Video data analysis method and system based on real-time landing of unmanned aerial vehicle

Abstract

The invention relates to the technical field of unmanned aerial vehicle landing power consumption optimization, and particularly discloses a video data analysis method and system based on unmanned aerial vehicle real-time landing, and the system comprises a first analysis unit and a second analysis unit. The second analysis unit obtains an obstacle coefficient by analyzing the image information, and controls and adjusts the frequency of the video acquisition module for obtaining the image information based on the obstacle coefficient, the obstacle coefficient is obtained by analyzing the image information, and the frequency of the video acquisition module for obtaining the image information based on the obstacle coefficient is controlled and adjusted. In the face of a complex and changeable flight environment, the acquisition frequency of the image information can be adjusted according to the environment, the energy consumption for acquiring the image information can be effectively reduced, meanwhile, the burden of a built-in analysis module can be reduced through fewer images, the consumption of the built-in analysis module is further reduced, and thus the cruising ability of the unmanned aerial vehicle is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicle (UAV) landing power consumption optimization, and in particular to a video data analysis method and system based on real-time UAV landing. Background Art

[0002] Drone landing has always been a relatively important issue in drone flight. Usually, drones are equipped with automatic landing systems, which can achieve automatic landing through GPS, lidar or visual sensors. The three methods have their own advantages and disadvantages. GPS can achieve precise landing but lacks environmental perception. Lidar can sense obstacles but requires the addition of multiple related equipment, which is costly. Visual sensors can assist in landing, but long-term video acquisition and analysis consumes more power, affecting the drone's endurance.

[0003] The current modern drones all use a combination of multiple solutions to achieve landing systems, among which the combination of GPS and visual sensors is moderately expensive and has high landing accuracy and is widely used. Usually in areas with Internet access, the power consumption of drones can be effectively reduced by uploading the data collected by drones to the control center for analysis. Some drones need to be used in special scenarios such as rescue or exploration, which are usually in areas with poor network signals or no Internet access. Obviously, this combination solution cannot adapt.

[0004] In view of this, the present invention proposes a video data analysis method and system based on real-time drone landing, which optimizes the video solution of the drone landing process in areas with poor network signals or without network access, reduces power consumption during the use of the video solution, and improves the drone's endurance. Summary of the invention

[0005] The purpose of the present invention is to provide a video data analysis method and system based on real-time landing of unmanned aerial vehicles to solve the following technical problems:

[0006] How to optimize the video solution during the drone landing process in areas with poor network signals or no network access, reduce the power consumption during the use of the video solution, and improve the drone's endurance.

[0007] One of the purposes of the present invention can be achieved by the following technical solutions:

[0008] The video data analysis system based on real-time drone landing includes:

[0009] A video acquisition module, a built-in analysis module and a positioning module, wherein the video acquisition module is used to acquire image information during the flight of the UAV; the built-in analysis module includes a first analysis unit and a second analysis unit, wherein the first analysis unit generates a planned path by analyzing the image information in cooperation with the positioning module, and the second analysis unit acquires an obstacle coefficient by analyzing the image information, and adjusts the frequency of the video acquisition module acquiring image information based on the obstacle coefficient control; the positioning module is used for UAV positioning and generating a planned path.

[0010] Through the above technical solution: a solution is provided for obtaining the obstacle coefficient by analyzing the image information, and adjusting the frequency of the video acquisition module obtaining the image information based on the obstacle coefficient control. In this way, when facing a complex and changeable flight environment, the present invention can adjust the frequency of obtaining image information, or the number of camera frames, according to the environment. The reduction in the number of frames can effectively reduce the energy consumption of obtaining image information. At the same time, fewer images can also reduce the burden on the built-in analysis module, further reducing the consumption of the built-in analysis module, thereby increasing the endurance of the UAV in some special flight environments.

[0011] As a further technical solution of the present invention: the process of obtaining the obstacle coefficient includes:

[0012] Set a unit flight distance, and continuously acquire image information at a preset frequency while the drone completes the unit flight distance along the planned path;

[0013] Based on the image information obtained each time, multiple obstacle factors are generated, and then the average of the multiple obstacle factors is set as the obstacle coefficient.

[0014] As a further technical solution of the present invention: the obstacle coefficient and the obstacle factor are expressed by the formula:

[0015]

[0016] Get the obstacle coefficient Ob corresponding to the j-th flight unit distance j The obstacle factor corresponding to the i-th image information obtained during the completion of the j-th flight unit distance Where n is the total number of image information acquired during the j-th flight unit distance, S i is the obstacle area identified in the i-th image information, S0 is the preset standard area, δ1 is the first correction index preset based on the flight environment, N i is the number of obstacles identified and obtained in the i-th image information, N0 is the preset standard number, δ2 is the second correction index preset based on the flight environment, α and β are the preset first weight coefficient and second weight coefficient respectively, and i is a positive integer belonging to n.

[0017] As a further technical solution of the present invention: the process of adjusting the frequency of the video acquisition module acquiring image information based on the obstacle coefficient control includes:

[0018] Obtain the obstacle coefficient Ob j Compare with the preset reference interval [Re1, Re2];

[0019] If Ob j <Re1, it is judged that there are very few obstacles encountered in the current flight process, and the drone can maintain or reduce the frequency of acquiring image information during the next unit flight distance;

[0020] If Ob j > Re1, it is judged that there are very few obstacles encountered in the current flight process, and the drone needs to increase the frequency of acquiring image information during the next unit flight distance. It should be noted that the increase or decrease in the frequency of acquiring image information cannot exceed the preset maximum and minimum values, and the adjustment range is based on the obstacle coefficient Ob j The difference between Re1 or Re1, that is, Ob j -The larger the Re2, the greater the frequency increase, Re1-Ob j The larger it is, the greater the frequency reduction will be.

[0021] If Ob j If it falls within the reference interval [Re1, Re2], it is judged that the number of obstacles encountered during the current flight is normal, a secondary judgment is made based on the historical data of the obstacle coefficient, and the frequency of obtaining image information is adjusted according to the secondary judgment result.

[0022] Through the above technical solution: a process of obtaining an obstacle coefficient and adjusting the frequency of obtaining image information based on the obstacle coefficient is provided. The obstacle coefficient of the present invention is generated based on multiple pieces of image information obtained during a unit flight distance, and the area of ​​obstacles in the image and the number of obstacles are included in the generation process of the obstacle coefficient, that is, the more obstacles there are or the larger the area of ​​obstacles is, the higher the obstacle coefficient is. At the same time, the allocation of weights also comprehensively considers the different influences of the two on the final result. For example, if there are many obstacles but a small area or if there are large areas but a small number of obstacles, different situations can be distinguished in terms of the numerical value of the obstacle coefficient by setting different weight values.

[0023] As a further technical solution of the present invention: the process of obtaining the reference interval includes:

[0024] Set up multiple standard flight environments and store the obstacle coefficients obtained during normal flight in each flight environment;

[0025] In a standard flight environment, the minimum value of the stored obstacle coefficient is set as the left end point Re1 of the reference interval, and the maximum value of the stored obstacle coefficient is set as Set to the right endpoint Re2 of the reference interval, where m is the confidence coefficient of the current standard flight environment and a is the adjustment value based on the drone model setting.

[0026] As a further technical solution of the present invention: the process of performing secondary judgment includes:

[0027] Obtain historical data of obstacle coefficients during the current flight and construct a rectangular coordinate system and data point set;

[0028] Perform linear regression analysis based on a set of data points to obtain the slope of the regression line;

[0029] If the slope of the regression line is greater than the first critical value, it is judged that the obstacle coefficient continues to increase, the corresponding flight environment is becoming more and more complex, and the frequency of image information collection needs to be increased;

[0030] If the slope of the regression line is less than the second critical value, it is judged that the obstacle coefficient continues to decrease, the corresponding flight environment is becoming simpler, and the frequency of image information acquisition remains unchanged;

[0031] If the slope of the regression line is between the first critical value and the second critical value, a judgment coefficient is obtained based on a plurality of obstacle coefficients, and the acquisition frequency of the image information is controlled based on the judgment coefficient.

[0032] As a further technical solution of the present invention: the process of obtaining the judgment coefficient includes:

[0033] By formula:

[0034]

[0035] Obtain the judgment coefficient Jg, where Ob0 is a preset standard obstacle coefficient, M is the total number of completed unit flight distances, and j is a positive integer belonging to M.

[0036] As a further technical solution of the present invention: the process of controlling the acquisition frequency of image information based on the judgment coefficient includes:

[0037] Compare the judgment coefficient Jg with the comparison value Jg0;

[0038] If Jg>Jg0, the acquisition frequency of image information needs to be increased;

[0039] If Jg≤Jg0, the acquisition frequency of image information is maintained.

[0040] Through the above technical scheme: a secondary judgment scheme is provided. The secondary judgment process of the present invention first performs linear regression analysis, obtains the judgment coefficient based on the result of the regression analysis, and obtains a more complete secondary judgment result based on the judgment coefficient. In addition, the secondary analysis of the present invention is performed when the number of obstacles encountered during the current flight is normal, that is, in the case of conventional flight, the present invention can still make detailed distinctions and respond to the situation of continuous changes in the flight environment in a timely manner, thereby realizing the optimal scheme for controlling the acquisition frequency, and ensuring that the UAV maintains a high image acquisition frequency in a complex environment and controls the image acquisition frequency to continue to decrease in a simple flight environment or an environment where the complexity of obstacles continues to become simpler.

[0041] Another object of the present invention is to provide a video data analysis method based on real-time landing of a drone, comprising the following steps:

[0042] S1, obtain image information during the flight of the drone;

[0043] S2, the first analysis unit generates a planning path by analyzing the image information and cooperating with the positioning module;

[0044] S3. The second analysis unit obtains an obstacle coefficient by analyzing the image information, and controls and adjusts the frequency of the video acquisition module acquiring the image information based on the obstacle coefficient.

[0045] Beneficial effects of the present invention:

[0046] (1) The present invention obtains the obstacle coefficient by analyzing the image information, and adjusts the frequency of the video acquisition module acquiring the image information based on the obstacle coefficient. When facing a complex and changeable flight environment, the frequency of acquiring the image information, or the number of camera frames, can be adjusted according to the environment. The reduction in the number of frames can effectively reduce the energy consumption of acquiring image information. At the same time, fewer images can also reduce the burden on the built-in analysis module, further reducing the consumption of the built-in analysis module, thereby increasing the endurance of the UAV in some special flight environments.

[0047] (2) The obstacle coefficient of the present invention is generated based on multiple sets of image information obtained during a unit flight distance. The area of ​​the obstacles in the image and the number of obstacles are included in the generation process of the obstacle coefficient. That is, the more obstacles there are or the larger the area of ​​the obstacles is, the higher the obstacle coefficient is. At the same time, the distribution of weights also comprehensively considers the different influences of the two on the final result.

[0048] (3) The secondary judgment process of the present invention first performs a linear regression analysis, obtains a judgment coefficient based on the result of the regression analysis, and obtains a more complete secondary judgment result based on the judgment coefficient. In addition, the secondary analysis of the present invention is performed when the number of obstacles encountered during the current flight is normal, that is, in the case of routine flight, the present invention can still make detailed distinctions and respond to the situation of continuous changes in the flight environment in a timely manner, thereby achieving the optimal solution for controlling the acquisition frequency, and ensuring that the UAV maintains a high image acquisition frequency in a complex environment and controls the image acquisition frequency to continue to decrease in a simple flight environment or an environment where the complexity of obstacles continues to become simpler. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below in conjunction with the accompanying drawings.

[0050] Figure 1 It is a schematic diagram of the modular composition of the analysis system of the present invention;

[0051] Figure 2 It is a schematic flow chart of the steps of the analysis method of the present invention. DETAILED DESCRIPTION

[0052] 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] See also Figure 1 As shown, in one embodiment, a video data analysis system based on real-time landing of a drone is provided, comprising:

[0054] The video acquisition module has a built-in analysis module and a positioning module. The positioning module is a global positioning system such as GPS. The built-in analysis module adopts a microprocessor. The video acquisition module is a high-definition camera. The video acquisition module is used to obtain image information during the flight of the UAV. The built-in analysis module includes a first analysis unit and a second analysis unit. The first analysis unit generates a planned path by analyzing the image information in cooperation with the positioning module. The second analysis unit obtains an obstacle coefficient by analyzing the image information, and adjusts the frequency of the video acquisition module obtaining image information based on the obstacle coefficient control. The positioning module is used for UAV positioning and generating a planned path.

