Unmanned ship electric control system based on multi-source data

Abstract

The invention relates to the technical field of unmanned surface vehicle control, in particular to an unmanned surface vehicle electric control system based on multi-source data, which is provided with an electric control monitoring module, a wide area monitoring unit of the electric control monitoring module acquires monitoring data and determines a dynamic disturbance value and a characteristic distribution value, and an attention monitoring unit responds to a judgment result of an electric control adjusting module and controls the electric control monitoring module. The method comprises the steps of determining a ripple characterization value and a bubble characteristic value of an attention area, calculating an abnormal risk value of a sub-target area through an electric control adjustment module, dividing the attention area, judging whether an attention monitoring unit needs to be started or not, and calculating a drowning characterization coefficient in response to the starting state of the attention monitoring unit through an electric control analysis module. According to the method, drowning monitoring can be carried out on a large area on the premise that the computing power is saved, the unmanned surface vehicle can be rapidly deployed, and the drowning monitoring efficiency and the unmanned surface vehicle deployment efficiency are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned boat control, and particularly to an electric control system for an unmanned boat based on multi-source data. Background Art

[0002] When an unmanned boat sails in a complex and changeable water environment, it needs to have an accurate and comprehensive perception of the surrounding environment. With the development of automatic control technology, some unmanned boats can already achieve automatic navigation to the target location through the electric control system. Currently, unmanned boats have broad application prospects, especially in the water rescue field, combined with a drowning monitoring system, they can quickly deploy unmanned boats to improve safety.

[0003] Chinese Patent Publication No.: CN118395347A, discloses a method and system for unmanned boat task decision-making based on multi-source data. The method specifically includes: collecting the operation information of the unmanned boat; evaluating the health status of the unmanned boat according to the operation information to obtain a health status evaluation result; establishing a decision-making library according to the health status evaluation result and the task decision corresponding to the health status evaluation result; and performing task decision-making on the to-be-decided unmanned boat through the decision-making library. This invention can solve the problem of instruction conflict when the unmanned boat executes tasks, ensure the safety of the unmanned boat itself, and improve the decision-making speed.

[0004] Chinese Patent Publication No.: CN119088004A, discloses an intelligent all-weather autonomous cruise unmanned rescue boat and its rescue electric control method. The intelligent all-weather autonomous cruise unmanned rescue boat includes a boat body and a multi-source energy supply system, an environment and target perception system, an intelligent electric control system, a propulsion system, a satellite positioning system, and an autonomous navigation system thereon. The rescue boat can independently obtain environmental data and information of drowning victims, and dynamically plan the optimal cruise route through a deep reinforcement learning algorithm. The intelligent electric control system is responsible for electric control cruise, identifying drowning victims, generating rescue strategies, and executing rescue tasks. After the rescue is completed, the system will automatically re-plan the cruise route to continue the task. This design realizes all-weather and fully autonomous water cruise and rescue, significantly improves the rescue coverage and efficiency, reduces manpower consumption and safety risks, shortens the rescue response time, improves the rescue success rate, and especially significantly improves the rescue ability in complex environments.

[0005] However, the following problems still exist in the prior art. When monitoring for drowning in a large area, usually high-precision video data is required, and the data to be analyzed is massive. The prior art does not consider the abnormal tendencies in different regions and thus does not adjust the monitoring resources and analysis methods accordingly. The computing power consumption during the monitoring process is high and the accuracy is not good. Summary of the Invention

[0006] To this end, the present invention provides an unmanned boat electric control system based on multi-source data to solve the problems in actual situations that when monitoring drowning in a large area, high-precision video data is usually required, and the data to be analyzed is massive. The prior art does not consider the abnormal tendencies in different regions and thus does not adjust the monitoring resources and analysis methods accordingly. The computing power consumption during the monitoring process is high and the accuracy is poor.

[0007] To achieve the above object, the present invention provides an unmanned boat electric control system based on multi-source data, which includes: An electric control monitoring module, which includes a wide-area monitoring unit and an attention monitoring unit. The wide-area monitoring unit is used to obtain the monitoring data of the target area and determine the dynamic disturbance index based on the basic motion characteristics of the moving targets in each sub-target area. The attention monitoring unit is used to respond to the determination result of the electric control adjustment module, adjust the monitoring direction to obtain the monitoring data of the attention area, and determine the ripple characterization value and the bubble characteristic value of the attention area; An electric control adjustment module, which is connected to the electric control monitoring module, calculates the abnormal risk value of the sub-target area based on the dynamic disturbance index, determines several attention areas, and controls the attention monitoring unit; An electric control analysis module, which is connected to the electric control monitoring module, in response to the startup state of the attention monitoring unit, calculates the drowning characterization coefficient based on the ripple characterization value and the bubble characteristic value, determines the drowning state of the area, and judges whether a warning signal needs to be issued; An electric control rescue module, which is connected to the electric control analysis module, is used to judge whether to control the unmanned boat to implement rescue based on the warning signal emission state and determine the rescue method.

[0008] Further, the electric control monitoring module is used to determine the dynamic disturbance index based on the basic motion characteristics of the moving targets in each sub-target area, including: To determine the basic motion characteristics of the moving targets in the sub-target area, including the moving speed of the center of the moving target and the contour area of the moving target; To use the absolute variance of the moving speed of the center of the moving target at each moment as the moving speed dynamic disturbance index; To use the absolute variance of the contour area of the moving target at each moment as the contour area dynamic disturbance index.

[0009] Further, the electric control monitoring module determines the ripple characterization value and the bubble characteristic value of the attention area, including: To identify the frequency of ripple appearance within the reference time of the attention area and determine the frequency as the ripple characterization value; To determine the difference in the contour lengths of continuous bubbles; To determine the variance of the contour length difference as the bubble characteristic value.

[0010] Further, the electric control adjustment module is used to calculate the abnormal risk value of the sub-target area, including, Determining the ratio of the dynamic disturbance index of the moving speed to the dynamic disturbance threshold of the reference moving speed as the first abnormal risk factor; Determining the ratio of the dynamic disturbance index of the contour area to the dynamic disturbance threshold of the reference contour area as the second abnormal risk factor; Determining the weighted sum value of the first abnormal risk factor and the second abnormal risk factor as the abnormal risk value of the sub-target area.

[0011] Further, the electric control adjustment module is used to divide the attention area, where, If the abnormal risk value of the sub-target area is greater than the preset abnormal risk threshold, it is determined that the sub-target area is the attention area, and the attention monitoring unit needs to be activated; If the abnormal risk value of the sub-target area is less than or equal to the preset abnormal risk threshold, it is determined that there is no need to activate the attention monitoring unit, and the wide-area monitoring unit continues to monitor the sub-target area.

[0012] Further, the electric control analysis module calculates the drowning characterization coefficient, including, Determining the ratio of the ripple characterization value to the reference ripple characterization value as the first characterization factor; Determining the ratio of the bubble characteristic value to the reference bubble characteristic value as the second characterization factor; Determining the weighted sum value of the first characterization factor and the second characterization factor as the drowning characterization coefficient.

[0013] Further, the electric control analysis module determines the drowning state of the area and judges whether a warning signal needs to be issued, where, If the drowning characterization coefficient is greater than the drowning characterization coefficient threshold, it is determined that the drowning state of the area is the drowning state, and a warning signal needs to be issued; If the drowning characterization coefficient is less than or equal to the drowning characterization coefficient threshold, it is determined that the drowning state of the area is the non-drowning state, and there is no need to issue a warning signal.

[0014] Further, the electric control rescue module determines whether to control the unmanned boat to implement rescue based on the warning signal emission state, where, If the warning signal emission state is to issue a warning signal, it is necessary to control the unmanned boat to implement rescue; If the warning signal emission state is not to issue a warning signal, there is no need to control the unmanned boat to implement rescue, and the continuous acquisition of the warning signal emission state is maintained.

[0015] Further, the electric control rescue module determines the rescue method, including, To locate the rescue coordinates of the attention area based on the drowning state; To determine the unmanned boat closest to the rescue coordinates in terms of the positioning distance; To control the unmanned boat to go to the rescue coordinates.

[0016] Further, the electric control adjustment module is used to determine a number of attention areas. Controlling the attention monitoring unit includes, To adjust the shooting angle of the attention monitoring unit, monitor each of the attention areas for a preset duration one by one, and obtain the monitoring data of each attention area.

[0017] Compared with the prior art, the present invention sets up an electric control monitoring module. Its wide-area monitoring unit obtains monitoring data, determines the dynamic disturbance value and the feature distribution value. The attention monitoring unit responds to the determination result of the electric control adjustment module, determines the ripple characterization value and the bubble feature value of the attention area, calculates the abnormal risk value of the sub-target area through the electric control adjustment module, divides the attention area, determines whether to start the attention monitoring unit, through the electric control analysis module, in response to the start state of the attention monitoring unit, calculates the drowning characterization coefficient, determines the regional drowning state, judges whether to issue a warning signal, and controls the unmanned boat to implement the rescue through the electric control rescue module, determines the rescue method. The present invention can monitor drowning in a large area and quickly deploy the unmanned boat on the premise of saving computing power, improving the drowning monitoring efficiency and the unmanned boat deployment efficiency.

[0018] In particular, by calculating the abnormal risk value of the sub-target area, the attention area is determined, and then the attention monitoring unit is correspondingly activated. In actual situations, in a large target area, the abnormal situations are in the minority. Therefore, an attention mechanism is considered to be introduced. The dynamic disturbance index is determined through the basic motion characteristics of the moving target, which characterizes the abnormal tendency existing in the sub-target area. Then, the corresponding sub-target area is divided into the attention area. When calculating the dynamic disturbance index, the moving speed dynamic disturbance index and the contour area dynamic disturbance index are considered. The above two indexes are easy to analyze and can preliminarily characterize whether there is a drowning tendency. For example, in the case of drowning, the moving speed of the moving target is uncontrollable, which is reflected in the monitoring data as a relatively high discreteness of the moving speed. Relatively speaking, the situation of speed mutation and disturbance is less likely to occur under normal circumstances. On the other hand, when drowning occurs, the moving target undulates in the water, which is reflected in the monitoring data as a relatively high discreteness of the target contour area. Relatively speaking, based on this, calculating the abnormal risk value provides a basis for subsequently invoking the attention monitoring unit. In most cases, a wide-area monitoring unit is used to cover the large target area, and when there is an attention area, the attention monitoring unit is quickly invoked for precise analysis and positioning, which can ensure the monitoring of the large area and save computing power on the premise of ensuring reliability to achieve drowning monitoring, quickly deploy the unmanned boat, and improve the drowning monitoring efficiency and the unmanned boat deployment efficiency.

[0019] In particular, by determining the ripple characterization value and the bubble characteristic value of the attention area, it provides a data basis for calculating the drowning characterization coefficient. In actual situations, when determining the drowning state of the target area, most rely on human key point detection and behavior analysis. However, the non-rigid structure of the human body makes the posture change diverse. Especially in the case of self-occlusion and complex postures, it increases the difficulty of key point detection and behavior judgment, resulting in judgment errors. Based on this, the present invention analyzes the ripples and bubbles in the attention area, calculates the drowning characterization coefficient, and then determines the regional drowning state, providing a forward data basis for subsequent controlling the unmanned boat to implement rescue, and improving the regional rescue speed and rescue accuracy.

[0020] In particular, by calculating the drowning characterization coefficient, the regional drowning state is determined, and then it is judged whether it is necessary to issue a warning signal to control the unmanned boat to implement rescue to ensure the smooth progress of the rescue work, and the regional rescue speed and rescue accuracy are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a schematic structural diagram of the unmanned boat electronic control system based on multi-source data according to an embodiment of the invention; Figure 2 It is a logic block diagram of the electronic control adjustment module dividing the attention area according to an embodiment of the invention; Figure 3Logic block diagram for determining the drowning state of a specific area in an invention embodiment and judging whether a warning signal needs to be issued; Figure 4 Logic block diagram for judging whether to control an unmanned boat to implement rescue based on the warning signal emission state in an invention embodiment. Detailed implementation manners

[0022] In order to make the purpose and advantages of the present invention clearer and more understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] The preferred implementation manners of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these implementation manners are only used to explain the technical principle of the present invention and do not limit the protection scope of the present invention.

[0024] It should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0025] Please refer to Figure 1 , Figure 1 Structural schematic diagram of an unmanned boat electric control system based on multi-source data in an invention embodiment. The unmanned boat electric control system based on multi-source data provided by the embodiment of the present invention includes: An electric control monitoring module, which includes a wide-area monitoring unit and an attention monitoring unit. The wide-area monitoring unit is used to obtain monitoring data of a target area and determine a dynamic disturbance index based on the basic motion characteristics of moving targets in each sub-target area. The attention monitoring unit is used to respond to the determination result of the electric control adjustment module, adjust the monitoring direction to obtain monitoring data of the attention area, so as to determine the ripple characterization value and bubble feature value of the attention area; An electric control adjustment module, which is connected to the electric control monitoring module, calculates the abnormal risk value of the sub-target area based on the dynamic disturbance index, determines several attention areas, and controls the attention monitoring unit; An electric control analysis module, which is connected to the electric control monitoring module, responds to the startup state of the attention monitoring unit, calculates a drowning characterization coefficient based on the ripple characterization value and the bubble feature value, determines the drowning state of the area, and judges whether a warning signal needs to be issued; The electric control rescue module is connected to the electric control analysis module and is used to determine whether to control the unmanned boat to implement rescue based on the warning signal emission status and determine the rescue method.

[0026] Specifically, the specific forms of the electric control adjustment module, the electric control analysis module, and the electric control rescue module are not limited. They can be composed of logic components or combinations of logic components. The logic components include field programmable processors, computers, or microprocessors in computers.

[0027] Specifically, the areas and division methods of the target area and the sub-target areas are not limited. For example, the area of the target area can be the maximum area that the wide-area monitoring unit can monitor, and the area of the sub-target area can be 0.1 to 0.2 times the area of the target area. Of course, those skilled in the art can also adjust according to the actual situation, as long as the target area and the sub-target areas can be completely monitored, which will not be elaborated here.

[0028] Specifically, the specific forms of the wide-area monitoring unit and the attention monitoring unit are not limited. For example, it can be a photographic device placed at a high place. Preferably, it can be a combination of a photographic device and a logic component, which can analyze the monitoring data obtained by the photographic device through the logic component. At the same time, the photographic device needs to be able to adjust the monitoring angle, which will not be elaborated here.

[0029] Specifically, the form and transmission target of the warning signal are not limited. For example, it can be a warning light, a warning bell, or a combination of a warning light and a warning bell. Those skilled in the art can choose according to the actual situation, as long as it can achieve the warning effect. The transmission target can be only the electric control module of the system, and this auxiliary module can be called via the warning signal to synchronously call medical personnel, which will not be elaborated here.

[0030] Specifically, the electric control monitoring module is used to determine the dynamic disturbance index based on the basic motion characteristics of the moving targets in each sub-target area, including, To determine the basic motion characteristics of the moving targets in the sub-target area, including the moving speed of the center of the moving target and the contour area of the moving target; To use the absolute variance of the moving speed of the center of the moving target at each moment as the moving speed dynamic disturbance index; To use the absolute variance of the contour area of the moving target at each moment as the contour area dynamic disturbance index.

[0031] Specifically, the method for determining the moving target is not limited. For example, an image segmentation algorithm can be used to identify the target contour, and the moving target contour is determined as the moving target. Then, the moving speed of the center of the moving target and the contour area of the moving target can be determined, which will not be elaborated here.

[0032] Specifically, the electric control monitoring module determines the ripple characterization value and the bubble feature value of the attention area, including: To identify the frequency of ripples occurring within the reference time of the attention area, and determine the frequency as the ripple characterization value, where the reference time is 1 s; To determine the difference in the contour lengths of consecutive bubbles; To determine the variance of the contour length difference as the bubble feature value.

[0033] Specifically, in implementation, consecutive bubbles are bubbles that appear on the water surface successively in the same area. Thus, the difference in the contour lengths of the bubbles that appear successively can be calculated, which will not be elaborated here.

[0034] There is no limitation on the method of identifying ripples and bubbles. An image processing model or algorithm capable of identifying corresponding features can be pre-trained and imported into the logic component to implement the corresponding functions, which will not be elaborated here.

[0035] Specifically, determining the ripple characterization value and the bubble feature value of the attention area provides a data basis for calculating the drowning characterization coefficient. In actual situations, when determining the drowning state of the target area, mostly through human key point detection and behavior analysis. However, the non-rigid structure of the human body makes the posture change diverse, especially in the case of self-occlusion and complex postures, which increases the difficulty of key point detection and behavior judgment, resulting in judgment errors. Based on this, the present invention analyzes the ripples and bubbles in the attention area, calculates the drowning characterization coefficient, and then determines the regional drowning state, providing a data basis for subsequent control of the unmanned boat to implement rescue, improving the regional rescue speed and rescue accuracy.

[0036] Specifically, the electric control adjustment module is used to calculate the abnormal risk value of the sub-target area, including: To determine the ratio of the moving speed dynamic disturbance index to the reference moving speed dynamic disturbance threshold as the first abnormal risk factor; To determine the ratio of the contour area dynamic disturbance index to the reference contour area dynamic disturbance threshold as the second abnormal risk factor; To determine the weighted sum value of the first abnormal risk factor and the second abnormal risk factor as the abnormal risk value of the sub-target area.

[0037] Specifically, the reference moving speed dynamic disturbance threshold is pre-calculated. Among them, the moving speed dynamic disturbance indexes of several moving targets without abnormalities are pre-obtained, the average value of the moving speed dynamic disturbance indexes is determined, and the reference moving speed dynamic disturbance threshold is set to be selected between 1.15 times and 1.3 times of the average value of the moving speed dynamic disturbance indexes.

[0038] Specifically, the dynamic disturbance threshold of the reference contour area is pre-calculated. Among them, the dynamic disturbance indexes of the contour areas of several moving targets without anomalies are obtained in advance, the mean value of the dynamic disturbance indexes of the contour areas is determined, and the dynamic disturbance threshold of the reference contour area is selected between 1.25 times and 1.5 times of the mean value of the dynamic disturbance indexes of the contour areas.

[0039] Specifically, the sum of the weight coefficients of the first anomaly risk factor and the second anomaly risk factor is 1. The weight coefficient of the first anomaly risk factor is 0.57, and the weight coefficient of the second anomaly risk factor is 0.43.

[0040] Please refer to Figure 2 , Figure 2 which is the logic block diagram for dividing the attention area of the electronic control adjustment module in the invention embodiment. Specifically, the electronic control adjustment module is used to divide the attention area, where if the anomaly risk value of the sub-target area is greater than the preset anomaly risk threshold, it is determined that the sub-target area is the attention area, and the attention monitoring unit needs to be activated; if the anomaly risk value of the sub-target area is less than or equal to the preset anomaly risk threshold, it is determined that there is no need to activate the attention monitoring unit, and the wide-area monitoring unit is continued to be used to monitor the sub-target area.

[0041] Specifically, the preset anomaly risk threshold is selected within the range of [0.65, 0.85].

[0042] Specifically, for the unactivated state of the attention monitoring unit, the target area is continuously monitored according to the monitoring data of the wide-area monitoring unit.

[0043] Specifically, by calculating the abnormal risk value of the sub-target area, the attention area is determined, and then the attention monitoring unit is correspondingly mobilized. In actual situations, in a large-scale target area, the abnormal situations are in the minority. Therefore, an attention mechanism is considered to be introduced. The dynamic disturbance index is determined through the basic motion characteristics of the moving target, which characterizes the abnormal tendency existing in the sub-target area. Then, the corresponding sub-target area is divided into the attention area. When calculating the dynamic disturbance index, the moving speed dynamic disturbance index and the contour area dynamic disturbance index are considered. The above two indexes are easy to analyze and can initially characterize whether there is a drowning tendency. For example, in the case of drowning, the moving speed of the moving target is uncontrollable, which is reflected in the monitoring data as a relatively high discreteness of the moving speed. Relatively speaking, the situation of speed mutation and disturbance is less under normal circumstances. On the other hand, when drowning occurs, the moving target fluctuates in the water, which is reflected in the monitoring data as a relatively high discreteness of the target contour area. Relatively speaking, based on this, calculating the abnormal risk value provides a basis for subsequently invoking the attention monitoring unit. In most cases, the wide-area monitoring unit is used to cover the large-scale target area, and when there is an attention area, the attention monitoring unit is quickly invoked for precise analysis and positioning, which can ensure the monitoring of the large-scale area and save computing power on the premise of ensuring reliability to achieve drowning monitoring, quickly deploy the unmanned boat, and improve the drowning monitoring efficiency and the unmanned boat deployment efficiency.

[0044] Specifically, the electric control analysis module calculates the drowning characterization coefficient, including used to determine that the ratio of the ripple characterization value to the reference ripple characterization value is the first characterization factor; used to determine that the ratio of the bubble characteristic value to the reference bubble characteristic value is the second characterization factor; used to determine that the weighted sum value of the first characterization factor and the second characterization factor is the drowning characterization coefficient.

[0045] Specifically, the reference bubble characteristic value is pre-calculated. Image data of the sub-target area in several periods when drowning does not occur is pre-obtained, the bubble characteristic value in each period is determined, the mean value of the bubble characteristic values is solved, and the reference bubble characteristic value is set to be selected between 1.15 times and 1.35 times of the mean value.

[0046] The reference ripple characterization value is pre-calculated. Image data of the sub-target area in several periods when drowning does not occur is pre-obtained, the ripple characterization value in each period is determined, the mean value of the ripple characterization values is solved, and the reference ripple characterization value is set to be selected between 1.15 times and 1.35 times of the mean value.

[0047] Specifically, the sum of the weight coefficients of the first characterization factor and the second characterization factor is 1, the weight coefficient of the first characterization factor is 0.51, and the weight coefficient of the second characterization factor is 0.49.

[0048] Please refer to Figure 3 , Figure 3 which is a logic block diagram for determining the drowning state of a specific area in an invention embodiment and judging whether a warning signal needs to be issued. Specifically, an electronic control analysis module determines the drowning state of the area and judges whether a warning signal needs to be issued. Among them, if the drowning characterization coefficient is greater than the drowning characterization coefficient threshold, it is determined that the drowning state of the area is the drowning state and a warning signal needs to be issued; if the drowning characterization coefficient is less than or equal to the drowning characterization coefficient threshold, it is determined that the drowning state of the area is the non-drowning state and a warning signal does not need to be issued.

[0049] Specifically, the drowning characterization coefficient threshold represents the lowest value when drowning occurs in the target area. Therefore, the drowning characterization coefficient threshold is set to be selected within the interval [1.25, 1.65].

[0050] Please refer to Figure 4 , Figure 4 which is a logic block diagram for judging whether it is necessary to control an unmanned boat to implement a rescue based on the warning signal emission state in an invention embodiment. Specifically, an electronic control rescue module judges whether it is necessary to control an unmanned boat to implement a rescue based on the warning signal emission state. Among them, if the warning signal emission state is to issue a warning signal, it is necessary to control the unmanned boat to implement a rescue; if the warning signal emission state is not to issue a warning signal, it is not necessary to control the unmanned boat to implement a rescue, and the continuous acquisition of the warning signal emission state is maintained.

[0051] Specifically, the electronic control rescue module determines the rescue method, including, using it to locate the rescue coordinates based on the attention area of the drowning state; using it to determine the unmanned boat closest to the located rescue coordinates; using it to control the unmanned boat to go to the rescue coordinates.

[0052] Specifically, there is no limitation on the control method of the unmanned boat. The unmanned boat can be equipped with a navigation control system and a GPS positioning device and move to the corresponding position based on the rescue coordinates. Those skilled in the art can adopt the existing unmanned boat navigation control system as long as it can make the unmanned boat move to the target position based on the predetermined rescue coordinates. This will not be elaborated here.

[0053] Specifically, the electronic control adjustment module is used to determine several attention areas and control the attention monitoring unit, including, using it to adjust the shooting angle of the attention monitoring unit, monitoring each of the attention areas for a predetermined duration one by one, and obtaining the monitoring data of each attention area.

[0054] The preset duration is selected within the interval [3s, 5s].

[0055] Specifically, by calculating the drowning characterization coefficient, the drowning state of the area is determined, and then it is judged whether it is necessary to issue a warning signal to control the unmanned boat to implement the rescue, so as to ensure the smooth progress of the rescue work and improve the regional rescue speed and rescue accuracy rate.

[0056] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or replacements to the relevant technical features, and the technical solutions after these changes or replacements will all fall within the protection scope of the present invention.

[0057] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An electric control system for an unmanned boat based on multi-source data, characterized in that, Including: An electronic control monitoring module, which includes a wide - area monitoring unit and an attention monitoring unit. The wide - area monitoring unit is used to obtain monitoring data of the target area, determine a dynamic disturbance index based on the basic motion characteristics of moving targets in each sub - target area. The attention monitoring unit is used to respond to the determination result of the electronic control adjustment module, adjust the monitoring direction to obtain monitoring data of the attention area, so as to determine the ripple characterization value and the bubble characteristic value of the attention area; An electronic control adjustment module, which is connected to the electronic control monitoring module, calculates the abnormal risk value of the sub - target area based on the dynamic disturbance index, determines several attention areas, and controls the attention monitoring unit; An electronic control analysis module, which is connected to the electronic control monitoring module, responds to the startup state of the attention monitoring unit, calculates the drowning characterization coefficient based on the ripple characterization value and the bubble characteristic value, determines the drowning state of the area, and judges whether it is necessary to issue a warning signal; An electronic control rescue module, which is connected to the electronic control analysis module, is used to judge whether it is necessary to control the unmanned boat to implement rescue based on the warning signal emission state, and determine the rescue method.

2. The electric control system for an unmanned boat based on multi-source data according to claim 1, characterized in that, The electronic control monitoring module is used to determine the dynamic disturbance index based on the basic motion characteristics of moving targets in each sub - target area, including, Used to determine the basic motion characteristics of moving targets in the sub - target area, including the moving speed of the center of the moving target and the contour area of the moving target; Used to take the absolute variance of the moving speed of the center of the moving target at each moment as the moving speed dynamic disturbance index; Used to take the absolute variance of the contour area of the moving target at each moment as the contour area dynamic disturbance index.

3. The electric control system for an unmanned boat based on multi-source data according to claim 2, characterized in that, The electronic control monitoring module determines the ripple characterization value and the bubble characteristic value of the attention area, Including, Used to identify the frequency of ripple appearance within the reference time of the attention area, and determine the frequency as the ripple characterization value; Used to determine the difference in contour lengths of continuous bubbles; Used to determine the variance of the contour length difference as the bubble characteristic value.

4. The electric control system for an unmanned boat based on multi-source data according to claim 3, characterized in that, The electronic control adjustment module is used to calculate the abnormal risk value of the sub - target area, including, Used to determine the ratio of the moving speed dynamic disturbance index to the reference moving speed dynamic disturbance threshold as the first abnormal risk factor; Used to determine the ratio of the contour area dynamic disturbance index to the reference contour area dynamic disturbance threshold as the second abnormal risk factor; Used to determine the weighted sum value of the first abnormal risk factor and the second abnormal risk factor as the abnormal risk value of the sub - target area.

5. The electric control system for an unmanned boat based on multi-source data according to claim 1, characterized in that, The electronic control adjustment module is used to divide the attention area, where, If the abnormal risk value of the sub - target area is greater than the preset abnormal risk threshold, it is determined that the sub - target area is an attention area, and the attention monitoring unit needs to be started; If the abnormal risk value of the sub - target area is less than or equal to the preset abnormal risk threshold, it is determined that there is no need to start the attention monitoring unit, and the wide - area monitoring unit continues to monitor the sub - target area.

6. The electric control system for an unmanned boat based on multi-source data according to claim 1, characterized in that, The electronic control analysis module calculates the drowning characterization coefficient, including, Used to determine the ratio of the ripple characterization value to the reference ripple characterization value as the first characterization factor; Used to determine the ratio of the bubble characteristic value to the reference bubble characteristic value as the second characterization factor; The weighted sum value of the first characterization factor and the second characterization factor is determined as the drowning characterization coefficient.

7. The electric control system for an unmanned boat based on multi-source data according to claim 1, characterized in that, The electric control analysis module determines the regional drowning state and judges whether a warning signal needs to be issued. Among them, if the drowning characterization coefficient is greater than the drowning characterization coefficient threshold, it is determined that the regional drowning state is a drowning state and a warning signal needs to be issued; if the drowning characterization coefficient is less than or equal to the drowning characterization coefficient threshold, it is determined that the regional drowning state is a non-drowning state and a warning signal does not need to be issued.

8. The electric control system for an unmanned boat based on multi-source data according to claim 1, characterized in that, The electric control rescue module judges whether it is necessary to control the unmanned boat to implement rescue based on the warning signal issuance state. Among them, if the warning signal issuance state is to issue a warning signal, it is necessary to control the unmanned boat to implement rescue; if the warning signal issuance state is not to issue a warning signal, it is not necessary to control the unmanned boat to implement rescue, and the continuous acquisition of the warning signal issuance state is maintained.

9. The unmanned boat electric control system based on multi-source data according to claim 1, wherein, The electric control rescue module determines the rescue method, including, locating the rescue coordinates based on the attention area of the drowning state; determining the unmanned boat closest to the located rescue coordinates; controlling the unmanned boat to go to the rescue coordinates.

10. The unmanned boat electric control system based on multi-source data according to claim 1, wherein, The electric control adjustment module is used to determine a number of attention areas and control the attention monitoring unit, including, adjusting the shooting angle of the attention monitoring unit, monitoring each attention area for a preset duration one by one, and obtaining the monitoring data of each attention area.

Images