Target monitoring and expelling system based on dynamic grid

Abstract

The invention discloses a target monitoring and expelling system based on a dynamic grid, which comprises a control end and a plurality of terminals, and is characterized in that each terminal comprises a driving device, a communication device, a monitoring device and an expelling device; the control end is in wireless communication connection with the communication device and is used for controlling the running of the running device, the monitoring device and the expelling device; the monitoring device is used for monitoring a target, and the control end collects monitoring images of the same target by the monitoring devices of the plurality of terminals, obtains position information of the target and identifies category information; the plurality of terminals are distributed in a preset monitoring area to form a grid, and the control end is used for generating a moving instruction according to the position information of each monitoring device and adjusting the position of each terminal; the driving device is used for controlling the terminal to move according to a moving instruction of the control end; the expelling device is used for expelling the target according to the category information after the terminal arrives at the designated position of the control end, the terminal is dynamically adjusted, manual participation is reduced, efficiency is improved, and cost is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of target monitoring, and in particular to a target monitoring and expulsion system based on a dynamic grid. Background Art

[0002] With the rapid development of the economy, the increase in flight frequency and the increase in aircraft types have led to more and more frequent bird strikes at airports, which have even become one of the three major disasters in the world's aviation industry. In addition, in recent years, more and more light and small drones have entered people's lives, and illegal aircraft have interfered with aircraft more and more seriously. In order to ensure the safety of flights, it is necessary to control and monitor the targets at the airport. The expulsion of birds and other targets is mostly carried out by emitting sound waves or electromagnetic waves from fixed devices. Therefore, the existing detection means are mainly radars. When expelling targets, the corresponding expulsion means cannot be selected in time, and the process of deploying fixed devices is relatively cumbersome, resulting in the inability to dynamically adjust the deployment position after deployment, making the monitoring and expulsion of airport targets highly dependent on manual labor and the operating cost is relatively high. Summary of the invention

[0003] To achieve the above-mentioned purpose and other related purposes, the present invention discloses a target monitoring and expelling system based on dynamic grid, including a control end and several terminals, wherein the terminals include a driving device, a communication device, a monitoring device, and an expelling device; The control end is connected to the communication device by wireless communication, and is used to control the operation of the driving device, the monitoring device, and the expelling device; The monitoring device is used to monitor the target. The control end collects the monitoring images of the same target from the monitoring devices of several terminals, obtains the location information of the target and identifies the category information; Several terminals are distributed in a preset monitoring area to form a grid, and the control terminal is used to generate movement instructions according to the location information of each monitoring device and adjust the position of each terminal; The driving device is used to control the terminal to move according to the movement instruction of the control terminal; The expelling device is used to expel the target according to the category information when the terminal reaches the designated position of the control end.

[0004] Furthermore, the control terminal is used to generate a movement instruction according to the position information of each monitoring device, and the adjustment of the position of each terminal includes: Preliminary planning of the expulsion area based on the geographic information system, instructing several terminals to go to their respective areas to collect terrain data and form a preliminary grid; Feedback the monitoring information of the target, receive external prior information at the same time, adjust the initial grid according to the target monitoring information and external prior information to form a dynamic grid; The terminals adjust their positions according to the dynamic grid. Some terminals are anchored in the corresponding expulsion area, while others patrol and monitor on a certain trajectory.

[0005] Furthermore, according to the preliminary planning of the expulsion area based on the geographic information system, several terminals are directed to collect terrain data in their respective areas and form a preliminary grid including: According to the terrain data and preliminary network, the coverage optimization algorithm is used to evenly distribute the terminals around the eviction area to form a closed eviction area.

[0006] Furthermore, adjusting the preliminary grid to form a dynamic grid according to the target monitoring information and external prior information includes: The random forest network is trained using previous target monitoring information, external prior information, expulsion formation, and expulsion efficiency evaluated afterwards, wherein the target monitoring information and external prior information are used as variables, the expulsion formation is used as the result, and the expulsion efficiency evaluated afterwards is used as a weighting parameter. The trained random forest network is used to predict the source direction and number of types of the next target.

[0007] Furthermore, the operation trajectory of the terminal performing patrol monitoring is: ; In the formula, is the set of trajectories of each terminal; is the trajectory function of each terminal, the function variable is time, and the trajectory is Map to space; is the sum of time, indicating the time it takes for all terminals to move to the designated location; The trajectory is mapped to The polynomial coefficients after the space, which determine the shape of the trajectory; is the formula for parameter mapping, are the middle points, which are the key control points of the trajectory and are used to ensure the smoothness and accuracy of the trajectory. is the time vector; is an M-dimensional M-segment trajectory: ; The i-th trajectory It can be expressed as a fifth-order polynomial as follows: ; in is the coefficient matrix of the 6*m-dimensional matrix, is the length of the i-th time segment, It is natural based and is related to time.

[0008] Furthermore, the expulsion device includes an electromagnetic interference device, a sound wave emitting device, and a laser emitting device.

[0009] Furthermore, the monitoring device adopts visual detection equipment to utilize vision to monitor the target.

[0010] By adopting the above technical solution, a quadruped robot is used as a driving device equipped with a monitoring device and an expelling device. First, the monitoring device is used to obtain a monitoring image of the target, obtain the target's position information and identify the category information. Then, the control end generates a movement instruction according to the position information of each monitoring device, and dynamically adjusts the position of each terminal. When the terminal arrives at the target location, the expelling device is controlled to work and the target is expelled, thereby improving the safety in the airport, reducing dependence on manpower, and being able to dynamically adjust the terminal's position according to actual conditions, with high efficiency and low operating costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0012] Figure 1 The system block diagram of a target monitoring and expulsion system based on dynamic grid; Figure 2 It is a schematic diagram of the structure of the traveling device.

[0013] Figure numerals: 100, three-axis gimbal, 200, quadruped robot, 300, anchoring device. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0015] Reference Figure 1 , an embodiment of the present invention provides a target monitoring and expulsion system based on a dynamic grid, comprising: Control end, several terminals, the terminals include driving device, communication device, monitoring device, and expulsion device; The control end is connected to the communication device by wireless communication, and is used to control the operation of the driving device, the monitoring device, and the expelling device; The monitoring device is used to monitor the target. The control end collects the monitoring images of the same target from the monitoring devices of several terminals, obtains the location information of the target and identifies the category information; Several terminals are distributed in a preset monitoring area to form a grid, and the control terminal is used to generate movement instructions according to the location information of each monitoring device and adjust the position of each terminal; The driving device is used to control the terminal to move according to the movement instruction of the control terminal; The expelling device is used to expel the target according to the category information when the terminal reaches the designated position of the control end.

[0016] As mentioned above, the traveling device can adopt various devices that are well known to those skilled in the art and can carry modules for traveling, such as a track system. Various types of traveling devices that can be obtained by those skilled in the art without paying creative labor are within the scope of protection of the present invention.

[0017] The preferred traveling device in this embodiment is a quadruped robot 200, and a three-axis gimbal 100 for loading a monitoring device and an expelling device is installed on the top of the quadruped robot 200, and an anchoring device 300 is installed on the bottom of the quadruped robot 200. When the terminal arrives at the specified position, the control end controls the anchoring device 300 to fix the position of the terminal. The three-axis gimbal 100 and the anchoring device 300 are common three-axis gimbals 100 and anchoring devices 300 on the market. The control end controls the anchoring device 300 as a commonly used technical means in the field, which will not be repeated here.

[0018] The quadruped robot 200 has four adjustable support points, which can keep stability on uneven ground. At the same time, the position and angle of each leg can be adjusted to adapt to different terrains and obstacles. It has high maneuverability and strong adaptability, and can move efficiently when it is necessary to expel a target.

[0019] Among them, the monitoring device adopts visual detection equipment to monitor the target in a visual way. Monitoring objects in a visual way is an existing technology well known to technical personnel in this field. Technical personnel in this field can choose different visual detection equipment according to actual needs, which will not be repeated here.

[0020] The category information is the specific type of the target. The type of the target is set by those skilled in the art according to actual conditions and will not be described in detail here.

[0021] The above-mentioned expulsion devices include electromagnetic interference devices, sound wave emitting devices, and laser emitting devices. The above-mentioned devices are common equipment and will not be described in detail here.

[0022] As described above, according to the category information of the identified target, different expulsion methods are adopted for the target according to different category information, so as to improve the expulsion efficiency and reduce the harm to the animals.

[0023] The control terminal is used to generate movement instructions according to the position information of each monitoring device, and adjust the position of each terminal including: Preliminary planning of the expulsion area based on the geographic information system, instructing several terminals to go to their respective areas to collect terrain data and form a preliminary grid; Specifically include: According to the terrain data and preliminary network, the coverage optimization algorithm is used to evenly distribute the terminals around the eviction area to form a closed eviction area.

[0024] Feedback the monitoring information of the target, receive external prior information at the same time, adjust the initial grid according to the target monitoring information and external prior information to form a dynamic grid; Specifically include: The random forest network is trained using previous target monitoring information, external prior information, expulsion formation, and expulsion efficiency evaluated afterwards, wherein the target monitoring information and external prior information are used as variables, the expulsion formation is used as the result, and the expulsion efficiency evaluated afterwards is used as a weighting parameter. The trained random forest network is used to predict the source direction and number of types of the next target.

[0025] The random forest algorithm is a machine learning algorithm based on classification and regression trees. It is a nonlinear model. When training data is input into the model, the random forest uses different subsets and feature attributes to build multiple small decision trees, and then merges them into a more powerful model. By combining the results of multiple decision trees, the effect of the model can be enhanced.

[0026] The study uses the random forest algorithm to establish the relationship between the source direction and the number of types of targets in different time periods within the monitoring range, and uses the trained random forest network to predict the source direction and number of types of the next target, and find a more suitable expulsion formation. The sample set is the source direction and number of types of targets in the monitoring range in the past ten years, the previous flight environment monitoring information (such as temperature, humidity, wind speed direction, etc.) in the characteristic variable monitoring range, and external prior information. The sample set is divided into two parts using a uniform random sampling method to eliminate any possible bias caused by using the same sample for classifier training and testing. The bootstrap method is used to randomly extract n samples with replacement from the sample (the number of n is determined according to the size of the sample set) to construct n decision trees, and 10 feature variables are randomly extracted at each node of each decision tree. The n trees produced are combined into a random forest, in which each tree has one vote. The post-evaluation eviction efficiency is used as a weighting parameter. Through multiple voting, the random forest classification result, that is, the eviction efficiency result, is obtained. The evaluation accuracy of the random forest evaluation model is verified by five-fold cross validation and ROC curve.

[0027] The terminals adjust their positions according to the dynamic grid. Some terminals are anchored in the corresponding expulsion area, while others patrol and monitor on a certain trajectory.

[0028] Specifically, the operation trajectory of the terminal performing patrol monitoring is: ; In the formula, is the set of trajectories of each terminal; is the trajectory function of each terminal, the function variable is time, and the trajectory is Map to space; is the sum of time, indicating the time it takes for all terminals to move to the designated location; The trajectory is mapped to The polynomial coefficients after the space, which determine the shape of the trajectory; is the formula for parameter mapping, are the middle points, which are the key control points of the trajectory and are used to ensure the smoothness and accuracy of the trajectory. is the time vector; is an M-dimensional M-segment trajectory: ; The i-th trajectory It can be expressed as a fifth-order polynomial as follows: ; in is the coefficient matrix of the 6*m-dimensional matrix, is the length of the i-th time segment, It is natural based and is related to time.

[0029] An embodiment of the present invention provides a target monitoring and expelling system based on a dynamic grid, which uses a quadruped robot 200 as a driving device equipped with a monitoring device and an expelling device. First, the monitoring device is used to obtain a monitoring image of the target, obtain the position information of the target and identify the category information. Then, the control end generates a movement instruction according to the position information of each monitoring device, and dynamically adjusts the position of each terminal. When the terminal arrives at the target location, the expelling device is controlled to work and the target is expelled, thereby improving the safety in the airport, reducing dependence on manpower, and being able to dynamically adjust the position of the terminal according to actual conditions, with high efficiency and low operating costs.

[0030] Those skilled in the art will appreciate that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined.

[0031] For the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0032] It can be known from the description of the above implementation modes that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute the methods of various implementation modes of the present application or certain parts of the implementation modes.

[0033] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A target monitoring and expulsion system based on dynamic grid, characterized in that: It includes a control terminal and several terminals, and the terminals include a driving device, a communication device, a monitoring device, and an expulsion device; The control end is connected to the communication device by wireless communication, and is used to control the operation of the driving device, the monitoring device, and the expelling device; The monitoring device is used to monitor the target. The control end collects the monitoring images of the same target from the monitoring devices of several terminals, obtains the location information of the target and identifies the category information; Several terminals are distributed in a preset monitoring area to form a grid, and the control terminal is used to generate movement instructions according to the location information of each monitoring device and adjust the position of each terminal; The driving device is used to control the terminal to move according to the movement instruction of the control terminal; The expelling device is used to expel the target according to the category information when the terminal reaches the designated position of the control end.

2. The system according to claim 1, characterized in that The control terminal is used to generate a movement instruction according to the position information of each monitoring device, and adjust the position of each terminal includes: Preliminary planning of the expulsion area based on the geographic information system, instructing several terminals to go to their respective areas to collect terrain data and form a preliminary grid; Feedback the monitoring information of the target, receive external prior information at the same time, adjust the initial grid according to the target monitoring information and external prior information to form a dynamic grid; The terminals adjust their positions according to the dynamic grid. Some terminals are anchored in the corresponding expulsion area, while others patrol and monitor on a certain trajectory.

3. The system according to claim 2, characterized in that According to the preliminary planning of the expulsion area based on the geographic information system, several terminals were directed to collect terrain data in their respective areas and form a preliminary grid including: According to the terrain data and preliminary network, the coverage optimization algorithm is used to evenly distribute the terminals around the eviction area to form a closed eviction area.

4. The system according to claim 2, characterized in that The adjusting of the preliminary grid to form a dynamic grid according to the target monitoring information and external prior information comprises: The random forest network is trained using previous target monitoring information, external prior information, expulsion formation, and expulsion efficiency evaluated afterwards, wherein the target monitoring information and external prior information are used as variables, the expulsion formation is used as the result, and the expulsion efficiency evaluated afterwards is used as a weighting parameter. The trained random forest network is used to predict the source direction and number of types of the next target.

5. The system according to claim 2, characterized in that The operation trajectory of the terminal performing patrol monitoring is: ； In the formula, is the set of trajectories of each terminal; is the trajectory function of each terminal, the function variable is time, and the trajectory is Map to space; is the sum of time, indicating the time it takes for all terminals to move to the designated location; The trajectory is mapped to The polynomial coefficients after the space, which determine the shape of the trajectory; is the formula for parameter mapping, are the middle points, which are the key control points of the trajectory and are used to ensure the smoothness and accuracy of the trajectory. is the time vector; is an M-dimensional M-segment trajectory: ； The i-th trajectory It can be expressed as a fifth-order polynomial as follows: ； in is the coefficient matrix of the 6*m-dimensional matrix, is the length of the i-th time segment, It is natural based and is related to time.

6. The system according to claim 1, characterized in that The expelling device includes an electromagnetic interference device, a sound wave emitting device, and a laser emitting device.

7. The system according to claim 1, characterized in that The monitoring device adopts visual detection equipment and utilizes vision to monitor the target.

Images