CN115355764A - Unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets - Google Patents
Unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets Download PDFInfo
- Publication number
- CN115355764A CN115355764A CN202211070718.9A CN202211070718A CN115355764A CN 115355764 A CN115355764 A CN 115355764A CN 202211070718 A CN202211070718 A CN 202211070718A CN 115355764 A CN115355764 A CN 115355764A
- Authority
- CN
- China
- Prior art keywords
- target
- unmanned aerial
- aerial vehicle
- module
- identification
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000000007 visual effect Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 238000004088 simulation Methods 0.000 claims abstract description 5
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 239000000428 dust Substances 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 6
- 230000005693 optoelectronics Effects 0.000 claims description 3
- 230000005622 photoelectricity Effects 0.000 claims description 3
- 230000003340 mental effect Effects 0.000 abstract description 4
- 238000003780 insertion Methods 0.000 description 9
- 230000037431 insertion Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 4
- 230000005484 gravity Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000000087 stabilizing effect Effects 0.000 description 1
- 238000003756 stirring Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F41—WEAPONS
- F41H—ARMOUR; ARMOURED TURRETS; ARMOURED OR ARMED VEHICLES; MEANS OF ATTACK OR DEFENCE, e.g. CAMOUFLAGE, IN GENERAL
- F41H11/00—Defence installations; Defence devices
- F41H11/02—Anti-aircraft or anti-guided missile or anti-torpedo defence installations or systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets, which comprises the following steps: firstly, receiving target information issued by a radar by a photoelectric system; then judging whether the target reaches the identification distance: if the target does not reach the identification distance, the target is tracked in the detection range, and after the target reaches the identification distance, the visual tracking is realized through the photoelectric system, and meanwhile, the photoelectric holder is controlled by the servo control system to rotate towards the direction of reducing the miss distance all the time, so that the stable tracking is realized; and finally, driving away or forcing to land the unmanned aerial vehicle through the unmanned aerial vehicle counter-braking equipment. According to the invention, a target image is obtained by taking a photoelectric system as a visual basis, and stable visual tracking is realized by utilizing the control of a servo system; feature extraction is carried out on the target image through a mental network, discrimination is made, and visual-based friend or foe target identification is achieved; and the unmanned aerial vehicle target drone can be used for carrying out mental network simulation training and self-learning so as to enhance the target recognition capability of the enemy unmanned aerial vehicle in a long distance.
Description
Technical Field
The invention relates to the technical field of anti-unmanned aerial vehicles, in particular to an unmanned aerial vehicle confrontation method based on vision based enemy and my target identification.
Background
Because unmanned aerial vehicle is small, lower infrared characteristic has, mobility is stronger, flexibility is high, the flight path is irregular, therefore it is difficult to stably track in real time, the tracking algorithm realizes the degree of difficulty greatly, to unmanned aerial vehicle target identification problem under the remote distance, because the shared pixel proportion of target in the image is very little, lead to the imaging characteristic of target to reduce in a large number, traditional characteristic information is difficult to express, in addition, the unmanned aerial vehicle target is from the bird crowd, the vegetation is complicated background identification screening, still need adapt to unmanned aerial vehicle target rotation, translation, change such as scale transform, so unmanned aerial vehicle target identification is difficult, in order to realize that enemy unmanned aerial vehicle target distinguishes under the remote distance, and visual stable tracking, provide the unmanned aerial vehicle countermeasure method of enemy target identification based on vision.
Disclosure of Invention
The invention aims to: in order to overcome the defects in the prior art, the invention provides the unmanned aerial vehicle countermeasure method based on vision enemy-my target identification, which is used for enhancing the identification capability of the enemy-my unmanned aerial vehicle target in a long distance and realizing visual and stable tracking through simulated training learning, and is beneficial to implementing effective countermeasures.
The technical scheme is as follows: in order to achieve the purpose, the invention provides a vision-based unmanned aerial vehicle confrontation method for identifying enemy and my targets, which comprises the following steps:
step one, receiving target information by an optoelectronic system: receiving target information issued by a radar system through a photoelectric system, wherein the target information specifically comprises a target distance, an azimuth angle and a pitch angle, adjusting the posture of a photoelectric holder according to the received target information, and selecting manual or automatic focusing and zooming;
step two, judging whether the target reaches the identification distance: the method comprises the steps that a target is tracked in a detection range when the target does not reach an identification distance, and the target is identified and tracked when the target reaches the identification distance, wherein the identification adopts an unmanned aerial vehicle target identification method based on deep learning, specifically, a sliding window slides on an image, the whole image is traversed, feature extraction is carried out through a neural network, classification of window images is respectively judged, an accurate frame of the object is adjusted through a regression method, the purposes of identification and positioning are achieved, and neural network simulation training is carried out through an unmanned aerial vehicle target drone so as to improve the discrimination capability of the unmanned aerial vehicle;
step three, tracking the photoelectric target: the method comprises the steps that targets and backgrounds in the atmosphere are obtained through a photoelectric system, the targets are guided to be found and automatically locked and are displayed on a display screen, visual tracking is achieved, meanwhile, a photoelectric upper computer receives the target miss distance of the unmanned aerial vehicle in the azimuth direction and the pitching direction, PID control is conducted according to the distance, the focal length and the field angle, a servo control system controls a photoelectric holder to always rotate in the direction of reducing the miss distance, and a photoelectric visual axis points to the targets and stably tracks the targets;
step four, the unmanned aerial vehicle resists: the electronic countercheck cloud platform follows the motion of photoelectricity cloud platform and opens the interference, drives away or compels to land unmanned aerial vehicle through unmanned aerial vehicle counter-braking equipment.
Further, the unmanned aerial vehicle target identification method based on deep learning firstly generates a plurality of candidate region frames, namely potential target regions, then extracts target features, and carries out category judgment and position positioning.
Further, including fuselage power module, horn module and undercarriage module, it is a plurality of horn module and undercarriage module encircle everywhere in fuselage power module symmetric distribution sets up, the horn module with the interval sets up in turn of undercarriage module, fuselage power module is provided with the arm exhibition along directional central radial flexible and adjusts the module, the expansion end cartridge of arm exhibition regulation module the horn module.
Furthermore, the undercarriage module passes through the spacing subassembly of elasticity for its both sides the expansion end follow-up setting of arm exhibition adjusting module, the spacing subassembly of elasticity is including clamping the seat, fixed mounting has a plurality of parallel quarter butt on clamping the terminal surface of seat, the cover is equipped with the elastic component on the parallel quarter butt, and is a plurality of the same board that bulldozes is established to parallel quarter butt tip cover, bulldoze the board compare in the root fixed setting of undercarriage module, be located same two on the undercarriage module bulldoze the parallel interval fixed setting of board.
Further, the rotating groove has been seted up on the fuselage power module, a plurality of sliding trays have been seted up to the rotating groove bottom surface, and is a plurality of the sliding tray radially disperses to set up and even equidistant distribution, the module is adjusted through adjusting drive arrangement drive edge to the arm exhibition the sliding tray outwards removes, the module is adjusted through first reset assembly kick-back edge to the arm exhibition the sliding tray inwards removes.
Furthermore, the root up end of module is adjusted in the arm exhibition is provided with the stub roll, the stub roll slides in the strip leads to the inslot, the strip leads to the groove rather than corresponding the sliding tray syntropy sets up, the strip leads to the groove and sets up on the end liner board, the end liner board cover in sliding tray notch top, the end liner board top is rotated and is provided with adjust drive arrangement, adjust drive arrangement top cover and establish the dust screen, the dust screen corresponds the card and locates rotate the inslot that clamps of groove upper port, the dust screen compresses tightly fixedly through the block.
Has the advantages that: according to the unmanned aerial vehicle confrontation method based on vision enemy-me target identification, a photoelectric system is used as a vision basis to obtain a target image, and a servo system is used for controlling to realize stable visual tracking; feature extraction is carried out on the target image through a mental network, discrimination is made, and visual-based friend or foe target identification is achieved; and the unmanned aerial vehicle target drone can be used for carrying out mental network simulation training and self-learning so as to enhance the target recognition capability of the enemy unmanned aerial vehicle in a long distance.
Drawings
Fig. 1 is a block diagram of a method for unmanned aerial vehicle confrontation based on visual sense identification of friend or foe targets;
FIG. 2 is a schematic flow chart of the visual tracking of the photoelectric target;
FIG. 3 is a schematic block diagram of an algorithm implementation of a deep learning-based unmanned aerial vehicle target identification method;
figure 4 is a block diagram of an unmanned drone;
figure 5 is a top view block diagram of an unmanned drone;
FIG. 6 is a structural view of an elastic stopper assembly;
FIG. 7 is an exploded view of the fuselage power module;
FIG. 8 is a partially exploded view of the power module of the fuselage;
FIG. 9 is a perspective view of the arm spread adjustment module;
fig. 10 is an exploded view of a portion of the arm extension adjustment module.
Detailed Description
The present invention will be further described with reference to the accompanying drawings.
1-3, a method for a vision-based enemy-me target identification drone confrontation, comprising the steps of:
step one, receiving target information by an optoelectronic system: receiving target information issued by a radar system through a photoelectric system, wherein the target information specifically comprises a target distance, an azimuth angle and a pitch angle, adjusting the posture of a photoelectric holder according to the received target information, and selecting manual or automatic focusing and zooming;
step two, judging whether the target reaches the identification distance: tracking the target in a detection range when the target does not reach the identification distance, and identifying and tracking the target when the target reaches the identification distance, wherein the identification adopts an unmanned aerial vehicle target identification method based on deep learning, specifically, a sliding window slides on an image, the whole image is traversed, feature extraction is carried out through a neural network, classification of window images is respectively judged, the accurate frame of the object is adjusted through a regression method, the purposes of identification and positioning are achieved, and neural network simulation training is carried out through an unmanned aerial vehicle target drone so as to improve the discrimination capability of the unmanned aerial vehicle;
step three, tracking the photoelectric target: the method comprises the steps that targets and backgrounds in the atmosphere are obtained through a photoelectric system, the targets are guided to be found and automatically locked and are displayed on a display screen, visual tracking is achieved, meanwhile, a photoelectric upper computer receives the target miss distance of the unmanned aerial vehicle in the azimuth direction and the pitching direction, PID control is conducted according to the distance, the focal length and the field angle, a servo control system controls a photoelectric holder to always rotate in the direction of reducing the miss distance, and a photoelectric visual axis points to the targets and stably tracks the targets;
step four, the unmanned aerial vehicle resists: the electronic countercheck cloud platform follows the motion of photoelectricity cloud platform and opens the interference, drives away or compels to land unmanned aerial vehicle through unmanned aerial vehicle counter-braking equipment.
According to the unmanned aerial vehicle target identification method based on deep learning, a plurality of candidate region frames, namely potential target regions, are generated firstly, target features are extracted, and category judgment and position positioning are carried out.
The unmanned aerial vehicle target drone shown in the attached figures 4-5 comprises a body power module 1, a horn module 2 and an undercarriage module 3, is convenient to disassemble and store in a modular assembling and splicing mode, comprises two types of large-scale fixed-wing unmanned aerial vehicle target drone and rotor unmanned aerial vehicle target drone according to requirements, and aims at the rotor unmanned aerial vehicle target drone, a plurality of horn modules 2 and undercarriage modules 3 are symmetrically distributed and arranged around the body power module 1, the horn modules 2 and the undercarriage modules 3 are alternately arranged at intervals, the body power module 1 is provided with a spread-arm adjusting module 4 in a telescopic manner along the radial direction pointing to the center, and the movable end of the spread-arm adjusting module 4 is inserted into the horn module 2;
the stability of the gravity center is ensured by the symmetrical and alternate spaced arrangement mode, and the target drone arm can be expanded or reduced proportionally by stretching along the radial direction.
The undercarriage module 3 is arranged along with the movable ends of the arm spread adjusting modules 4 on two sides of the undercarriage module through elastic limiting components 5, and the elastic limiting components 5 on two sides of the same undercarriage module 3 are symmetrically arranged;
through elasticity locating part with the undercarriage module for arm exhibition regulation module elastic connection for the position of the in-process undercarriage that the arm exhibition was adjusted also follows and makes the equal proportion transform, realizes the holistic scale transform of target drone, guarantees that the focus of unmanned aerial vehicle arrangement is level and smooth, guarantees to fly and rise and fall stably.
As shown in fig. 6, the elastic limiting component 5 includes a clamping seat 6, the clamping seat 6 is clamped with respect to a side wall of a movable end of the arm extension adjusting module 4, a plurality of parallel short rods 7 are fixedly mounted on an end surface of the clamping seat 6, an elastic member 8 is sleeved on each of the parallel short rods 7, the same pushing plate 9 is sleeved on end portions of the plurality of parallel short rods 7, the pushing plate 9 is fixedly arranged with respect to a root of the undercarriage module 3, two pushing plates 9 on the same undercarriage module 3 are fixedly arranged in parallel at intervals, and the two pushing plates 9 respectively compress the plurality of elastic members 8 on two sides;
during installation, the relative arm exhibition of the seat that clamps of one side is adjusted the module lateral wall and is clamped earlier, and the board that bulldozes of homonymy overlaps to its a plurality of parallel quarter butts that correspond again to slide along the quarter butt and compress the elastic component, bulldoze the opposite side again and bulldoze the board cover to another group elasticity spacing subassembly on the parallel quarter butt, compress the elastic component on it simultaneously, until it clamps the seat and can block to establish on its arm exhibition that corresponds one side adjusts the module lateral wall, support the undercarriage module in the middle part through the elasticity of both sides compression. Avoid enlarging or reducing the in-process at the yardstick, the undercarriage module is partial to the unstable problem of focus that leads to in arbitrary one side to guarantee safe rising and falling, reduce the damage to unmanned aerial vehicle target drone aircraft, reduce the cost of maintaining.
As shown in fig. 7-8, a rotating groove 10 is formed in the fuselage power module 1, a plurality of sliding grooves 11 are formed in the bottom surface of the rotating groove 10, the plurality of sliding grooves 11 are radially diverged and uniformly distributed at equal intervals, the arm spread adjusting module 4 is driven by an adjusting driving device to move outwards along the sliding grooves 11, and the arm spread adjusting module 4 rebounds through a first resetting component and moves inwards along the sliding grooves 11;
the first reset assembly specifically adopts a first reset spring 13 and a first guide rod 14, the root of the arm extension adjusting module 4 is elastically connected to the inner wall of the end part of the sliding groove 11 through the first reset spring 13, the first reset spring 13 is sleeved outside the first guide rod 14, the root of the first guide rod 14 is fixed to the inner wall of the end part of the sliding groove 11, and the end part of the first guide rod 14 is inserted into a sliding cavity 38 in the arm extension adjusting module 4;
the motion trail of the arm spread adjusting modules is limited according to the arrangement of the sliding grooves, so that the plurality of arm spread adjusting modules do symmetrical telescopic motion relative to the gravity center of the power module of the airplane body, the gravity center is ensured to be stable in the arm spread adjusting process, and the stable flying state can be ensured even if the arm spread adjusting module is adjusted in the flying state; the arm extension adjusting module is further guided to be limited through the first guide rod, the adjustment stability is further guaranteed, the arm extension adjusting module stretches the first reset spring when extending the arm extension outwards, and the reset effect is achieved through the contraction of the first reset spring.
The upper end face of the root of the arm extension adjusting module 4 is provided with a short roller 15, the short roller 15 slides in a strip-shaped through groove 16, the strip-shaped through groove 16 is arranged in the same direction as the corresponding sliding groove 11, the strip-shaped through groove 16 is formed in a bottom lining plate 17, the bottom lining plate 17 covers the notch of the sliding groove 11, the adjusting driving device is rotatably arranged above the bottom lining plate 17, a dust screen 22 is covered above the adjusting driving device, the dust screen 22 is correspondingly clamped in a clamping groove 23 at the upper port of the rotating groove 10, and the dust screen 22 is tightly pressed and fixed through a cover cap 24;
as a preferred embodiment, the adjusting driving device specifically includes a driving disc 18, the short roller 15 is attached to a driving surface 18-1 of the driving disc 18 to roll, the driving disc 18 rotates around a central short shaft 19, the central short shaft 19 is fixedly arranged in comparison with the central position of the rotating groove 10, the driving disc 18 is driven by a driving motor 20, the driving motor 20 is installed in a mounting hole 21 on the mounting table 12 in a clamping manner, the upper end of the central short shaft 19 is penetrated by a central hole of the dust screen 22, and the end of the central short shaft 19 is provided with the cap 24;
utilize the driving-disc drive, guarantee the flexible synchronism of a plurality of arm exhibition adjusting device, change arm exhibition adjusting device's flexible volume through the radius distance of driving face surface to driving-disc center, the driving face in every unit portion is by the smooth transition of shortest distance to the maximum distance, the annular driving face of whole driving-disc of drive face of smooth transition connection constitution of driving face in a plurality of unit portions, utilize the roll cooperation of stub roll and driving face, it is smooth and easy to guarantee the relative motion between drive wheel and the stub roll, and reduce the wearing and tearing of driving wheel driving face, through setting up the dust screen, have dustproof radiating effect concurrently.
The inner core part 24-1 of the cap 24 is screwed and fixed relative to the end part of the central short shaft 19 through threaded connection, the outer side cylinder wall 24-2 of the cap 24 is pressed against the upper end surface of the dustproof net 22, and the bottom surface of the inner core part (24-1) of the cap (24) is provided with a brake assembly which controls the unit feeding adjustment of the adjusting and driving device;
as a preferred embodiment, the brake assembly specifically includes a card-assisting spring 25, the card-assisting spring 25 is disposed on the bottom surface of the inner core portion 24-1, a card disc 26 is connected to the bottom end of the card-assisting spring 25, a card slot disc 27 is correspondingly disposed below the card disc 26, the card slot disc 27 is fixed on the upper end surface of the drive disc 18, a plurality of clips 29 and card slots 28 are correspondingly disposed on the joint surfaces of the card disc 26 and the card slot disc 27, the clips 29 and the card slots 28 are uniformly arranged in an equidistant manner, the clips 29 and the card slots 28 are both in a quarter sphere shape, and the sphere faces the opposite direction of rotation of the drive disc 18;
the relative position of the inner core part pair card dish through the block is fixed, guarantee that card dish and draw-in groove dish can gomphosis each other, utilize helping the card spring drive card dish to compress tightly in the draw-in groove dish, it is spacing to brake the driving-disc through gomphosis between them, encircle evenly to lay the checkpost and the draw-in groove that correspond the setting through equidistant, realize the arm exhibition flexible regulation of unit feeding volume, the shape structure of quarter spheroid form, when guaranteeing normal corotation regulation, prevent the driving-disc reversal phenomenon that the module backward thrust arouses is adjusted to the arm exhibition, in order to guarantee that the arm exhibition adjusts back relative position's locking.
As shown in fig. 9-10, the arm extension adjusting module 4 includes an inverted L-shaped housing 30, a second guide rod 31 is fixedly mounted on the inner side of the bottom end of the housing 30, a vertical insertion groove 32 is separately formed in the vertical part of the outer side of the housing 30, the root of the arm module 2 is inserted in the vertical insertion groove 32, and the root of the arm module 2 is fixed by being abutted against the bottom surface of a baffle 36 through an abutting block 34;
the root of the horn module 2 is fixedly provided with an insertion rod 33, the insertion rod 33 is correspondingly inserted into the vertical insertion groove 32, the bottom of the insertion rod 33 is supported on a jacking block 34, the jacking block 34 is elastically connected into a guide hole in the bottom surface of the vertical insertion groove 32 through a second return spring 35, the top of the insertion rod 33 abuts against the bottom surface of a baffle 36, and the baffle 36 slides in a limiting groove 40;
insert the cartridge pole by vertical cartridge groove upper end inserted hole, the horn module then stretches out by the terminal surface notch, through the degree of freedom of vertical cartridge groove restriction horn module in the horizontal plane, utilize the ascending degree of freedom of the spacing cartridge pole vertical direction of jack-up piece and baffle, and then realize that the horn module is fixed for the cartridge of arm exhibition adjusting module, carry on spacingly to the baffle through the spacing groove for the horizontal slip along the spacing groove is done to the baffle, and then realize the switching of vertical cartridge groove upper end inserted hole.
The baffle 36 is connected to the sliding block 37 through a mounting plate 41, the mounting plate 41 is fixedly mounted on the upper end surface of the sliding block 37, the mounting plate 41 slides in the limiting groove 40, the sliding block 37 slides in the sliding cavity 38, and the sliding block 37 is connected to the inner end surface of the sliding cavity 38 through a third return spring 39;
compress tightly the baffle in vertical cartridge groove upper end insertion port department through third reset spring, cooperation jack-up piece is tight in the baffle bottom surface with the cartridge pole top, and both gomphosis restriction each other prevents that the cartridge pole from breaking away from vertical cartridge groove, guarantees the structure safety of stabilizing.
The baffle plate 36 is hinged with the front end of the mounting plate 41 through a hinge assembly 42, and a limit plate 43 at the tail end of the baffle plate 36 is embedded with a limit surface 44 at the front end of the mounting plate 41 for limiting;
through articulated setting, carrying out the horn and dismantling the in-process, make the jack-up piece push down compression second reset spring through pressing down the baffle, stir the baffle to keeping away from vertical cartridge groove direction again, when the baffle breaks away from vertical cartridge groove inserted hole, utilize the energy of second reset spring release to pop out vertical cartridge groove with the horn module, easy operation and convenience.
The above description is only of the preferred embodiments of the present invention, and it should be noted that: it will be apparent to those skilled in the art that various modifications and adaptations can be made without departing from the principles of the invention described above, and such modifications and adaptations are intended to be within the scope of the invention.
Claims (6)
1. An unmanned aerial vehicle confrontation method based on vision identification of friend or foe targets is characterized by comprising the following steps:
step one, receiving target information by an optoelectronic system: receiving target information issued by a radar system through a photoelectric system, wherein the target information specifically comprises a target distance, an azimuth angle and a pitch angle, adjusting the posture of a photoelectric holder according to the received target information, and selecting manual or automatic focusing and zooming;
step two, judging whether the target reaches the identification distance: the method comprises the steps that a target is tracked in a detection range when the target does not reach an identification distance, and the target is identified and tracked when the target reaches the identification distance, wherein the identification adopts an unmanned aerial vehicle target identification method based on deep learning, specifically, a sliding window slides on an image, the whole image is traversed, feature extraction is carried out through a neural network, classification of window images is respectively judged, an accurate frame of the object is adjusted through a regression method, the purposes of identification and positioning are achieved, and neural network simulation training is carried out through an unmanned aerial vehicle target drone so as to improve the discrimination capability of the unmanned aerial vehicle;
step three, tracking the photoelectric target: the method comprises the steps that targets and backgrounds in the atmosphere are obtained through a photoelectric system, the targets are guided to be found and automatically locked and displayed on a display screen, visual tracking is achieved, meanwhile, a photoelectric upper computer receives the target miss distance of the unmanned aerial vehicle in the azimuth direction and the pitch direction, PID control is conducted according to the distance, the focal length and the angle of view, a servo control system controls a photoelectric holder to rotate towards the direction of reducing the miss distance all the time, and a photoelectric visual axis points at the targets and stably tracks;
step four, the unmanned aerial vehicle resists: the electronic countermeasure cloud platform follows the motion of photoelectricity cloud platform and opens the interference, drives away or compels to land unmanned aerial vehicle through unmanned aerial vehicle counter-braking equipment.
2. The method of claim 1, wherein the method comprises the following steps: according to the unmanned aerial vehicle target identification method based on deep learning, a plurality of candidate region frames, namely potential target regions, are generated firstly, target features are extracted, and category judgment and position positioning are carried out.
3. The unmanned aerial vehicle target drone related in the unmanned aerial vehicle confrontation method based on vision friend or foe target recognition of any one of claims 1-2, characterized in that: including fuselage power module (1), horn module (2) and undercarriage module (3), a plurality of all around in fuselage power module (1) symmetric distribution sets up horn module (2) and undercarriage module (3) interval in turn sets up, fuselage power module (1) is provided with arm exhibition regulation module (4) along directional central radial flexible, the expansion end cartridge of arm exhibition regulation module (4) horn module (2).
4. The drone target machine involved in a method of drone confrontation based on visual sense of friend or foe target recognition according to claim 3, characterized in that: undercarriage module (3) are for its both sides through elasticity spacing subassembly (5) the expansion end follow-up setting of arm exhibition adjusting module (4), elasticity spacing subassembly (5) is including clamping seat (6), fixed mounting has a plurality of parallel quarter butt (7) on clamping the terminal surface of seat (6), it is equipped with elastic component (8) to overlap on parallel quarter butt (7), and is a plurality of parallel quarter butt (7) tip cover is established same and is pushed and press board (9), it compares in to push and press board (9) the root of undercarriage module (3) is fixed to be set up, is located same two on undercarriage module (3) it sets up to push and press board (9) parallel interval.
5. The drone target machine involved in a method of drone confrontation based on visual sense of friend or foe target recognition according to claim 3, characterized in that: seted up on fuselage power module (1) and rotated groove (10), a plurality of sliding trays (11), a plurality of have been seted up to rotation groove (10) bottom surface, it is a plurality of sliding tray (11) radially set up and even equidistant distribution radially disperse, arm exhibition is adjusted module (4) and is followed through adjusting the drive arrangement drive sliding tray (11) outwards remove, arm exhibition is adjusted module (4) and is kick-backed along through first reset assembly sliding tray (11) inwardly moved.
6. The drone in the method for drone confrontation based on visual identification of friend or foe targets according to claim 5, characterized in that: the root up end of module (4) is adjusted in the arm exhibition is provided with stub roll (15), stub roll (15) slide in the bar leads to groove (16), the bar leads to groove (16) and corresponds rather than sliding tray (11) syntropy sets up, the bar leads to groove (16) and sets up on end liner board (17), end liner board (17) cover in sliding tray (11) notch top, end liner board (17) top is rotated and is provided with adjust drive arrangement, adjust drive arrangement top cover and establish dust screen (22), dust screen (22) correspond the card and locate rotate in groove (10) upper port clamp groove (23), dust screen (22) compress tightly fixedly through block cap (24).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211070718.9A CN115355764A (en) | 2022-09-02 | 2022-09-02 | Unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211070718.9A CN115355764A (en) | 2022-09-02 | 2022-09-02 | Unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115355764A true CN115355764A (en) | 2022-11-18 |
Family
ID=84005675
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211070718.9A Pending CN115355764A (en) | 2022-09-02 | 2022-09-02 | Unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115355764A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109269352A (en) * | 2018-09-20 | 2019-01-25 | 北京机械设备研究所 | A kind of unmanned plane tracking goal approach and system based on ground location |
| CN109283521A (en) * | 2018-10-18 | 2019-01-29 | 广州市海林电子科技发展有限公司 | It blocks the method for unmanned plane and blocks the anti-UAV system of formula |
| CN109373821A (en) * | 2017-05-16 | 2019-02-22 | 北京加西亚联合技术有限公司 | Anti- unmanned machine equipment, system and method |
| CN110398720A (en) * | 2019-08-21 | 2019-11-01 | 深圳耐杰电子技术有限公司 | A kind of anti-unmanned plane detection tracking interference system and photoelectric follow-up working method |
| CN210487967U (en) * | 2019-08-21 | 2020-05-08 | 深圳耐杰电子技术有限公司 | Anti-unmanned aerial vehicle detection tracking interference system |
| CN112414401A (en) * | 2020-11-06 | 2021-02-26 | 北京理工大学 | Unmanned aerial vehicle cooperative positioning system and method based on graph neural network |
| CN113591735A (en) * | 2021-08-04 | 2021-11-02 | 上海新纪元机器人有限公司 | Pedestrian detection method and system based on deep learning |
| CN113780246A (en) * | 2021-11-09 | 2021-12-10 | 中国电力科学研究院有限公司 | Unmanned aerial vehicle three-dimensional track monitoring method and system and three-dimensional monitoring device |
-
2022
- 2022-09-02 CN CN202211070718.9A patent/CN115355764A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109373821A (en) * | 2017-05-16 | 2019-02-22 | 北京加西亚联合技术有限公司 | Anti- unmanned machine equipment, system and method |
| CN109269352A (en) * | 2018-09-20 | 2019-01-25 | 北京机械设备研究所 | A kind of unmanned plane tracking goal approach and system based on ground location |
| CN109283521A (en) * | 2018-10-18 | 2019-01-29 | 广州市海林电子科技发展有限公司 | It blocks the method for unmanned plane and blocks the anti-UAV system of formula |
| CN110398720A (en) * | 2019-08-21 | 2019-11-01 | 深圳耐杰电子技术有限公司 | A kind of anti-unmanned plane detection tracking interference system and photoelectric follow-up working method |
| CN210487967U (en) * | 2019-08-21 | 2020-05-08 | 深圳耐杰电子技术有限公司 | Anti-unmanned aerial vehicle detection tracking interference system |
| CN112414401A (en) * | 2020-11-06 | 2021-02-26 | 北京理工大学 | Unmanned aerial vehicle cooperative positioning system and method based on graph neural network |
| CN113591735A (en) * | 2021-08-04 | 2021-11-02 | 上海新纪元机器人有限公司 | Pedestrian detection method and system based on deep learning |
| CN113780246A (en) * | 2021-11-09 | 2021-12-10 | 中国电力科学研究院有限公司 | Unmanned aerial vehicle three-dimensional track monitoring method and system and three-dimensional monitoring device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105744163B (en) | A kind of video camera and image capture method based on depth information tracking focusing | |
| US11908207B2 (en) | Method for detecting road diseases by intelligent cruise via unmanned aerial vehicle, unmanned aerial vehicle and detecting system therefor | |
| US9838595B2 (en) | Video generating method and apparatus of video generating system | |
| US12007794B2 (en) | Method and apparatus for tracking moving target and unmanned aerial vehicle | |
| CN104828256A (en) | Intelligent multi-mode flying shooting equipment and flying control method thereof | |
| CN106864751A (en) | Unmanned plane during flying landing system and method based on image procossing | |
| CN104154997A (en) | Unmanned aerial vehicle mounted light and small-sized self-stabilized flight multispectral imaging system | |
| US10812727B1 (en) | Machine vision system and method with steerable mirror | |
| CN106973221B (en) | Unmanned aerial vehicle camera shooting method and system based on aesthetic evaluation | |
| WO2021098453A1 (en) | Target tracking method and unmanned aerial vehicle | |
| CN112215860A (en) | Unmanned aerial vehicle positioning method based on image processing | |
| CN101702076A (en) | Stereoscopic shooting auto convergence tracking method and system | |
| WO2020233682A1 (en) | Autonomous circling photographing method and apparatus and unmanned aerial vehicle | |
| CN106742051B (en) | Aircraft hovering function stability testing method and system | |
| CN110182375B (en) | Unmanned aerial vehicle image sensor control device and control method thereof | |
| CN106647758A (en) | Target object detection method and device and automatic guiding vehicle following method | |
| CN108132677B (en) | Sunshade unmanned aerial vehicle control system and control method | |
| CN111319502A (en) | Unmanned aerial vehicle laser charging method based on binocular vision positioning | |
| WO2020114432A1 (en) | Water detection method and apparatus, and unmanned aerial vehicle | |
| CN115355764A (en) | Unmanned aerial vehicle confrontation method based on vision for identifying enemy and my targets | |
| CN209572966U (en) | A kind of bird-repellent robots of power industry application | |
| CN109218587A (en) | A kind of image-pickup method and system based on binocular camera | |
| CN113031634B (en) | Photovoltaic inspection method based on unmanned aerial vehicle | |
| CN111160123A (en) | Airplane target identification method and device and storage medium | |
| CN207901217U (en) | A kind of AGV robots based on more mesh cameras inclination angle target identification |
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 |