, and a streaming media service was configured on the server to support real-time transmission and protocol conversion.

[0039] In order to solve the problem of fast tracking of multiple targets, the team used a pre-labeled personnel feature dataset to train the multi-target tracking model offline. After training, the model was deployed to the central server for real-time processing of video streams from the camera. In actual operation, when the system detects that an unauthorized person has entered a dangerous area, it immediately generates a bounding box for the target and predicts its next position based on the target's motion trajectory. At the same time, the camera automatically adjusts the viewing angle and focal length to achieve seamless relay tracking of the target. If the target behaves abnormally (such as staying for a long time or trying to touch the device), the system will trigger an alarm mechanism and notify the security personnel by text message and phone call. The test results are shown in Table 1.

[0040] Table 1 Performance comparison before and after the introduction of the method Before the renovation, due to the unreasonable layout of cameras, the blind area coverage rate was as high as 15%, resulting in some areas being in a state of long-term monitoring vacuum. After the renovation, by scientifically dividing the grid area and rationally arranging the cameras, the blind area coverage rate was reduced to 0%, achieving all-round monitoring without blind spots. This change has significantly improved the safety assurance capability of the substation.

[0041] Before the transformation, the system's recognition rate for unauthorized targets was only 65%, mainly due to insufficient camera resolution and limited back-end video processing capabilities. After the transformation, the system used a multi-target tracking model based on human characteristics and combined it with a high-resolution camera, increasing the recognition rate to 95%. This improvement provides technical support for the rapid identification of potential threats.

[0042] Before the transformation, due to the lack of an effective tracking mechanism, the target tracking loss rate reached 40%. After the transformation, by introducing the candidate region generation algorithm and multi-target tracking model, the loss rate dropped significantly to 5%, achieving continuous tracking of the target. This makes the monitoring of target behavior in complex scenarios more stable and reliable.

[0043] Before the transformation, the alarm response time was heavily dependent on manual processing, and it took an average of 5 minutes to complete alarm confirmation and response, which delayed the opportunity to quickly respond to emergencies. After the transformation, the system realized automatic analysis and alarm functions, and the response time was shortened to 20 seconds, an increase of 15 times. This efficient response mechanism has greatly enhanced the efficiency of handling security incidents in actual operation.

[0044] Before the transformation, there were about 10 unauthorized intrusion incidents each year, mainly due to the existing system's insufficient detection and tracking capabilities for unauthorized targets. After the transformation, through the combination of target locking and real-time alarm mechanisms, no similar incidents occurred within a year, indicating that the improvement of the system has effectively reduced security risks.

[0045] Before the transformation, the system was down for an average of about 2 hours per week, which affected the continuity of monitoring. After the transformation, by optimizing the system architecture and deploying stable software and hardware solutions, the system availability was improved to 99.99%, ensuring long-term uninterrupted operation. This high stability provides a solid technical guarantee for daily monitoring and emergency handling.

[0046] In summary, the transformed system has been significantly improved in terms of monitoring blind area coverage, target identification and tracking capabilities, alarm response efficiency, system stability, etc. This not only solves the problems existing in the original system, but also effectively reduces the safety management cost of the substation, improves the prevention capability and handling efficiency of safety incidents, and provides a practical solution for reference for similar scenarios.

Claims

1. A video fast tracking and locking method based on the grid-based substation site, characterized in that: The steps include: S1, select and arrange cameras to monitor key equipment, entrances and exits, and walled areas, and associate and match cameras with segmented grids; S2. Deploy a video stream transmission network. The camera transmits the video stream to the central server. The video streaming platform service is configured on the central server to operate the received video stream and output it into a video protocol stream. S3. Train a multi-target tracking model based on personnel characteristics, deploy it on a central server, analyze the video stream obtained from the grid video surveillance system in real time, extract feature values, compare them with the pre-stored feature library, and optimize the multi-target tracking model based on the comparison results; S4, draw the overall bounding box of the substation site and the coordinate area responsible for each video device, predict the possible position of the target in the current frame using the multi-target tracking model with human features based on the position and motion information of the target in the previous frame, and generate a candidate area around the position; S5. Use a matching algorithm to match the features of the candidate area with the target features extracted from the initial frame. According to the matching results, select the best candidate area as the target position in the current frame, and share the feature results recognized by multiple devices to achieve continuous target tracking. S6. Divide the substation into multiple grid areas according to the substation site layout, equipment distribution and monitoring requirements. Assign a unique identifier to each grid area, mark it on the map, design the equipment deployment plan, and monitor the equipment status in real time.

