CN115273565A - Airplane apron early warning method, device and terminal based on AI big data - Google Patents
Airplane apron early warning method, device and terminal based on AI big data Download PDFInfo
- Publication number
- CN115273565A CN115273565A CN202210728867.3A CN202210728867A CN115273565A CN 115273565 A CN115273565 A CN 115273565A CN 202210728867 A CN202210728867 A CN 202210728867A CN 115273565 A CN115273565 A CN 115273565A
- Authority
- CN
- China
- Prior art keywords
- frame image
- fod
- early warning
- real
- apron
- 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 45
- 238000001514 detection method Methods 0.000 claims abstract description 202
- 238000012545 processing Methods 0.000 claims abstract description 44
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 23
- 238000005520 cutting process Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 10
- 230000011218 segmentation Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 4
- 230000008685 targeting Effects 0.000 claims description 4
- 230000008447 perception Effects 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000003860 storage Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/04—Anti-collision systems
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/0073—Surveillance aids
Abstract
The invention provides an AI big data-based airplane apron early warning method, device and terminal, wherein the method comprises the following steps: dividing the apron into two or more FOD detection areas; collecting video signals of all FOD detection areas; carrying out transcoding processing, playing processing, slicing processing and image cutting processing on the video signals of all FOD detection areas to obtain image signals of all FOD detection areas; polling picture signals of all FOD detection areas based on a preset improved target detection algorithm early warning model to obtain early warning signals; acquiring the position information and the picture information of FOD based on the early warning signal; and sending the position information and the picture information of the FOD to a signal receiver of the airplane. The invention can complete safety early warning of the apron in time, accurately and fully automatically, thereby effectively avoiding data missing report, data error and data delay caused by manual perception.
Description
Technical Field
The invention belongs to the technical field of aviation, and particularly relates to an airport apron early warning method, device and terminal based on AI big data.
Background
The rhythm of the modern social life is faster and faster, and the air transportation is more and more developed. The use of aircraft has also presented the development of well-jet type. As air flow increases, aircraft safety issues become more of a concern, wherein apron foreign objects are a potential hazard for accidents. Foreign objects (Foreign Object Debris) are an important safety concept in any aviation, manufacturing or similar environment where tiny, discrete objects are likely to cause potential damage or injury. Foreign bodies outside airports constitute a serious safety risk for the safety of the aircraft in respect of taking-off and landing. At present, the main problems of risk prediction and evaluation on apron safety mainly exist:
1. traditional apron safety guarantee mainly relies on manual work to observe the video information that high definition digtal camera gathered, needs relevant personnel to carry out the discernment of foreign matter information, types, later handles, and response speed is slower, the unable real-time safety problem that perception apron exists.
2. When receiving information related to the apron, the command center cannot accurately and quickly sense the position of the foreign body causing the risk of the apron.
3. When the ground service personnel obtain the command of the command center, the accurate position of the external foreign body can not be quickly determined through the information given by the command center, and the problem can not be quickly checked on the risk.
4. For personnel who observe video information manually, the personnel rely on eyes to observe completely, fatigue is caused easily for a long time, and meanwhile, the working efficiency is low, and the observed information cannot be rapidly shared to a command center and ground service personnel.
5. At present, most of airport apron safety problems adopt manual methods, which can not quickly respond to the airport apron safety problems, and the prior system has poor timeliness, can not automatically identify FOD, has huge workload of related workers, and can not quickly sense the apron risks,
with the development of science and technology and the popularization of computers, network technologies, artificial intelligence, big data and video image processing technologies related to the computers are mature day by day, and the innovation and the development of video monitoring technologies are promoted to a great extent, so that AI-based big data images are used more and more in the field of airport apron safety, and the detection, the identification and the early warning of foreign object targets in airport apron areas are realized by analyzing and processing the video image data.
Disclosure of Invention
In view of the above, the invention provides an airport apron early warning method, an airport apron early warning device and an airport apron early warning terminal based on AI big data, which can complete safety early warning of an airport apron timely, accurately and fully automatically, and further effectively avoid data missing report, data errors and data delay caused by artificial perception.
The first aspect of the embodiment of the invention provides an airplane apron early warning method based on AI big data, which comprises the following steps:
dividing the apron into two or more FOD detection areas;
collecting video signals of all FOD detection areas;
carrying out transcoding processing, playing processing, slicing processing and image cutting processing on the video signals of all FOD detection areas to obtain image signals of all FOD detection areas;
polling picture signals of all FOD detection areas based on a preset improved target detection algorithm early warning model to obtain early warning signals;
acquiring the position information and the picture information of FOD based on the early warning signal;
and sending the position information and the picture information of the FOD to a signal receiver of the airplane.
Optionally, the collecting process of collecting the video signals of the respective FOD detection areas includes:
arranging two or more than two high-definition cameras at preset positions of all FOD detection areas;
and carrying out high-speed shooting on the apron environment through a high-definition camera to obtain a video signal.
Optionally, the step of polling the picture signals of each FOD detection area based on a preset improved target detection algorithm early warning model to obtain the early warning signal includes:
s1: polling the picture signals of all FOD detection areas in sequence according to a preset time interval, and setting a foreground target Ni(ii) a Wherein i =1;
s2: acquiring background frame images of picture signals of all FOD detection areas, judging whether the background frame images are acquired successfully or not, if the background frame images are acquired successfully, continuing to execute the step S3, and if the background frame images are not acquired successfully, re-executing the step S1; the background frame image is a frame image at any moment before the current moment of the picture signal of each FOD detection area;
s3: acquiring a real-time frame image and an adjacent frame image of a picture signal of each FOD detection area, judging whether the real-time frame image and the adjacent frame image are acquired successfully or not, if the real-time frame image and the adjacent frame image are acquired successfully, continuing to execute the step S4, and if the real-time frame image or the adjacent frame image is not acquired successfully, returning to execute the step S2; the real-time frame image is a frame image of the current moment of the picture signal of each FOD detection area, and the adjacent frame image is a frame image which is separated from the real-time frame image by a frame difference tau in the picture signal of each FOD detection area;
s4: firstly, performing background difference operation on a background frame image and a real-time frame image to obtain a background difference, performing adjacent inter-frame difference operation on the real-time frame image and an adjacent frame image to obtain an adjacent inter-frame difference, and then performing threshold segmentation operation on the background difference and the adjacent inter-frame difference respectively to obtain a first detection result and a second detection result;
s5: carrying out logical OR operation on the first detection result and the second detection result to obtain a third detection result, judging whether each FOD detection area has suspected FOD according to the third detection result, if yes, continuing to execute the step S6 and assigning the third detection result to the foreground target Ni, and if not, returning to execute the step S2;
s6: judging whether each FOD detection area is a sensitive area, if so, continuing to execute the step S7, and enabling i = i +1, if not, calibrating each FOD detection area as a sensitive area, giving a third detection result to a background frame image, and returning to execute the step S4;
s7: and optimizing the foreground target Ni based on an improved target optimization algorithm to obtain a foreground optimization target, and generating an early warning signal according to the foreground optimization target.
Optionally, the calculation method of the background difference includes:
Dk(x，y)＝|Pk(x，y)-Bk(x，y)|
wherein D isk(x, y) is the background difference, Pk(x, y) is a real-time frame image, Bk(x, y) are background frame images.
Optionally, the method for calculating the difference between adjacent frames includes:
Sk(x，y)＝|Pk(x，y)-Pk-τ(x，y)|
wherein S isk(x, y) is the difference between adjacent frames, pk(x, y) is a real-time frame image, Pk-τ(x, y) are adjacent frame images.
Optionally, the calculation method of the third detection result is as follows:
Bink(x，y)＝Bin 1k(x，y)||Bin 2k(x，y)
wherein Bin isk(x, y) is the third detection result, bin1k(x, y) is a first detection result, bin2kAnd (x, y) is a second detection result.
Optionally, the foreground object N is optimized based on the improved object optimization algorithmiThe method for optimizing to obtain the foreground optimization target comprises the following steps:
wherein B (x, y) is the foreground optimization objective, N1For the first detection of a foreground object, N2And for detecting the foreground target for the second time, th is a preset threshold value of the foreground.
A second aspect of the embodiments of the present invention provides an airport apron early warning device based on AI big data, including:
the area dividing module is used for dividing the apron into two or more FOD detection areas;
the video acquisition module is used for acquiring video signals of all FOD detection areas;
the signal processing module is used for carrying out transcoding processing, playing processing, slicing processing and image cutting processing on the video signals of all the FOD detection areas to obtain image signals of all the FOD detection areas;
the FOD early warning module is used for polling picture signals of all FOD detection areas based on a preset improved target detection algorithm early warning model to obtain early warning signals;
the FOD information acquisition module is used for acquiring the position information and the picture information of the FOD based on the early warning signal;
and the FOD information sending module is used for sending the position information and the picture information of the FOD to a signal receiver of the airplane.
Optionally, the steps executed by the FOD warning module include:
s1: sequentially polling the picture signals of all FOD detection areas according to a preset time interval, and setting a foreground target Ni(ii) a Wherein i =1;
s2: acquiring a background frame image of the picture signal of each FOD detection area, judging whether the background frame image is acquired successfully or not, if so, continuing to execute the step S3, and if not, re-executing the step S1; the background frame image is a frame image at any moment before the current moment of the picture signal of each FOD detection area;
s3: acquiring a real-time frame image and an adjacent frame image of a picture signal of each FOD detection area, judging whether the real-time frame image and the adjacent frame image are acquired successfully or not, if the real-time frame image and the adjacent frame image are acquired successfully, continuing to execute the step S4, and if the real-time frame image or the adjacent frame image is not acquired successfully, returning to execute the step S2; the real-time frame image is a frame image of the current moment of the picture signal of each FOD detection area, and the adjacent frame image is a frame image which is separated from the real-time frame image by a frame difference tau in the picture signal of each FOD detection area;
s4: firstly, performing background difference operation on a background frame image and a real-time frame image to obtain a background difference, performing adjacent inter-frame difference operation on the real-time frame image and an adjacent frame image to obtain an adjacent inter-frame difference, and then performing threshold segmentation operation on the background difference and the adjacent inter-frame difference respectively to obtain a first detection result and a second detection result;
s5: carrying out logical OR operation on the first detection result and the second detection result to obtain a third detection result, judging whether each FOD detection area has suspected FOD or not according to the third detection result, if yes, continuing to execute the step S6 and assigning the third detection result to the foreground target NiIf not, returning to execute the step S2;
s6: judging whether each FOD detection area is a sensitive area, if so, continuing to execute the step S7, and enabling i = i +1, if not, calibrating each FOD detection area as a sensitive area, giving a third detection result to a background frame image, and returning to execute the step S4;
s7: targeting foreground target N based on improved target optimization algorithmiAnd optimizing to obtain a foreground optimization target, and generating an early warning signal according to the foreground optimization target.
A third aspect of the embodiments of the present invention provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the AI-big-data-based apron pre-warning method as described above.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides an AII big data-based airport apron early-warning method, device and terminal, wherein the method comprises the following steps: dividing the airport apron into two or more FOD detection areas; collecting video signals of all FOD detection areas; carrying out transcoding processing, playing processing, slicing processing and image cutting processing on the video signals of all FOD detection areas to obtain image signals of all FOD detection areas; polling picture signals of all FOD detection areas based on a preset improved target detection algorithm early warning model to obtain early warning signals; acquiring the position information and the picture information of FOD based on the early warning signal; and sending the position information and the picture information of the FOD to a signal receiver of the airplane. The invention can complete safety early warning of the apron in time, accurately and fully automatically, thereby effectively avoiding data missing report, data error and data delay caused by manual perception.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the embodiments or the prior art description will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings may be obtained according to these drawings without inventive labor.
Fig. 1 is a schematic flow chart of an airplane apron early warning method based on AI big data according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating steps of a pre-set early warning model for an improved target detection algorithm according to an embodiment of the present invention;
fig. 3 is a structural block diagram of an airfield early warning device based on AI big data according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
To make the objects, technical solutions and advantages of the present invention more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.
Referring to fig. 1, a schematic flow chart of an AI big data-based method for early warning an airport apron according to an embodiment of the present invention is shown, which is detailed as follows:
the apron is divided into two or more FOD detection areas.
Optionally, in some embodiments, the rapid positioning of the foreign matters can be realized by blocking and detecting the apron in a partitioning manner, that is, the position information of the foreign matters can be timely sent to the airplane to be landed and take off, so that the safety of the airplane is guaranteed, ground workers can be timely notified to clean the foreign matters at the early warning position, and the early warning response speed and the foreign matter troubleshooting speed are improved.
And collecting video signals of all FOD detection areas.
Optionally, in some embodiments, the time interval for acquiring the video signal may be appropriately adjusted, and the processing speed of the computer for the video signal is faster than the observation speed of the human for the video, so as to realize real-time perception of the environmental condition of the apron.
And carrying out transcoding processing, playing processing, slicing processing and image cutting processing on the video signals of all the FOD detection areas to obtain image signals of all the FOD detection areas.
Optionally, in some embodiments, the video signals of the respective FOD detection areas are converted into picture signals, and the difference between the pictures is identified by a computer to realize target detection of the foreign object, so as to further improve accuracy and time efficiency of detection of the foreign object.
And polling the picture signals of all FOD detection areas based on a preset improved target detection algorithm early warning model to obtain early warning signals.
And acquiring the position information and the picture information of the FOD based on the early warning signal.
Optionally, in some embodiments, the position information of the FOD is the position of a FOD detection area.
And sending the position information and the picture information of the FOD to a signal receiver of the airplane.
Optionally, in some embodiments, the signal receiver of the aircraft quickly senses the risk of the apron through the received position information and the picture information of the FOD, and cooperates with ground staff to perform danger clearing work.
Optionally, as a specific implementation manner of the AI big data-based airport apron early-warning method provided in the embodiment of the present invention, the collecting process of the video signals of each FOD detection area includes:
two and even more than high definition digtal camera setting in each FOD detection area's preset position.
And carrying out high-speed shooting on the apron environment through a high-definition camera to obtain a video signal.
Optionally, in some embodiments, in this embodiment, the apron may be transversely divided into two or more rows of FOD detection areas, may also be longitudinally divided into two or more columns of FOD detection areas, and may also be transversely and longitudinally divided into two or more block-shaped FOD detection areas in a crossed manner.
Referring to fig. 2, as a specific implementation manner of the AI big data-based airport apron early-warning method provided in the embodiment of the present invention, the step of polling the picture signals of each FOD detection area based on the preset improved target detection algorithm early-warning model to obtain the early-warning signals includes:
s1: sequentially polling the picture signals of all FOD detection areas according to a preset time interval, and setting a foreground target Ni(ii) a Wherein i =1.
Optionally, in some embodiments, the picture signal extraction of each FOD detection area is sequentially achieved for each FOD detection area in a polling manner, and the picture signals of each FOD detection area are sequentially detected, so as to finally obtain the FOD detection result of each FOD detection area.
S2: acquiring background frame images of picture signals of all FOD detection areas, judging whether the background frame images are acquired successfully or not, if the background frame images are acquired successfully, continuing to execute the step S3, and if the background frame images are not acquired successfully, re-executing the step S1; the background frame image is an image of any time before the current time of the picture signal of each FOD detection area.
Optionally, in some embodiments, the background frame image may be obtained by performing a time domain averaging process on the picture signals of the respective FOD detection areas.
S3: acquiring a real-time frame image and an adjacent frame image of a picture signal of each FOD detection area, judging whether the real-time frame image and the adjacent frame image are successfully acquired, if so, continuing to execute the step S4, and if not, returning to execute the step S2; the real-time frame image is a frame image of the current moment of the picture signal of each FOD detection area, and the adjacent frame image is a frame image which is separated from the real-time frame image by a frame difference tau in the picture signal of each FOD detection area.
Optionally, in some embodiments, the background frame image and the real-time frame image are not the same frame image.
S4: the method comprises the steps of firstly carrying out background difference operation on a background frame image and a real-time frame image to obtain a background difference, carrying out adjacent inter-frame difference operation on the real-time frame image and an adjacent frame image to obtain an adjacent inter-frame difference, and then respectively carrying out threshold segmentation operation on the background difference and the adjacent inter-frame difference to obtain a first detection result and a second detection result.
Optionally, in some embodiments, the calculation method for performing the threshold segmentation operation on the background difference includes:
wherein Bin1k(x, y) is the first detection result, Dk(x, y) is the background difference, T1Is a first preset threshold.
Optionally, in some embodiments, the method for calculating the threshold segmentation operation on the adjacent frame-to-frame difference includes:
wherein Bin2k(x, y) is the second detection result, Sk(x, y) is the difference between adjacent frames, T2Is a second preset threshold.
S5: carrying out logical OR operation on the first detection result and the second detection result to obtain a third detection result, judging whether each FOD detection area has suspected FOD according to the third detection result, if yes, continuing to execute the step S6 and assigning the third detection result to the foreground target NiIf not, the step S2 is executed again.
Optionally, in some embodiments, the foreground target N may be subjected to before performing step S6iMorphological treatment is carried out.
S6: and judging whether each FOD detection area is a sensitive area, if so, continuing to execute the step S7, enabling i = i +1, if not, calibrating each FOD detection area as a sensitive area, giving a third detection result to the background frame image, and returning to execute the step S4.
S7: targeting foreground target N based on improved target optimization algorithmiAnd optimizing to obtain a foreground optimization target, and generating an early warning signal according to the foreground optimization target.
Optionally, as a specific implementation manner of the AI big data-based airplane apron early warning method provided in the embodiment of the present invention, the calculation method of the background difference is as follows:
Dk(x，y)＝|Pk(x，y)-Bk(x，y)|
wherein D isk(x, y) is the background difference, Pk(x, y) is the real-time frame image, Bk(x, y) is a background frame image.
Optionally, as a specific implementation manner of the AI big data-based method for early warning an airport apron provided in the embodiment of the present invention, the method for calculating the difference between adjacent frames is as follows:
Sk(x，y)＝|Pk(x，y)-Pk-τ(x，y)|
wherein S isk(x, y) is the adjacent inter-frame difference,Pk(x, y) is the real-time frame image, Pk-τAnd (x, y) are adjacent frame images.
Optionally, as a specific implementation manner of the AI big data-based airplane apron early warning method provided in the embodiment of the present invention, the calculation method of the third detection result is:
Bink(x，y)＝Bin 1k(x，y)||Bin 2k(x，y)
wherein Bin isk(x, y) is the third detection result, bin1k(x, y) is the first detection result, bin2k(x, y) is the second detection result.
Optionally, as a specific implementation manner of the AI big data-based airport apron early-warning method provided in the embodiment of the present invention, the foreground target N is subjected to an improved target optimization algorithmiThe method for obtaining the foreground optimization target by optimizing comprises the following steps:
wherein B (x, y) is the foreground optimization target, N1For the first detection of foreground objects, N2For the second detection of the foreground object, th is a foreground preset threshold.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides an AI big data-based airplane apron early warning method, device and terminal, wherein the method comprises the following steps: dividing the apron into two or more FOD detection areas; collecting video signals of all FOD detection areas; carrying out transcoding processing, playing processing, slicing processing and image cutting processing on the video signals of all FOD detection areas to obtain image signals of all FOD detection areas; polling picture signals of all FOD detection areas based on a preset improved target detection algorithm early warning model to obtain early warning signals; acquiring position information and picture information of FOD based on the early warning signal; and sending the position information and the picture information of the FOD to a signal receiver of the airplane. The invention can complete safety early warning of the apron in time, accurately and fully automatically, thereby effectively avoiding data missing report, data errors and data delay caused by manual perception.
Corresponding to the AI big data based apron early warning method in the above embodiment, fig. 3 is a structural block diagram of the AI big data based apron early warning device provided in the embodiment of the present invention. For convenience of explanation, only portions related to the embodiments of the present invention are shown. Referring to fig. 3, the AI big data-based apron warning apparatus 300 includes: the system comprises an area division module 301, a video acquisition module 302, a signal processing module 303, an FOD early warning module 304, an FOD information acquisition module 305 and an FOD information sending module 306.
The area dividing module 301 is configured to divide the apron into two or more FOD detection areas.
And the video acquisition module 302 is used for acquiring video signals of all FOD detection areas.
The signal processing module 303 is configured to perform transcoding processing, playing processing, slicing processing, and image cutting processing on the video signal in each FOD detection area to obtain an image signal in each FOD detection area.
The FOD early warning module 304 is configured to poll the picture signal of each FOD detection area based on a preset improved target detection algorithm early warning model to obtain an early warning signal.
The FOD information acquisition module 305 is configured to acquire position information and picture information of the FOD based on the early warning signal.
And the FOD information sending module 306 is used for sending the position information and the picture information of the FOD to a signal receiver of the airplane.
Optionally, the AI big data-based apron early warning device 300 and the fod early warning module 304 provided in the embodiment of the present invention execute the following steps:
s1: sequentially polling the picture signals of all FOD detection areas according to a preset time interval, and setting a foreground target Ni(ii) a Wherein i =1.
S2: acquiring background frame images of picture signals of all FOD detection areas, judging whether the background frame images are acquired successfully or not, if the background frame images are acquired successfully, continuing to execute the step S3, and if the background frame images are not acquired successfully, re-executing the step S1; the background frame image is a frame image at any time before the current time of the picture signal of each FOD detection area.
S3: acquiring a real-time frame image and an adjacent frame image of a picture signal of each FOD detection area, judging whether the real-time frame image and the adjacent frame image are acquired successfully or not, if the real-time frame image and the adjacent frame image are acquired successfully, continuing to execute the step S4, and if the real-time frame image or the adjacent frame image is not acquired successfully, returning to execute the step S2; the real-time frame image is a frame image of the current moment of the picture signal of each FOD detection area, and the adjacent frame image is a frame image which is separated from the real-time frame image by a frame difference tau in the picture signal of each FOD detection area.
S4: the method comprises the steps of firstly carrying out background difference operation on a background frame image and a real-time frame image to obtain a background difference, carrying out adjacent inter-frame difference operation on the real-time frame image and an adjacent frame image to obtain an adjacent inter-frame difference, and then respectively carrying out threshold segmentation operation on the background difference and the adjacent inter-frame difference to obtain a first detection result and a second detection result.
S5: carrying out logical OR operation on the first detection result and the second detection result to obtain a third detection result, judging whether each FOD detection area has suspected FOD according to the third detection result, if yes, continuing to execute the step S6 and assigning the third detection result to the foreground target NiIf not, the step S2 is executed again.
S6: and judging whether each FOD detection area is a sensitive area, if so, continuing to execute the step S7, enabling i = i +1, if not, calibrating each FOD detection area as a sensitive area, assigning a third detection result to the background frame image, and returning to execute the step S4.
S7: for foreground target N based on improved target optimization algorithmiAnd optimizing to obtain a foreground optimization target, and generating an early warning signal according to the foreground optimization target.
Fig. 4 is a schematic structural diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 4, the terminal device 4 of this embodiment includes: a processor 40, a memory 41 and a computer program 42 stored in the memory 41 and executable on the processor 40. The steps in each of the above embodiments of the AI-big-data-based apron warning method are implemented when the processor 40 executes the computer program 42.
Illustratively, the computer program 42 may be partitioned into one or more modules/units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. One or more of the modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 42 in the terminal device 4.
The terminal device 4 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 40, a memory 41. Those skilled in the art will appreciate that fig. 4 is merely an example of a terminal device 4, and does not constitute a limitation of terminal device 4, and may include more or fewer components than those shown, or some of the components may be combined, or different components, e.g., the terminal device may also include input-output devices, network access devices, buses, etc.
The Processor 40 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 41 may be an internal storage unit of the terminal device 4, such as a hard disk or a memory of the terminal device 4. The memory 41 may also be an external storage device of the terminal device 4, such as a plug-in hard disk provided on the terminal device 4, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like. Further, the memory 41 may also include both an internal storage unit of the terminal device 4 and an external storage device. The memory 41 is used for storing computer programs and other programs and data required by the terminal device. The memory 41 may also be used to temporarily store data that has been output or is to be output.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.
Claims (10)
1. An AII big data-based airplane apron early warning method is characterized by comprising the following steps:
dividing the apron into two or more FOD detection areas;
collecting video signals of all FOD detection areas;
carrying out transcoding processing, playing processing, slicing processing and image cutting processing on the video signals of all FOD detection areas to obtain image signals of all FOD detection areas;
polling picture signals of all FOD detection areas based on a preset improved target detection algorithm early warning model to obtain early warning signals;
acquiring the position information and the picture information of FOD based on the early warning signal;
and sending the position information and the picture information of the FOD to a signal receiver of the airplane.
2. The AI big data-based airport apron early warning method of claim 1, wherein the collecting process of the video signal of each FOD detection area comprises:
arranging two or more than two high-definition cameras at preset positions of all FOD detection areas;
and shooting the apron environment at a high speed by using a high-definition camera to obtain the video signal.
3. The AI big data-based airport apron early warning method of claim 1, wherein the step of polling the picture signals of each FOD detection area based on the pre-set advanced target detection algorithm early warning model to obtain the early warning signal comprises:
s1: sequentially polling the picture signals of each FOD detection area according to a preset time interval, and setting a foreground target Ni(ii) a Wherein i =1;
s2: acquiring background frame images of the picture signals of all FOD detection areas, judging whether the background frame images are acquired successfully or not, if the background frame images are acquired successfully, continuing to execute the step S3, and if the background frame images are not acquired successfully, re-executing the step S1; the background frame image is a frame image at any moment before the current moment of the picture signal of each FOD detection area;
s3: acquiring a real-time frame image and an adjacent frame image of the picture signal of each FOD detection area, judging whether the real-time frame image and the adjacent frame image are successfully acquired, if the real-time frame image and the adjacent frame image are successfully acquired, continuing to execute the step S4, and if the real-time frame image or the adjacent frame image is not successfully acquired, returning to execute the step S2; the real-time frame image is a frame image of the picture signal of each FOD detection area at the current moment, and the adjacent frame image is a frame image which is separated from the real-time frame image by a frame difference tau in the picture signal of each FOD detection area;
s4: firstly, performing background difference operation on a background frame image and a real-time frame image to obtain a background difference, performing adjacent inter-frame difference operation on the real-time frame image and an adjacent frame image to obtain an adjacent inter-frame difference, and then performing threshold segmentation operation on the background difference and the adjacent inter-frame difference respectively to obtain a first detection result and a second detection result;
s5: carrying out logical OR operation on the first detection result and the second detection result to obtain a third detection result, judging whether each FOD detection area has suspected FOD according to the third detection result, if yes, continuing to execute the step S6 and assigning the third detection result to the foreground target NiIf not, returning to execute the step S2;
s6: judging whether each FOD detection area is a sensitive area, if so, continuing to execute the step S7, enabling i = i +1, if not, calibrating each FOD detection area as a sensitive area, giving a third detection result to a background frame image, and returning to execute the step S4;
s7: targeting foreground target N based on improved target optimization algorithmiAnd optimizing to obtain a foreground optimization target, and generating an early warning signal according to the foreground optimization target.
4. The AI big data-based airport apron early warning method of claim 3, wherein the background difference is calculated by:
Dk(x，y)＝|Pk(x，y)-Bk(x，y)|
wherein D isk(x, y) is the background difference, Pk(x, y) is the real-time frame image, Bk(x, y) is a background frame image.
5. The AI big data-based airport apron early warning method of claim 3, wherein the adjacent frame-to-frame difference is calculated by:
Sk(x，y)＝|Pk(x，y)-Pk-τ(x，y)|
wherein S isk(x, y) is the difference between the adjacent frames, Pk(x, y) is the real-time frame image, Pk-τ(x, y) are adjacent frame images.
6. The AI-big-data-based airport apron early-warning method of claim 3, wherein the third detection result is calculated by:
Bink(x，y)＝Bin 1k(x，y)||Bin 2k(x，y)
wherein Bin isk(x, y) is the third detection result, bin1k(x, y) is the first detection result, bin2k(x, y) is the second detection result.
7. The AI-big-data-based airport apron early-warning method of claim 3, wherein said improved-target-optimization-based algorithm is to foreground target NiThe method for obtaining the foreground optimization target by optimizing comprises the following steps:
wherein B (x, y) is the foreground optimization objective, N1For the first detection of foreground objects, N2For the second detection of the foreground object, th is a foreground preset threshold.
8. An airport apron early warning device based on AI big data, characterized by includes:
the area dividing module is used for dividing the apron into two or more FOD detection areas;
the video acquisition module is used for acquiring video signals of all FOD detection areas;
the signal processing module is used for carrying out transcoding processing, playing processing, slicing processing and image cutting processing on the video signals of all the FOD detection areas to obtain image signals of all the FOD detection areas;
the FOD early warning module is used for polling picture signals of all FOD detection areas based on a preset improved target detection algorithm early warning model to obtain early warning signals;
the FOD information acquisition module is used for acquiring the position information and the picture information of the FOD based on the early warning signal;
and the FOD information sending module is used for sending the position information and the picture information of the FOD to a signal receiver of the airplane.
9. The AI big data-based apron early warning device of claim 8, wherein the FOD early warning module performs the steps comprising:
s1: sequentially polling the picture signals of each FOD detection area according to a preset time interval, and setting a foreground target Ni(ii) a Wherein i =1;
s2: acquiring background frame images of the picture signals of all FOD detection areas, judging whether the background frame images are acquired successfully or not, if the background frame images are acquired successfully, continuing to execute the step S3, and if the background frame images are not acquired successfully, re-executing the step S1; the background frame image is a frame image at any moment before the current moment of the picture signal of each FOD detection area;
s3: acquiring a real-time frame image and an adjacent frame image of the picture signal of each FOD detection area, judging whether the real-time frame image and the adjacent frame image are successfully acquired, if the real-time frame image and the adjacent frame image are successfully acquired, continuing to execute the step S4, and if the real-time frame image or the adjacent frame image is not successfully acquired, returning to execute the step S2; the real-time frame image is a frame image of the picture signal of each FOD detection area at the current moment, and the adjacent frame image is a frame image which is separated from the real-time frame image by a frame difference tau in the picture signal of each FOD detection area;
s4: firstly, performing background difference operation on a background frame image and a real-time frame image to obtain a background difference, performing adjacent inter-frame difference operation on the real-time frame image and an adjacent frame image to obtain an adjacent inter-frame difference, and then performing threshold segmentation operation on the background difference and the adjacent inter-frame difference respectively to obtain a first detection result and a second detection result;
s5: carrying out logical OR operation on the first detection result and the second detection result to obtain a third detection result, judging whether each FOD detection area is suspected to have the FOD or not according to the third detection result, if yes, continuing to execute the step S6 and assigning the third detection result to the foreground target NiIf not, returning to execute the step S2;
s6: judging whether each FOD detection area is a sensitive area, if so, continuing to execute the step S7, and enabling i = i +1, if not, calibrating each FOD detection area as a sensitive area, assigning a third detection result to a background frame image, and returning to execute the step S4;
s7: targeting foreground target N based on improved target optimization algorithmiAnd optimizing to obtain a foreground optimization target, and generating an early warning signal according to the foreground optimization target.
10. A terminal comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor when executing the computer program implements the steps of the AI-big-data-based apron pre-warning method according to any one of the preceding claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210728867.3A CN115273565A (en) | 2022-06-24 | 2022-06-24 | Airplane apron early warning method, device and terminal based on AI big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210728867.3A CN115273565A (en) | 2022-06-24 | 2022-06-24 | Airplane apron early warning method, device and terminal based on AI big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115273565A true CN115273565A (en) | 2022-11-01 |
Family
ID=83762183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210728867.3A Pending CN115273565A (en) | 2022-06-24 | 2022-06-24 | Airplane apron early warning method, device and terminal based on AI big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115273565A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473547A (en) * | 2013-09-23 | 2013-12-25 | 百年金海科技有限公司 | Vehicle target recognizing algorithm used for intelligent traffic detecting system |
| CN105611244A (en) * | 2015-12-23 | 2016-05-25 | 东南大学 | Method for detecting airport foreign object debris based on monitoring video of dome camera |
| CN105678803A (en) * | 2015-12-29 | 2016-06-15 | 南京理工大学 | Video monitoring target detection method based on W4 algorithm and frame difference |
| CN107452005A (en) * | 2017-08-10 | 2017-12-08 | 中国矿业大学(北京) | A kind of moving target detecting method of jointing edge frame difference and gauss hybrid models |
| CN111539273A (en) * | 2020-04-12 | 2020-08-14 | 南京理工大学 | Traffic video background modeling method and system |
| WO2021238325A1 (en) * | 2020-05-29 | 2021-12-02 | 华为技术有限公司 | Image processing method and apparatus |
-
2022
- 2022-06-24 CN CN202210728867.3A patent/CN115273565A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473547A (en) * | 2013-09-23 | 2013-12-25 | 百年金海科技有限公司 | Vehicle target recognizing algorithm used for intelligent traffic detecting system |
| CN105611244A (en) * | 2015-12-23 | 2016-05-25 | 东南大学 | Method for detecting airport foreign object debris based on monitoring video of dome camera |
| CN105678803A (en) * | 2015-12-29 | 2016-06-15 | 南京理工大学 | Video monitoring target detection method based on W4 algorithm and frame difference |
| CN107452005A (en) * | 2017-08-10 | 2017-12-08 | 中国矿业大学(北京) | A kind of moving target detecting method of jointing edge frame difference and gauss hybrid models |
| CN111539273A (en) * | 2020-04-12 | 2020-08-14 | 南京理工大学 | Traffic video background modeling method and system |
| WO2021238325A1 (en) * | 2020-05-29 | 2021-12-02 | 华为技术有限公司 | Image processing method and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2019104780A1 (en) | Laser radar point cloud data classification method, apparatus and device, and storage medium | |
| CN106851229B (en) | Security and protection intelligent decision method and system based on image recognition | |
| EP3940665A1 (en) | Detection method for traffic anomaly event, apparatus, program and medium | |
| CN113205037B (en) | Event detection method, event detection device, electronic equipment and readable storage medium | |
| CN111259957A (en) | Visibility monitoring and model training method, device, terminal and medium based on deep learning | |
| WO2020007119A1 (en) | Display screen peripheral circuit detection method and device, electronic device and storage medium | |
| CN111523362A (en) | Data analysis method and device based on electronic purse net and electronic equipment | |
| CN112785591B (en) | Method and device for detecting and segmenting rib fracture in CT image | |
| CN113177968A (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN113392681A (en) | Human body falling detection method and device and terminal equipment | |
| CN111079621A (en) | Method and device for detecting object, electronic equipment and storage medium | |
| CN113392794A (en) | Vehicle over-line identification method and device, electronic equipment and storage medium | |
| CN112084945A (en) | Active bird repelling method and device, computer equipment and storage medium | |
| CN112257604A (en) | Image detection method, image detection device, electronic equipment and storage medium | |
| CN109543533B (en) | Automatic identification method for airport operation personnel management | |
| CN109302580A (en) | A kind of aircraft disengaging berth automatic testing method based on video monitoring | |
| US11211070B2 (en) | Method, device and system for detecting working state of tower controller | |
| CN112542800A (en) | Method and system for identifying transmission line fault | |
| CN115273565A (en) | Airplane apron early warning method, device and terminal based on AI big data | |
| EP4303827A1 (en) | Automated change assessment of target objects during a dynamic isr mission | |
| CN112418089A (en) | Gesture recognition method and device and terminal | |
| US20210125013A1 (en) | Image recognition system and updating method thereof | |
| Yongli et al. | Analysis of Remote Tower System | |
| CN112101134A (en) | Object detection method and device, electronic device and storage medium | |
| CN114581890B (en) | Method and device for determining lane line, electronic equipment and storage medium |
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 |