CN114092522B - Airport plane take-off and landing intelligent capturing and tracking method - Google Patents
Airport plane take-off and landing intelligent capturing and tracking method Download PDFInfo
- Publication number
- CN114092522B CN114092522B CN202111440553.5A CN202111440553A CN114092522B CN 114092522 B CN114092522 B CN 114092522B CN 202111440553 A CN202111440553 A CN 202111440553A CN 114092522 B CN114092522 B CN 114092522B
- Authority
- CN
- China
- Prior art keywords
- target
- tracking
- intelligent
- module
- image
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000005259 measurement Methods 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000001914 filtration Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 abstract description 3
- 238000013461 design Methods 0.000 abstract description 2
- 230000005693 optoelectronics Effects 0.000 abstract 1
- 206010063385 Intellectualisation Diseases 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- 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
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
Abstract
An intelligent capturing and tracking method for taking off and landing an airport aircraft relates to the technical field of intelligent tracking, and solves the problems of poor intelligent accuracy and tracking stability caused by complex weather environment, bird interference and the like of the existing intelligent tracking mode, including automatic identification of the aircraft; the method is used for continuously acquiring the image information of the airplane during landing or taking off of the airplane at the airport, and the target is identified and tracked through processing the airplane image, so that the problems of complex weather environment, bird interference and the like are solved, the identification accuracy and the tracking stability of intelligent equipment are improved, and the automatic identification and tracking of equipment such as an optoelectronic theodolite and the like are realized. Finally, the identification precision and the tracking precision of the photoelectric equipment are ensured. Meanwhile, the design of the invention improves the adaptability and independence of the optical measurement system, so that the device has unmanned autonomous measurement capability.
Description
Technical Field
The invention relates to the technical field of intelligent tracking, in particular to an intelligent capturing and tracking method for taking off and landing of an airport plane.
Background
The existing photoelectric system for aircraft tracking is difficult to realize automation and intellectualization, and has the problems of low aircraft identification success rate, poor tracking stability, complex operation logic and the like. And the system is applied to an airport outdoor environment, and the influence factors such as atmospheric turbulence, airplane rotation, illumination change, sky flyers, ground towers and the like can cause certain interference to the airplane identification tracking.
With the rapid development of modern technology, more and more intelligent systems are beginning to be widely applied to modern target range measurement. In the flight training task of pilots, the intelligent recognition photoelectric equipment can automatically recognize the aircraft, stably track the take-off section and the landing section, has high intelligence and unattended and automatic tracking measurement capability.
The identification accuracy and the tracking stability of the intelligent capture tracking system are directly related to whether the equipment can independently complete the monitoring and guiding process of the aircraft under the unattended condition, so that the aircraft in the field of view must be accurately identified and captured first to improve the automation level of the photoelectric equipment, and then the stable tracking of the target is completed.
Disclosure of Invention
The invention provides an intelligent capturing and tracking method for taking off and landing of an airport plane, which aims to solve the problems of poor intelligent accuracy and tracking stability caused by complex weather environment, bird interference and the like of the existing intelligent tracking mode.
An intelligent capturing and tracking method for taking off and landing of an airport aircraft is realized by the following steps:
step one, automatically identifying an airplane;
the system points to a capturing area and automatically captures after the measurement target appears; starting a camera to acquire an image, transmitting the image to an image processing module for target identification, automatically focusing by an intelligent focusing module when a suspected target appears in a view field, judging whether the suspected target appears as a target to be detected or not by the target identification module, and executing a second step if the suspected target appears as the target to be detected; if not, continuing to capture the target;
Step two, stably tracking the target;
The central server judges whether the tracked target to be detected is a mission plane, if so, a template is generated to continue tracking, and the third step is executed; if not, releasing the target and returning to the capturing area, and executing the step one;
Step three, judging whether the current target is interfered by the environment, and if so, performing interference rejection and recapture; if not, continuing tracking; executing the fourth step; when the system moves to the tracking end point, the system points to the capturing area again, and returns to the step one when the next target to be detected appears;
outputting and displaying tracking information;
And when the tracking is stable, the central server collects relevant data of the sorting identification confidence, the tracking state information and the off-target amount information, ensures the synchronism of all the data participating in calculation according to the time stamp, continuously updates and calculates the state information of the target through smooth filtering processing, outputs and displays the tracking information, controls the equipment to complete the tracking process until the target flies to the measurement end point, finishes the tracking measurement, redirects the equipment to the capture area to wait for the next measurement target to appear, resets the system state, and prepares the target to be captured again automatically.
The invention has the beneficial effects that: the intelligent identifying and tracking method is used for continuously acquiring the image information of the airplane when the airplane in the airport lands or takes off, and identifying and tracking the target through processing the airplane image, so that the problems of complex weather environment, bird interference and the like are solved, the identifying accuracy and the tracking stability of intelligent equipment are improved, and the automatic identifying and tracking of equipment such as a photoelectric theodolite and the like are realized.
The method fully considers the automation and the intellectualization of the equipment such as the photoelectric theodolite, and the like, accurately and automatically captures and identifies the airplane target by utilizing the intelligent identification tracking method of the airplane, solves the problem that the airplane is likely to be interfered by flying birds, clouds, high buildings and the like in the tracking state, realizes the stable tracking of the airplane, and finally ensures the identification precision and the tracking precision of the photoelectric equipment. Meanwhile, the design of the invention improves the adaptability and independence of the optical measurement system, so that the device has unmanned autonomous measurement capability.
Drawings
FIG. 1 is a schematic block diagram of an airport aircraft take-off and landing intelligent capture tracking system according to the invention;
FIG. 2 is a flow chart of an intelligent capturing and tracking method for taking off and landing of an airport aircraft according to the invention;
fig. 3 is a flowchart of a tracking decision mechanism in the intelligent capturing and tracking method for taking off and landing of an airport aircraft.
Detailed Description
Referring to fig. 1 to 3, a hardware system according to the present embodiment is described, and an aircraft intelligent recognition and tracking method may be applied to the system, where the system includes a camera, an image acquisition card, an image processor, and a backbone server, as shown in fig. 1. The camera collects target images through the image collecting card, the image processor acquires images and performs intelligent identification of the airplane, and the central server synthesizes all paths of information (image information, encoder azimuth pitching information, identified boundary frames and confidence coefficient) to complete tracking decision of the target, output tracking information and control equipment to track the target.
The invention relates to an intelligent identifying and tracking method for an airplane. As shown in fig. 2, the following steps are employed to achieve automatic tracking of the aircraft.
Step 1: the automatic identification of the aircraft is realized;
Firstly, after the system is started, the equipment automatically points to a capturing area to wait for the occurrence of a measurement target, and is ready for automatic capturing. The camera is started and acquires images, the images are sent to the image processing module, and the center server analyzes and calculates the image processing result so as to determine whether to enter the next module;
when a suspected target appears in the visual field, the intelligent focusing module starts to work, continuously adjusts the focal length of the vision sensor, and provides a stable and clear image with proper size for the target recognition module for detection and recognition;
The target recognition module can accurately judge whether the target is a target to be detected, and the module mainly uses the deep neural network to make a decision, and can decide whether to continue waiting for the occurrence of the target to be measured or immediately switch to a tracking state (i.e. perform step 2).
Step 2: finishing stable tracking of the target;
If the tracking state is shifted, the hub server starts to play an intelligent decision-making role, as shown in fig. 3. Firstly judging whether the tracking target is an airplane, if so, generating a template to continue tracking, and if not, releasing the target and returning to the capturing area, and repeating the step 1. And secondly, judging whether the current target is interfered by the environment, and if so, performing interference rejection and reacquiring. And finally judging whether the equipment moves to a tracking end point, if so, ending the tracking, returning to the capturing area, and carrying out the step 1 again, otherwise, continuing the tracking, and continuing the intelligent focusing, the characteristic point tracking, the target locking and the executing of the step 3 of the step 2.
The intelligent focusing module can always ensure proper imaging size of the target according to the distance information, definition and the like of the target throughout the whole tracking process, and provides good preconditions for confirming and transferring to stable tracking of aircraft feature points. After the tracking state is shifted, the characteristic point tracking module takes the target captured by the system as a template, and the template is designed to be 30 x 30 pixel points, so that the template is suitable for tracking small targets and can detect matched targets according to characteristics such as textures, colors and the like; because the aircraft has bright and dark characteristics and the birds and the tower has dark and bright characteristics, the characteristic point tracking module is designed to be more sensitive to bright targets so as to improve the success rate of aircraft tracking. Finally, the system has a target locking function, so that a target cannot be captured at will; once in the locking state, the detection range of target identification and relevant filtering is reduced, and factors which can occur in the tracking process and interfere stable tracking such as clouds, towers and the like are eliminated, so that the success rate of aircraft tracking is ensured.
Step 3: outputting and displaying the tracking information.
And when tracking is stable, the central server also collects relevant data such as sorting identification confidence, tracking state information, off-target amount information and the like, ensures the synchronism of all the data participating in calculation according to the time stamp, and after necessary smooth filtering processing, unnecessary errors are avoided being introduced, the state information of the target is continuously updated and calculated, the tracking information is output and displayed, the control equipment finishes the tracking process until the target flies to the measurement end point, the tracking measurement is ended, the equipment is redirected to the capture area to wait for the occurrence of the next measurement target, the system state is reset, and the target is prepared for automatic capture again.
The tracking method described in this embodiment can be used for optical measurement devices such as an electro-optical theodolite.
Claims (3)
1. An intelligent capturing and tracking method for taking off and landing of an airport aircraft is characterized by comprising the following steps of: the tracking method is realized by the following steps:
step one, automatically identifying an airplane;
the system points to a capturing area and automatically captures after the measurement target appears; starting a camera to acquire an image, transmitting the image to an image processing module for target identification, automatically focusing by an intelligent focusing module when a suspected target appears in a view field, judging whether the suspected target appears as a target to be detected or not by the target identification module, and executing a second step if the suspected target appears as the target to be detected; if not, continuing to capture the target;
Step two, stably tracking the target;
The central server judges whether the tracked target to be detected is a mission plane, if so, a template is generated to continue tracking, and the third step is executed; if not, releasing the target and returning to the capturing area, and executing the step one;
In the second step, the target captured by the system is used as a template through a characteristic point tracking module, the template is designed to be 30 x 30 pixel points, so that the template is suitable for tracking a small target, and the matching target can be detected according to texture and color characteristics;
step three, judging whether the current target is interfered by the environment, if so, eliminating the interference and capturing again; if not, continuing tracking; executing the fourth step; when the system moves to the tracking end point, the system points to the capturing area again, and returns to the step one when the next target to be detected appears;
outputting and displaying tracking information;
And when the tracking is stable, the central server collects relevant data of the sorting identification confidence, the tracking state information and the off-target amount information, ensures the synchronism of all the data participating in calculation according to the time stamp, continuously updates and calculates the state information of the target through smooth filtering processing, outputs and displays the tracking information, controls the equipment to complete the tracking process until the target flies to the measurement end point, finishes the tracking measurement, redirects the equipment to the capture area to wait for the next measurement target to appear, resets the system state, and prepares the target to be captured again automatically.
2. The intelligent capture tracking method for taking off and landing of an airport aircraft according to claim 1, wherein the method comprises the following steps: the system comprises a camera acquisition module, an image processing module, an intelligent focusing module, a target identification module and a central server;
The camera acquisition module acquires a target image and transmits the target image to the image processing module, and the target recognition module intelligently recognizes the image processed by the image processing module and then completes tracking decision of a target, tracking information output and target tracking of control equipment through the central server.
3. The intelligent capture tracking method for taking off and landing of an airport aircraft according to claim 1, wherein the method comprises the following steps: the system further includes an object-locking module that reduces object recognition and filtering processing when the captured object is in a locked state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111440553.5A CN114092522B (en) | 2021-11-30 | 2021-11-30 | Airport plane take-off and landing intelligent capturing and tracking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111440553.5A CN114092522B (en) | 2021-11-30 | 2021-11-30 | Airport plane take-off and landing intelligent capturing and tracking method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114092522A CN114092522A (en) | 2022-02-25 |
| CN114092522B true CN114092522B (en) | 2024-06-07 |
Family
ID=80305809
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111440553.5A Active CN114092522B (en) | 2021-11-30 | 2021-11-30 | Airport plane take-off and landing intelligent capturing and tracking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114092522B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115115992B (en) * | 2022-07-26 | 2022-11-15 | 中国科学院长春光学精密机械与物理研究所 | Multi-platform photoelectric auto-disturbance rejection tracking system and method based on brain map control right decision |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004341A (en) * | 2006-01-20 | 2007-07-25 | 中国科学院沈阳自动化研究所 | High-speed flight target recording method |
| CN105300345A (en) * | 2015-11-10 | 2016-02-03 | 中国科学院长春光学精密机械与物理研究所 | Photoelectric theodolite multi-target tracking method |
| WO2018121286A1 (en) * | 2016-12-30 | 2018-07-05 | 纳恩博（北京）科技有限公司 | Target tracking method and device |
| CN109099779A (en) * | 2018-08-31 | 2018-12-28 | 江苏域盾成鹫科技装备制造有限公司 | A kind of detecting of unmanned plane and intelligent intercept system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6206857B1 (en) * | 2016-08-24 | 2017-10-04 | パナソニックＩｐマネジメント株式会社 | Tracking support device, tracking support system, and tracking support method |
-
2021
- 2021-11-30 CN CN202111440553.5A patent/CN114092522B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004341A (en) * | 2006-01-20 | 2007-07-25 | 中国科学院沈阳自动化研究所 | High-speed flight target recording method |
| CN105300345A (en) * | 2015-11-10 | 2016-02-03 | 中国科学院长春光学精密机械与物理研究所 | Photoelectric theodolite multi-target tracking method |
| WO2018121286A1 (en) * | 2016-12-30 | 2018-07-05 | 纳恩博（北京）科技有限公司 | Target tracking method and device |
| CN109099779A (en) * | 2018-08-31 | 2018-12-28 | 江苏域盾成鹫科技装备制造有限公司 | A kind of detecting of unmanned plane and intelligent intercept system |
Non-Patent Citations (2)
| Title |
|---|
| Research on Detection and Tracking of Moving Target in Intelligent Video Surveillance;Lin Lizhong等;《2012 International Conference on Computer Science and Electronics Engineering》;20120423;全文 * |
| 光电经纬仪跟踪飞行目标的一种仿真方法;王***;;计算机仿真;20090415(第04期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114092522A (en) | 2022-02-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111326023A (en) | Unmanned aerial vehicle route early warning method, device, equipment and storage medium | |
| CN108153334B (en) | Visual autonomous return and landing method and system for unmanned helicopter without cooperative target | |
| CN105758397B (en) | A kind of aircraft camera positioning method | |
| Thurrowgood et al. | A vision based system for attitude estimation of UAVs | |
| CN109063532B (en) | Unmanned aerial vehicle-based method for searching field offline personnel | |
| CN111709968B (en) | Low-altitude target detection tracking method based on image processing | |
| CN110515378A (en) | A kind of intelligent Target searching method applied to unmanned boat | |
| CN104125372A (en) | Target photoelectric search and detection method | |
| CN109765931B (en) | Near-infrared video automatic navigation method suitable for breakwater inspection unmanned aerial vehicle | |
| CN114092522B (en) | Airport plane take-off and landing intelligent capturing and tracking method | |
| CN113066050B (en) | Method for resolving course attitude of airdrop cargo bed based on vision | |
| CN111898444A (en) | Aircraft landing gear state determination method based on image recognition | |
| CN109194284A (en) | Photovoltaic plant cruising inspection system, ground based terminal and equipment of taking photo by plane | |
| CN113837044B (en) | Organ positioning method based on ambient brightness and related equipment | |
| CN104113733B (en) | A kind of low slow Small object TV reconnaissance probe method | |
| Chiu et al. | Vision-only automatic flight control for small UAVs | |
| CN112650304B (en) | Unmanned aerial vehicle autonomous landing system and method and unmanned aerial vehicle | |
| CN110068827A (en) | A kind of method of the autonomous object ranging of unmanned plane | |
| CN114020039A (en) | Automatic focusing system and method for unmanned aerial vehicle inspection tower | |
| CN113987246A (en) | Automatic picture naming method, device, medium and electronic equipment for unmanned aerial vehicle inspection | |
| CN117572885A (en) | Night tracking method, system and related device based on thermal infrared camera of unmanned aerial vehicle | |
| CN109708659B (en) | Distributed intelligent photoelectric low-altitude protection system | |
| CN112862862B (en) | Aircraft autonomous oil receiving device based on artificial intelligence visual tracking and application method | |
| EP4089649A1 (en) | Neuromorphic cameras for aircraft | |
| CN108520286A (en) | Infrared dark dim light small target deteection system based on convolutional Neural and candidate region |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |