CN108109156A - SAR image Approach for road detection based on ratio feature - Google Patents
SAR image Approach for road detection based on ratio feature Download PDFInfo
- Publication number
- CN108109156A CN108109156A CN201711415934.1A CN201711415934A CN108109156A CN 108109156 A CN108109156 A CN 108109156A CN 201711415934 A CN201711415934 A CN 201711415934A CN 108109156 A CN108109156 A CN 108109156A
- Authority
- CN
- China
- Prior art keywords
- pixel
- road
- image
- point
- dictionary
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
- G06T7/41—Analysis of texture based on statistical description of texture
- G06T7/45—Analysis of texture based on statistical description of texture using co-occurrence matrix computation
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- 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
- G06T2207/20076—Probabilistic image processing
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
Abstract
The present invention discloses a kind of SAR image Approach for road detection based on ratio feature, mainly solves the problems, such as that the prior art is high to road edge position inaccurate, false alarm rate.Its realization includes：1) drop spot is carried out to SAR image and extracts 9 kinds of textural characteristics, 2) the 3 kind textural characteristics maximum to classification contribution are screened according to Pasteur's distance from 9 kinds of textural characteristics；3) after node-by-node algorithm drop spot ratio feature R1 and similar ratio feature R2 is compared in image；4) with the sample architecture road dictionary D 2) with 3) result1With background dictionary D2；5) each pixel is solved respectively and road dictionary D1Mean difference E1With with background dictionary D2Mean difference E2, classified by difference to pixel, obtain Preliminary detection result；6) Preliminary detection result is optimized, obtains final having arrived testing result.The present invention can be than more completely, clearly detecting the road in SAR image, the road of different directions, different in width suitable for detection SAR image.
Description
Technical field
The invention belongs to the Approach for road detection in digital image processing techniques field, more particularly to SAR image, available for ground
Figure update, transportation logistics and urban planning.
Background technology
In recent years, with the continuous development of synthetic aperture radar key technology, SAR imaging resolutions are continuously improved, signal
Processing capacity constantly enhances, message transmission rate is continuously increased, equipment volume constantly reduces, quality constantly reduces, and SAR image can
It is widely used in information gathering, battlefield surveillance, attack guiding, Hitting Effect Evaluation etc..SAR image is born till now from it more than 50
The time in year technically has been achieved for rapid progress and development.In SAR image analysis, line feature has very important
Meaning, because some objects have linear structure, such as road, bridge, river, coastline in itself in image.Utilize computer
The Linear feature information of road etc is automatically extracted from SAR image, is the hope of people for many years.Line feature is for mostly biography
Sensor image registration, cartography application and image segmentation and target identification etc..For there is the object of one fixed width scope, accurately
Contour line contribute to the segmentation of different objects and the identification of target.
Road is the major part for forming modern traffic system, has important geography, political affairs as important artificial atural object
It controls, many meanings of economic dispatch.Since synthetic aperture radar SAR system has many advantages, such as round-the-clock, round-the-clock, scheme from SAR
Extraction road is paid more and more attention and applies as in.In a large amount of High Resolution SAR Images of acquisition, the extraction of road was usually both
It is the pilot process of SAR interpretations, can also be used as a kind of interpretation result.The extraction of SAR image road is that academic circles at present is universal
The hot spot of concern.Meanwhile SAR image road extraction has important answer in the fields such as military information interpretation and civilian urban planning
With value.
General SAR image Road Detection algorithm is first to determine road seeds according to unit detection, is then examined using line
Road seeds are connected into road line segment, such as Tupin, Kartartzis etc. and the method for the propositions such as Jeon by method of determining and calculating.Often
Rule these unit detection methods exist to road edge position inaccurate, false alarm rate is high the problems such as.
The content of the invention
It is an object of the invention to be directed to the deficiency of above-mentioned prior art, a kind of SAR image based on ratio feature is proposed
Approach for road detection to reduce false alarm rate, improves the accuracy to edge positioning.
To achieve the above object, implementation of the invention includes as follows：
(1) SAR image to be detected is read in, and drop spot pretreatment is carried out to SAR image；
(2) gray level co-occurrence matrixes are constructed point by point to the image after drop spot, and with gray level co-occurrence matrixes calculate energy, entropy,
Contrast, average, variance, correlation, non-similarity, unfavourable balance away from 9 kinds of textural characteristics of uniformity；
(3) the 9 kinds of textural characteristics extracted above are optimized and screened according to Bhattacharyya range indexs, only
Choosing can be respectively effectively to the feature of 3 kinds of Road Detection in SAR image and classification contribution maximum：Average, variance and right
Degree of ratio；
(4) ratio feature is extracted：
(4a) extracts two kinds of ratio features, i.e., the comparison ratio between road and two side areas point by point to the image after drop spot
Similar ratio feature R2 between feature R1 and both sides of the road region；
3 kinds of textural characteristics of extraction in step (3) and step (4a) are extracted two kinds of ratio features and are normalized by (4b),
Obtain 5 dimensional feature vectors of each pixel；
(5) pixel of part tape label is randomly choosed as sample, including road waypoint and non-rice habitats point, with the sample structure
Produce road dictionary D1With background dictionary D2；
(6) Preliminary detection：
(6a) solves each pixel and road dictionary D respectively1Difference E1With each pixel and background dictionary D2Difference
Value E2；
(6b) is according to the two differences E1And E2Classify to pixel：If E1-E2＜ 0 represents the pixel of test sample
The Atomic Correlations of point and road area are stronger, then are tentatively judged to pixel and belong to road area；If E1-E2>=0, represent test
The pixel of sample and the Atomic Correlations of background area are stronger, then are tentatively judged to pixel and belong to background area；
(7) Preliminary detection that obtains for step (6) is as a result, leptosomatic feature further according to road, with area perimeter
The optimization algorithm of ratio excludes false-alarm region, obtains the final result of Road Detection.
Compared with prior art, the present invention it has the following advantages that：
1. for the present invention due to defining a kind of computational methods of new ratio feature, which has taken into full account road and two
Difference is big between side region, and the both sides similitude of road is strong, overcomes lacking for conventional unit detection operator edge position inaccurate
Point, two kinds of ratio features of extraction accurately can carry out edge positioning to road；
2. the present invention is directed between textural characteristics there are redundancy, propose to screen feature with Bhattacharyya distances
Rule, since Bhattacharyya distances have taken into full account the correlation between the average, variance and standard drawing of feature, not only
The complexity of feature is reduced, also improves the operational efficiency of algorithm；
3. the present invention is directed to the characteristics of Road Detection is high to requirement of real-time, it is proposed that by constructing dictionary using difference point
The design of class, this taken into full account it is similar between the characteristics of similitude is strong, difference is big between inhomogeneity, compared with some complexities
Grader high, practicability is low, difference grader of the invention simplify calculating, disclosure satisfy that the requirement of real-time；
4. it is proposed by the present invention with area perimeter than optimization algorithm, can effectively exclude false-alarm region.Due to preliminary
There are false-alarms for testing result, it is known that road all has the characteristics that leptosomatic, the i.e. constant closed curve of a length, according to integration
The characteristics of principle, shape more level off to slender type, and area is smaller, this more meets road.
Description of the drawings
Fig. 1 is the Road Detection general flow chart of the present invention；
Fig. 2 is the sub-process figure of the optimization algorithm in the present invention；
Fig. 3 is the road area schematic diagram of three kinds of different in width in the present invention；
Fig. 4 is the test image that the present invention uses；
Fig. 5 is image after the denoising in the present invention；
Fig. 6 is the Road Detection PRELIMINARY RESULTS figure in the present invention；
Fig. 7 is that the present invention uses the result figure after optimization algorithm removal false-alarm；
Fig. 8 is the standard drawing of test image.
Specific embodiment
Below in conjunction with the accompanying drawings, the present invention is described in detail：
With reference to Fig. 1, realization step of the invention is as follows：
Step 1：Input data simultaneously carries out drop spot.
The inhibition of SAR coherent spots is the key that the premise of the work such as SAR image processing and subsequent image identification.
The SAR image of input is first carried out drop spot by the present invention using PPB algorithms, obtains the image that road becomes apparent from, with
Weaken the influence of noise, increase the contrast between road and background, the feature in order to carry out Road Detection exactly is beaten
Basis is descended.
Step 2：Texture feature extraction.
SAR image includes abundant textural characteristics, if these texture informations are with reasonable, it would be beneficial in Road Detection.
Gray level co-occurrence matrixes are constructed according to the image after denoising point by point, then extract 9 kinds of textural characteristics with gray level co-occurrence matrixes, respectively
It is：Energy, entropy, contrast, non-similarity, unfavourable balance away from, uniformity, average, variance and correlation.Textural characteristics have embodied road
The detailed information on road has apparent difference with background, can be distinguished road and background by textural characteristics.
