Drowning monitoring method and device for reservoirs, rivers and lakes and medium

Abstract

The invention discloses a drowning monitoring method and device for a reservoir, a river and a lake and a medium, and relates to the field of river, lake and reservoir monitoring, and the method comprises the steps: determining a target smart rod pre-arranged in a target water area, and associating and verifying the monitoring device configured in the target smart rod; collecting video data of the target water area in real time through monitoring equipment; identifying personnel actions in the video data through a trained neural network model, and obtaining an identification result output by the neural network model; and determining a drowning risk event in the video data according to an identification result, and giving an alarm through the monitoring equipment based on an alarm rule corresponding to the drowning risk event. The target water area is monitored in real time through the intelligent rod, the drowning risk event is automatically identified through the neural network model, and the early warning capability of the drowning accident can be effectively improved.

Description

Technical Field

[0001] The present application relates to the technical field of river, lake and reservoir monitoring, and specifically to a drowning monitoring method, equipment and medium for reservoirs, rivers and lakes. Background Art

[0002] With the development of society and the improvement of people's living standards, water activities are increasing, and the frequency of drowning accidents is also increasing. Reservoirs, rivers, lakes and other waters are high-incidence areas for drowning accidents, especially in summer and holidays, when there are many tourists and the risk of drowning increases. In order to protect people's lives and reduce the occurrence of drowning accidents, the society's demand for anti-drowning measures is becoming increasingly urgent.

[0003] The traditional method of anti-drowning monitoring in reservoirs, rivers and lakes mainly relies on staff inspections. This method requires a lot of manpower costs and is easily limited by time, weather and other factors. It is difficult to achieve all-weather and all-round monitoring. In addition, staff may not be able to cover all potential danger areas, resulting in monitoring blind spots, which increases the risk of drowning accidents. Summary of the invention

[0004] In order to solve the above problems, this application proposes a drowning monitoring method for reservoirs, rivers and lakes, including:

[0005] Determine the target smart pole pre-deployed in the target waters, and associate and verify the monitoring equipment configured in the target smart pole;

[0006] By means of the monitoring device, video data of the target water area is collected in real time;

[0007] Recognize the actions of people in the video data by using a trained neural network model, and obtain a recognition result output by the neural network model;

[0008] According to the recognition result, a drowning risk event present in the video data is determined, and based on an alarm rule corresponding to the drowning risk event, an alarm is issued through the monitoring device.

[0009] On the other hand, the present application also proposes a drowning monitoring device for reservoirs, rivers and lakes, comprising:

[0010] at least one processor; and,

[0011] a memory communicatively connected to the at least one processor; wherein,

[0012] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a drowning monitoring method for reservoirs, rivers and lakes as described in the above example.

[0013] On the other hand, the present application also proposes a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as: a drowning monitoring method for reservoirs, rivers and lakes as described in the above example.

[0014] The present application proposes a drowning monitoring method for reservoirs, rivers and lakes, which can bring the following beneficial effects:

[0015] Through real-time monitoring of the target waters by the smart pole and automatic identification of drowning risk events through a neural network model, the early warning capability of drowning accidents can be effectively improved. Combining the real-time monitoring function of the smart pole with the alarm mechanism can greatly shorten the response time to drowning or other emergencies and improve rescue efficiency.

[0016] The smart pole system can effectively replace some manual inspection tasks and reduce labor costs through automated real-time monitoring. At the same time, the system can run 24 hours a day, reducing the workload of monitoring personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0018] Figure 1 A schematic diagram of a drowning monitoring method for reservoirs, rivers and lakes in an embodiment of the present application;

[0019] Figure 2 This is a schematic diagram of a drowning monitoring device for reservoirs, rivers and lakes in an embodiment of the present application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0021] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0022] It should be noted that with the rapid development of the Internet of Things, big data and artificial intelligence technologies, smart poles have become an important part of smart water conservancy construction. Smart poles usually include multiple sensors, data acquisition and processing systems, wireless communication modules and other components. By combining with information applications such as drowning prevention, they can form electronic archives, closed-loop management processes and visual statistical analysis results displays, providing technical support and decision-making support for drowning prevention management in reservoirs, rivers and lakes.

[0023] The anti-drowning dynamic sensing smart pole integrates intelligent perception, data analysis and real-time response. Through scientific and advanced front-end sensing equipment and intelligent technical prevention technology, it can patrol dangerous waters around the clock and identify relevant scenes in dangerous waters in real time. It can provide more effective supervision means for water management departments and improve the effectiveness of anti-drowning monitoring. The anti-drowning alarm system uses advanced artificial intelligence algorithms, combined with high-definition cameras, water monitoring equipment and other technical means to achieve real-time monitoring and analysis of waters. The system can automatically identify AI scenes and send out early warning signals at the first time to notify nearby personnel to take emergency rescue measures.

[0024] like Figure 1 As shown, the embodiment of the present application provides a drowning monitoring method for reservoirs, rivers and lakes, including:

[0025] S101: Determine a target smart pole pre-deployed in a target water area, and associate and verify the monitoring equipment configured in the target smart pole.

[0026] Specifically, multiple smart poles are pre-deployed in rivers, lakes and reservoirs, each of which is used to monitor a designated water area, determine the target smart pole pre-deployed in the target water area, obtain the monitoring equipment configured in the target smart pole, and associate and verify the monitoring equipment. The monitoring equipment includes video equipment, sound column equipment, help equipment and alarm equipment.

[0027] Furthermore, after the installation of the smart pole and the monitoring device is completed, each device is identified and encoded, and the parameters of each device are configured based on the device code, including device type, monitoring parameters, sampling frequency, data transmission method, etc., to establish an association relationship between the smart pole and the monitoring device, and perform communication tests to verify whether each monitoring device can communicate normally.

[0028] Among them, the video recording equipment is used to collect dynamic images of the target water area in real time, record changes in the water area, personnel activities and any abnormal situations; the sound column equipment amplifies and broadcasts the received audio signals to achieve sound propagation and coverage. When a high-risk drowning incident is detected, the sound column equipment quickly plays an alarm or notification message to ensure that relevant personnel can receive and take action in time; the help-seeking equipment is used to call relevant units and persons in charge for rescue. If personnel accidentally fall into the water or encounter other emergencies, they can send a help-seeking signal to the management personnel or rescue team through the help-seeking equipment to ensure that they can get rescue in time; the role of the alarm equipment is to issue a warning in time when potential dangers or abnormal situations are detected so that management personnel can quickly take rescue measures.

[0029] Before determining the target smart poles to be pre-deployed in the target waters, it is necessary to deploy multiple smart poles based on the information of rivers, lakes and reservoirs. Specifically, obtain the geographical location information of the reservoirs, rivers and lakes, divide the reservoirs, rivers and lakes into multiple monitoring waters according to the geographical location information, and pre-deploy a corresponding number of smart poles based on the monitoring waters, and specify the corresponding monitoring waters for monitoring through the smart poles.

[0030] Among them, the geographical location information includes the longitude and latitude information and water characteristics of rivers, lakes and reservoirs. The water characteristics include the natural characteristics of the water area, shape, depth, flow rate, and the topography and vegetation coverage around the water area. According to the water characteristics, the large water area is divided into multiple small areas to ensure that the monitoring coverage of each area is reasonable. The deployment location of the smart pole is determined according to the surrounding environment and behavioral characteristics of the reservoirs, rivers and lakes, such as the activities of people, such as the density, type and regularity of human activities, to ensure that each monitored water area can be effectively monitored by at least one smart pole.

[0031] S102: Collect video data of the target water area in real time through the monitoring device.

[0032] Specifically, through the recording device installed in the smart pole, the recording angle of the recording device is rotated within a preset time interval to collect video data of different areas in the target waters in real time. By automatically rotating the recording device, continuous monitoring of multiple areas in the target waters can be achieved without manually adjusting the device angle, so that it can cover a wider area, thereby improving the monitoring coverage.

[0033] S103: recognizing the actions of people in the video data using a trained neural network model, and obtaining a recognition result output by the neural network model.

[0034] Specifically, the video data is decomposed into continuous frame images and input into a trained neural network model. The temporal characteristics and spatial characteristics of people in the continuous frame images are extracted through the trained neural network model. Based on the temporal characteristics and the spatial characteristics, the predicted drowning risk events appearing in the continuous frame images are identified and output.

[0035] Among them, temporal features refer to attributes that change over time, such as a person's movement trajectory, speed changes, etc.; spatial features refer to a person's position, posture, and relative relationship with the surrounding environment at a certain moment. By analyzing the extracted temporal and spatial features, the neural network model will try to identify whether there are events that may indicate drowning, including abnormal behavior of people (such as sudden sinking, struggling, head down for a long time, etc.), position changes (such as moving away from a safe area, entering a deep water area, etc.), or unusual interactions with the surrounding environment (such as no other swimmers around, rescue equipment is not nearby, etc.).

[0036] Before using the neural network model, it is necessary to build and train the neural network model. Specifically, historical video data of the target waters is obtained, the historical video data is decomposed into multiple historical continuous frame image sets, the historical continuous frame image sets are preprocessed, the preprocessed historical continuous frame image sets are divided into a training set and a verification set, a neural network model is built based on a preset neural network, the training set is input into the neural network model, the neural network model is trained, and the trained neural network model is verified through the verification set.

[0037] In an embodiment of the present application, a convolutional neural network and a long short-term memory network are combined to construct a neural network model. The convolutional neural network can automatically learn useful spatial features from video frames, and the long short-term memory network can capture long-term dependencies. The obtained neural network model can use the convolutional neural network to extract spatial features in video frames, and then use the long short-term memory network to process the temporal relationship between frames to identify drowning behavior.

[0038] Furthermore, based on preset drowning risk event types, corresponding type labels are added to the preprocessed historical continuous frame image set. The drowning risk event types include water operation events (for example, fishermen, water athletes, water construction workers, etc. performing water operations), waterside activity events (such as playing in the water, fishing, etc.), and water play (such as swimming, water fights, etc.) events; based on the type labels, the historical continuous frame image set is divided into a training set and a validation set.

[0039] Furthermore, the training set is input into the neural network model. Through the neural network model, the temporal and spatial characteristics of the personnel actions in the training set are extracted. Based on the temporal and spatial characteristics, the dynamic events appearing in the training set are identified and output. According to the type label corresponding to the training set, the loss function of the dynamic event is obtained, and the model parameters of the neural network model are adjusted based on the loss function.

[0040] S104: Determine the drowning risk event present in the video data according to the recognition result, and issue an alarm through the monitoring device based on an alarm rule corresponding to the drowning risk event.

[0041] Specifically, according to the event type corresponding to the drowning risk event, the alarm rule corresponding to the drowning risk event is called, an alarm instruction is generated based on the alarm rule, the alarm instruction is sent to the monitoring device, and the monitoring device executes the alarm based on the alarm instruction.

[0042] Through real-time monitoring of the target waters by the smart pole and automatic identification of drowning risk events through a neural network model, the early warning capability of drowning accidents can be effectively improved. Combining the real-time monitoring function of the smart pole with the alarm mechanism can greatly shorten the response time to drowning or other emergencies and improve rescue efficiency.

[0043] The smart pole system can effectively replace some manual inspection tasks and reduce labor costs through automated real-time monitoring. At the same time, the system can run 24 hours a day, reducing the workload of monitoring personnel.

[0044] like Figure 2 As shown, the embodiment of the present application also proposes a drowning monitoring device for reservoirs, rivers and lakes, including:

[0045] at least one processor; and,

[0046] a memory communicatively connected to the at least one processor; wherein,

[0047] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a drowning monitoring method for reservoirs, rivers and lakes as described in any of the above embodiments.

[0048] An embodiment of the present application also provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to be: a drowning monitoring method for reservoirs, rivers and lakes as described in any of the above embodiments.

[0049] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0050] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0051] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0053] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0055] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0056] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0057] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0058] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0059] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A drowning monitoring method for reservoirs, rivers and lakes, characterized in that: include: Determine the target smart pole pre-deployed in the target waters, and associate and verify the monitoring equipment configured in the target smart pole; By means of the monitoring device, video data of the target water area is collected in real time; Recognize the actions of people in the video data by using a trained neural network model, and obtain a recognition result output by the neural network model; According to the recognition result, a drowning risk event present in the video data is determined, and based on an alarm rule corresponding to the drowning risk event, an alarm is issued through the monitoring device.

2. A drowning monitoring method for reservoirs, rivers and lakes according to claim 1, characterized in that: Before identifying the actions of people in the video data by using the trained neural network model, the method further includes: Acquire historical video data of the target water area, and decompose the historical video data into a plurality of historical continuous frame image sets; Preprocessing the historical continuous frame image set, and dividing the preprocessed historical continuous frame image set into a training set and a verification set; Build a neural network model based on a preset neural network; The training set is input into the neural network model to train the neural network model, and the trained neural network model is verified by the verification set.

3. A drowning monitoring method for reservoirs, rivers and lakes according to claim 2, characterized in that: The division of the preprocessed historical continuous frame image set into a training set and a verification set specifically includes: Based on the preset drowning risk event types, adding corresponding type labels to the preprocessed historical continuous frame image set; the drowning risk event types include water operation events, waterside activity events, and water play events; Based on the type label, the historical continuous frame image set is divided into a training set and a validation set.

4. A drowning monitoring method for reservoirs, rivers and lakes according to claim 3, characterized in that: Inputting the training set into the neural network model to train the neural network model specifically includes: The training set is input into the neural network model, and the time characteristics and spatial characteristics of the actions of the personnel in the training set are extracted through the neural network model. Based on the time characteristics and spatial characteristics, dynamic events appearing in the training set are identified, and the dynamic events are output; According to the type label corresponding to the training set, a loss function of the dynamic event is obtained, and model parameters of the neural network model are adjusted based on the loss function.

5. A drowning monitoring method for reservoirs, rivers and lakes according to claim 4, characterized in that: The identifying the actions of the personnel in the video data by using the trained neural network model and obtaining the identification result output by the neural network model specifically includes: Decomposing the video data into continuous frame images and inputting them into a trained neural network model; The trained neural network model is used to extract the temporal characteristics and spatial characteristics of the persons in the continuous frame images, and based on the temporal characteristics and the spatial characteristics, the predicted drowning risk events appearing in the continuous frame images are identified, and the predicted drowning risk events are output.

6. A drowning monitoring method for reservoirs, rivers and lakes according to claim 1, characterized in that: The step of issuing an alarm through the monitoring device based on the alarm rule corresponding to the drowning risk event specifically includes: According to the event type corresponding to the drowning risk event, calling the alarm rule corresponding to the drowning risk event, generating an alarm instruction based on the alarm rule, and sending the alarm instruction to the monitoring device; The monitoring device executes an alarm based on the alarm instruction.

7. A drowning monitoring method for reservoirs, rivers and lakes according to claim 1, characterized in that: The associating and verifying the monitoring device configured in the target smart pole specifically includes: According to the water characteristics and monitoring requirements of the target water area, the monitoring equipment required to be configured in the target smart pole is determined; the monitoring equipment includes video recording equipment, sound column equipment, help equipment and alarm equipment; Based on the device code corresponding to the monitoring device, the monitoring device is associated, and communication verification is performed on the associated monitoring device.

8. A drowning monitoring method for reservoirs, rivers and lakes according to claim 1, characterized in that: Before determining the target smart poles pre-deployed in the target water area, the method further includes: Obtaining geographical location information of reservoirs, rivers and lakes, and dividing the reservoirs, rivers and lakes into a plurality of monitoring water areas according to the geographical location information; Based on the monitored water area, a corresponding number of smart poles are deployed in advance, and the corresponding monitored water area is designated to be monitored through the smart poles.

9. A drowning monitoring device for reservoirs, rivers and lakes, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute a drowning monitoring method for reservoirs, rivers and lakes as described in any one of claims 1 to 8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are set to: a drowning monitoring method for reservoirs, rivers and lakes as described in any one of claims 1 to 8.

Images