2. The video fast tracking and locking method based on the grid-based substation site plan according to claim 1 is characterized in that: The S1 specifically includes: S11. Identify the specific areas that need to be monitored and understand the size, shape and key areas of the monitoring area; S12, dividing and laying out the on-site environment in geometrically proportioned grids, marking and numbering the divided on-site layout grids; S13. Clarify the purpose of monitoring and the requirements for monitoring images; S14, selecting a camera type according to the monitoring area and monitoring requirements, and calculating the required number of cameras according to the area and shape of the monitoring area and the field of view of the camera; S15. According to the monitoring requirements and environmental characteristics, the height and angle of the camera are reasonably adjusted, and the monitoring grid number set that each camera is responsible for is bound according to the monitoring area and the optimal monitoring range of the camera; S16, installing the camera according to the predetermined installation position; S17. After the installation is completed, configure and test the monitoring system parameters.

3. The video fast tracking and locking method based on the grid-based substation site plan according to claim 2 is characterized in that: The key areas mainly include: entrance; exit; dangerous construction area.

4. The video fast tracking and locking method based on the grid-based substation site plan according to claim 2 is characterized in that: The camera types include: for short-distance monitoring, select a hemispherical camera or an infrared integrated camera; for medium- and long-distance monitoring, select a gun-type camera or a ball camera.

5. The video fast tracking and locking method based on the grid-based substation site plan according to claim 2 is characterized in that: The parameter configuration and testing include: the resolution and frame rate of the camera, the viewing angle and focal length of the camera, the stability of the test system and the picture quality.

6. The video fast tracking and locking method based on the grid-based substation site plan according to claim 1 is characterized in that: The S3 specifically includes: S31, the monitoring terminal or video streaming media provides a video stream in RTSP protocol; S32, the data processing unit accesses the standard video stream, and extracts the video frame images according to the configured recognition speed parameters and the rules; S33, using a convolutional neural network to extract pedestrian-related features from the preprocessed image, input the image into the network, and obtain a series of feature maps containing image semantic information and spatial structure through multi-layer convolution, pooling and other operations; S34, using the labeled personnel data set to train the personnel feature multi-target tracking model; S35, using the personnel feature multi-target tracking model to detect pedestrians, and output position information, and further adjust the position and size of the bounding box according to the bounding box regression operation; S36. Evaluate the detection results, including detection accuracy, recall rate, and false positive rate indicators, and optimize the model based on the evaluation results.

7. The video fast tracking and locking method based on the grid-based substation site plan according to claim 1 is characterized in that: The generation method of the candidate area depends on the prediction result and search strategy of the personnel feature multi-target tracking model.

8. The video fast tracking and locking method based on the grid-based substation site plan according to claim 1 is characterized in that: The matching algorithm includes: cosine similarity based on similarity measurement and a classifier based on machine learning.

9. The video fast tracking and locking method based on the grid-based substation site plan according to claim 1 is characterized in that: The S6 also includes: when an abnormal target is detected, the grid where the target is located will be automatically locked; when the target moves to an adjacent grid, the system will automatically dispatch the camera of the adjacent grid to relay tracking. The system will also predict its possible future position based on the target's movement trajectory and speed, and adjust the camera's viewing angle and focal length in advance.

10. The video fast tracking and locking method based on the grid-based substation site plan according to claim 1 is characterized in that: The steps also include: using machine learning algorithms to analyze and learn the fused data, identify abnormal behavior patterns, and monitor the target's behavior in real time; designing an alarm mechanism, selecting an alarm method and alarm level based on the severity and urgency of the abnormal behavior; recording and processing the triggered alarm information, and promptly feeding back the alarm information to relevant personnel for processing and response.

Images