CN109324638A - Quadrotor drone Target Tracking System based on machine vision - Google Patents
Quadrotor drone Target Tracking System based on machine vision Download PDFInfo
- Publication number
- CN109324638A CN109324638A CN201811477359.2A CN201811477359A CN109324638A CN 109324638 A CN109324638 A CN 109324638A CN 201811477359 A CN201811477359 A CN 201811477359A CN 109324638 A CN109324638 A CN 109324638A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- target
- camera
- target tracking
- 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
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 claims abstract description 28
- 230000005540 biological transmission Effects 0.000 claims description 16
- 238000003709 image segmentation Methods 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 10
- 230000005611 electricity Effects 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 4
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 claims description 3
- 229910052744 lithium Inorganic materials 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000000087 stabilizing effect Effects 0.000 claims description 3
- 238000012546 transfer Methods 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 abstract description 7
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000000465 moulding Methods 0.000 abstract 1
- 230000009017 pursuit movement Effects 0.000 abstract 1
- 238000001514 detection method Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/12—Target-seeking control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/215—Motion-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a kind of quadrotor drone Target Tracking System based on machine vision belongs to unmanned plane target tracking field.A kind of quadrotor drone Target Tracking System based on machine vision includes flight control molding block, laser ranging module, target tracking module, wireless transport module, power module.Flight control modules include microcontroller, barometer, three-axis gyroscope, accelerometer, magnetometer.Laser ranging module energy accurate height measuring.Target tracking module includes image procossing embedded board, dual camera.The invention is flown using Headless mode, visual range is expanded by dual camera, it can not only keep quadrotor drone to the consistent pursuit movement of target real-time, dual camera can check whether target loses, so that search target is more efficient and convenient when target is lost.
Description
Technical field
The invention belongs to target tracking domains, are related to aircraft field, specifically say, are a kind of based on machine vision
Quadrotor drone Target Tracking System.
Background technique
Small drone can be easily accomplished a variety of different flying methods, with good flight advantage and wide fly
Line range, so as to be readily achieved take photo by plane, search and rescue, the tasks such as topographic(al) reconnaissance, monitoring are scouted, have in numerous areas more next
More it is widely applied.It is mounted with that the small drone of visual sensor platform can be held on a surface target in low-latitude flying
It is continuous to monitor and obtain high-resolution video image, automated analysis is carried out by the method for image procossing and helps to realize military affairs
The tasks such as investigation, magnitude of traffic flow monitoring, target tracking.Therefore small drone is taken photo by plane target detection in video image, tracking
Technical research has important theory and engineering value.Due to the kinetic characteristic of small drone, it can expand and target is chased after
Track range, at the same can active take multi-angle, multi-faceted tracking to shoot the target.Small drone low latitude is taken photo by plane video
The correlative study of target detection technique in image, military field and civil field such as tracing monitoring, in terms of,
All there is important practical value.Tracking technique can play the role of a kind of persistently detection lock onto target, thus same with very
High researching value.
Summary of the invention
The technical problem to be solved by the present invention is to.Provide a kind of quadrotor drone target based on machine vision with
Track system.The tracking automatically to target may be implemented, dual camera can check whether target loses.
The present invention realizes purpose and the technical solution that uses are as follows:
A kind of quadrotor drone Target Tracking System based on machine vision proposed according to the present invention, including flight control system
System, laser ranging module, target tracking module, wireless transport module, power module.Characterized by further comprising rack, horn,
Blade, remote-control receiver, undercarriage, motor, PC host computer.The horn is fixedly connected with rack, the symmetrically placed quadrangle of horn.
The undercarriage is fixedly connected with rack.The horn is fixedly connected with motor.The motor is fixedly connected with blade.
The flight control modules include microcontroller, barometer, three-axis gyroscope, three axis accelerometer, magnetometer.
The laser ranging module is ultra-small volume LIDAR Lite V3 laser range finder module.Laser ranging module is logical
I2C bus interface is crossed to be connected with flight control system.
The Target Tracking System includes camera module, image procossing embedded board.The camera module packet
Include camera 1, camera 2.
The wireless transport module includes data transmission module and image transmission module.Image sending module by USB with
The connection of image procossing embedded board, data transmission blocks are connect by UART serial ports with flight control modules.Image receives
Module and data reception module are located at ground and are connected by USB with PC host computer.
The flight control modules are connect with remote-control receiver, motor and electricity adjust connection, electric adjust to connect with flight control modules
It connects.
The power module includes lithium battery and Voltage stabilizing module, and power module is to motor, flight control modules, target following
Module for power supply.
The camera 1 and camera 2 are horizontally fixed on two whippletrees of undercarriage, and camera 1 is imaged towards front
First 2 towards below.Camera module is connected by USB with image procossing embedded board, image procossing embedded board
Turn TTL mode by USB to be connected with flight control system.
In specific implementation, aircraft uses quadrotor, carries out fixed high and ranging by laser ranging module.Camera shooting
Module uses sensitive chip OV2710 camera module, and 2,000,000 pixels, 3.6 millimeters of lens focus, frame per second is high speed 640*480@
120fps.USB2.0 interface ensures high transfer rate.Embedded open is passed to by USB after camera 1 and the acquisition image of camera 2
It sends out plate and carries out image procossing.
The characteristics of image procossing is a complicated system engineering, processing be contain much information, strong real-time.First camera
Or it after second camera obtains image, due to containing noise in image, is pre-processed first, filters noise and others
Interference etc. reinforces useful information, improves the signal-to-noise ratio of signal, while original image being made to become to be conducive to computer characteristic
The form of extraction.
Image is with regard to carrying out image segmentation after pretreatment, and image segmentation is mainly according to certain threshold value to be identified
Image object is separated from image.Image segmentation is usually an important link in Target Recognition Algorithms, mainly includes
Two process, that is, threshold calculations and Target Segmentation.In entire identifying system, image segmentation is both basic fundamental and crucial skill
One of art, subsequent all algorithms are carried out on the basis of image procossing after sectioning.
After target image segmentation, the feature for being able to reflect target essence is extracted from obtained image information, it is as special
Sign is extracted.Feature selecting should be according to target identification and the needs of tracking, and should have separability and opposite stability, and guaranteeing
Under the requirement of accuracy of identification and reliability, number of features is reduced to the greatest extent.
After being extracted characteristic value, according to the discriminant classification rule and decision function selected in algorithm to the feature of extraction into
Row classification, to differentiate target.After recognizing the target to be tracked, it is tracked using track algorithm appropriate, it should
Algorithm will be simultaneously in view of the accuracy and speed of tracking.
The present invention has the advantage that compared with the prior art
(1) present invention is using dual camera formula tracking before and after unmanned plane, and dual camera can check whether target loses, so that mesh
Search target is more efficient and convenient when mark is lost, and structure is simple, and real-time is good.
(2) present invention uses LIDAR Lite V3 laser range finder module, is a high integration, and high-performance optical is surveyed
Away from module.The accuracy for ensuring laser ranging module acquired quadrotor drone height during tracking, effectively mentions
The high precision and stability of tracking.
(3) image is handled using airborne embedded board, improves the real-time for correcting UAV Attitude.
Detailed description of the invention
Fig. 1 is the structural diagram of the present invention.
Fig. 2 is the working principle of the invention figure.
Specific embodiment
The present invention is further described with example with reference to the accompanying drawing.
As shown in Figure 1, the present invention includes flight control system, laser ranging module, target tracking module, wireless transmission mould
Block, power module.Characterized by further comprising rack, horn, blade, remote-control receiver, undercarriage, the mechanical, electrical tune of electricity, PC are upper
Machine.The horn is fixedly connected with rack, the symmetrically placed quadrangle of horn.The undercarriage is fixedly connected with rack.The machine
Arm is fixedly connected with motor.The motor is fixedly connected with blade.
Flight control modules, for being responsible for the calculating of unmanned plane during flying posture, navigation calculates, control algolithm application, control
The task relevant to flight control such as output.
Laser ranging module is connected by I2C bus interface with flight control system, for obtaining quadrotor drone reality
When flying height.
Target Tracking System includes camera module, image procossing embedded board.The camera module includes taking the photograph
As head 1, camera 2.Image is transmitted to embedded board by USB for acquiring image by camera.Embedded board
Image for acquiring to camera carries out image procossing and obtains target signature, will output information to flight control modules.
Flight subsystem is mainly responsible for the smooth flight in aircraft tracing process, passes through various kinds of sensors in system
Parameter is monitored state of flight, if receiving dependent instruction, issues dependent instruction to body power sub-system by calculating
Signal, adjusts state of flight, and the signal which receives both may be from the sending of earth station system manual operation, and also may be from mesh
Mark tracking system microprocessor target following calculating is occurred.
Wireless transport module includes data transmission module and image transmission module.Image sending module passes through USB and image
Embedded board connection is handled, data transmission blocks are connect by UART serial ports with flight control modules, image receiver module
It is located at ground with data reception module and is connected by USB with PC host computer.Data transmission module is used for flight control modules
The quadrotor drone flight parameter of sending is exported through earth station's data transmission module to PC host computer.Image transmission module is used for
The image with target signature that image procossing is crossed is exported through earth station's image transmission module to PC host computer.
Power module includes lithium battery and Voltage stabilizing module, and power module is responsible for motor, flight control modules, target following
Module for power supply.
Remote-control receiver is gone back for being received, being amplified to the radio carrier signals that transmit circuit issues, demodulated
It originally was control signal, flight control modules output control signals to electric tune after receiving control signal.
Electricity adjusts input terminal input DC power, can be according to PWM after receiving the pwm signal that flight control system is sent
Metal-oxide-semiconductor in signal characteristic control electricity tune adjusts the voltage swing of output, reaches control motor speed size with this and frequency is high
Low purpose.
Earth station's PC host computer can observe the letter such as its location information, attitude angle, remaining capacity by data transmission module
Breath.The figure of target signature information can be had after embedded board image procossing with real-time display by image transmission module
Picture.
If Fig. 2 is indicated, specific embodiments of the present invention are as follows:
In specific implementation, aircraft uses quadrotor, carries out fixed high and ranging by laser ranging module.Photographing module
Using sensitive chip OV2710 camera module, 2,000,000 pixels, 3.6 millimeters of lens focus, frame per second is high speed 640*480@
120fps.USB2.0 interface ensures high transfer rate.Embedded open is passed to by USB after camera 1 and the acquisition image of camera 2
It sends out plate and carries out image procossing.
The characteristics of image procossing is a complicated system engineering, processing be contain much information, strong real-time.First camera
Or it after second camera obtains image, due to containing noise in image, is pre-processed first, filters noise and others
Interference etc. reinforces useful information, improves the signal-to-noise ratio of signal, while original image being made to become to be conducive to computer characteristic to mention
The form taken.
Image is with regard to carrying out image segmentation after pretreatment, and image segmentation is mainly according to certain threshold value to be identified
Image object is separated from image.Image segmentation is usually an important link in Target Recognition Algorithms, mainly includes
Two process, that is, threshold calculations and Target Segmentation.In entire identifying system, image segmentation is both basic fundamental and crucial skill
One of art, subsequent all algorithms are carried out on the basis of image procossing after sectioning.
After target image segmentation, the feature for being able to reflect target essence is extracted from obtained image information, it is as special
Sign is extracted.Feature selecting should be according to target identification and the needs of tracking, and should have separability and opposite stability, and guaranteeing
Under the requirement of accuracy of identification and reliability, number of features is reduced to the greatest extent.
Target identification is exactly to separate target image to be identified first, then extracts the feature of the image after over-segmentation
Value, and the feature that can correctly distinguish image is obtained, knowledge is realized according to this feature, the classification method being pre-designed etc.
Not, it determines the target which kind of to belong to that oneself knows object, completes target identification process.When target loses or is blocked, taken the photograph using double
Continue to acquire new image as head returns to Image Acquisition, dual camera can increase search range, until identifying target.
Unmanned aerial vehicle (UAV) control: camera is towards that can remain unchanged, if camera 1 or camera 2 identify target to be tracked,
Target following is carried out based on track algorithm.It, will using the relative position design object tracking control unit of moving target and unmanned plane
Target centroid coordinate and picture centre coordinate carry out difference operation, and difference is passed through ratio, integral, the feedback control of differential.With
Unmanned plane current location information is merged.PWM wave is converted by fused information and is sent to winged control, while carrying out position letter
Breath resolves and solving of attitude.Control attitude of flight vehicle.To obtain the pitching of specific flight directive control unmanned plane, turn over
Rolling, jaw channel appears in moving target in camera view always, while predicting the characteristics of motion of target, so that nobody
Machine adjusts state in advance, realizes unmanned plane and target object autonomous classification following function function.
Claims (9)
1. a kind of quadrotor drone Target Tracking System based on machine vision, including flight control modules, laser ranging mould
Block (8), target tracking module, wireless transport module, power module, it is characterised in that further include rack (1), horn (2), blade
(3), remote-control receiver (6), undercarriage (9), motor (15), PC host computer, the horn (2) are fixedly connected with rack (1), machine
The symmetrically placed quadrangle of arm, the undercarriage (9) are fixedly connected with rack (1), and the horn (2) is fixedly connected with motor (15),
The motor (15) is fixedly connected with blade (3).
2. a kind of quadrotor drone Target Tracking System based on machine vision according to claim 1, feature exist
In flight control modules (4) include microcontroller, barometer, three-axis gyroscope, three axis accelerometer, magnetometer.
3. a kind of quadrotor drone Target Tracking System based on machine vision according to claim 1, feature exist
In laser ranging module (8) is ultra-small volume LIDAR Lite V3 laser range finder module, and laser ranging module (8) passes through
I2C bus interface is connected with flight control system.
4. a kind of quadrotor drone Target Tracking System based on machine vision according to claim 1, feature exist
In Target Tracking System includes camera module, image procossing embedded board (5), and the camera module includes camera shooting
Head 1(10), camera 2(11).
5. a kind of quadrotor drone Target Tracking System based on machine vision according to claim 1, feature exist
In wireless transport module includes data transmission module (12) and image transmission module (13), and image sending module (13) passes through USB
It is connect with image procossing embedded board (5), data transmission blocks (12) are connected by UART serial ports and flight control modules (4)
It connects, image receiver module and data reception module are located at ground and are connected by USB with PC host computer.
6. a kind of quadrotor drone Target Tracking System based on machine vision according to claim 1, feature exist
In flight control modules (4) are connect with remote-control receiver (6), motor (15) is connect with electricity tune (7), electricity adjusts (7) and flight control
Module (4) connection.
7. a kind of quadrotor drone Target Tracking System based on machine vision according to claim 1, feature exist
In power module includes lithium battery (14) and Voltage stabilizing module (16), and power module is to motor, flight control modules, target following
Module for power supply.
8. a kind of quadrotor drone Target Tracking System based on machine vision according to claim 4, feature exist
In camera 1(10) and camera 2(11) be horizontally fixed on (9) two whippletrees of undercarriage, camera 1(10) before
Face, camera 2(11) towards below, camera module is connected by USB with image procossing embedded board (5), at image
Reason embedded board (5) turns TTL mode by USB and is connected with flight control system (4).
9. a kind of quadrotor drone Target Tracking System based on machine vision, it is characterised in that:
In specific implementation, aircraft uses quadrotor, carries out fixed high and ranging, photographing module by laser ranging module
Using sensitive chip OV2710 camera module, 2,000,000 pixels, 3.6 millimeters of lens focus, frame per second is high speed 640*480@
120fps, USB2.0 interface ensure high transfer rate, and camera 1 and camera 2 acquire and be passed to embedded open by USB after image
Send out plate and carry out image procossing, the characteristics of image procossing is a complicated system engineering, processing be contain much information, strong real-time,
After first camera or second camera obtain image, due to containing noise in image, is pre-processed first, filter and make an uproar
Sound and other interference etc., reinforce useful information, improve the signal-to-noise ratio of signal, while original image being made to become to be conducive to count
The form of calculation machine feature extraction.Image is with regard to carrying out image segmentation after pretreatment, and image segmentation is mainly according to certain threshold
Value is separated image object to be identified from image, and image segmentation is usually an important ring in Target Recognition Algorithms
Section includes mainly two process, that is, threshold calculations and Target Segmentation, and in entire identifying system, image segmentation is both basic fundamental
It is one of key technology again, subsequent all algorithms are carried out on the basis of image procossing after sectioning, target figure
After segmentation, the feature for being able to reflect target essence, as feature extraction, feature selecting are extracted from obtained image information
Should be according to target identification and the needs of tracking, and should have separability and opposite stability, and in guarantee accuracy of identification and reliably
Property requirement under, reduce number of features to the greatest extent, after being extracted characteristic value, according to the discriminant classification rule that is selected in algorithm and sentence
Certainly function classifies to the feature of extraction, so that target is differentiated, after recognizing the target to be tracked, using tracking appropriate
Algorithm tracks it, which will be simultaneously in view of the accuracy and speed of tracking.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811477359.2A CN109324638A (en) | 2018-12-05 | 2018-12-05 | Quadrotor drone Target Tracking System based on machine vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811477359.2A CN109324638A (en) | 2018-12-05 | 2018-12-05 | Quadrotor drone Target Tracking System based on machine vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109324638A true CN109324638A (en) | 2019-02-12 |
Family
ID=65256256
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811477359.2A Pending CN109324638A (en) | 2018-12-05 | 2018-12-05 | Quadrotor drone Target Tracking System based on machine vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109324638A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008919A (en) * | 2019-04-09 | 2019-07-12 | 南京工业大学 | The quadrotor drone face identification system of view-based access control model |
CN110109478A (en) * | 2019-05-13 | 2019-08-09 | 西安电子科技大学 | A kind of miniature drone based on AI vision |
CN111340857A (en) * | 2020-02-20 | 2020-06-26 | 浙江大华技术股份有限公司 | Camera tracking control method and device |
CN111559501A (en) * | 2020-05-21 | 2020-08-21 | 百色学院 | Dynamic directional tracking sound transmission automatic control system |
CN111824406A (en) * | 2020-07-17 | 2020-10-27 | 南昌航空大学 | Public safety independently patrols four rotor unmanned aerial vehicle based on machine vision |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140132729A1 (en) * | 2012-11-15 | 2014-05-15 | Cybernet Systems Corporation | Method and apparatus for camera-based 3d flaw tracking system |
CN104700408A (en) * | 2015-03-11 | 2015-06-10 | 中国电子科技集团公司第二十八研究所 | Indoor singe target positioning method based on camera network |
CN105323540A (en) * | 2014-07-18 | 2016-02-10 | 南京专创知识产权服务有限公司 | Intelligent control four-axis aircraft with multiple cameras |
CN106444847A (en) * | 2016-11-14 | 2017-02-22 | 徐志勇 | Omnibearing target tracking system for unmanned aerial vehicle |
CN106485736A (en) * | 2016-10-27 | 2017-03-08 | 深圳市道通智能航空技术有限公司 | A kind of unmanned plane panoramic vision tracking, unmanned plane and control terminal |
CN108107920A (en) * | 2017-12-19 | 2018-06-01 | 天津工业大学 | A kind of microminiature twin shaft vision stablizes holder target detection tracing system |
-
2018
- 2018-12-05 CN CN201811477359.2A patent/CN109324638A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140132729A1 (en) * | 2012-11-15 | 2014-05-15 | Cybernet Systems Corporation | Method and apparatus for camera-based 3d flaw tracking system |
CN105323540A (en) * | 2014-07-18 | 2016-02-10 | 南京专创知识产权服务有限公司 | Intelligent control four-axis aircraft with multiple cameras |
CN104700408A (en) * | 2015-03-11 | 2015-06-10 | 中国电子科技集团公司第二十八研究所 | Indoor singe target positioning method based on camera network |
CN106485736A (en) * | 2016-10-27 | 2017-03-08 | 深圳市道通智能航空技术有限公司 | A kind of unmanned plane panoramic vision tracking, unmanned plane and control terminal |
CN106444847A (en) * | 2016-11-14 | 2017-02-22 | 徐志勇 | Omnibearing target tracking system for unmanned aerial vehicle |
CN108107920A (en) * | 2017-12-19 | 2018-06-01 | 天津工业大学 | A kind of microminiature twin shaft vision stablizes holder target detection tracing system |
Non-Patent Citations (2)
Title |
---|
姜俊俊 等: ""基于视觉的四旋翼无人机目标跟踪系统设计"", 《中国科技信息》 * |
李国仁 等: ""基于视觉的四旋翼无人机目标跟踪研究"", 《控制与信息技术》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110008919A (en) * | 2019-04-09 | 2019-07-12 | 南京工业大学 | The quadrotor drone face identification system of view-based access control model |
CN110109478A (en) * | 2019-05-13 | 2019-08-09 | 西安电子科技大学 | A kind of miniature drone based on AI vision |
CN111340857A (en) * | 2020-02-20 | 2020-06-26 | 浙江大华技术股份有限公司 | Camera tracking control method and device |
CN111340857B (en) * | 2020-02-20 | 2023-09-19 | 浙江大华技术股份有限公司 | Tracking control method and device for camera |
CN111559501A (en) * | 2020-05-21 | 2020-08-21 | 百色学院 | Dynamic directional tracking sound transmission automatic control system |
CN111824406A (en) * | 2020-07-17 | 2020-10-27 | 南昌航空大学 | Public safety independently patrols four rotor unmanned aerial vehicle based on machine vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109324638A (en) | Quadrotor drone Target Tracking System based on machine vision | |
CN111415388B (en) | Visual positioning method and terminal | |
CN110494360B (en) | System and method for providing autonomous photography and photography | |
US9977434B2 (en) | Automatic tracking mode for controlling an unmanned aerial vehicle | |
CN106017463B (en) | A kind of Aerial vehicle position method based on orientation sensing device | |
CN108399642B (en) | General target following method and system fusing rotor unmanned aerial vehicle IMU data | |
CN110398720B (en) | Anti-unmanned aerial vehicle detection tracking interference system and working method of photoelectric tracking system | |
CN102353377B (en) | High altitude long endurance unmanned aerial vehicle integrated navigation system and navigating and positioning method thereof | |
CN205540288U (en) | Unmanned aerial vehicle system with multi -functional ground satellite station | |
US20190007670A1 (en) | Estimation system and automobile | |
CN106056075A (en) | Important person identification and tracking system in community meshing based on unmanned aerial vehicle | |
WO2018103689A1 (en) | Relative azimuth control method and apparatus for unmanned aerial vehicle | |
CN109063532B (en) | Unmanned aerial vehicle-based method for searching field offline personnel | |
CN105512628A (en) | Vehicle environment sensing system and method based on unmanned plane | |
CN108475442A (en) | Augmented reality method, processor and unmanned plane for unmanned plane | |
CN211055366U (en) | Campus patrol system of rotor unmanned aerial vehicle based on visual identification | |
CN204956941U (en) | A airborne system for unmanned aerial vehicle helps and falls vision -guided | |
CN110498039A (en) | A kind of intelligent monitor system based on bionic flapping-wing flying vehicle | |
CN105761245A (en) | Automatic tracking method and device based on visual feature points | |
CN205909832U (en) | Unmanned aerial vehicle navigation based on machine vision | |
CN112904874A (en) | Unmanned aerial vehicle autonomous landing control method for unmanned ship | |
CN112037252A (en) | Eagle eye vision-based target tracking method and system | |
Stuckey et al. | A spatial localization and attitude estimation system for unmanned aerial vehicles using a single dynamic vision sensor | |
Stuckey et al. | An optical spatial localization system for tracking unmanned aerial vehicles using a single dynamic vision sensor | |
CN105678805A (en) | ARM platform-based aerial-photography target detection system |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190212 |
|
WD01 | Invention patent application deemed withdrawn after publication |