CN106525027A - Star sensor star point extracting method based on local binary pattern - Google Patents
Star sensor star point extracting method based on local binary pattern Download PDFInfo
- Publication number
- CN106525027A CN106525027A CN201610952197.8A CN201610952197A CN106525027A CN 106525027 A CN106525027 A CN 106525027A CN 201610952197 A CN201610952197 A CN 201610952197A CN 106525027 A CN106525027 A CN 106525027A
- Authority
- CN
- China
- Prior art keywords
- star
- pixel
- cornea
- punctate opacity
- local binary
- 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
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/02—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by astronomical means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/02—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by astronomical means
- G01C21/025—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 by astronomical means with the use of startrackers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Physics & Mathematics (AREA)
- Astronomy & Astrophysics (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention discloses a star sensor star point extracting method based on a local binary pattern. The star sensor star point extracting method comprises the following steps: S1, carrying out average filtering on a star image to obtain gray values of various pixel points in the filtered star image, and acquiring the filtered star image; S2, calculating feature vectors of the pixel points in the filtered star image by a local binary pattern LBP operator; S3, training a star point pixel sample and a background pixel sample in a live shot star image by using a support vector machine (SVM); and S4, matching a star point training result with the feature vectors of the image pixel points calculated by the LBP operator to finish star point extracting. The star sensor star point extracting method based on the local binary pattern has the advantages that image features of star points are considered fully, star point information is retained as much as possible while parasitic light background pixels are eliminated, and therefore, the problems that by the traditional star point extracting algorithm under interference of parasitic light, parasitic light high-frequency noise points in the star image and pixel points with low gray values in star points lost easily are easily extracted are solved.
Description
Technical field
The present invention relates to star sensor technical field, and in particular to a kind of star sensor star point based on local binary patterns
Extracting method.
Background technology
Star sensor is by the observation to fixed star, recognizes, is calculated the attitude information of spacecraft, and it is a kind of
Using fixed star as the high accuracy aircraft attitude measurement sensor of observation benchmark.
Star sensor splits punctate opacity of the cornea pixel first from star chart, is carried out using punctate opacity of the cornea pixel extraction punctate opacity of the cornea afterwards, further according to
The punctate opacity of the cornea of extraction carries out importance in star map recognition and Attitude Calculation.The precision that punctate opacity of the cornea is extracted has been largely affected by star sensor work
Performance.
In existing star sensor star point extracting method, one kind is using global threshold method, then according to global threshold
Punctate opacity of the cornea pixel is extracted, specifically, first, the gray average of calculating entire image in entire image, and entire image
Gray standard deviation, using gray average plus three times times gray standard deviation as global threshold, in window, grey scale pixel value is more than threshold
The pixel of value is punctate opacity of the cornea pixel, conversely, the pixel is background pixel.Also one kind is using based on Digital High Pass Filter method
Punctate opacity of the cornea is extracted, specifically, first, using the threshold value of each pixel of high-pass filtering formwork calculation, then, by the pixel threshold
Value is compared with the gray value of pixel, and pixel gray value is more than threshold value, then the pixel is punctate opacity of the cornea pixel, conversely, being background
Pixel.
However, above-mentioned two kinds of conventional punctate opacity of the cornea extracting method are all easily affected by uneven illumination, punctate opacity of the cornea is being extracted
Extract veiling glare background pixel simultaneously.
The content of the invention
It is an object of the invention to provide a kind of star sensor star point extracting method based on local binary patterns, by right
Star chart under light disturbance carries out mean filter process, obtains the gray average of star chart pixel, and then calculates pixel again
LBP operator characteristic vectors, with sample punctate opacity of the cornea complete SVM training, finally using SVM from star chart by punctate opacity of the cornea pixel and background pixel
Distinguish, so as to complete the extraction algorithm of punctate opacity of the cornea, solve traditional punctate opacity of the cornea extraction algorithm under light disturbance and easily extract star chart
In veiling glare high-frequency noise point and punctate opacity of the cornea easy to lose in the relatively low pixel of gray value problem.
In order to achieve the above object, the present invention is achieved through the following technical solutions:
A kind of star sensor star point extracting method based on local binary patterns, is characterized in that, comprise the steps of:
S1, mean filter is carried out to star chart, after being filtered in star chart each pixel gray value, and obtain filtered
Star chart;
S2, the characteristic vector that pixel in star chart after filtering is calculated using local binary patterns LBP operators;
S3, using support vector machines training real scene shooting star chart in punctate opacity of the cornea pixel samples and background sample of pixels;
The characteristic vector of the image slices vegetarian refreshments that S4, matching punctate opacity of the cornea training result and LBP operators are calculated, completes punctate opacity of the cornea extraction.
The above-mentioned star sensor star point extracting method based on local binary patterns, wherein, described step S1 is specifically wrapped
Contain:
By computing formulaThe gray value of multiple pixels is obtained, in formula, I (i, j)
For the gray value of pixel (i, j), gray averages of the m (i, j) for (i, j) of pixel.
The above-mentioned star sensor star point extracting method based on local binary patterns, wherein, described step S2 is specifically wrapped
Contain:
According to the gray value of each pixel obtained in step S1, the feature at punctate opacity of the cornea pixel is calculated using LBP operators
Vector, including:
In formula, gcCentered on pixel value, gPFor neighborhood territory pixel value, P is neighborhood point number, and R is neighborhood point radius.
The above-mentioned star sensor star point extracting method based on local binary patterns, wherein, described step S4 is specifically wrapped
Contain:
The characteristic vector of star chart pixel will be calculated after S41, the filtering obtained using LBP operators in step S2
Input condition of the characteristic vector as support vector machine;
S42, support vector machine will be filtered according to the characteristic vector of the punctate opacity of the cornea sampled pixel that acquisition is trained in step S3 after star
In figure, pixel is divided into punctate opacity of the cornea pixel and background pixel, so as to complete punctate opacity of the cornea extraction.
The present invention has advantages below compared with prior art:The characteristics of image of punctate opacity of the cornea is taken into full account, can have been eliminated
Retain punctate opacity of the cornea information as much as possible while veiling glare background pixel, therefore solve traditional punctate opacity of the cornea extraction algorithm under light disturbance
The problem of the relatively low pixel of gray value in veiling glare high-frequency noise point and the punctate opacity of the cornea easy to lose in star chart is extracted easily.
Description of the drawings
Fig. 1 is method of the present invention flow chart;
Fig. 2 is LBP circle shaped neighborhood region schematic diagrams in embodiments of the invention;
Fig. 3 is the star chart used in embodiments of the invention;
Fig. 4 is the experimental result for carrying out punctate opacity of the cornea extraction using the global threshold algorithm of prior art to the star chart of Fig. 3;
Fig. 5 is the experimental result for carrying out punctate opacity of the cornea extraction using the method for the present invention to the star chart of Fig. 3.
Specific embodiment
Below in conjunction with accompanying drawing, by describing a preferably specific embodiment in detail, the present invention is further elaborated.
As shown in figure 1, the invention discloses a kind of star sensor star point extracting method based on local binary patterns, its bag
Containing following steps:
S1, mean filter is carried out to star chart, after being filtered in star chart each pixel gray value, and obtain filtered
Star chart;This step is to prevent background pixel, noise pixel interference punctate opacity of the cornea pixel extraction, in the present embodiment, first by equal
Value filtering template, Filtering Template are typically sized to 3 × 3;
S2, the characteristic vector that pixel in star chart after filtering is calculated using local binary patterns LBP operators;
S3, using support vector machines train real scene shooting star chart in punctate opacity of the cornea pixel samples and background sample of pixels feature to
Amount;
The characteristic vector of the image slices vegetarian refreshments that S4, matching punctate opacity of the cornea training result and LBP operators are calculated, completes punctate opacity of the cornea extraction.
Described step S1 is specifically included, and carries out mean filter to star chart using following formula, and the gray scale for obtaining star chart midpoint is equal
Value:
In above formula, m (i, j) represents the gray average of pixel (i, j) after image filtering, and I (i, j) represents point (i, j)
Grey scale pixel value.
Described step S2 is specifically included, according to the gray value of each pixel obtained in step S1, using LBP operators
Calculate the characteristic vector at punctate opacity of the cornea pixel;
Generally LBP operators take 3 × 3 neighborhoods, and traditional LBP operators have that sampling number is very few, and this can reduce LBP
The robustness of operator.Therefore, the LBP operators of standard are expanded to the calculation that any radius and neighborhood points are obtained after circle shaped neighborhood region
Son, increases sampled point number, improves LBP operator robustness.When Fig. 2 gives that (P, R) takes different value under circular field, operator is adjacent
Domain schematic diagram,
In formula, gcCentered on pixel value;gPFor neighborhood territory pixel value;P is neighborhood point number;R is neighborhood point radius.In star chart,
Punctate opacity of the cornea size is generally 3 × 3 pixel sizes, in order that LBP operators can accurately calculate the characteristic vector of punctate opacity of the cornea pixel, this enforcement
It is 12 for 1.5, P that LBP operator radius R are chosen in example.According to above-mentioned LBP operators calculate the feature of pixel in star chart after filtering to
Amount.
Described step S3 specially calculates punctate opacity of the cornea pixel samples and background sample of pixels in real scene shooting star chart using LBP operators
Characteristic vector, and with the characteristic vector of SVM training sample punctate opacity of the corneas, specifically, in the present embodiment, select from real scene shooting star chart
200 punctate opacity of the cornea pixel samples and 200 background sample of pixels, calculate punctate opacity of the cornea pixel samples with the LBP operators in S2 steps first
With the characteristic vector of background sample of pixels, then punctate opacity of the cornea pixel and background sample of pixels are trained with SVM.
SVM is trained using sample punctate opacity of the cornea, α values are solved, SVM training principle is as follows:
The optimization object function of SVM can be write as:
In above formula, label is tag variable, if data point is in positive direction position, label values are 1;Conversely,
Label values are -1.Angle brackets represent x(i)And x(j)Two vectorial inner products;
Its constraints is:
C >=α >=0 He
Constant C is used to control to maximize interval and ensures the function interval of most of point less than 1.0.The groundwork of SVM
α is just to solve for, α is solved with SVM training sample punctate opacity of the corneas, then segmentation hyperplane just can be expressed with these α.
Described step S4 is specifically included:
S41, filtered using LBP operators in step S2 after star chart pixel characteristic vector and by calculated spy
Vector is levied as the input condition of support vector machine;
S42, support vector machine will be filtered according to the characteristic vector of the punctate opacity of the cornea sampled pixel that acquisition is trained in step S3 after star
In figure, pixel is divided into punctate opacity of the cornea pixel and background pixel, so as to complete punctate opacity of the cornea extraction.
Punctate opacity of the cornea pixel is extracted from star chart using SVM, specifically, with reference in star chart after the filtering that LBP operators in S2 are calculated
The characteristic vector of pixel, and the support vector machine trained in step S3, are completed, punctate opacity of the cornea pixel is extracted from star chart.
The star sensor star point extracting method based on local binary patterns that the present invention is provided, by being filtered to star chart
Process, obtain the gray average of pixel in star chart, so recycle LBP operators calculate the feature of punctate opacity of the cornea pixel in star chart to
Amount, and punctate opacity of the cornea sample is trained using SVM, the SVM for finally being completed using training extracts punctate opacity of the cornea pixel from star chart, and the present invention fills
Divide the characteristics of image that make use of punctate opacity of the cornea, punctate opacity of the cornea information as much as possible can be retained while veiling glare background pixel is eliminated, because
This solves traditional punctate opacity of the cornea extraction algorithm under light disturbance and easily extracts veiling glare high-frequency noise point and star easy to lose in star chart
The problem of the relatively low pixel of gray value in point.
During in order to verify that the present invention processes star sensor star chart under light disturbance, eliminating veiling glare background pixel and retaining punctate opacity of the cornea
The ability of Pixel Information, is presented herein below according to above-mentioned specific embodiment, with the real scene shooting star chart that moonlight enters star sensor visual field is
Example, and the comparing result of the punctate opacity of the cornea extracting method actual experiment acquisition with reference to the marginal data present invention:
Fig. 3 is star sensor star chart under the light disturbance used in the present embodiment, respectively using global threshold algorithm and office
Portion's thresholding algorithm processes the figure, experimental result as shown in Figure 4,5, the respectively experimental result schematic diagram of veiling glare pixel, wherein Fig. 4
For the experimental result that Global Algorithm punctate opacity of the cornea is extracted, Fig. 5 is the experimental result that inventive algorithm punctate opacity of the cornea is extracted, and can be seen according to result
Go out, the present invention can retain punctate opacity of the cornea information as much as possible while veiling glare background pixel is eliminated, be conducive to improving subsequent step
The precision of middle center coordination.
It should be noted that one of ordinary skill in the art will appreciate that:Realize above-mentioned each method embodiment whole or
Part steps can be completed by the related hardware of programmed instruction.Aforesaid program can be stored in an embodied on computer readable and deposit
In storage media.The program upon execution, performs the step of including above-mentioned each method embodiment;And aforesaid storage medium includes:
ROM, RAM, magnetic disc or CD etc. are various can be with the medium of store program codes.
Although present disclosure has been made to be discussed in detail by above preferred embodiment, but it should be appreciated that above-mentioned
Description is not considered as limitation of the present invention.After those skilled in the art have read the above, for the present invention's
Various modifications and substitutions all will be apparent.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (4)
1. a kind of star sensor star point extracting method based on local binary patterns, it is characterised in that comprise the steps of:
S1, mean filter is carried out to star chart, after being filtered in star chart each pixel gray value, and obtain filtered star
Figure;
S2, the characteristic vector that pixel in star chart after filtering is calculated using local binary patterns LBP operators;
S3, using support vector machines training real scene shooting star chart in punctate opacity of the cornea pixel samples and background sample of pixels;
The characteristic vector of the image slices vegetarian refreshments that S4, matching punctate opacity of the cornea training result and LBP operators are calculated, completes punctate opacity of the cornea extraction.
2. the star sensor star point extracting method based on local binary patterns as claimed in claim 1, it is characterised in that described
The step of S1 specifically include:
By computing formulaThe gray value of multiple pixels is obtained, in formula, I (i, j) is picture
The gray value of vegetarian refreshments (i, j), gray averages of the m (i, j) for (i, j) of pixel.
3. the star sensor star point extracting method based on local binary patterns as claimed in claim 1, it is characterised in that described
The step of S2 specifically include:
According to the gray value of each pixel obtained in step S1, the characteristic vector at punctate opacity of the cornea pixel is calculated using LBP operators,
Including:
In formula, gcCentered on pixel value, gPFor neighborhood territory pixel value, P is neighborhood point number, and R is neighborhood point radius.
4. the star sensor star point extracting method based on local binary patterns as claimed in claim 1, it is characterised in that described
The step of S4 specifically include:
The characteristic vector of star chart pixel by calculated feature after S41, the filtering obtained using LBP operators in step S2
Input condition of the vector as support vector machine;
S42, support vector machine will be filtered according to the characteristic vector of the punctate opacity of the cornea sampled pixel that acquisition is trained in step S3 after in star chart
Pixel is divided into punctate opacity of the cornea pixel and background pixel, so as to complete punctate opacity of the cornea extraction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610952197.8A CN106525027B (en) | 2016-11-02 | 2016-11-02 | A kind of star sensor star point extracting method based on local binary patterns |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610952197.8A CN106525027B (en) | 2016-11-02 | 2016-11-02 | A kind of star sensor star point extracting method based on local binary patterns |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106525027A true CN106525027A (en) | 2017-03-22 |
CN106525027B CN106525027B (en) | 2019-04-09 |
Family
ID=58325294
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610952197.8A Active CN106525027B (en) | 2016-11-02 | 2016-11-02 | A kind of star sensor star point extracting method based on local binary patterns |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106525027B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909073A (en) * | 2017-10-18 | 2018-04-13 | 天津大学 | Multidimensional local binary patterns and the hand-written music score spectral line delet method of machine learning |
CN108805050A (en) * | 2018-05-28 | 2018-11-13 | 上海交通大学 | Electric wire detection method based on local binary patterns |
CN113205063A (en) * | 2021-05-19 | 2021-08-03 | 云南电网有限责任公司电力科学研究院 | Visual identification and positioning method for defects of power transmission conductor |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103968845A (en) * | 2014-04-15 | 2014-08-06 | 北京控制工程研究所 | DSP and FPGA parallel multi-mode star image processing method for star sensor |
WO2014186081A1 (en) * | 2013-05-14 | 2014-11-20 | The Charles Stark Draper Laboratory, Inc. | Star tracker with steerable field-of-view baffle coupled to wide field-of-view camera |
WO2014209510A1 (en) * | 2013-06-28 | 2014-12-31 | The Charles Stark Draper Laboratory, Inc. | Chip-scale star tracker |
CN104931044A (en) * | 2015-06-16 | 2015-09-23 | 上海新跃仪表厂 | Star sensor image processing method and system |
CN105374035A (en) * | 2015-11-03 | 2016-03-02 | 北京航空航天大学 | Star sensor star point extraction method under stray light interference |
-
2016
- 2016-11-02 CN CN201610952197.8A patent/CN106525027B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014186081A1 (en) * | 2013-05-14 | 2014-11-20 | The Charles Stark Draper Laboratory, Inc. | Star tracker with steerable field-of-view baffle coupled to wide field-of-view camera |
WO2014209510A1 (en) * | 2013-06-28 | 2014-12-31 | The Charles Stark Draper Laboratory, Inc. | Chip-scale star tracker |
CN103968845A (en) * | 2014-04-15 | 2014-08-06 | 北京控制工程研究所 | DSP and FPGA parallel multi-mode star image processing method for star sensor |
CN104931044A (en) * | 2015-06-16 | 2015-09-23 | 上海新跃仪表厂 | Star sensor image processing method and system |
CN105374035A (en) * | 2015-11-03 | 2016-03-02 | 北京航空航天大学 | Star sensor star point extraction method under stray light interference |
Non-Patent Citations (1)
Title |
---|
郑胜等: "基于支持向量机的导航星选取算法研究", 《计算机应用研究》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107909073A (en) * | 2017-10-18 | 2018-04-13 | 天津大学 | Multidimensional local binary patterns and the hand-written music score spectral line delet method of machine learning |
CN108805050A (en) * | 2018-05-28 | 2018-11-13 | 上海交通大学 | Electric wire detection method based on local binary patterns |
CN108805050B (en) * | 2018-05-28 | 2021-01-01 | 上海交通大学 | Electric wire detection method based on local binary pattern |
CN113205063A (en) * | 2021-05-19 | 2021-08-03 | 云南电网有限责任公司电力科学研究院 | Visual identification and positioning method for defects of power transmission conductor |
Also Published As
Publication number | Publication date |
---|---|
CN106525027B (en) | 2019-04-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111325764B (en) | Fruit image contour recognition method | |
CN108765325B (en) | Small unmanned aerial vehicle blurred image restoration method | |
CN107424171B (en) | Block-based anti-occlusion target tracking method | |
Masias et al. | A review of source detection approaches in astronomical images | |
CN107368792A (en) | A kind of finger vein identification method and system based on wave filter and Bone Edge | |
CN110543837A (en) | visible light airport airplane detection method based on potential target point | |
CN109146911B (en) | Target tracking method and device | |
CN103218605B (en) | A kind of fast human-eye positioning method based on integral projection and rim detection | |
CN105931255A (en) | Method for locating target in image based on obviousness and deep convolutional neural network | |
CN108154519A (en) | Dividing method, device and the storage medium of eye fundus image medium vessels | |
CN110120065B (en) | Target tracking method and system based on hierarchical convolution characteristics and scale self-adaptive kernel correlation filtering | |
CN106558072A (en) | A kind of method based on SIFT feature registration on remote sensing images is improved | |
CN108009554A (en) | A kind of image processing method and device | |
CN108197644A (en) | A kind of image-recognizing method and device | |
Liu et al. | Stochastic lane shape estimation using local image descriptors | |
CN104794721A (en) | Quick optic disc positioning method based on multi-scale macula detection | |
CN104217422A (en) | Sonar image detection method of self-adaption narrow-band level set | |
CN109117746A (en) | Hand detection method and machine readable storage medium | |
CN103761768A (en) | Stereo matching method of three-dimensional reconstruction | |
CN109766818A (en) | Pupil center's localization method and system, computer equipment and readable storage medium storing program for executing | |
CN106525027A (en) | Star sensor star point extracting method based on local binary pattern | |
CN108564019A (en) | A kind of face identification method and system | |
CN112926516B (en) | Robust finger vein image region-of-interest extraction method | |
CN109241981A (en) | A kind of characteristic detection method based on sparse coding | |
Arora et al. | An algorithm to straighten the bent human chromosomes |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 |