CN108777776A - A kind of airfield runway foreign object identification image processing apparatus and method - Google Patents
A kind of airfield runway foreign object identification image processing apparatus and method Download PDFInfo
- Publication number
- CN108777776A CN108777776A CN201810416366.5A CN201810416366A CN108777776A CN 108777776 A CN108777776 A CN 108777776A CN 201810416366 A CN201810416366 A CN 201810416366A CN 108777776 A CN108777776 A CN 108777776A
- Authority
- CN
- China
- Prior art keywords
- image
- exotic
- fpga
- airfield runway
- high definition
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 8
- 230000003287 optical effect Effects 0.000 claims abstract description 4
- 238000005286 illumination Methods 0.000 claims description 5
- 238000003672 processing method Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 abstract description 3
- 238000011084 recovery Methods 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 3
- 241001156002 Anthonomus pomorum Species 0.000 description 2
- 239000003990 capacitor Substances 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 239000011800 void material Substances 0.000 description 2
- HPTJABJPZMULFH-UHFFFAOYSA-N 12-[(Cyclohexylcarbamoyl)amino]dodecanoic acid Chemical compound OC(=O)CCCCCCCCCCCNC(=O)NC1CCCCC1 HPTJABJPZMULFH-UHFFFAOYSA-N 0.000 description 1
- 238000012935 Averaging Methods 0.000 description 1
- 208000025274 Lightning injury Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 239000010426 asphalt Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000015271 coagulation Effects 0.000 description 1
- 238000005345 coagulation Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- -1 rubbery chip Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/74—Circuitry for compensating brightness variation in the scene by influencing the scene brightness using illuminating means
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
Abstract
A kind of airfield runway foreign object identification image processing apparatus of present invention offer and method, including high definition network head；The FPGA being connect with high definition network head；FPGA connection consoles.It obtains the exotic location information of airfield runway by radar, and the optical axis of the high definition network head being arranged outside airfield runway is turned to the region where exotic according to exotic location information；High definition network head carries out video acquisition to the region where exotic, and processing module calculates the gray average of the current frame image received, and according to gray average and judges whether to need to open laser lighting unit；Simultaneously according to the location information of exotic, the area identification of exotic on the image is gone out；Image is restored by atmospheric turbulance Image Restoration Algorithm.The present invention has the clear recovery for realizing degraded image under weak atmospheric turbulance in, improves airfield runway foreign object detection system adaptive capacity to environment.
Description
Technical field
The present invention relates to a kind of identification of airfield runway foreign object image processing apparatus is good and method, using GPU+FPGA skills
Art is completed under the conditions of different weather to external by a kind of exotic Target Recognition Algorithms being adapted to runway use environment
The detected with high accuracy of object, and under weak atmospheric turbulance realize degraded image clear recovery, improve airfield runway foreign object inspection
Examining system adaptive capacity to environment.
Background technology
Typical FOD targets have metal device（Screw, nut, washer, nail and fuse etc.）, machine tool, fly
Row article（The personal effects, pen, pencil and button etc.）, coagulation natural asphalt fragment, rubbery chip, plastic products and animals and plants
Deng.Current domestic airport runway inspection relies primarily on face patrolman completion, will close runway when road face is patrolled, this makes
The flight traffic capacity substantially reduces.
Invention content
A kind of airfield runway foreign object identification image processing apparatus of present invention offer and method, to solve prior art presence
The problem of.
The present invention uses following technical scheme：
A kind of airfield runway foreign object identification image processing apparatus, including：
Obtain the high definition network head of airfield runway image information；
The FPGA of the image of high definition network head is received by ethernet interface module；It is connected in distal end on the FPGA
Control platform；
Receive the CPU module of FPGA treated images.
There are the GPU 256 General Porcess Unit, the image that FPGA is sent to GPU to be divided at least nine macro block, each
Macro block, which is sent on different General Porcess Unit, carries out parallel processing.
It is connected with magnetically coupled circuit on the FPGA and the serial ports of the console of distal end connection.
A kind of airfield runway foreign object identification image processing method,
S1：The exotic location information of airfield runway is obtained by radar, and will be arranged on airport according to exotic location information
The optical axis of high definition network head outside runway turns to the approximate region where exotic；
S2：High definition network head to where exotic region carry out video acquisition, and by the video data of acquisition by with
Too net receiving module is transferred to subsequent processing module, after subsequent processing module receives video image, calculates working as reception
The average gray mean value of prior image frame, and by gray average compared with the gray threshold of setting, if gray average is more than setting
Threshold value then closes the laser lighting unit for light filling；If gray average is less than the threshold value of setting, swashing for light filling is opened
Light illuminating unit；
S3：According to the location information of exotic, the area identification of exotic on the image is gone out；
S4：Image is restored by atmospheric turbulance Image Restoration Algorithm.
In the S2, if gray average is less than the threshold value of setting, the laser lighting unit for light filling is opened, is then passed through
The console of processing module and distal end connects, and current weather weather information is obtained, using image irradiation backoff algorithm to image
Carry out illumination compensation.
The processing module includes FPFA and the GPU that is connect with FPGA, and FPGA is filtered to image and integrogram processing
Afterwards, by treated, image is sent to GPU.
Beneficial effects of the present invention：The present invention improves the abilities such as anti-lightning and surge using magnetic coupling isolation technology, can hold
By ± 15kV high pressures without damaging, to the AC-DC converter of major loop there is soft starting circuit to ensure rear class meter before power unit
Calculate unit stable power-supplying.Have the clear recovery for realizing degraded image under weak atmospheric turbulance in, improves airfield runway foreign object
Detecting system adaptive capacity to environment.
Description of the drawings
Fig. 1 is that the present invention relates to hardware block diagrams；
Fig. 2 is 422 partial circuit schematic diagram of " Anti-surging " serial ports of the present invention；
Fig. 3 is image processing algorithm flow chart of the present invention.
Specific implementation mode
Invention is further described in detail with reference to the accompanying drawings and detailed description.
The present invention provides a kind of airfield runway foreign object identification image processing apparatus, photoelectric detecting system can be enable in thunder
It hits, used under the complex environments such as atmospheric turbulance.
As shown in Figure 1, the inventive system comprises the high definition network heads for obtaining airfield runway image information；By with
Too network interface module receives the FPGA of the image of high definition network head, and FPGA is communicated by 422 serial ports with the console of distal end,
And pass through VGA channel transfer images；Treated that image is sent to CPU module by FPGA.
It is slow by reaching FPGA under Ethernet conversion module high speed after high definition network head samples exotic
In depositing, FPGA uses XILINX XC7K325T3FFG900I chips, considers the problems of that high speed signal clock is likely to be out of synchronization,
In this FPGA interface control circuit, clock high level of synchronization is ensured by using the dynamic phase correction based on FIFO.And to carry
High target signal to noise ratio SNR, noise reduction process is filtered using medium filtering, in conjunction with practical outfield characteristics of image, two dimension pattern plate W
It is chosen by 3 × 3 regions.[- 3-2-1 012 are pressed by image averaging gray scale dynamic adjust gain coefficient g in integrogram, g
3] it is chosen.GPU processing is handed over after the completion of pretreatment.
As shown in Fig. 2, be likely to occur the influences such as lightning stroke and surge for airport, the device of the invention and PERCOM peripheral communication connect
Mouth such as serial ports 422 using the magnetic coupling technology of ADM2682EBRIZ, plays the role of isolation, can bear ± 15kV high pressures without damaging
It is bad.And the present invention connects the electricity consumption power elements that external power supply is device by power module, power module is converted by AC-DC
Device connection electric device, AC-DC converter have soft starting circuit, and it is single that the outlets DC use a point solution capacitor array to ensure that rear class calculates
First stable power-supplying.Soft start can directly prevent surge phenomenon；Capacitor array can absorb voltage fluctuation and ensure that rear class calculates list
The stable power-supplying of member.
As shown in Figure 1, inventive algorithm uses the macro block processing method based on GPU, and each macro block is arranged into different
Independent General Porcess Unit executes up, and GPU uses NVIDEA TX2, has 256 independent General Porcess Unit, can be in CUDA
Possess 256 independently operated threads under environment, i.e. Cuda_Thread is realized using Linux programming platforms to NVIDEA TX2
Online programming, divide the image into 100 macro blocks, it is enterprising that each macro block is arranged to the different independent General Porcess Unit of GPU
Row parallel processing reduces image procossing delay.After GPU is to image procossing, degraded image is answered using atmospheric turbulance restoration algorithm
Console is output to by the VGA modules of FPGA after original.
The present invention also provides a kind of airfield runway foreign objects to identify image processing method, specifically includes following steps：
S1：The exotic location information of airfield runway is obtained by radar, and will be arranged on airport according to exotic location information
The optical axis of high definition network head outside runway turns to the region where exotic；
S2：High definition network head to where exotic region carry out video acquisition, and by the video data of acquisition by with
Too net receiving module is transferred to subsequent processing module, after subsequent processing module receives video image, calculates working as reception
The gray average of prior image frame, and by gray average compared with the gray threshold of setting, if gray average is more than the threshold value of setting,
Then close the laser lighting unit for light filling；If gray average is less than the threshold value of setting, opens and shone for the laser of light filling
Bright unit；Processing module includes FPFA and the GPU that is connect with FPGA.
S3：According to the location information of exotic, the area identification of exotic on the image is gone out；The region is that exotic exists
Approximate region on image needs to realize the size that setting needs the range marked.
S4：Image restoration is carried out by atmospheric turbulance restoration algorithm.By obtaining the edge gradient of continuous multiple frames image, from
It is dynamic to judge atmospheric turbulence intensity, if weak turbulent flow, then use existing algorithm for image enhancement, otherwise startup Brenner algorithms into
Line definition judges to obtain most clear image, clearly be restored to image by wavelet transformation realization on this basis.
In S2, if gray average is less than the threshold value of setting, the laser lighting unit for light filling is opened, processing is then passed through
The console of module and distal end connects, and obtains current weather weather information, is carried out to image using image irradiation backoff algorithm
Illumination compensation.
The specific implementation process of above-mentioned algorithm is given below：
Step1：Camera is called to carry out video acquisition using VideoCapture classes.
Step2：A Mat variable is defined, the image for storing each frame is then read in present frame to Mat variables.
Present frame is only needed to read in mat variables, using this frame as the subsequent image procossing of original image progress, after final display processing
Picture.
Step3：Read present image mean intensity LaserPowerOnThreshold（）, image histogram depicts figure
The pixel number of each brightness value, indicates the distribution of brightness in image as in.Color ash is carried out to the image of present frame in Step 2
Degree statistics, calculates the gray-scale intensity mean value of entire image, is compared with the threshold value of setting.If gray scale mean intensity is more than setting
Threshold value, then send laser active illumination enable shutdown signal（It is judged to sunshine daytime, being not required to laser lighting）, carry out Gauss
It is filtered.If gray scale mean intensity is less than the threshold value of setting, sends laser active illumination and enable opening signal（Night or day
Gas is gloomy, and laser lighting is needed to assist）, carry out step Step 4.
Step4：Same day weather information is read, adaptable image compensation algorithm is automatically switched.
Step5：Parsing target is located at image approximate location scope.The control information of composite focal distance and turntable, radar etc., soon
The image approximate region Void ObjectDomain that speed parsing exotic is located substantially at（float f,float sigma）；
Step6：After determining the approximate location scope of target in the picture, nearby region, Void are drawn around its central vision
DrawDomain (Mat img, int nPixel, k), target area is signed on image img, and image includes n pixel, superfluous
Remaining coefficient k=1.2（The value is engineering experience value）.
Step 8：At this time by the frame Image edge gradient characteristic automatic decision atmospheric turbulence intensities of continuous n=10, if weak
Turbulent flow then uses precision Image Processing Algorithm, otherwise starts Brenner algorithms and carries out definition judgment acquisition most clear image,
Image is clearly restored by small transformation realization on this basis.
What has been described above is only a preferred embodiment of the present invention, it is noted that for those skilled in the art,
Under the premise of not departing from general idea of the present invention, several changes and improvements can also be made, these should also be considered as the present invention's
Protection domain.
Claims (6)
1. a kind of airfield runway foreign object identifies image processing apparatus, which is characterized in that including：
Obtain the high definition network head of airfield runway image information；
The FPGA of the image of high definition network head is received by ethernet interface module；It is connected in distal end on the FPGA
Control platform；
Receive the CPU module of FPGA treated images.
2. the apparatus according to claim 1, it is characterised in that：
There are the GPU 256 General Porcess Unit, the image that FPGA is sent to GPU to be divided at least nine macro block, each macro block
It is sent on different General Porcess Unit and carries out parallel processing.
3. the apparatus according to claim 1, it is characterised in that：
It is connected with magnetically coupled circuit on the FPGA and the serial ports of the console of distal end connection.
4. a kind of airfield runway foreign object identifies image processing method, it is characterised in that：
S1：The exotic location information of airfield runway is obtained by radar, and will be arranged on airport according to exotic location information
The optical axis of high definition network head outside runway turns to the approximate region where exotic；
S2：High definition network head to where exotic region carry out video acquisition, and by the video data of acquisition by with
Too net receiving module is transferred to subsequent processing module, after subsequent processing module receives video image, calculates working as reception
The average gray mean value of prior image frame, and by gray average compared with the gray threshold of setting, if gray average is more than setting
Threshold value then closes the laser lighting unit for light filling；If gray average is less than the threshold value of setting, swashing for light filling is opened
Light illuminating unit；
S3：According to the location information of exotic, the area identification of exotic on the image is gone out；
S4：Image is restored by atmospheric turbulance Image Restoration Algorithm.
5. according to the method described in claim 4, it is characterized in that：
In the S2, if gray average is less than the threshold value of setting, the laser lighting unit for light filling is opened, processing is then passed through
The console of module and distal end connects, and obtains current weather weather information, is carried out to image using image irradiation backoff algorithm
Illumination compensation.
6. according to the method described in claim 4, it is characterized in that：
The processing module includes FPFA and the GPU that is connect with FPGA, FPGA to image be filtered and integrogram processing after, will
Treated, and image is sent to GPU.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810416366.5A CN108777776A (en) | 2018-05-03 | 2018-05-03 | A kind of airfield runway foreign object identification image processing apparatus and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810416366.5A CN108777776A (en) | 2018-05-03 | 2018-05-03 | A kind of airfield runway foreign object identification image processing apparatus and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108777776A true CN108777776A (en) | 2018-11-09 |
Family
ID=64026970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810416366.5A Pending CN108777776A (en) | 2018-05-03 | 2018-05-03 | A kind of airfield runway foreign object identification image processing apparatus and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108777776A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113009507A (en) * | 2021-03-07 | 2021-06-22 | 航泰众联(北京)科技有限公司 | Distributed airport runway FOD monitoring system and method based on laser radar |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101852869A (en) * | 2010-05-18 | 2010-10-06 | 中国民航大学 | Airfield runway foreign object detection system |
| CN102186010A (en) * | 2011-04-20 | 2011-09-14 | 长春奥普光电技术股份有限公司 | Device for scanning airport pavement foreign object |
| CN104112153A (en) * | 2014-07-17 | 2014-10-22 | 上海透云物联网科技有限公司 | Method for bar code recognition based on mobile terminal and system thereof |
| CN104302051A (en) * | 2014-10-08 | 2015-01-21 | 山东新帅克能源科技有限公司 | Solar street lamp control system and method based on time, illuminance and visibility |
| CN204116868U (en) * | 2014-09-10 | 2015-01-21 | 昆明高驰科技有限公司 | A kind of multichannel energy consumption data acquisition device |
| CN106018409A (en) * | 2016-06-29 | 2016-10-12 | 哈尔滨工程大学 | Airfield runway foreign matter and crack recognizing system and detecting and recognizing method thereof |
-
2018
- 2018-05-03 CN CN201810416366.5A patent/CN108777776A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101852869A (en) * | 2010-05-18 | 2010-10-06 | 中国民航大学 | Airfield runway foreign object detection system |
| CN102186010A (en) * | 2011-04-20 | 2011-09-14 | 长春奥普光电技术股份有限公司 | Device for scanning airport pavement foreign object |
| CN104112153A (en) * | 2014-07-17 | 2014-10-22 | 上海透云物联网科技有限公司 | Method for bar code recognition based on mobile terminal and system thereof |
| CN204116868U (en) * | 2014-09-10 | 2015-01-21 | 昆明高驰科技有限公司 | A kind of multichannel energy consumption data acquisition device |
| CN104302051A (en) * | 2014-10-08 | 2015-01-21 | 山东新帅克能源科技有限公司 | Solar street lamp control system and method based on time, illuminance and visibility |
| CN106018409A (en) * | 2016-06-29 | 2016-10-12 | 哈尔滨工程大学 | Airfield runway foreign matter and crack recognizing system and detecting and recognizing method thereof |
Non-Patent Citations (3)
| Title |
|---|
| 刘镪等: "空间目标幸运成像技术的实验研究", 《激光与光电子学进展》 * |
| 张立峰: "特殊天气下图像复原", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 赵芳斌: "基于FPGA和GPU的外辐射源雷达信号处理平台的研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113009507A (en) * | 2021-03-07 | 2021-06-22 | 航泰众联(北京)科技有限公司 | Distributed airport runway FOD monitoring system and method based on laser radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020199538A1 (en) | Bridge key component disease early-warning system and method based on image monitoring data | |
| CN101344988B (en) | Image acquisition and processing equipment and method, vehicle monitoring and recording system | |
| CN101739827B (en) | Vehicle detecting and tracking method and device | |
| CN104994311B (en) | Electronic police device adjust automatically light compensation method | |
| CN202676156U (en) | Electric transmission line condition monitoring system based on target image identification and benchmark measurement | |
| CN104302051B (en) | Control system of solar energy street lamp based on time, illumination and visibility and method | |
| CN106503707B (en) | Licence plate recognition method and device under a kind of infrared lighting condition | |
| CN101388146B (en) | Image acquisition and treatment apparatus and method, and vehicle monitoring and recording system | |
| CN203747909U (en) | EMCCD camera imaging and data transmission system | |
| CN107274836A (en) | AMOLED display panels and display device with temperature compensation function | |
| CN108093175B (en) | A kind of adaptive defogging method of real-time high-definition video and device | |
| CN108777776A (en) | A kind of airfield runway foreign object identification image processing apparatus and method | |
| CN103438822B (en) | Accumulated snow depth monitoring system based on controllable light source | |
| CN105161053A (en) | Anti-streaking row-scanning control chip and anti-streaking LED display circuit | |
| CN201247528Y (en) | Apparatus for obtaining and processing image | |
| CN106910347A (en) | Electronic police Intelligent supplemental lighting system | |
| CN102779412B (en) | Integrated video traffic information detection method and system | |
| CN102968177A (en) | Gesture sensing method and device | |
| CN105827982B (en) | Triggering method, device and the controller for triggering method of LED light supplement lamp | |
| CN108090910A (en) | It is a kind of that tomato plant image segmentation algorithm outside the night room of PCNN models is simplified based on comentropy gradient | |
| CN101060592A (en) | Same vision field multi-spectral video stream acquiring device and method | |
| CN106900105B (en) | The intelligent analysis system being arranged on solar street light | |
| CN112379362B (en) | Event self-adaptive acquisition equipment and method based on multi-source data fusion | |
| CN105303569B (en) | A kind of object detection method and device of automatic switchover scene mode | |
| CN205622764U (en) | Video monitoring equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181109 |
|
| RJ01 | Rejection of invention patent application after publication |