[0055] In this embodiment, a solution is provided for obtaining an obstacle coefficient by analyzing image information, and adjusting the frequency of the video acquisition module obtaining image information based on the obstacle coefficient control. In this way, when facing a complex and changeable flight environment, the present invention can adjust the frequency of obtaining image information, or the number of camera frames, according to the environment. The reduction in the number of frames can effectively reduce the energy consumption of obtaining image information. At the same time, fewer images can also reduce the burden on the built-in analysis module, further reducing the consumption of the built-in analysis module, thereby increasing the endurance of the UAV in some special flight environments.

[0056] The process of obtaining the obstacle coefficient includes:

[0057] Set a unit flight distance, and continuously acquire image information at a preset frequency while the drone completes the unit flight distance along the planned path;

[0058] Based on the image information obtained each time, multiple obstacle factors are generated, and then the average of the multiple obstacle factors is set as the obstacle coefficient.

[0059] The barrier coefficient and barrier factor are calculated by the formula:

[0060]

[0061] Get the obstacle coefficient Ob corresponding to the j-th flight unit distance j The obstacle factor corresponding to the i-th image information obtained during the completion of the j-th flight unit distance Where n is the total number of image information acquired during the jth flight unit distance, S i is the obstacle area identified in the i-th image information, S0 is the preset standard area, δ1 is the first correction index preset based on the flight environment, N i is the number of obstacles identified and obtained in the i-th image information, N0 is the preset standard number, δ2 is the second correction index preset based on the flight environment, α and β are the preset first weight coefficient and second weight coefficient respectively, i is a positive integer belonging to n. It should be noted that in the process of collecting image information, the collection direction is the moving direction of the UAV along the planned path, and the collected image camera parameters such as focal length are the same to ensure that the picture is uniform and reliable.

[0062] The process of adjusting the frequency of the video acquisition module acquiring image information based on the obstacle coefficient control includes:

[0063] Obtain the obstacle coefficient Ob j Compare with the preset reference interval [Re1, Re2];

[0064] If Ob j<Re1, it is judged that there are very few obstacles encountered in the current flight process, and the drone can maintain or reduce the frequency of acquiring image information during the next unit flight distance;

[0065] If Ob j > Re1, it is judged that there are very few obstacles encountered in the current flight process, and the drone needs to increase the frequency of acquiring image information during the next unit flight distance. It should be noted that the increase or decrease in the frequency of acquiring image information cannot exceed the preset maximum and minimum values, and the adjustment range is based on the obstacle coefficient Ob j The difference between Re1 or Re1, that is, Ob j -The larger the Re2, the greater the frequency increase, Re1-Ob j The larger it is, the greater the frequency reduction will be.

[0066] If Ob j If it falls within the reference interval [Re1, Re2], it is judged that the number of obstacles encountered during the current flight is normal, a secondary judgment is made based on the historical data of the obstacle coefficient, and the frequency of obtaining image information is adjusted according to the secondary judgment result.

[0067] In this embodiment, a process of obtaining an obstacle coefficient and adjusting the frequency of obtaining image information based on the obstacle coefficient is provided. The obstacle coefficient of the present invention is generated based on multiple pieces of image information obtained during a unit flight distance, and the area of ​​obstacles in the image and the number of obstacles are included in the generation process of the obstacle coefficient. That is, the more obstacles there are or the larger the area of ​​obstacles is, the higher the obstacle coefficient is. At the same time, the allocation of weights also comprehensively considers the different influences of the two on the final result. For example, if there are many obstacles but a small area or if there are large areas but a small number of obstacles, different situations can be distinguished in terms of the value of the obstacle coefficient by setting different weight values.

