CN112489074A - Unmanned aerial vehicle behavior pattern classification method based on motion characteristics - Google Patents
Unmanned aerial vehicle behavior pattern classification method based on motion characteristics Download PDFInfo
- Publication number
- CN112489074A CN112489074A CN202011373186.7A CN202011373186A CN112489074A CN 112489074 A CN112489074 A CN 112489074A CN 202011373186 A CN202011373186 A CN 202011373186A CN 112489074 A CN112489074 A CN 112489074A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- hovering
- behavior
- judging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 11
- 230000009194 climbing Effects 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 6
- 230000009189 diving Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned aerial vehicle behavior pattern classification method based on motion characteristics, which comprises the following steps: the motion types of the unmanned aerial vehicle are as follows: dive, climb, level fly and hover. The determination of dive, climb, level fly and hover is made separately. The invention has the advantages that: the system provides technical support for decisions made by a commander and a controller, improves the recognition capability of the unmanned aerial vehicle, and provides technical support for the 'black flight' phenomenon control of the unmanned aerial vehicle.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle behavior classification, in particular to an unmanned aerial vehicle behavior pattern classification method based on motion characteristics.
Background
Along with the technological progress and the continuous expansion of application scene, unmanned aerial vehicle develops to today, and its usage mainly can divide into military use and civilian unmanned aerial vehicle two parts. The unmanned aerial vehicle industry has developed extremely rapidly and finds application in a number of areas, with the attendant increased operational risks. From the whole development trend, the equipment quantity and the effect of unmanned aerial vehicle in the army of each country will develop at a rapid pace in a future period, and the combat mission that it undertakes will also be more and more extensive. In civilian field, unmanned aerial vehicle will be used by more and more trades, forms diversified unmanned aerial vehicle in the situation of low latitude intensive flight, and airspace structure will be more complicated. Meanwhile, a perfect unmanned aerial vehicle supervision system is not formed in China at present, and the safe operation of the unmanned aerial vehicle is difficult to be effectively controlled. In recent years, with the opening of low-altitude airspace, the flying accidents of the unmanned aerial vehicle frequently threaten public safety and national safety. Therefore, the behavior intentions of various unmanned aerial vehicles are classified, the unmanned aerial vehicle behavior intentions become important measures for defense and supervision of unmanned aerial vehicle operation, the theory significance and the practice value are important, and support is provided for airspace flight situation perception and intelligent airspace management of combined battle fields.
In the current existing scheme for unmanned aerial vehicle classification, unmanned aerial vehicle classification is to classify unmanned aerial vehicles from technical features and application fields. From a technical point of view, unmanned planes can be divided into fixed-wing unmanned planes, helicopter unmanned planes, multi-rotor unmanned planes and other unmanned planes; classify unmanned aerial vehicle according to technical characteristic, can divide into military unmanned aerial vehicle and civilian unmanned aerial vehicle with unmanned aerial vehicle, and civilian unmanned aerial vehicle divide into industrial grade unmanned aerial vehicle and consumption level unmanned aerial vehicle again, and these three kinds of unmanned aerial vehicle carry on equipment again, have great difference in the aspect of customer group and the concrete usage and classify according to these differences.
The prior art has the disadvantages that
(i) The classification is mainly carried out according to known information, and the behavior pattern of the unmanned aerial vehicle with unknown information cannot be classified.
(ii) Classification is not done by means of models, but primarily by using human experience and known information. Therefore, the classification is easy to carry out error classification on an unmanned aerial vehicle due to certain specific factors, and finally, the overall recognition accuracy is low.
(iii) The classification method is too general, and the classification method does not classify specific models in detail and cannot provide effective reference significance for management departments.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a method for classifying the behavior mode of the unmanned aerial vehicle based on the motion characteristics, and solves the defects in the prior art.
In order to realize the purpose, the technical scheme adopted by the invention is as follows:
an unmanned aerial vehicle behavior pattern classification method based on motion characteristics comprises the following steps:
s1: classifying the motion types of the unmanned aerial vehicles;
the motion types of the unmanned aerial vehicle are as follows: dive, climb, level fly and hover.
S2: each exercise type behavior determination method;
s21: and (6) hovering behavior judgment.
S211: judging the hovering behavior under the condition of the reference object: let the profile gravity center of the unmanned plane of m frames of images be (x)m，ym) The apparent contour gravity center of the m +1 frame image is (x)m+1，ym+1) The fluctuation value is μ, and the threshold value is ω. By the formula:
when the fluctuation value mu is larger than omega, the non-hovering state of the unmanned aerial vehicle can be judged;
when the fluctuation value mu is less than or equal to omega, the unmanned aerial vehicle is possibly in a hovering state.
S212: judging the hovering behavior under the condition without the reference object: firstly, establishing a minimum circumscribed rectangle of the profile of the unmanned aerial vehicle, then calculating the area difference of the minimum rectangles of two adjacent frames, and judging hovering if the area difference delta A is smaller than a fluctuation threshold gamma. The area difference is calculated as follows:
ΔA＝|Sm-Sm+1| (3)
wherein S ismIs the minimum bounding rectangle face value of m frames of video, Sm+1Is the smallest rectangular area of m +1 frames of video, and if Δ A > γ, non-hovering is indicated.
S22: judging dive, climbing and flat flight.
S221: according to the kinematics principle, the altitude change speed of the drone can be calculated by the following formula:
wherein Δ H is the altitude change speed of the drone;
theta is a depression angle of the unmanned aerial vehicle;
v is the speed of the unmanned aerial vehicle.
S222: the acceleration change rate of the unmanned aerial vehicle can be obtained by the following formula:
delta a is the acceleration rate of the unmanned aerial vehicle;
v0, Vt is the instantaneous velocity at the adjacent time instant.
S223: the change threshold is set to μ, and the calculation formula is as follows.
μ＝(ΔHη+Δaχ)·C (6)
Eta is the influence coefficient of the height change rate, chi is the influence coefficient of the speed change, and C is the inherent parameters of the unmanned aerial vehicle (related to the volume and air parameters of the unmanned aerial vehicle).
S224: unmanned aerial vehicle behavior judgment result
When mu is larger than 0, climbing is performed, when mu is smaller than 0, diving is performed, and when mu is equal to 0, flat flying is performed.
Compared with the prior art, the invention has the advantages that:
the behavior mode of the unmanned aerial vehicle can be judged, technical support can be provided for decisions of a commander and a controller, and flight safety is guaranteed. Simultaneously, through the classification to unmanned aerial vehicle behavioral pattern, can promote the discernment ability to unmanned aerial vehicle to a certain extent, provide technical support to unmanned aerial vehicle "black flying" phenomenon management and control.
Drawings
FIG. 1 is a diagram of unmanned aerial vehicle behavior classification based on motion characteristics according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating the extraction of hovering behavior of an unmanned aerial vehicle in an environmental background according to an embodiment of the present invention, where a is an m-frame image, b is an m + 1-frame image, c is an m-frame outline, and d is an m + 1-frame outline;
fig. 3 is a schematic diagram illustrating extraction of hovering features of an unmanned aerial vehicle in background-free flight in an embodiment of the present invention, where a is a minimum rectangular area of m frames of video, and b is a minimum rectangular area of m +1 frames of video.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings by way of examples.
As shown in FIG. 1, behavior pattern classification based on unmanned aerial vehicle motion characteristics
And (I) classifying the motion types of the unmanned aerial vehicles.
The motion types of the unmanned aerial vehicle can be roughly divided into actions such as diving, climbing, flat flying, hovering and the like.
And (II) judging the behavior of each motion type.
(1) And (6) hovering behavior judgment.
(i) Judging the hovering behavior under the condition of the reference object: let the gravity center (black circle) of the appearance profile of the unmanned aerial vehicle with m frames of images be (x)m，ym) The apparent contour gravity center (black circle) of the m +1 frame image is (x)m+1，ym+1) As shown in fig. 2, the fluctuation value is μ and the threshold value is ω. By the formula:
when the fluctuation value mu is larger than omega, the non-hovering state of the unmanned aerial vehicle can be judged;
when the fluctuation value mu is less than or equal to omega, the unmanned aerial vehicle is possibly in a hovering state.
(ii) hovering behavior judgment under no reference condition: firstly, establishing a minimum circumscribed rectangle of the profile of the unmanned aerial vehicle, then calculating the area difference of the minimum rectangles of two adjacent frames, and judging hovering if the area difference delta A is smaller than a fluctuation threshold gamma. The area difference is calculated as follows:
ΔA＝|Sm-Sm+1| (3)
wherein S ismIs the minimum bounding rectangle face value of m frames of video, Sm+1Is the smallest rectangular area of the m +1 frame video, as shown in fig. 3. If Δ A > γ, non-hovering is indicated.
(2) Judging dive, climbing and flat flight.
(i) According to the kinematics principle, the altitude change speed of the drone can be calculated by the following formula:
wherein Δ H is the altitude change speed of the drone;
theta is a depression angle of the unmanned aerial vehicle;
v is the speed of the unmanned aerial vehicle.
(ii) the acceleration rate of the drone can be calculated by the following equation:
delta a is the acceleration rate of the unmanned aerial vehicle;
v0, Vt is the instantaneous velocity at the adjacent time instant.
(iii) the change threshold is set to μ, and the calculation formula is as follows.
μ＝(ΔHη+Δaχ)·C (6)
Eta is the influence coefficient of the height change rate, chi is the influence coefficient of the speed change, and C is the inherent parameters of the unmanned aerial vehicle (related to the volume and air parameters of the unmanned aerial vehicle).
(iv) unmanned aerial vehicle behavior judgment result
When mu is larger than 0, climbing is performed, when mu is smaller than 0, diving is performed, and when mu is equal to 0, flat flying is performed.
It will be appreciated by those of ordinary skill in the art that the examples described herein are intended to assist the reader in understanding the manner in which the invention is practiced, and it is to be understood that the scope of the invention is not limited to such specifically recited statements and examples. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (1)
1. An unmanned aerial vehicle behavior pattern classification method based on motion characteristics is characterized by comprising the following steps:
s1: classifying the motion types of the unmanned aerial vehicles;
the motion types of the unmanned aerial vehicle are as follows: dive, climb, level fly and hover.
S2: each exercise type behavior determination method;
s21: and (6) hovering behavior judgment.
S211: judging the hovering behavior under the condition of the reference object: let the profile gravity center of the unmanned plane of m frames of images be (x)m，ym) The apparent contour gravity center of the m +1 frame image is (x)m+1，ym+1) The fluctuation value is μ, and the threshold value is ω. By the formula:
when the fluctuation value mu is larger than omega, the non-hovering state of the unmanned aerial vehicle can be judged;
when the fluctuation value mu is less than or equal to omega, the unmanned aerial vehicle is possibly in a hovering state.
S212: judging the hovering behavior under the condition without the reference object: firstly, establishing a minimum circumscribed rectangle of the profile of the unmanned aerial vehicle, then calculating the area difference of the minimum rectangles of two adjacent frames, and judging hovering if the area difference delta A is smaller than a fluctuation threshold gamma. The area difference is calculated as follows:
ΔA＝|Sm-Sm+1| (3)
wherein S ismIs the minimum bounding rectangle face value of m frames of video, Sm+1Is the smallest rectangular area of m +1 frames of video, and if Δ A > γ, non-hovering is indicated.
S22: judging dive, climbing and flat flight.
S221: according to the kinematics principle, the altitude change speed of the drone can be calculated by the following formula:
wherein Δ H is the altitude change speed of the drone;
theta is a depression angle of the unmanned aerial vehicle;
v is the speed of the unmanned aerial vehicle.
S222: the acceleration change rate of the unmanned aerial vehicle can be obtained by the following formula:
delta a is the acceleration rate of the unmanned aerial vehicle;
v0, Vt is the instantaneous velocity at the adjacent time instant.
S223: the change threshold is set to μ, and the calculation formula is as follows.
μ＝(ΔHη+Δaχ)·C (6)
Eta is the influence coefficient of the height change rate, chi is the influence coefficient of the speed change, and C is the inherent parameter of the unmanned aerial vehicle.
S224: unmanned aerial vehicle behavior judgment result
When mu is larger than 0, climbing is performed, when mu is smaller than 0, diving is performed, and when mu is equal to 0, flat flying is performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011373186.7A CN112489074B (en) | 2020-11-30 | 2020-11-30 | Unmanned aerial vehicle behavior pattern classification method based on motion characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011373186.7A CN112489074B (en) | 2020-11-30 | 2020-11-30 | Unmanned aerial vehicle behavior pattern classification method based on motion characteristics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112489074A true CN112489074A (en) | 2021-03-12 |
| CN112489074B CN112489074B (en) | 2024-09-17 |
Family
ID=74937347
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011373186.7A Active CN112489074B (en) | 2020-11-30 | 2020-11-30 | Unmanned aerial vehicle behavior pattern classification method based on motion characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112489074B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040071319A1 (en) * | 2002-09-19 | 2004-04-15 | Minoru Kikuchi | Object velocity measuring apparatus and object velocity measuring method |
| CN101231696A (en) * | 2008-01-30 | 2008-07-30 | 安防科技（中国）有限公司 | Method and system for detection of hangover |
| CN107580161A (en) * | 2016-07-04 | 2018-01-12 | 奥林巴斯株式会社 | Photographic equipment and method, travelling shot device, photography moving body and its control device |
| CN107977985A (en) * | 2017-11-29 | 2018-05-01 | 上海拓攻机器人有限公司 | Unmanned plane hovering method, apparatus, unmanned plane and storage medium |
| CN109211573A (en) * | 2018-09-12 | 2019-01-15 | 北京工业大学 | A kind of evaluating method of unmanned plane hoverning stability |
| TWI652954B (en) * | 2018-01-30 | 2019-03-01 | 和碩聯合科技股份有限公司 | Operation mode switching method and electronic device using the same |
| WO2019244893A1 (en) * | 2018-06-19 | 2019-12-26 | 本田技研工業株式会社 | Aircraft and control method for same |
| KR20200048216A (en) * | 2018-10-29 | 2020-05-08 | 진광식 | Drone performance evaluation system |
| CN111504341A (en) * | 2020-04-30 | 2020-08-07 | 中国直升机设计研究所 | Helicopter flight state identification method |
-
2020
- 2020-11-30 CN CN202011373186.7A patent/CN112489074B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040071319A1 (en) * | 2002-09-19 | 2004-04-15 | Minoru Kikuchi | Object velocity measuring apparatus and object velocity measuring method |
| CN101231696A (en) * | 2008-01-30 | 2008-07-30 | 安防科技（中国）有限公司 | Method and system for detection of hangover |
| CN107580161A (en) * | 2016-07-04 | 2018-01-12 | 奥林巴斯株式会社 | Photographic equipment and method, travelling shot device, photography moving body and its control device |
| CN107977985A (en) * | 2017-11-29 | 2018-05-01 | 上海拓攻机器人有限公司 | Unmanned plane hovering method, apparatus, unmanned plane and storage medium |
| TWI652954B (en) * | 2018-01-30 | 2019-03-01 | 和碩聯合科技股份有限公司 | Operation mode switching method and electronic device using the same |
| WO2019244893A1 (en) * | 2018-06-19 | 2019-12-26 | 本田技研工業株式会社 | Aircraft and control method for same |
| CN109211573A (en) * | 2018-09-12 | 2019-01-15 | 北京工业大学 | A kind of evaluating method of unmanned plane hoverning stability |
| KR20200048216A (en) * | 2018-10-29 | 2020-05-08 | 진광식 | Drone performance evaluation system |
| CN111504341A (en) * | 2020-04-30 | 2020-08-07 | 中国直升机设计研究所 | Helicopter flight state identification method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112489074B (en) | 2024-09-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11087632B1 (en) | Autonomous UAV obstacle avoidance using machine learning from piloted UAV flights | |
| CN110007675B (en) | Vehicle automatic driving decision-making system based on driving situation map and training set preparation method based on unmanned aerial vehicle | |
| CN109871628B (en) | Simulation computing system and method for evaluating seaworthiness compliance of amphibious aircraft | |
| CN107045638B (en) | Flight safety event analysis method based on situational awareness model | |
| De Croon et al. | Sky segmentation approach to obstacle avoidance | |
| CN108153334B (en) | Visual autonomous return and landing method and system for unmanned helicopter without cooperative target | |
| CN1856810A (en) | Flight simulator | |
| CN114330115B (en) | Neural network air combat maneuver decision-making method based on particle swarm search | |
| CN115755956B (en) | Knowledge and data collaborative driving unmanned aerial vehicle maneuvering decision method and system | |
| CN112053593B (en) | Airport unmanned aerial vehicle control area planning method based on risk assessment | |
| CN115903865A (en) | Aircraft near-distance air combat maneuver decision implementation method | |
| CN115033022A (en) | DDPG unmanned aerial vehicle landing method based on expert experience and oriented to mobile platform | |
| CN111504341A (en) | Helicopter flight state identification method | |
| CN114063644A (en) | Unmanned combat aircraft air combat autonomous decision method based on pigeon flock reverse confrontation learning | |
| Pointner et al. | Using formal methods to verify safe deep stall landing of a MAV | |
| CN114003052B (en) | Fixed wing unmanned aerial vehicle longitudinal movement robust self-adaptive control method based on dynamic compensation system | |
| CN111192481A (en) | Method for determining boundary of unmanned aerial vehicle control area of approach and departure procedure based on collision risk | |
| Chiu et al. | Vision-only automatic flight control for small UAVs | |
| Haartsen et al. | Simulation of unmanned aerial vehicles in the determination of accident locations | |
| CN113096448B (en) | General design method for lifting route of trainer | |
| CN117892552A (en) | Carrier-borne aircraft landing risk situation modeling method and system | |
| CN112489074A (en) | Unmanned aerial vehicle behavior pattern classification method based on motion characteristics | |
| CN112034880A (en) | Novel multi-unmanned aerial vehicle collaborative route planning method | |
| KR102046823B1 (en) | Aircraft maneuvering simulator in engagement level, simulation method thereof and a computer-readable storage medium for executing the method | |
| CN114326766B (en) | Cooperative autonomous tracking and landing method for vehicle and machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |