CN109407697A - A kind of unmanned plane pursuit movement goal systems and method based on binocular distance measurement - Google Patents
A kind of unmanned plane pursuit movement goal systems and method based on binocular distance measurement Download PDFInfo
- Publication number
- CN109407697A CN109407697A CN201811100610.3A CN201811100610A CN109407697A CN 109407697 A CN109407697 A CN 109407697A CN 201811100610 A CN201811100610 A CN 201811100610A CN 109407697 A CN109407697 A CN 109407697A
- Authority
- CN
- China
- Prior art keywords
- target
- image
- binocular
- aerial vehicle
- target area
- 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 24
- 238000005259 measurement Methods 0.000 title claims abstract description 20
- 230000009017 pursuit movement Effects 0.000 title claims abstract description 16
- 239000007787 solid Substances 0.000 claims abstract description 17
- 238000013459 approach Methods 0.000 claims abstract description 13
- 230000033001 locomotion Effects 0.000 claims abstract description 13
- 238000004891 communication Methods 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 23
- 230000000007 visual effect Effects 0.000 claims description 13
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000004807 localization Effects 0.000 abstract description 5
- 230000007306 turnover Effects 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000005693 optoelectronics Effects 0.000 description 1
- 238000006467 substitution reaction Methods 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
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of unmanned plane pursuit movement goal systems and method based on binocular distance measurement, belong to unmanned plane tracking technique field, solve the problems, such as that aerial non-cooperative moving targets can not be tracked in the prior art.Include: unmanned aerial vehicle platform, movement destination image is obtained by binocular camera in real time, carry out benchmark image tracking and binocular solid matching, obtains the 3 d space coordinate of moving target, and approach and track automatically to moving target；Ground control station for guiding unmanned aerial vehicle platform tentatively close to moving target, to receive the movement destination image that unmanned aerial vehicle platform is sent and display, and is tentatively demarcated the target area in image.The advantages of carrying out the three-dimensional localization of target with binocular camera, there is non-contact high-frequency measurement, implement simple and high real-time；By the real-time location information for obtaining moving target, control unmanned plane accurately approaches and tracks automatically non-cooperative moving targets, disposes moving target for subsequent unmanned plane and provides basis.
Description
Technical field
The present invention relates to unmanned plane tracking technique field more particularly to a kind of unmanned plane tracking based on binocular distance measurement
Moving target system and method.
Background technique
In recent years, with the development of unmanned air vehicle technique, " low slow small " aircraft in the rapid extension of Military and civil fields, is easy quilt
Criminal is brought greatly hidden using illegally being investigated, shedding the leaflet even attack of terrorism to public safety and social stability
Suffer from.Therefore, how is carried out by effectively control and has become global problem for " low slow small " target.The object of black winged unmanned plane is managed at present
Reason interception means have a modes such as microwave, laser, but it there are working service is this height, easily causes the problems such as secondary injury.It utilizes
UAV flight throws net device, provides target information by ground optoelectronic device or radar and airborne vision system, guides nobody
Machine carries out net formula soft destruction interception close to after target, is a kind of the feasible of control " low slow small " target with unmanned plane counter unmanned plane
Mode.
Currently, UAV system vision system has the relevant technologies to the tracking of moving target, but mostly tracked with visual pattern
Based on, target can not be obtained relatively with the specific three-dimensional coordinate of our unmanned plane, be generally used for the planar targets such as Tracking Ground Targets,
Aerial non-cooperative moving targets can not accurately be tracked.Unmanned plane is located above target in a kind of method in the prior art, is used for
Planar target is tracked, and target is cooperative target, has feature significantly to indicate red rectangle frame, is identified based on these notable features
Target position is not used to track aerial noncooperative target.Unmanned plane establishes row for tracking ground pedestrian in another method
People's gesture feature and gesture motion model carry out recognition and tracking；Aerial noncooperative target can not equally be tracked.
Summary of the invention
In view of above-mentioned analysis, the present invention is intended to provide a kind of unmanned plane pursuit movement target based on binocular distance measurement
System and method can not track aerial non-cooperative moving targets to solve the problems, such as in the prior art.
The purpose of the present invention is mainly achieved through the following technical solutions:
On the one hand, a kind of unmanned plane pursuit movement goal systems based on binocular distance measurement is provided, comprising: unmanned plane
Platform, ground control station；
The unmanned aerial vehicle platform obtains movement destination image by binocular camera in real time, carries out benchmark image tracking and double
Mesh Stereo matching obtains the 3 d space coordinate of moving target, and approach and track automatically to moving target；
The ground control station, for guiding unmanned aerial vehicle platform tentatively close to moving target, to receive unmanned aerial vehicle platform and send
Movement destination image and display, and the target area in image is tentatively demarcated.
The present invention has the beneficial effect that:
This system carries out the three-dimensional localization of target using binocular camera, has non-contact measurement, implements simple and high
The advantages of real-time.Image frame per second reaches 60 frame per second, i.e. the turnover rate of target position also reaches 60Hz, passes through the real-time acquisition
The location information of ground moving target, control unmanned plane accurately approach automatically and track non-cooperative moving targets, for it is subsequent nobody
Machine disposes moving target and provides basis.
On the basis of above scheme, the present invention has also done following improvement:
Further, the unmanned aerial vehicle platform, comprising: binocular camera, onboard image processing module, airborne communication module, fortune
Dynamic control module；
The ground control station, comprising: industrial personal computer, ground communication module, display module；
The onboard image processing module is respectively connected with binocular camera, airborne communication module, motion-control module；With
In the data that the movement destination image and ground control station obtained according to binocular camera is sent, image trace and binocular solid are carried out
Matching treatment obtains the three-dimensional coordinate of moving target；
Image data after onboard image processing module coding is sent to ground control station by the airborne communication module,
The data of ground control station are received simultaneously；
The motion-control module, the three-dimensional coordinate of the moving target for being sent according to onboard image processing module, control
Unmanned plane processed approaches and pursuit movement target；
The ground communication module, the Data Concurrent for receiving airborne communication module transmission give industrial personal computer, meanwhile, by ground
The data of control station are sent to airborne communication module；
The industrial personal computer is decoded received data, and is sent to display module and is shown.
Further, the onboard image processing module, using KCF algorithm to the mesh in the every frame benchmark image obtained in real time
It marks region and carries out detecting and tracking；It is matching with grey scale pixel value and according to the coordinate position of target area in every frame benchmark image
Primitive carries out binocular solid matching.
On the other hand, a kind of unmanned plane pursuit movement goal approach based on binocular distance measurement is provided, including following
Step:
Step S1, ground control station guides unmanned aerial vehicle platform tentatively close to moving target, and moving target is made to enter binocular phase
Machine visual field；
Step S2, in binocular camera visual field, binocular solid matching is carried out, and target position is measured by binocular ranging,
Three dimensional local information of the target relative to unmanned plane is obtained in real time；
Step S3, according to the above-mentioned three dimensional local information obtained in real time, unmanned plane carries out target quickly accurate automatic
Tracking.
The present invention has the beneficial effect that:
This method carries out the three-dimensional localization of target using binocular camera, has non-contact measurement, implements simple and high
The advantages of real-time.Image frame per second reaches 60 frame per second, i.e. the turnover rate of target position also reaches 60Hz, passes through the real-time acquisition
The location information of ground moving target, control unmanned plane accurately approach automatically and track non-cooperative moving targets, for it is subsequent nobody
Machine disposes moving target and provides basis.
On the basis of above scheme, the present invention has also done following improvement:
Further, the progress benchmark image tracking, comprising:
The image that unmanned aerial vehicle platform obtains binocular camera, real-time Transmission are shown into ground control station；
The target area demarcated in display image is obtained, and the position coordinates of target area are transmitted to unmanned plane and are put down
Platform；
According to the position coordinates of target area, using KCF algorithm to the target area in the every frame benchmark image obtained in real time
Domain carries out detecting and tracking.
It is further, described that benchmark image tracking is carried out using KCF algorithm, comprising:
After the coordinate position for the target area for getting calibration, the positive sample based on image grayscale latent structure acquisition target
Sheet and negative sample, training objective detector；
In each frame benchmark image later, is detected using above-mentioned object detector in region of search, set with highest
The region of reliability is as target area；When the confidence value of target area is less than preset value, region of search range is expanded, weight
Newly scan for.
Further, unmanned aerial vehicle platform is with grey scale pixel value according to the coordinate position of target area in every frame benchmark image
Matching unit carries out binocular solid matching, comprising:
Every frame RGB image that two mesh of left and right obtain is converted into grayscale image；
On the basis of target area in a wherein mesh grayscale image, in another mesh grayscale image in identical height region, successively
The mean pixel point gray value and corresponding area coordinate in the region for each piece of same size of calculating not being spaced；
The absolute difference of the mean pixel point gray value in above-mentioned each region and datum target region is calculated,
The minimum value and sub-minimum for seeking the absolute difference, when minimum value be less than preset minimum value and sub-minimum with most
When the difference of small value is less than preset difference value, then using the corresponding region of minimum value as the target area in matched another mesh image.
Further, the three dimensional local information for obtaining moving target in real time by binocular ranging, including, it is seeking moving
When the three-dimensional coordinate depth value of target, Kalman filtering is carried out, rejects the outlier occurred in partial frame image.
Further, described according to the above-mentioned three dimensional local information obtained in real time, unmanned plane carries out target quickly accurate
Automatically track, comprising: according to the real-time three-dimensional coordinate information of target be input value, construction location PID controller, control unmanned plane
It quickly tracks close to target.
Further, further includes: when unmanned aerial vehicle platform has tracked false target, then cancel current tracking, and reacquire
The target area of calibration.
It in the present invention, can also be combined with each other between above-mentioned each technical solution, to realize more preferred assembled schemes.This
Other feature and advantage of invention will illustrate in the following description, also, certain advantages can become from specification it is aobvious and
It is clear to, or understand through the implementation of the invention.The objectives and other advantages of the invention can by specification, claims with
And it is achieved and obtained in specifically noted content in attached drawing.
Detailed description of the invention
Attached drawing is only used for showing the purpose of specific embodiment, and is not to be construed as limiting the invention, in entire attached drawing
In, identical reference symbol indicates identical component.
Fig. 1 is the unmanned plane pursuit movement goal systems structure chart based on binocular distance measurement in the embodiment of the present invention；
Fig. 2 is the unmanned plane pursuit movement goal approach flow chart based on binocular distance measurement in the embodiment of the present invention.
Specific embodiment
Specifically describing the preferred embodiment of the present invention with reference to the accompanying drawing, wherein attached drawing constitutes the application a part, and
Together with embodiments of the present invention for illustrating the principle of the present invention, it is not intended to limit the scope of the present invention.
Embodiment 1
A specific embodiment of the invention discloses a kind of unmanned plane pursuit movement target based on binocular distance measurement
System, as shown in Figure 1, comprising: unmanned aerial vehicle platform, ground control station；
Unmanned aerial vehicle platform obtains movement destination image by binocular camera in real time, carries out benchmark image tracking and binocular is vertical
Body matching obtains the 3 d space coordinate of moving target, and approach and track automatically to moving target；
Ground control station, for guiding unmanned aerial vehicle platform tentatively close to moving target, to receive the fortune that unmanned aerial vehicle platform is sent
Moving-target image is simultaneously shown, and is tentatively demarcated to the target area in image.
When implementation, unmanned aerial vehicle platform is being guided tentatively close to moving target using ground control station and other ancillary equipments
Afterwards, it after moving target enters binocular camera visual field, is matched by binocular solid, obtains moving target in real time relative to unmanned plane
Three dimensional local information, control unmanned plane quickly accurately close to target and are automatically tracked, and carry out throwing net convenient for subsequent unmanned plane
Equal interceptions disposition.
Compared with prior art, the unmanned plane pursuit movement goal systems of binocular distance measurement provided in this embodiment, is adopted
The advantages of carrying out the three-dimensional localization of target with binocular camera, there is non-contact measurement, implement simple and high real-time.Image
Frame per second reaches 60 frame per second, i.e. the turnover rate of target position also reaches 60Hz, passes through the real-time position for obtaining ground moving target
Information, control unmanned plane accurately approach and track automatically non-cooperative moving targets, dispose moving target for subsequent unmanned plane and mention
For basis.
Specifically, unmanned aerial vehicle platform is equipped with binocular camera, further includes: onboard image processing module, airborne communication mould
Block, motion-control module；Wherein,
Onboard image processing module is respectively connected with binocular camera, airborne communication module, motion-control module；For root
The data that the movement destination image and ground control station obtained according to two-sided camera is sent carry out image trace and binocular solid matching
Processing, obtains the three-dimensional coordinate of moving target；Specifically, using KCF algorithm to the mesh in the every frame benchmark image obtained in real time
It marks region and carries out detecting and tracking；It is matching with grey scale pixel value and according to the coordinate position of target area in every frame benchmark image
Primitive carries out binocular solid matching.
Airborne communication module is connected by network interface with image processing module, after receiving airborne image processing module coding
Data, and it is transferred to ground control station；Meanwhile receiving the data that ground control station is sent；
Motion-control module, the three-dimensional coordinate of the target point for being sent according to onboard image processing module, controls nobody
Machine is close and tracks target；
Ground control station, comprising: industrial personal computer, ground communication module, display module；
Ground communication module, the Data Concurrent for receiving airborne communication module transmission are sent to industrial personal computer；Meanwhile ground being controlled
The data stood are sent to airborne communication module.
Industrial personal computer is used to analyze the received data and is decoded, and is sent to display module and is shown.
Display module can be display or touch screen for showing image and data information.
Embodiment 2
Present embodiment discloses a kind of system using in embodiment 1, the unmanned planes based on binocular distance measurement of realization
Pursuit movement goal approach, as shown in Figure 2, comprising the following steps:
Step S1, ground control station guides unmanned plane tentatively close to target, and target is made to enter binocular camera visual field；
Step S2, in binocular camera visual field, benchmark image tracking and binocular solid matching are carried out, and pass through binocular ranging
The three dimensional local information of moving target is obtained in real time；
Step S3, according to the above-mentioned three dimensional local information obtained in real time, unmanned aerial vehicle platform carries out target quickly accurate
It automatically tracks.
Compared with prior art, the unmanned plane pursuit movement target side provided in this embodiment based on binocular distance measurement
Method carries out the three-dimensional localization of target using binocular camera, has non-contact measurement, implements simple and high real-time excellent
Point.Image frame per second reaches 60 frame per second, i.e. the turnover rate of target position also reaches 60Hz, passes through the real-time acquisition ground moving target
Location information, control unmanned plane accurately approaches automatically and tracks non-cooperative moving targets, for the disposition movement of subsequent unmanned plane
Target provides basis.
Specifically, in step sl, ground control station guiding unmanned plane is tentatively close to target, and ground handling operator can be with
Using remote controler or other ground-support equipments, control unmanned aerial vehicle platform and move closer to moving target, until moving target into
Enter binocular camera (two mesh of left and right) visual field (can be clearly seen that moving target in the display screen of ground control station).
Unmanned plane tentatively close to moving target during, after onboard image processing module obtains the image of binocular camera
It is not processed, video flowing is subjected to H264 real-time coding, and be transferred to airborne communication module, airborne communication module is sent to ground
Control station is shown.
In step s 2, after determining that moving target enters in binocular camera visual field, unmanned aerial vehicle platform carries out benchmark image
Tracking and binocular solid matching, and moving target is obtained by binocular ranging in real time and is believed relative to the three-dimensional position of unmanned aerial vehicle platform
Breath；Specifically, comprising the following steps:
Step S201, the image that unmanned aerial vehicle platform obtains binocular camera, real-time Transmission to ground control station；
When target enters in binocular camera visual field, onboard image processing module obtains image and is still not processed, and is encoded
After be transmitted directly to airborne communication module, be subsequently sent to ground control station carry out real-time display.
Step S202 obtains the target area demarcated in display image, and the position coordinates of target area is transmitted to
Unmanned aerial vehicle platform；
Terrestrial operation person can be true in such a way that mouse/gesture draws rectangle in the video image of display/touch screen
Set the goal region；Can also the heart is nearby clicked in the target area in such a way that left mouse button/finger is clicked, according to setting
Threshold value is using neighbouring a certain range region as target area.Wherein, with two apex coordinate value tables on diagonal line a certain in rectangle
Show the position coordinates of target area, ground control station is according to display image and original image (and display image and binocular camera
Middle image) size obtain position coordinates of the target area in original image, and be sent to the airborne of unmanned aerial vehicle platform
Image processing module；
It should be noted that moving target position is obtained carrying out ranging using binocular camera, with mesh figure a certain in camera
As being used as benchmark, another mesh image carries out binocular solid matching；Reference map of the present embodiment using left mesh image as image procossing
Picture, right mesh image are only used for binocular solid matching；Therefore, operator needs in the display/touch screen for showing left mesh image
Frame selects target area.
Step S203, unmanned aerial vehicle platform is after receiving the coordinate position of target area, to the reference map of each frame later
The target area of picture is automatically tracked, and determines the coordinate position of every frame objective area in image, and enters step S204；
Carry out image trace automatically in left mesh, to carry out binocular ranging in real time, image trace can use a variety of
Existing algorithm, in the present embodiment, using KCF algorithm (Kernel Correlation Filter, core correlation filtering), one
Kind of tracking effect and all very outstanding image tracking algorithm of tracking velocity, mainly using the training of core correlation filter one sentence
Other formula classifier accelerates algorithm using fast Fourier variation using circular matrix to sample collection；In view of movement
The problems such as when target is mobile quick, detection window is too small, will cause tracking failure, increases the adaptive adjustment of detection window,
I.e. when the confidence value of current search Region Matching target image is too low, search range matched jamming again will be enlarged by；Meanwhile
It is optimized again in conjunction with the confidence level of matching target image during object detector updates；To improve image trace
Accuracy and adaptability.
Specifically, onboard image processing module is based on image grayscale feature after getting the coordinate position of target area
The positive sample and negative sample of construction acquisition target image, training objective detector in the left mesh image of each frame hereafter, all will
Using object detector in target search region detection object region, using the region of highest confidence level as target area,
To realize automatically tracking for image (target area).When the target area image of the highest confidence level that is detected in region of search
When confidence value is less than preset value (preferred, 0.6), target search range will expand, and re-search for, and want until meeting
It asks, to guarantee that KCF track algorithm adapts to Fast Moving Object.
Step S204, unmanned aerial vehicle platform are with grey scale pixel value according to the coordinate position of every frame objective area in image
Binocular solid matching is carried out with primitive；
Onboard image processing module choose target area grey scale pixel value be Matching unit, the identical height of right mesh (i.e.
Same level height) block-by-block same size region in carry out binocular vision matching, it is absolute with the mean pixel point gray scale in region
Difference is evaluation criterion, finds out target area, calculates target position.Specifically, comprising the following steps:
The RGB image that two mesh cameras of left and right obtain is converted to grayscale image by step S20401；
Step S20402, on the basis of target area in left mesh grayscale image, in right mesh grayscale image in identical height region,
The mean pixel point gray value and area coordinate in the region for each piece of same size of calculating not being spaced from left to right；
Step S20403 calculates the absolute difference of the mean pixel point gray value of above-mentioned each region and left mesh target area
Value；
Step S20404 seeks the minimum value dMinDiff and sub-minimum dSecondDiff of the absolute difference, works as minimum
When value is less than preset minimum value (preferred ,≤25) and the difference of sub-minimum and minimum value is less than preset difference value (preferred, 8),
Then using the corresponding region of minimum value as matched target area, i.e., target area is had found in the visual field of right side.
Step S205, according to the binocular target area of above-mentioned Stereo matching, with the target area central point of two visual fields of left and right
Based on pixel coordinate, according to binocular range measurement principle, 3 d space coordinate of the moving target relative to camera focus is sought.
It should be noted that in the three-dimensional coordinate depth value for seeking moving target, (moving target is relative to unmanned aerial vehicle platform
The vertical range of plane where image coordinate) when, Kalman filtering is carried out, it is wild can effectively to reject the mistake occurred in partial frame
Value.To improve the accuracy of target following and location algorithm.
In step s3, according to the three dimensional local information obtained in real time in step S2, unmanned plane carries out quickly essence to target
True automatically tracks.
According to the real-time three-dimensional coordinate information of target be input value, construction location PID controller, control unmanned plane quickly with
Track close to target, reach it is desired can intercept distance, intercepted convenient for open net of the unmanned plane to target.
In order to further ensure the stability during motion target tracking, avoid the tracking of external environment factor bring wrong
Accidentally the problems such as, in the tracking and ranging process of target image, if terrestrial operation person has found that unmanned aerial vehicle platform has tracked wrong mesh
Mark, can be sent a signal in onboard image processing module by modes such as a mouse click right buttons, cancelled current tracking, laid equal stress on
New frame selects spotting region, repeats step S202-S3, continues the tracking of moving target.
Specifically, above method embodiment and Installation practice are based on identical inventive concept, and specific implementation place can
Mutually use for reference.
It will be understood by those skilled in the art that realizing all or part of the process of above-described embodiment method, meter can be passed through
Calculation machine program instruction relevant hardware is completed, and the program can be stored in computer readable storage medium.Wherein, described
Computer readable storage medium is disk, CD, read-only memory or random access memory etc..
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by anyone skilled in the art,
It should be covered by the protection scope of the present invention.
Claims (10)
1. a kind of unmanned plane pursuit movement goal systems based on binocular distance measurement characterized by comprising unmanned plane is flat
Platform, ground control station；
The unmanned aerial vehicle platform obtains movement destination image by binocular camera in real time, carries out benchmark image tracking and binocular is vertical
Body matching obtains the 3 d space coordinate of moving target, and approach and track automatically to moving target；
The ground control station, for guiding unmanned aerial vehicle platform tentatively close to moving target, to receive the fortune that unmanned aerial vehicle platform is sent
Moving-target image is simultaneously shown, and is tentatively demarcated to the target area in image.
2. the method according to claim 1, wherein the unmanned aerial vehicle platform, comprising: binocular camera, airborne figure
As processing module, airborne communication module, motion-control module；
The ground control station, comprising: industrial personal computer, ground communication module, display module；
The onboard image processing module is respectively connected with binocular camera, airborne communication module, motion-control module；For root
The data that the movement destination image and ground control station obtained according to binocular camera is sent carry out image trace and binocular solid matching
Processing, obtains the three-dimensional coordinate of moving target；
Data after onboard image processing module coding are sent to ground control station, received simultaneously by the airborne communication module
The data of ground control station；
The motion-control module, the three-dimensional coordinate of the moving target for being sent according to onboard image processing module control nothing
Man-machine close and pursuit movement target；
The ground communication module, the Data Concurrent for receiving airborne communication module transmission give industrial personal computer, meanwhile, ground is controlled
The data stood are sent to airborne communication module；
The industrial personal computer is decoded received data, and is sent to display module and is shown.
3. system according to claim 2, which is characterized in that the onboard image processing module, using KCF algorithm to reality
When every frame benchmark image for obtaining in target area carry out detecting and tracking；And according to the seat of target area in every frame benchmark image
Cursor position carries out binocular solid matching by Matching unit of grey scale pixel value.
4. a kind of unmanned plane pursuit movement target side based on binocular distance measurement using system described in one of claim 1-3
Method, which comprises the following steps:
Ground control station guides unmanned aerial vehicle platform tentatively close to moving target, and moving target is made to enter binocular camera visual field；
In binocular camera visual field, benchmark image tracking and binocular solid matching are carried out, and fortune is obtained by binocular ranging in real time
The three dimensional local information of moving-target；
According to the above-mentioned three dimensional local information obtained in real time, unmanned aerial vehicle platform quickly accurately automatically tracks target progress.
5. according to the method described in claim 4, it is characterized in that, the progress benchmark image tracking, comprising:
The image that unmanned aerial vehicle platform obtains binocular camera, real-time Transmission are shown into ground control station；
The target area demarcated in display image is obtained, and the position coordinates of target area are transmitted to unmanned aerial vehicle platform；
According to the position coordinates of target area, using KCF algorithm to the target area in the every frame benchmark image obtained in real time into
Row detecting and tracking.
6. according to the method described in claim 5, it is characterized in that, described carry out benchmark image tracking, packet using KCF algorithm
It includes:
After the coordinate position for the target area for getting calibration, based on image grayscale latent structure acquisition target positive sample with
Negative sample, training objective detector；
In each frame benchmark image later, detected using above-mentioned object detector in region of search, with highest confidence level
Region as target area；When the confidence value of target area be less than preset value when, region of search range is expanded, again into
Row search.
7. according to the method described in claim 6, it is characterized in that, unmanned aerial vehicle platform is according to target area in every frame benchmark image
Coordinate position, using grey scale pixel value as Matching unit carry out binocular solid matching, comprising:
Every frame RGB image that two mesh of left and right obtain is converted into grayscale image；
On the basis of target area in a wherein mesh grayscale image, in another mesh grayscale image in identical height region, successively not between
Every calculating each piece of same size region mean pixel point gray value and corresponding area coordinate；
Calculate the absolute difference of the mean pixel point gray value in above-mentioned each region and datum target region；
The minimum value and sub-minimum for seeking the absolute difference, when minimum value is less than preset minimum value and sub-minimum and minimum value
Difference be less than preset difference value when, then using the corresponding region of minimum value as the target area in matched another mesh image.
8. the method according to the description of claim 7 is characterized in that described obtain the three of moving target by binocular ranging in real time
Location information is tieed up, including, in the three-dimensional coordinate depth value for seeking moving target, Kalman filtering is carried out, rejects partial frame figure
The outlier occurred as in.
9. according to the method described in claim 8, it is characterized in that, described according to the above-mentioned three dimensional local information obtained in real time,
Unmanned plane to target progress quickly accurately automatically track, comprising: according to the real-time three-dimensional coordinate information of target be input value, structure
Position PID controller is made, control unmanned plane is quickly tracked close to target.
10. according to the method described in claim 9, it is characterized by further comprising: when unmanned aerial vehicle platform has tracked false target
When, then cancel current tracking, and reacquire the target area of calibration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811100610.3A CN109407697A (en) | 2018-09-20 | 2018-09-20 | A kind of unmanned plane pursuit movement goal systems and method based on binocular distance measurement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811100610.3A CN109407697A (en) | 2018-09-20 | 2018-09-20 | A kind of unmanned plane pursuit movement goal systems and method based on binocular distance measurement |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109407697A true CN109407697A (en) | 2019-03-01 |
Family
ID=65465142
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811100610.3A Pending CN109407697A (en) | 2018-09-20 | 2018-09-20 | A kind of unmanned plane pursuit movement goal systems and method based on binocular distance measurement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109407697A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110018692A (en) * | 2019-04-24 | 2019-07-16 | 五邑大学 | A kind of unmanned plane method of guidance, system, device and storage medium |
| CN110262534A (en) * | 2019-06-25 | 2019-09-20 | 北京机械设备研究所 | A kind of unmanned plane tracking and intercepting system and method for low slow Small object |
| CN110287957A (en) * | 2019-06-24 | 2019-09-27 | 北京中电慧视科技有限公司 | A kind of localization method and positioning device of low slow Small object |
| CN110400333A (en) * | 2019-07-26 | 2019-11-01 | 中国安全生产科学研究院 | Coach's formula binocular stereo vision device and High Precision Stereo visual pattern acquisition methods |
| CN110393165A (en) * | 2019-07-11 | 2019-11-01 | 浙江大学宁波理工学院 | A kind of off-lying sea cultivation net cage bait-throwing method based on Autoamtic bait putting ship |
| CN110647156A (en) * | 2019-09-17 | 2020-01-03 | 中国科学院自动化研究所 | Target object docking ring-based docking equipment pose adjusting method and system |
| CN110764537A (en) * | 2019-12-25 | 2020-02-07 | 中航金城无人系统有限公司 | Automatic tripod head locking system and method based on motion estimation and visual tracking |
| CN111754542A (en) * | 2019-03-27 | 2020-10-09 | 顺丰科技有限公司 | Target object determination method, tracking method, device, equipment and storage medium thereof |
| CN112539732A (en) * | 2020-12-04 | 2021-03-23 | 杭州电子科技大学 | Unmanned aerial vehicle cluster state and trajectory data acquisition platform |
| WO2021128189A1 (en) * | 2019-12-26 | 2021-07-01 | 深圳市大疆创新科技有限公司 | Data processing method and apparatus, unmanned aerial vehicle and flight control system |
| CN113365030A (en) * | 2021-06-01 | 2021-09-07 | 珠海大横琴科技发展有限公司 | Multi-angle target tracking method and tracking system |
| CN113449566A (en) * | 2020-03-27 | 2021-09-28 | 北京机械设备研究所 | Intelligent image tracking method and system for low-speed small target in human-in-loop |
| WO2021217372A1 (en) * | 2020-04-27 | 2021-11-04 | 深圳市大疆创新科技有限公司 | Control method and device for movable platform |
| CN114127510A (en) * | 2019-06-04 | 2022-03-01 | 菲力尔无人机系统公司 | 3D localization and mapping system and method |
| CN114155290A (en) * | 2021-11-18 | 2022-03-08 | 合肥富煌君达高科信息技术有限公司 | System and method for large-field-of-view high-speed motion measurement |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106444829A (en) * | 2016-09-22 | 2017-02-22 | 北京机械设备研究所 | Guidance unmanned aerial vehicle net cast interception method for "low-altitude, slow-speed and small" target |
| CN107424177A (en) * | 2017-08-11 | 2017-12-01 | 哈尔滨工业大学（威海） | Positioning amendment long-range track algorithm based on serial correlation wave filter |
| CN107610157A (en) * | 2016-07-12 | 2018-01-19 | 深圳雷柏科技股份有限公司 | A kind of unmanned plane target method for tracing and system |
| CN107621266A (en) * | 2017-08-14 | 2018-01-23 | 上海宇航系统工程研究所 | The space non-cooperative target Relative Navigation of distinguished point based tracking |
| US20180095479A1 (en) * | 2016-03-31 | 2018-04-05 | Ninebot (Beijing) Tech. Co., Ltd | Method, mobile device and computer storage medium for processing information |
| CN107894590A (en) * | 2017-10-17 | 2018-04-10 | 湖北林青测控科技有限公司 | New full passive type unmanned plane management-control method, storage medium, electronic equipment |
| CN108010067A (en) * | 2017-12-25 | 2018-05-08 | 北京航空航天大学 | A kind of visual target tracking method based on combination determination strategy |
| CN108062764A (en) * | 2017-11-30 | 2018-05-22 | 极翼机器人(上海)有限公司 | A kind of object tracking methods of view-based access control model |
-
2018
- 2018-09-20 CN CN201811100610.3A patent/CN109407697A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180095479A1 (en) * | 2016-03-31 | 2018-04-05 | Ninebot (Beijing) Tech. Co., Ltd | Method, mobile device and computer storage medium for processing information |
| CN107610157A (en) * | 2016-07-12 | 2018-01-19 | 深圳雷柏科技股份有限公司 | A kind of unmanned plane target method for tracing and system |
| CN106444829A (en) * | 2016-09-22 | 2017-02-22 | 北京机械设备研究所 | Guidance unmanned aerial vehicle net cast interception method for "low-altitude, slow-speed and small" target |
| CN107424177A (en) * | 2017-08-11 | 2017-12-01 | 哈尔滨工业大学（威海） | Positioning amendment long-range track algorithm based on serial correlation wave filter |
| CN107621266A (en) * | 2017-08-14 | 2018-01-23 | 上海宇航系统工程研究所 | The space non-cooperative target Relative Navigation of distinguished point based tracking |
| CN107894590A (en) * | 2017-10-17 | 2018-04-10 | 湖北林青测控科技有限公司 | New full passive type unmanned plane management-control method, storage medium, electronic equipment |
| CN108062764A (en) * | 2017-11-30 | 2018-05-22 | 极翼机器人(上海)有限公司 | A kind of object tracking methods of view-based access control model |
| CN108010067A (en) * | 2017-12-25 | 2018-05-08 | 北京航空航天大学 | A kind of visual target tracking method based on combination determination strategy |
Non-Patent Citations (4)
| Title |
|---|
| LUIS RODOLFO GARCIA CARRILLO: "《四旋冀无人机控制 基于视觉的悬停与导航》", 30 June 2016, 国防工业出版社 * |
| 彭鹏菲 等: "《舰载无人机系统及作战应用》", 31 January 2016, 国防工业出版社 * |
| 杜军平 等: "《跨尺度运动图像的目标检测与跟踪》", 30 June 2018, 北京邮电大学出版社 * |
| 齐俊桐 等: "《无人机输电线路巡检与架设技术》", 30 November 2014, 东北大学出版社 * |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111754542A (en) * | 2019-03-27 | 2020-10-09 | 顺丰科技有限公司 | Target object determination method, tracking method, device, equipment and storage medium thereof |
| CN110018692A (en) * | 2019-04-24 | 2019-07-16 | 五邑大学 | A kind of unmanned plane method of guidance, system, device and storage medium |
| CN114127510A (en) * | 2019-06-04 | 2022-03-01 | 菲力尔无人机系统公司 | 3D localization and mapping system and method |
| CN110287957A (en) * | 2019-06-24 | 2019-09-27 | 北京中电慧视科技有限公司 | A kind of localization method and positioning device of low slow Small object |
| CN110287957B (en) * | 2019-06-24 | 2021-09-07 | 北京中电慧视科技有限公司 | Low-slow small target positioning method and positioning device |
| CN110262534A (en) * | 2019-06-25 | 2019-09-20 | 北京机械设备研究所 | A kind of unmanned plane tracking and intercepting system and method for low slow Small object |
| CN110393165A (en) * | 2019-07-11 | 2019-11-01 | 浙江大学宁波理工学院 | A kind of off-lying sea cultivation net cage bait-throwing method based on Autoamtic bait putting ship |
| CN110393165B (en) * | 2019-07-11 | 2021-06-25 | 浙江大学宁波理工学院 | Open sea aquaculture net cage bait feeding method based on automatic bait feeding boat |
| CN110400333A (en) * | 2019-07-26 | 2019-11-01 | 中国安全生产科学研究院 | Coach's formula binocular stereo vision device and High Precision Stereo visual pattern acquisition methods |
| CN110400333B (en) * | 2019-07-26 | 2020-06-26 | 中国安全生产科学研究院 | Training binocular stereoscopic vision device and high-precision stereoscopic vision image acquisition method |
| CN110647156B (en) * | 2019-09-17 | 2021-05-11 | 中国科学院自动化研究所 | Target object docking ring-based docking equipment pose adjusting method and system |
| CN110647156A (en) * | 2019-09-17 | 2020-01-03 | 中国科学院自动化研究所 | Target object docking ring-based docking equipment pose adjusting method and system |
| CN110764537A (en) * | 2019-12-25 | 2020-02-07 | 中航金城无人系统有限公司 | Automatic tripod head locking system and method based on motion estimation and visual tracking |
| WO2021128189A1 (en) * | 2019-12-26 | 2021-07-01 | 深圳市大疆创新科技有限公司 | Data processing method and apparatus, unmanned aerial vehicle and flight control system |
| CN113474741A (en) * | 2019-12-26 | 2021-10-01 | 深圳市大疆创新科技有限公司 | Data processing method and device, unmanned aerial vehicle and flight control system |
| CN113449566A (en) * | 2020-03-27 | 2021-09-28 | 北京机械设备研究所 | Intelligent image tracking method and system for low-speed small target in human-in-loop |
| CN113449566B (en) * | 2020-03-27 | 2024-05-07 | 北京机械设备研究所 | Intelligent image tracking method and system for 'low-small' target of human in loop |
| WO2021217372A1 (en) * | 2020-04-27 | 2021-11-04 | 深圳市大疆创新科技有限公司 | Control method and device for movable platform |
| CN114096931A (en) * | 2020-04-27 | 2022-02-25 | 深圳市大疆创新科技有限公司 | Control method and device for movable platform |
| CN112539732A (en) * | 2020-12-04 | 2021-03-23 | 杭州电子科技大学 | Unmanned aerial vehicle cluster state and trajectory data acquisition platform |
| CN113365030A (en) * | 2021-06-01 | 2021-09-07 | 珠海大横琴科技发展有限公司 | Multi-angle target tracking method and tracking system |
| CN114155290A (en) * | 2021-11-18 | 2022-03-08 | 合肥富煌君达高科信息技术有限公司 | System and method for large-field-of-view high-speed motion measurement |
| CN114155290B (en) * | 2021-11-18 | 2022-09-09 | 合肥富煌君达高科信息技术有限公司 | System and method for large-field-of-view high-speed motion measurement |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109407697A (en) | A kind of unmanned plane pursuit movement goal systems and method based on binocular distance measurement | |
| US11915502B2 (en) | Systems and methods for depth map sampling | |
| CN105955258B (en) | Robot global grating map construction method based on the fusion of Kinect sensor information | |
| US9429945B2 (en) | Surveying areas using a radar system and an unmanned aerial vehicle | |
| CN104820998B (en) | A kind of human testing based on unmanned motor platform and tracking and device | |
| CN110361727A (en) | A kind of millimetre-wave radar multi-object tracking method | |
| CN106405540A (en) | Radar and photoelectric device complementation-based detection and identification device and method | |
| US11113896B2 (en) | Geophysical sensor positioning system | |
| CN112068111A (en) | Unmanned aerial vehicle target detection method based on multi-sensor information fusion | |
| US11182043B2 (en) | Interactive virtual interface | |
| CN103824070A (en) | Rapid pedestrian detection method based on computer vision | |
| CN104536009A (en) | Laser infrared composite ground building recognition and navigation method | |
| CN106093934B (en) | Based on multiple target location estimation method after the through-wall radar imaging for improving Dynamic Programming | |
| Papaioannou et al. | Tracking people in highly dynamic industrial environments | |
| CN106033601A (en) | Method and apparatus for detecting abnormal situation | |
| Cai et al. | Robust hybrid approach of vision-based tracking and radio-based identification and localization for 3D tracking of multiple construction workers | |
| CN104570764A (en) | Verification platform for airborne target indicating system | |
| CN108303094A (en) | The Position Fixing Navigation System and its positioning navigation method of array are merged based on multiple vision sensor | |
| CN105637322A (en) | A method of determining the location of a point of interest and the system thereof | |
| CN107783555A (en) | A kind of object localization method based on unmanned plane, apparatus and system | |
| Papaioannou et al. | Accurate positioning via cross-modality training | |
| CN113156417A (en) | Anti-unmanned aerial vehicle detection system and method and radar equipment | |
| KR20150031530A (en) | Method and apparatus for video surveillance by using surveillance apparatus of unmanned aerial vehicle | |
| CN109858499A (en) | A kind of tank armor object detection method based on Faster R-CNN | |
| Liu et al. | Manhole cover detection from natural scene based on imaging environment perception |
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 |