[0068] The process of obtaining the reference interval includes:

[0069] Set up multiple standard flight environments and store the obstacle coefficients obtained during normal flight in each flight environment;

[0070] In a standard flight environment, the minimum value of the stored obstacle coefficient is set as the left end point Re1 of the reference interval, and the maximum value of the stored obstacle coefficient is set as Set to the right endpoint Re2 of the reference interval, where m is the confidence coefficient of the current standard flight environment, a is an adjustment value based on the UAV model setting, and in this embodiment it is preferably 1. The confidence coefficient is a positive number obtained based on the reference table, and the confidence coefficient is inversely proportional to the number of errors during the flight in the current standard flight environment. The more errors there are, the smaller the confidence coefficient.

[0071] The process of making a secondary judgment includes:

[0072] Obtain the historical data of the obstacle coefficient during the current flight, and construct a rectangular coordinate system and a set of data points. For example, the horizontal axis of the coordinate system uses the i value, and the vertical axis uses the obstacle coefficient value;

[0073] Perform linear regression analysis based on a set of data points to obtain the slope of the regression line;

[0074] If the slope of the regression line is greater than the first critical value, it is judged that the obstacle coefficient continues to increase, the corresponding flight environment is becoming more and more complex, and the frequency of image information collection needs to be increased;

[0075] If the slope of the regression line is less than the second critical value, it is judged that the obstacle coefficient continues to decrease, the corresponding flight environment is becoming simpler, and the frequency of image information acquisition remains unchanged;

[0076] If the slope of the regression line is between the first critical value and the second critical value, a judgment coefficient is obtained based on a plurality of obstacle coefficients, and the acquisition frequency of the image information is controlled based on the judgment coefficient.

[0077] The process of obtaining the judgment coefficient includes:

[0078] By formula:

[0079]

[0080] Obtain the judgment coefficient Jg, where Ob0 is a preset standard obstacle coefficient, M is the total number of completed unit flight distances, and j is a positive integer belonging to M.

[0081] The process of controlling the acquisition frequency of image information based on the judgment coefficient includes:

[0082] Compare the judgment coefficient Jg with the comparison value Jg0;

[0083] If Jg>Jg0, the acquisition frequency of image information needs to be increased;

[0084] If Jg≤Jg0, the acquisition frequency of image information is maintained.

[0085] In this embodiment, a secondary judgment scheme is provided. The secondary judgment process of the present invention first performs a linear regression analysis, obtains a judgment coefficient based on the result of the regression analysis, and obtains a more complete secondary judgment result based on the judgment coefficient. In addition, the secondary analysis of the present invention is performed when the number of obstacles encountered during the current flight is normal, that is, in the case of routine flight, the present invention can still make detailed distinctions and respond to the situation of continuous changes in the flight environment in a timely manner, thereby realizing the optimal scheme for controlling the acquisition frequency, and ensuring that the UAV maintains a high image acquisition frequency in a complex environment and controls the image acquisition frequency to continue to decrease in a simple flight environment or an environment where the complexity of obstacles continues to become simpler.

[0086] See also Figure 2 The present invention also provides a video data analysis method based on real-time landing of a drone, comprising the following steps:

[0087] S1, obtain image information during the flight of the drone;

[0088] S2, the first analysis unit generates a planning path by analyzing the image information and cooperating with the positioning module;

[0089] S3. The second analysis unit obtains an obstacle coefficient by analyzing the image information, and controls and adjusts the frequency of the video acquisition module acquiring the image information based on the obstacle coefficient.

[0090] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A video data analysis system based on real-time landing of a drone, including a video acquisition module, a built-in analysis module and a positioning module, characterized in that: The video acquisition module is used to acquire image information during the flight of the drone; The built-in analysis module includes a first analysis unit and a second analysis unit. The first analysis unit generates a planned path by analyzing the image information in cooperation with the positioning module. The second analysis unit obtains an obstacle coefficient by analyzing the image information and controls and adjusts the frequency of the video acquisition module acquiring image information based on the obstacle coefficient. The positioning module is used for UAV positioning and generating a planned path.

2. The video data analysis system based on real-time landing of unmanned aerial vehicle according to claim 1 is characterized in that: The process of obtaining the obstacle coefficient includes: Set a unit flight distance, and continuously acquire image information at a preset frequency while the drone completes the unit flight distance along the planned path; Based on the image information obtained each time, multiple obstacle factors are generated, and then the average of the multiple obstacle factors is set as the obstacle coefficient.

3. The video data analysis system based on real-time landing of unmanned aerial vehicle according to claim 2 is characterized in that: The barrier coefficient and barrier factor are expressed by the formula: Get the obstacle coefficient Ob corresponding to the j-th flight unit distance j The obstacle factor corresponding to the i-th image information obtained during the completion of the j-th flight unit distance Where n is the total number of image information acquired during the j-th flight unit distance, S i is the obstacle area identified in the i-th image information, S0 is the preset standard area, δ1 is the first correction index preset based on the flight environment, N i is the number of obstacles identified and obtained in the i-th image information, N0 is the preset standard number, δ2 is the second correction index preset based on the flight environment, α and β are the preset first weight coefficient and second weight coefficient respectively, and i is a positive integer belonging to n.

4. The video data analysis system based on real-time landing of unmanned aerial vehicle according to claim 3 is characterized in that: The process of adjusting the frequency of the video acquisition module acquiring image information based on the obstacle coefficient control includes: Obtain the obstacle coefficient Ob j Compare with the preset reference interval [Re1, Re2]; If Ob j <Re1, it is judged that there are very few obstacles encountered in the current flight process; If Ob j >Re1, it is judged that the obstacles encountered in the current flight process are very few and more; If Ob j If it falls within the reference interval [Re1, Re2], it is judged that the number of obstacles encountered during the current flight is normal, a secondary judgment is made based on the historical data of the obstacle coefficient, and the frequency of obtaining image information is adjusted according to the secondary judgment result.

5. The video data analysis system based on real-time landing of unmanned aerial vehicle according to claim 4 is characterized in that: The process of obtaining the reference interval includes: Set up multiple standard flight environments and store the obstacle coefficients obtained during normal flight in each flight environment; In a standard flight environment, the minimum value of the stored obstacle coefficient is set as the left end point Re1 of the reference interval, and the maximum value of the stored obstacle coefficient is set as Set to the right endpoint Re2 of the reference interval, where m is the confidence coefficient of the current standard flight environment and a is the adjustment value based on the drone model setting.

6. The video data analysis system based on real-time landing of unmanned aerial vehicle according to claim 1 is characterized in that: The process of making a secondary judgment includes: Obtain historical data of obstacle coefficients during the current flight and construct a rectangular coordinate system and data point set; Perform linear regression analysis based on a set of data points to obtain the slope of the regression line; If the slope of the regression line is greater than the first critical value, it is judged that the obstacle coefficient continues to increase, the corresponding flight environment is becoming more and more complex, and the frequency of image information collection needs to be increased; If the slope of the regression line is less than the second critical value, it is judged that the obstacle coefficient continues to decrease, the corresponding flight environment is becoming simpler, and the frequency of image information acquisition remains unchanged; If the slope of the regression line is between the first critical value and the second critical value, a judgment coefficient is obtained based on a plurality of obstacle coefficients, and the acquisition frequency of the image information is controlled based on the judgment coefficient.

7. The video data analysis system based on real-time landing of unmanned aerial vehicle according to claim 6 is characterized in that: The process of obtaining the judgment coefficient includes: By formula: Obtain the judgment coefficient Jg, where Ob0 is a preset standard obstacle coefficient, M is the total number of completed unit flight distances, and j is a positive integer belonging to M.

8. The video data analysis system based on real-time landing of unmanned aerial vehicle according to claim 7 is characterized in that: The process of controlling the acquisition frequency of image information based on the judgment coefficient includes: Compare the judgment coefficient Jg with the comparison value Jg0; If Jg>Jg0, the acquisition frequency of image information needs to be increased; If Jg≤Jg0, the acquisition frequency of image information is maintained.

9. A video data analysis method based on real-time landing of a drone, characterized in that: The video data analysis system based on real-time landing of a drone as described in any one of claims 1 to 8 comprises the following steps: Obtain image information during the flight of the drone; Generate a planned path by analyzing image information and coordinating with the positioning module; The obstacle coefficient is obtained by analyzing the image information, and the frequency of the video acquisition module acquiring the image information is adjusted based on the obstacle coefficient control.

Images