CN107507198A - Aircraft brake disc detects and method for tracing - Google Patents

Aircraft brake disc detects and method for tracing Download PDF

Info

Publication number
CN107507198A
CN107507198A CN201710724698.5A CN201710724698A CN107507198A CN 107507198 A CN107507198 A CN 107507198A CN 201710724698 A CN201710724698 A CN 201710724698A CN 107507198 A CN107507198 A CN 107507198A
Authority
CN
China
Prior art keywords
aircraft
region
result
stage
brake disc
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.)
Granted
Application number
CN201710724698.5A
Other languages
Chinese (zh)
Other versions
CN107507198B (en
Inventor
隋运峰
黄忠涛
吴宏刚
程志
赵士瑄
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Second Research Institute of CAAC
Original Assignee
Second Research Institute of CAAC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Second Research Institute of CAAC filed Critical Second Research Institute of CAAC
Priority to CN201710724698.5A priority Critical patent/CN107507198B/en
Publication of CN107507198A publication Critical patent/CN107507198A/en
Application granted granted Critical
Publication of CN107507198B publication Critical patent/CN107507198B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]

Abstract

The invention belongs to target tracking technical field, there is provided a kind of aircraft brake disc detection and method for tracing.This method includes original image inputting convolutional neural networks, generate convolution characteristic pattern, original image is divided into using image partition method by different regions, to the convolution characteristic pattern in each extracted region region being partitioned into, and be standardized, provincial characteristics figure corresponding to each region is obtained, examines the provincial characteristics figure in each region, the region according to corresponding to the characteristic pattern for being determined as aircraft, calculate and export aircraft region.Aircraft brake disc detection of the present invention and method for tracing, it is possible to increase the reliability and real-time of target acquisition and tracking during takeoff and landing, avoid similar target jamming, improve algorithm performs efficiency.

Description

Aircraft brake disc detects and method for tracing
Technical field
The present invention relates to target tracking technical field, and in particular to a kind of aircraft brake disc detection and method for tracing.
Background technology
The landing of aircraft with to take off be that two stages of accident rate highest are compared in flight course.To flying during landing Machine carries out video tracking shooting automatically, is a direction of current airport security surveillance technology development.
In the prior art, it is by automatically controlling turntable, autozoom telephoto lens and image enhancement technique, with biography mostly The working method of system is compared, and the vision signal of captured in real-time being capable of the apparent state for more stably observing aircraft.This is also certainly The data basis for the accident potential such as dynamic survey mission posture is abnormal, undercarriage is abnormal.Automatically the whole landing process recorded regards Frequency information is also the Primary Reference foundation of problem investigation afterwards.
When takeoff and landing process automatic tracing monitoring system is run, termination aircraft region to be taken off is gone in alignment first, or Person's landing preceding low latitude navigation channel region, starts to monitor.If object enters monitor area, after judgement is Aircraft Targets, locking Target, start tracking shooting.In tracing process, aircraft is kept in picture center, root according to the position adjust automatically turntable of aircraft Keep aircraft imaging size suitable apart from automatic focus adjustable according to aircraft.Descent is tracked after aircraft clears the runway and tied Beam, take-off process, which is tracked after aircraft leaves monitoring scope, to be terminated.
From system operating mode as can be seen that takeoff and landing tracking and common target tracking problem make a big difference. First, capture apparatus keeps rotating in whole process, causes the background in video in high-speed motion.Secondly as shooting process Target lock-on, aircraft is in picture central area erratic motion, and there is also change to a certain degree for imaging size.Finally, due to see The lasting change of angle and distance is examined, there is also very big change for aircraft imaging.In addition to these differences, takeoff and landing tracking is also Face some technological challenges, for example aircraft background at low clearance area is more complicated, there is other fly during activity in runway zone Machine target jamming.These differences and challenge cause to be unsuitable for based on conventional methods such as Kalman filter motion tracking, light stream trackings Takeoff and landing are followed the trail of.
The reliability and real-time of target acquisition and tracking during takeoff and landing are how improved, avoids similar target dry Disturb, the problem of being those skilled in the art's urgent need to resolve.
The content of the invention
For in the prior art the defects of, the invention provides a kind of aircraft brake disc detection and method for tracing, it is possible to increase The reliability and real-time of target acquisition and tracking, avoid similar target jamming during takeoff and landing.
In a first aspect, the present invention provides a kind of aircraft brake disc detection method, this method includes：
Original image is inputted into convolutional neural networks, generates convolution characteristic pattern, convolution characteristic pattern includes the N-dimensional of each pixel Characteristic vector；
Original image is divided into using image partition method by different regions；
To the convolution characteristic pattern in each extracted region region being partitioned into, and it is standardized, obtains each area Provincial characteristics figure corresponding to domain；
The provincial characteristics figure in each region is examined, the region according to corresponding to the characteristic pattern for being determined as aircraft, calculates and exports Aircraft region.
Further, original image is inputted into convolutional neural networks, generates convolution characteristic pattern, specifically include：
Convolution operation is carried out to original image using the convolution kernel of predefined parameter, generates convolved image；
Convolution operation is carried out to convolved image using the convolution kernel of predefined parameter, generates convolution characteristic pattern, convolutional Neural net Network includes the convolution kernel of predefined parameter.
Further, original image is divided into using image partition method by different regions, specifically included：
Calculate the aberration in adjacent subarea domain in original image；
By position is adjacent and aberration is no more than the subregion of default color threshold and merged, the field color after merging is two Sub-regions press pixel quantity weighted average, travel through all subregions, until all adjacent subarea domains aberration be all higher than it is pre- If color threshold, wherein, aberration be three channel strength difference absolute values of RGB sum；
Statistics is distributed in the most value on horizontal, ordinate per sub-regions, generates rectangular shaped rim, as current segmentation result, Exported；
Default color threshold is adjusted, repetition is compared, until the region quantity in image is one, and is merged identical Output result, then obtain the final result of image segmentation.
Further, the provincial characteristics figure in each region is examined, is specifically included：
Using PCA algorithms, dimensionality reduction is carried out to the provincial characteristics figure in each region, obtains characteristic vector, each characteristic vector The position of middle characteristic value determines according to the separating capacity power of this feature value；
Take a characteristic value in characteristic vector successively from front to back, and tested according to the classification thresholds of the dimension：If The test fails, then judges the region without aircraft；
If for all characteristic values by examining, it is aircraft to judge the region in characteristic vector.
As shown from the above technical solution, the aircraft brake disc detection method that the present embodiment provides, is given birth to by convolutional neural networks Into convolution characteristic pattern, relative to traditional feature describing mode so that this method has more preferable separating capacity, excludes same classification Mark interference, it is favorably improved the accuracy of target acquisition.Meanwhile this method is divided original image using image partition method Cut, relative to traditional sliding window way of search, search time is greatly shortened.Also, this method is entered to each provincial characteristics figure Performing check, and then judge that the region whether there is aircraft, it is big etc. dry to effectively prevent background complexity, movement velocity, object variations Disturb influence of the factor to target acquisition.
Therefore, the present embodiment aircraft brake disc detection method, it is possible to increase the reliability of target acquisition during takeoff and landing And real-time, similar target jamming is avoided, improves algorithm performs efficiency.
Second aspect, the present invention provide a kind of aircraft brake disc method for tracing, and this method includes：
Obtain the experience weight of mission phase；
According to the experience weight of mission phase, the result of detection of the detector in a preceding adjacent flight stage is calculated respectively Likelihood probability, the three-dimensional space position in result of detection are the positions according to the region conversion for being determined as aircraft in advance；
According to the result of calculation of likelihood probability, mission phase residing for current aircraft is judged, and switch the work of corresponding detector Make state, each detector corresponds with each mission phase.
Further, according to the experience weight of mission phase, respectively to the spy of the detector in a preceding adjacent flight stage Survey result and calculate likelihood probability, specifically include：
According to the experience weight of mission phase, using likelihood probability formula, to a preceding SiThe detection of the detector in stage As a result calculated：
b(Oi(α))=ti_iexp(-|A'-α|)
Wherein, OiRepresent SiThe result of detection of the detector in stage, α represent the center of search coverage, ti_iExpression experience S is kept in weightiThe probability of stage condition, A' represent the anticipation position of current aircraft；
According to the experience weight of mission phase, using likelihood probability formula, to a preceding Si+1The detection of the detector in stage As a result calculated：
b(Oi+1(α))=ti_i+1exp(-|A'-α|)
Wherein, Oi+1Represent Si+1The result of detection of the detector in stage, α represent the center of search coverage, ti_i+1Represent From S in experience weightiStage condition transfer is Si+1The probability of stage condition, A' represent the anticipation position of current aircraft；
According to the result of calculation of likelihood probability, judge mission phase residing for current aircraft, specifically include：
Determine the maximum probing result of likelihood probability；
By the stage residing for the maximum result of detection of likelihood probability, as the stage residing for current aircraft.
Further, the experience weight of mission phase is obtained, is specifically included：
Gather the sample data of takeoff and landing process；
Statistics calculating is carried out to sample data, obtains the experience weight of mission phase.
As shown from the above technical solution, the aircraft brake disc method for tracing that the present embodiment provides, can be according to the warp of pre-acquiring Weight is tested, the likelihood probability of the result of detection of an adjacent phases before calculating, the mission phase residing for aircraft is determined, in order to cut The working condition of Current detector is changed, without using all detector concurrent workings, a detector is only used as far as possible, improves algorithm Operational efficiency.
Therefore, the present embodiment aircraft brake disc method for tracing, it is possible to increase the reliability of target tracking during takeoff and landing And real-time, improve algorithm performs efficiency.
Brief description of the drawings
, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical scheme of the prior art The required accompanying drawing used is briefly described in embodiment or description of the prior art.In all of the figs, similar element Or part is typically identified by similar reference.In accompanying drawing, each element or part might not be drawn according to the ratio of reality.
Fig. 1 shows a kind of method flow diagram of aircraft brake disc detection method provided by the present invention；
Fig. 2 shows a kind of method flow diagram of aircraft brake disc method for tracing provided by the present invention；
Fig. 3 shows the relation schematic diagram of three dimensional space coordinate system provided by the present invention；
Fig. 4 shows the state transition diagram in stage residing for a kind of aircraft provided by the present invention.
Embodiment
The embodiment of technical solution of the present invention is described in detail below in conjunction with accompanying drawing.Following examples are only used for Clearly illustrate technical scheme, therefore be intended only as example, and the protection of the present invention can not be limited with this Scope.
It should be noted that unless otherwise indicated, technical term or scientific terminology used in this application should be this hair The ordinary meaning that bright one of ordinary skill in the art are understood.
In a first aspect, a kind of aircraft brake disc detection method that the embodiment of the present invention is provided, with reference to Fig. 1, this method includes：
Step S11, original image is inputted into convolutional neural networks, generate convolution characteristic pattern, convolution characteristic pattern includes each The N-dimensional characteristic vector of pixel, the characteristic vector of one 64 dimension is such as produced in each pixel.Wherein, the parameter of convolutional neural networks Be as mass data training obtained by, it is consistent to all mission phases.
Step S12, according to the continuity of picture material, original image is divided into using image partition method by different areas Domain.
Step S13, to the convolution characteristic pattern in each extracted region region being partitioned into, and it is standardized, obtains Take provincial characteristics figure corresponding to each region.For example, feature extraction is carried out to each region after segmentation, the characteristic pattern of extraction Size is (W, H, 64), and this feature figure then is zoomed into standard size (30,10,64).
Step S14, the provincial characteristics figure in each region is examined, the region according to corresponding to the characteristic pattern for being determined as aircraft, meter Calculate and export aircraft region.
As shown from the above technical solution, the aircraft brake disc detection method that the present embodiment provides, is given birth to by convolutional neural networks Into convolution characteristic pattern, relative to traditional feature describing mode so that this method has more preferable separating capacity, excludes same classification Mark interference, it is favorably improved the accuracy of target acquisition.Meanwhile this method is divided original image using image partition method Cut, relative to traditional sliding window way of search, search time is greatly shortened.Also, this method is entered to each provincial characteristics figure Performing check, and then judge that the region whether there is aircraft, it is big etc. dry to effectively prevent background complexity, movement velocity, object variations Disturb influence of the factor to target acquisition.
Therefore, the present embodiment aircraft brake disc detection method, it is possible to increase the reliability of target acquisition during takeoff and landing And real-time, similar target jamming is avoided, improves algorithm performs efficiency.
In order to further improve the accuracy of the present embodiment aircraft brake disc detection method, specifically, in terms of convolutional calculation, Original image is inputted into convolutional neural networks, when generating convolution characteristic pattern, the specific implementation process of this method is as follows：
Convolution operation is carried out to original image using the convolution kernel of predefined parameter, generates convolved image.
Convolution operation is carried out to convolved image using the convolution kernel of predefined parameter, generates convolution characteristic pattern, convolutional Neural net Network includes the convolution kernel of predefined parameter.
For example, the present embodiment aircraft brake disc detection method is handled using convolutional neural networks model, convolutional Neural net Network haves three layers altogether, and each layer parameter and calculating process are as follows：
First layer carries out convolution operation by the convolution kernel of 47 × 7 to original image, generates 4 convolved images.
The second layer carries out convolution operation to 4 convolved images that first layer exports respectively by the convolution kernel of 4 13 × 13, Generate 16 convolved images.
Third layer carries out convolution behaviour to 16 convolved images that the second layer exports respectively by the convolution kernel of 4 25 × 25 Make, 64 convolved images are generated, as convolution characteristic pattern.
Pass through above-mentioned convolution operation, you can to the characteristic vector of the dimension of each pixel generation 64.Also, in convolutional neural networks The parameter of 12 convolution kernels be as mass data training obtained by, it is consistent to all mission phases.
Here, relative to traditional character description method, the present embodiment aircraft brake disc detection method uses convolutional Neural net Network is handled original image, can realize more preferable separating capacity, reduces the interference of noise or complex background.
Specifically, in terms of image dividing processing, original image is divided into using image partition method by different regions When, the specific implementation process of this method is as follows：
Calculate the aberration in adjacent subarea domain in original image.Here, each pixel in original image is considered as a son Region, the color per sub-regions are the color of the pixel.
When initial, color threshold T=12 can be set.
By the subregion merging that position is adjacent and aberration is no more than default color threshold T, the field color after merging is Two sub-regions press the weighted average of pixel quantity, travel through all subregions, until the aberration in all adjacent subarea domains is all higher than Default color threshold, wherein, aberration is the sum of three channel strength difference absolute values of RGB.
Statistics is distributed in the most value on horizontal, ordinate per sub-regions, the minimum horizontal seat of the subregion after merging such as statistics Mark, minimum ordinate, maximum abscissa and maximum ordinate, rectangular shaped rim is generated, as current segmentation result, is exported.
Default color threshold is adjusted, color threshold is such as multiplied by 2, repetition is compared, until the region quantity in image is One, and merge identical output result, then it can obtain the final result of image segmentation.
Here, relative to traditional sliding window method, the present embodiment aircraft brake disc detection method is according between adjacent pixel Aberration merges processing, determines cut zone, increases substantially image segmentation efficiency, shortens image sliced time.Also, this Embodiment aircraft brake disc detection method can be split by the way of successive ignition to original image, and will be identical Region, as the region finally split, the degree of accuracy of image segmentation is favorably improved, to judge that region is provided with residing for aircraft The Informational support of effect.
Meanwhile when calculating the aberration in adjacent subarea domain in original image, the specific implementation process of this method is as follows：Count respectively Calculate intensity difference of the adjacent subarea domain on three passages in original image.
Intensity difference on three passages is taken absolute value, and summed up.Such as to the intensity on three passages of red, yellow, and green Difference takes absolute value.
Aberration of the numerical value with after as adjacent subarea domain will be added.
Here, the present embodiment aircraft brake disc detection method can determine aberration according to the intensity difference on different passages, improve The degree of accuracy of Colorimetry.
Specifically, in terms of flight range judgement, when examining the provincial characteristics figure in each region, the specific implementation of this method Process is as follows：
Using PCA algorithms, dimensionality reduction is carried out to the provincial characteristics figure in each region, 10 dimensions is such as reduced to, obtains feature Vector, the position of characteristic value determines according to the separating capacity of this feature value is strong and weak in each characteristic vector.
Take a characteristic value in characteristic vector successively from front to back, and tested according to the classification thresholds of the dimension：If The test fails, then judges the region without aircraft.
If for all characteristic values by examining, it is aircraft to judge the region in characteristic vector.
Here, plane prevention algorithm is formed by the cascade of several weak typing algorithms.In i-stage classification, dimensionality reduction is extracted I-th of dimension of characteristic pattern, by being contrasted with the classification thresholds of this grade, non-aircraft target is excluded step by step.
The affiliated image-region of characteristic pattern that every level testing is passed through, it is determined as the region of aircraft.Pass through the classification of 10 cascades After exclusion, still it is retained, then it is assumed that the region is aircraft.
Wherein, every grade of classification thresholds in the dimensionality reduction transition matrix and tandem type grader of PCA algorithms, are by each What the positive and negative aircraft sample training of mission phase obtained.Also, the more preferable characteristic of division of elimination ability, that is, separating capacity is more Feature caused by good subregion, is more preferably used in cascade process.So, most of non-aircraft target, which can pass through, compares What few classification is excluded.
Here, the present embodiment aircraft brake disc detection method, substitutes neural-network classification method using tandem type grader, carries The high execution speed of algorithm, improves the degree of accuracy for judging region residing for aircraft.
Second aspect, a kind of aircraft brake disc method for tracing that the embodiment of the present invention is provided, with reference to Fig. 2, this method includes：
Step S21, obtain the experience weight of mission phase.
Step S22, according to the experience weight of mission phase, respectively to the detection of the detector in a preceding adjacent flight stage As a result likelihood probability is calculated, the three-dimensional space position in result of detection is the position according to the region conversion for being determined as aircraft in advance Put.Here, region residing for the aircraft that is judged in above-mentioned aircraft brake disc detection method can be changed, to determine detection knot Coordinate in fruit.
Step S23, according to the result of calculation of likelihood probability, judge mission phase residing for current aircraft, and switch corresponding visit The working condition of device is surveyed, each detector corresponds with each mission phase.
Here, the takeoff and landing of aircraft has totally been divided into five stages in advance, it is respectively：Glide, put down and float, be sliding Run, be liftoff, rising, so that the performance for supporting total algorithm can be reached.One aircraft detector of each stage-training.Each detection The course of work of device is aircraft brake disc method for tracing.Five aircraft detectors are only in the parameter Shang You areas of tandem type grader Not, other parts are consistent.
In landing tracing process, five aircraft detectors are used alternatingly, and specific alternately rule is as follows：
First, descent starts since first stage detector；
Second, take-off process starts since phase III detector；
3rd, it can only keep using current detector, or switch to the detector of next stage, it is impossible to rank of jumping Section, can not switch forward.Here, this method can calculate the likelihood probability of the result of detection of adjacent phases detector, it is determined that Stage residing for current aircraft, and switch the detector of respective stage.
Wherein, the three-dimensional space position in result of detection is according to the position for the region conversion for being determined as aircraft in advance, tool Body implementation process is as follows：
Using runway centerline as X-axis, vertical direction is Y-axis, and vertical runway centerline direction is Z axis in runway plane, is run Road starting point is origin, establishes three-dimensional coordinate system, as shown in Figure 3.Surveillance camera is arranged on runway side, is designated as P (pX, pY,pZ) point, aircraft location is designated as A points, and the unit vector that A points are pointed to from P points is designated as V (vX,vY,vZ)。
After video camera installation is fixed, measurement obtains P point coordinates.Video camera obtains current be horizontally directed in real time in operation Angle and pitching orientation angle.After detecting aircraft in the picture, the pixel of aircraft region center and picture centre is calculated Deviation.Misalignment angle is calculated with reference to CCD component pixels size and focal length value, using misalignment angle to being horizontally directed to angle and bowing Face upward orientation angle to be modified, V direction is calculated by the goniometer of amendment.
During normal takeoff and landing, flight path is in X/Y plane.Therefore, in the direction of known P point coordinates and V In the case of, by equation below, the intersection point of calculating V extended lines and X/Y plane, it is believed that be the space that aircraft is currently located Position A.
Whether move in X/Y plane, can be judged roughly by the size that aircraft is imaged for aircraft.Positive reason Under condition, distance of the P points along V directions to X/Y plane can be calculated directly.With reference to CCD component pixels size and focal length value, Yi Jiyi The aircraft size known, expected imaging size can be calculated.If imaging area is significantly greater than or is significantly less than desired value, Then think that aircraft deviates X/Y plane.
As shown from the above technical solution, the aircraft brake disc method for tracing that the present embodiment provides, can be according to the warp of pre-acquiring Weight is tested, the likelihood probability of the result of detection of an adjacent phases before calculating, the mission phase residing for aircraft is determined, in order to cut The working condition of Current detector is changed, without using all detector concurrent workings, a detector is only used as far as possible, improves algorithm Operational efficiency.
Therefore, the present embodiment aircraft brake disc method for tracing, it is possible to increase the reliability of target tracking during takeoff and landing And real-time, improve algorithm performs efficiency.
Also, according to the experience weight of mission phase, respectively to the detection knot of the detector in a preceding adjacent flight stage When fruit calculates likelihood probability, the specific implementation process of this method is：
According to the experience weight of mission phase, using likelihood probability formula, to a preceding SiThe detection of the detector in stage As a result calculated：
b(Oi(α))=ti_iexp(-|A'-α|)
Wherein, OiRepresent SiThe result of detection of the detector in stage, α represent the center of search coverage, ti_iExpression experience S is kept in weightiThe probability of stage condition, A' represent the anticipation position of current aircraft.
According to the experience weight of mission phase, using likelihood probability formula, to a preceding Si+1The detection of the detector in stage As a result calculated：
b(Oi+1(α))=ti_i+1exp(-|A'-α|)
Wherein, Oi+1Represent Si+1The result of detection of the detector in stage, α represent the center of search coverage, ti_i+1Represent From S in experience weightiStage condition transfer is Si+1The probability of stage condition, A' represent the anticipation position of current aircraft.
According to the result of calculation of likelihood probability, when judging mission phase residing for current aircraft, the specific implementation of this method Cheng Wei：Determine the maximum probing result of likelihood probability.
By the stage residing for the maximum result of detection of likelihood probability, as the stage residing for current aircraft.
Here, the present embodiment aircraft brake disc method for tracing, can count the state transition probability in stage, calculate adjacent phases The likelihood probability of result of detection, with according to previous result of detection, the accurate mission phase calculated residing for current aircraft, so as to In the working condition of switching detector.
When obtaining the experience weight of mission phase, the specific implementation process of this method is：
Gather the sample data of takeoff and landing process.
Statistics calculating is carried out to sample data, obtains the experience weight of mission phase, such as keeps SiThe probability of mission phase ti_i, or from SiMission phase transfer is Si+1The probability t of mission phasei_i+1。
In actual application, aircraft position and state in statistical sample data, the experience weight of mission phase is determined.
For example, time of day when once being detected before making aircraft is S (A, L), wherein, A is the three-dimensional coordinate position of aircraft, L is the three-dimensional velocity vector of aircraft；
The anticipation state for making current aircraft is S'(A', L'), wherein, A'=A+L, L'=L；
The time of day for making current aircraft is S " (A ", L ").
With stage Si、Si+1Exemplified by, transition probability parameters between adjacent phases as shown in figure 4,
Wherein, ti_i+ti_i+1=1, ti_i=fi(A), ti+1_i=0, ti_iRepresent to keep SiThe probability in stage, ti_i+1Table Show from SiPhase transition is Si+1The probability in stage, ti+1_i+1Represent to keep Si+1The probability in stage, ti+1_iRepresent from the Si+1Phase transition is SiThe probability in stage, bi_iRepresent to keep SiThe likelihood probability in stage, bi_i+1Represent from SiStage turns It is changed to Si+1The likelihood probability in stage, bi+1_i+1Represent to keep Si+1The likelihood probability in stage, bi+1_iRepresent from Si+1Stage Be converted to SiThe likelihood probability in stage, function f () represent table lookup operation, can obtained herein according to aircraft position and state Corresponding transition probability, later State Transferring is by that analogy.
Here, the sample data of the present embodiment aircraft brake disc method for tracing, in advance collection takeoff and landing process, to sample number According to statistics calculating is carried out, according to aircraft position and state, and then the state transition probability of aircraft is determined, determine the warp of mission phase Weight is tested, subsequently to judge that the stage residing for aircraft provides effective Informational support.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description Point is contained at least one embodiment or example of the present invention.In this manual, to the schematic representation of above-mentioned term not Identical embodiment or example must be directed to.Moreover, specific features, structure, material or the feature of description can be with office Combined in an appropriate manner in one or more embodiments or example.In addition, in the case of not conflicting, the skill of this area Art personnel can be tied the different embodiments or example and the feature of different embodiments or example described in this specification Close and combine.
It should be noted that the flow chart and block diagram in accompanying drawing show the service of multiple embodiments according to the present invention Architectural framework in the cards, function and the operation of device, method and computer program product.At this point, flow chart or block diagram In each square frame can represent the part of a module, program segment or code, the module, one of program segment or code Subpackage is containing one or more executable instructions for being used to realize defined logic function.It should also be noted that at some as replacement Realization in, the function that is marked in square frame can also be to occur different from the order marked in accompanying drawing.For example, two continuous Square frame can essentially perform substantially in parallel, they can also be performed in the opposite order sometimes, and this is according to involved work( Depending on energy.It is also noted that each square frame and block diagram in block diagram and/or flow chart and/or the square frame in flow chart Combination, function or the special hardware based server of action it can be realized as defined in execution, or can be with special The combination of hardware and computer instruction is realized.
The configuration device that the embodiment of the present invention is provided can be computer program product, including store program code Computer-readable recording medium, the instruction that described program code includes can be used for performing the side described in previous methods embodiment Method, specific implementation can be found in embodiment of the method, will not be repeated here.
It is apparent to those skilled in the art that for convenience and simplicity of description, the service of foregoing description The specific work process of device, device and unit, the corresponding process in preceding method embodiment is may be referred to, will not be repeated here.
In several embodiments provided herein, it should be understood that disclosed server, apparatus and method, can To realize by another way.Device embodiment described above is only schematical, for example, the unit is drawn Point, only a kind of division of logic function, there can be other dividing mode when actually realizing, in another example, multiple units or group Part can combine or be desirably integrated into another server, or some features can be ignored, or not perform.It is another, show Show or the mutual coupling discussed or direct-coupling or communication connection can be by some communication interfaces, device or unit INDIRECT COUPLING or communication connection, can be electrical, mechanical or other forms.
The unit illustrated as separating component can be or may not be physically separate, show as unit The part shown can be or may not be physical location, you can with positioned at a place, or can also be published to multiple On NE.Some or all of unit therein can be selected to realize the mesh of this embodiment scheme according to the actual needs 's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, can also That unit is individually physically present, can also two or more units it is integrated in a unit.
If the function is realized in the form of SFU software functional unit and is used as independent production marketing or in use, can be with It is stored in a computer read/write memory medium.Based on such understanding, technical scheme is substantially in other words The part to be contributed to prior art or the part of the technical scheme can be embodied in the form of software product, the meter Calculation machine software product is stored in a storage medium, including some instructions are causing a computer equipment (can be People's computer, server, or network equipment etc.) perform all or part of step of each embodiment methods described of the present invention. And foregoing storage medium includes：USB flash disk, mobile hard disk, read-only storage (ROM, Read-Only Memory), arbitrary access are deposited Reservoir (RAM, Random Access Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
Finally it should be noted that：Various embodiments above is merely illustrative of the technical solution of the present invention, rather than its limitations；To the greatest extent The present invention is described in detail with reference to foregoing embodiments for pipe, it will be understood by those within the art that：Its according to The technical scheme described in foregoing embodiments can so be modified, either which part or all technical characteristic are entered Row equivalent substitution；And these modifications or replacement, the essence of appropriate technical solution is departed from various embodiments of the present invention technology The scope of scheme, it all should cover among the claim of the present invention and the scope of specification.

Claims (7)

  1. A kind of 1. aircraft brake disc detection method, it is characterised in that including：
    Original image is inputted into convolutional neural networks, generates convolution characteristic pattern, the convolution characteristic pattern includes the N-dimensional of each pixel Characteristic vector；
    The original image is divided into using image partition method by different regions；
    To the convolution characteristic pattern in each extracted region region being partitioned into, and it is standardized, obtains each region pair The provincial characteristics figure answered；
    The provincial characteristics figure in each region is examined, the region according to corresponding to the characteristic pattern for being determined as aircraft, calculates and exports aircraft Region.
  2. 2. aircraft brake disc detection method according to claim 1, it is characterised in that
    Original image is inputted into convolutional neural networks, convolution characteristic pattern is generated, specifically includes：
    Convolution operation is carried out to the original image using the convolution kernel of predefined parameter, generates convolved image；
    Convolution operation is carried out to the convolved image using the convolution kernel of predefined parameter, generates the convolution characteristic pattern, the volume Product neutral net includes the convolution kernel of the predefined parameter.
  3. 3. aircraft brake disc detection method according to claim 1, it is characterised in that
    The original image is divided into using image partition method by different regions, specifically included：
    Calculate the aberration in adjacent subarea domain in the original image；
    By position is adjacent and aberration is no more than the subregion of default color threshold and merged, the field color after merging is two sons Region press pixel quantity weighted average, travel through all subregions, until all adjacent subarea domains aberration be all higher than it is default Color threshold, wherein, aberration is the sum of three channel strength difference absolute values of RGB；
    Statistics is distributed in the most value on horizontal, ordinate per sub-regions, generates rectangular shaped rim, as current segmentation result, carries out Output；
    Default color threshold is adjusted, repetition is compared, until the region quantity in image is one, and merges identical output As a result, then the final result of image segmentation is obtained.
  4. 4. aircraft brake disc detection method according to claim 1, it is characterised in that
    The provincial characteristics figure in each region is examined, is specifically included：
    Using PCA algorithms, dimensionality reduction is carried out to the provincial characteristics figure in each region, obtains characteristic vector, it is special in each characteristic vector The position of value indicative determines according to the separating capacity power of this feature value；
    Take a characteristic value in characteristic vector successively from front to back, and tested according to the classification thresholds of the dimension：If examine Not by then judging the region without aircraft；
    If for all characteristic values by examining, it is aircraft to judge the region in characteristic vector.
  5. A kind of 5. aircraft brake disc method for tracing, it is characterised in that
    Obtain the experience weight of mission phase；
    According to the experience weight of mission phase, likelihood is calculated to the result of detection of the detector in a preceding adjacent flight stage respectively Probability, the three-dimensional space position in the result of detection are the positions according to the region conversion for being determined as aircraft in advance；
    According to the result of calculation of likelihood probability, mission phase residing for current aircraft is judged, and switch the work shape of corresponding detector State, each detector correspond with each mission phase.
  6. 6. aircraft brake disc method for tracing according to claim 5, it is characterised in that
    According to the experience weight of mission phase, likelihood is calculated to the result of detection of the detector in a preceding adjacent flight stage respectively Probability, specifically include：
    According to the experience weight of mission phase, using likelihood probability formula, to a preceding SiThe result of detection of the detector in stage enters Row calculates：
    b(Oi(α))=ti_iexp(-|A'-α|)
    Wherein, OiRepresent SiThe result of detection of the detector in stage, α represent the center of search coverage, ti_iExpression experience weight Middle holding SiThe probability of stage condition, A' represent the anticipation position of current aircraft；
    According to the experience weight of mission phase, using likelihood probability formula, to a preceding Si+1The result of detection of the detector in stage Calculated：
    b(Oi+1(α))=ti_i+1exp(-|A'-α|)
    Wherein, Oi+1Represent Si+1The result of detection of the detector in stage, α represent the center of search coverage, ti_i+1Expression experience From S in weightiStage condition transfer is Si+1The probability of stage condition, A' represent the anticipation position of current aircraft；
    According to the result of calculation of likelihood probability, judge mission phase residing for current aircraft, specifically include：
    Determine the maximum probing result of likelihood probability；
    By the stage residing for the maximum result of detection of likelihood probability, as the stage residing for current aircraft.
  7. 7. according to the aircraft brake disc method for tracing of claim 5 or 6, it is characterised in that
    The experience weight for obtaining mission phase, is specifically included：
    Gather the sample data of takeoff and landing process；
    Statistics calculating is carried out to the sample data, obtains the experience weight of mission phase.
CN201710724698.5A 2017-08-22 2017-08-22 Aircraft brake disc detection and method for tracing Active CN107507198B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710724698.5A CN107507198B (en) 2017-08-22 2017-08-22 Aircraft brake disc detection and method for tracing

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710724698.5A CN107507198B (en) 2017-08-22 2017-08-22 Aircraft brake disc detection and method for tracing

Publications (2)

Publication Number Publication Date
CN107507198A true CN107507198A (en) 2017-12-22
CN107507198B CN107507198B (en) 2019-11-19

Family

ID=60691419

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710724698.5A Active CN107507198B (en) 2017-08-22 2017-08-22 Aircraft brake disc detection and method for tracing

Country Status (1)

Country Link
CN (1) CN107507198B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108520527A (en) * 2018-03-28 2018-09-11 东北大学 A kind of space-time context fast track method based on color attribute and PCA
CN110211159A (en) * 2019-06-06 2019-09-06 中国民航科学技术研究院 A kind of aircraft position detection system and method based on image/video processing technique

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102142078A (en) * 2010-02-03 2011-08-03 中国科学院自动化研究所 Method for detecting and identifying targets based on component structure model
CN105512684A (en) * 2015-12-09 2016-04-20 江苏大为科技股份有限公司 Vehicle logo automatic identification method based on principal component analysis convolutional neural network
CN105989336A (en) * 2015-02-13 2016-10-05 中国科学院西安光学精密机械研究所 Scene identification method based on deconvolution deep network learning with weight
CN106295695A (en) * 2016-08-08 2017-01-04 中国民用航空总局第二研究所 A kind of takeoff and landing process automatic tracing image pickup method and device

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102142078A (en) * 2010-02-03 2011-08-03 中国科学院自动化研究所 Method for detecting and identifying targets based on component structure model
CN105989336A (en) * 2015-02-13 2016-10-05 中国科学院西安光学精密机械研究所 Scene identification method based on deconvolution deep network learning with weight
CN105512684A (en) * 2015-12-09 2016-04-20 江苏大为科技股份有限公司 Vehicle logo automatic identification method based on principal component analysis convolutional neural network
CN106295695A (en) * 2016-08-08 2017-01-04 中国民用航空总局第二研究所 A kind of takeoff and landing process automatic tracing image pickup method and device

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
BIN PAN 等: "Cascade Convolutional Neural Network Based on Transfer-Learning for Aircraft Detection on High-Resolution Remote Sensing Images", 《JOURNAL OF SENSORS》 *
FAN ZHANG 等: "Weakly Supervised Learning Based on Coupled Convolutional Neural Networks for Aircraft Detection", 《IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING》 *
JUNSEOK KWON 等: "Adaptive Visual Tracking with Minimum Uncertainty Gap Estimation", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 *
ROSS GIRSHICK 等: "Rich feature hierarchies for accurate object detection and semantic segmentation", 《PROCEEDINGS OF THE 2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION》 *
于雪梅 等: "极大似然法在飞机起飞性能参数辨识中的应用", 《飞行力学》 *
王思雨 等: "基于卷积神经网络的高分辨率SAR图像飞机目标检测方法", 《雷达学报》 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108520527A (en) * 2018-03-28 2018-09-11 东北大学 A kind of space-time context fast track method based on color attribute and PCA
CN110211159A (en) * 2019-06-06 2019-09-06 中国民航科学技术研究院 A kind of aircraft position detection system and method based on image/video processing technique

Also Published As

Publication number Publication date
CN107507198B (en) 2019-11-19

Similar Documents

Publication Publication Date Title
Li et al. Real-time detection of steel strip surface defects based on improved yolo detection network
CN108986064B (en) People flow statistical method, equipment and system
WO2018028103A1 (en) Unmanned aerial vehicle power line inspection method based on characteristics of human vision
CN105678811B (en) A kind of human body anomaly detection method based on motion detection
CN109117876A (en) A kind of dense small target deteection model building method, model and detection method
CN106845383A (en) People's head inspecting method and device
CN104378582B (en) A kind of intelligent video analysis system and method cruised based on Pan/Tilt/Zoom camera
CN103824070B (en) A kind of rapid pedestrian detection method based on computer vision
WO2019096952A1 (en) A system and method for single image object density estimation
CN107818326A (en) A kind of ship detection method and system based on scene multidimensional characteristic
CN106845364B (en) Rapid automatic target detection method
CN108037770A (en) Unmanned plane power transmission line polling system and method based on artificial intelligence
CN105930822A (en) Human face snapshot method and system
CN103077386A (en) Cascaded video streaming iris image quality detection method
CN108154159A (en) A kind of method for tracking target with automatic recovery ability based on Multistage Detector
KR102199252B1 (en) Method and Apparatus for Analyzing Traffic Situation
CN110210482A (en) Improve the object detection method of class imbalance
CN110276321A (en) Remote sensing video target tracking method and system
CN107507198B (en) Aircraft brake disc detection and method for tracing
CN113569981A (en) Power inspection bird nest detection method based on single-stage target detection network
CN110532853A (en) The classification method and device of remote sensing time-out phase data
Wang et al. Prior-guided data augmentation for infrared small target detection
Manninen et al. Multi-stage deep learning networks for automated assessment of electricity transmission infrastructure using fly-by images
CN117132870B (en) Wing icing detection method combining CenterNet and mixed attention
CN115690545A (en) Training target tracking model and target tracking method and device

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
GR01 Patent grant