(2a) generates the image elder generation normalized after drop spot by the probability density function of gray level co-occurrence matrixes GLCM
Gray level co-occurrence matrixes GLCM describes the SAR image after normalization with the gray level co-occurrence matrixes GLCM of generation,
The probability density function of gray level co-occurrence matrixes GLCM is as follows：
G (i, j)={ (x1,y1),(x2,y2)∈M×Nf(x1,y1)=i, f (x2,y2)=j },
Wherein, g (i, j) represents the frequency of element in SAR image, also referred to as GLCM probability density functions, and M is SAR image f
The transverse dimensions of (x, y), N are longitudinal dimensions of SAR image f (x, y), (x1,y1) and (x2,y2) it is image SAR image f (x, y)
Two pixels, f (x1,y1) and f (x2,y2) it is SAR image (x1,y1) and (x2,y2) gray value, i and j are to represent pixel f
(x1,y1) and f (x2,y2) gray value size numerical value；
(2b) according to gray level co-occurrence matrixes probability density function g (i, j) and normalization after SAR image at a distance of (Δ x,
The number that two gray-scale pixels during Δ y) occur simultaneously, generation gray level co-occurrence matrixes p (i, j), if grey level is divided into w
Grade, with regard to the gray level co-occurrence matrixes of a w × w can be obtained；
(2c) calculates 9 kinds of common textural characteristics respectively according to the gray level co-occurrence matrixes p (i, j) of generation：
(2c1) calculates energy feature Ene：
Energy is the parameter for weighing gray-value variation stable state in image, it can describe the journey of image texture precision
Degree and pixel gray value uniform state, calculation formula are as follows：
Wherein p (i, j) gray level co-occurrence matrixes, since gray level co-occurrence matrixes value is most for 1, Shao Shuowei in homogeneous region
0, thus energy value is big, it is that a kind of rule changes relatively stable texture to show current texture；Due to ash in non-homogeneous region
Most degree co-occurrence matrix value is 0, and minority is 1, thus energy value is smaller, and it is a kind of unstable line of variation to show current texture
Reason.
(2c2) calculates entropy feature Ent：
Entropy is to describe the measurement that random information is how many in image, and calculation formula is as follows：
When the matrix element value in gray level co-occurrence matrixes p (i, j) all relatively or in matrix element value be distributed with
When maximum uncertainty, entropy is bigger, shows that image is disorderly and unsystematic, texture is more numerous and diverse；
(2c3) calculates contrast metric Con：
Contrast is to weigh in image the how many parameter of varied number locally occur, and calculation formula is as follows：
Occur the local more of localized variation in image, contrast value is bigger, and the construction area in SAR image is due to minute surface
It is mingled with blackspot between the speck that reflection generates, so its contrast value is larger；
(2c4) calculates non-similarity feature Dis：
Similitude is to weigh in image the how many parameter of varied number locally occur, and calculation formula is as follows：
If local contrast is higher, non-similarity is also higher；
(2c5) calculates unfavourable balance moment characteristics Idm：
Inverse difference moment：It is to investigate matrix element value in gray level co-occurrence matrixes to be gathered in the how many ginseng of leading diagonal bigger numerical
Number, calculation formula are as follows：
If inverse difference moment value is bigger, definition graph picture is uniform；
(2c6) calculates homogeneity Hom：
Uniformity is to investigate matrix element value in gray level co-occurrence matrixes to be gathered in the how many ginseng of leading diagonal bigger numerical
Number, calculation formula are as follows：
If uniformity value is bigger, definition graph picture is uniform；
(2c7) calculates characteristics of mean Mea：
Average：It is the parameter for describing matrix element value in gray level co-occurrence matrixes, calculation formula is as follows：
Average reflects the central tendency of element value in gray level co-occurrence matrixes, can usually be used as square in gray level co-occurrence matrixes
Array element one estimate of element.
(2c8) calculates Variance feature Var：
Variance：It is to describe the parameter that matrix element value in gray level co-occurrence matrixes deviates equal extent value, calculation formula is as follows：
Variance reflects the uniformity coefficient of image with average jointly；
(2c9) calculates correlative character Cor：
Correlation：It is the parameter for describing correlation between each pixel gray value in image, from line direction and column direction
The similarity degree between gray level co-occurrence matrixes element is investigated respectively, can distinguish the grain direction in image, calculation formula is as follows：
Step 3：Feature Selection
According to the imaging characteristics of road area in SAR image, the feature for only selecting to be suitble to this kind of SAR image is as with generation
On the one hand the feature of table can reduce interference of the redundancy garbage to useful feature information, on the other hand can improve inspection
Survey efficiency.In the present invention, the optimization of feature and screening are carried out according to Bhattacharyya distances, this selection feature
Method is simple and quick and effective, and it is as follows to define Bhattacharyya distances：
Wherein, μ1、σ1The average and variance of first kind atural object pixel value on same texture template image are represented respectively；μ2、σ2
The average and variance of the second class atural object pixel value on same texture template image are represented respectively, and BD values are bigger, it was demonstrated that this feature area
The ability for being divided to this two classes atural object is stronger.
Due to, there are redundancy, being calculated between textural characteristics in order to simplify, this example is according to Bhattacharyya range indexs
The optimization of feature and screening are carried out, in concrete operations, road and background can be distinguished by selecting from 9 class textural characteristics
3 kinds of best features are average u, variance var and contrast cor respectively.
Step 4：Extract ratio feature
Textural characteristics cannot completely express the characteristics of road area in SAR image, and road edge is determined in order to extract
The accurate feature in position, the present invention extracts two kinds of ratio features point by point to the image after drop spot, i.e., between road and two side areas
Compare the similar ratio feature R2 between ratio feature R1 and both sides of the road region.Extraction step is as follows：
4a) extract 15 × 15 image block Q point by point to the image after drop spot；
The comparison ratio feature R1 of central pixel point 4b) is calculated in the center image block P of image block Q center extractions 7 × 7：
R1=min (max (u3/u1,u1/u3),max(u2/u1,u1/u2))
Wherein, u1Represent the average of pixel in region 1, u2Represent the average of pixel in region 2, u3It represents in region 3
The average of pixel.
With reference to Fig. 3, calculate the situation of 3 kinds of different roads width and retain maximum；According to the resolution ratio and reality of SAR image
The width of border road, road are usually exactly the width of 1-3 pixel in SAR image, and wherein Fig. 3 (a) represents road width
For the situation of 1 pixel, Fig. 3 (b) represents situation of the road width for 2 pixels, and Fig. 3 (c) represents that road width is 3
The situation of pixel, region 1 are the road assumed, and region 3 is the background area on the left of road, and region 2 is the back of the body on the right side of road
Scene area.The average ratio value between zoning 1 and region 3, region 1 and region 2 is distinguished in the present invention, i.e., maximum is first taken to take again
Minimum, this example are that the mutual ratios of 3 average of 1 average of region and region take maximum, 2 average of 1 average of region and region it is mutual
Ratio takes maximum；Then taken from above-mentioned maximum the two minimum to get to the comparison ratio feature of road area and background area；
Respectively calculate 3 kinds of roads width in the case of comparison ratio feature R1 value and be maximized, temporarily as in center image block P
The comparison ratio feature of imago vegetarian refreshments；
4c) 22.5 degree are rotated counterclockwise centered on central pixel point for image block Q, perform step 4b), obtain image
Block central pixel point corresponding comparison ratio feature R1 in the angle, in order to have found that closest to the direction of road, one
8 direction comparison ratio features have always been obtained in corotating 7 times；
4d) larger according to the contrast of road and two side areas, comparison ratio feature R1 values are bigger, and pixel is road
The characteristics of possibility of point is bigger, this example consider 8 directions altogether, compare 8 comparison ratio feature R1 and retain most
Big value, as the comparison ratio feature R1 of image block Q central pixel points, since center image block P is extracted from image block Q
Out, thus R1 be also center image block P central pixel points comparison ratio feature.It is special to retain comparison ratio in calculating process
Image block Q during R1 maximums is levied, using the direction of image block Q as closest to the direction of road.
4e) from step 4d) in retain image block Q in extraction 7 × 7 center image block P；
4f) calculate the similar ratio feature R2 of the central pixel point of image block P：
R2=max (u3/u2,u2/u3)
Wherein, u2Represent the average of pixel in region 2, u3Represent the average of pixel in region 3.
Similar ratio feature R2 represents the size of both sides of the road region similitude, and with reference to Fig. 3, Fig. 3 represents that road width is
The situation of 1-3 pixel the average ratio value in zoning 2 and region 3 and is taken big respectively in the present invention；3 kinds of roads are calculated respectively
Similar ratio feature R2 in the case of degree of having a lot of social connections retains minimum value, as the similar ratio feature of image block central point, the value of R2
Closer to 1, the central pixel point of image block P is bigger for the possibility of road waypoint.
Step 5：Construct dictionary.
To the image zooming-out average of input, variance, contrast, comparison ratio feature R1 and totally 5 kinds of similar ratio feature R2
Feature is normalized, and obtains a series of samples with 5 dimensional feature vectors, these samples are with markd, wherein one
Belong to the road area in image, another part belongs to the background area in image.Go out road word with these sample architectures
Allusion quotation D1With background dictionary D2；
Step 6：Preliminary detection.
Each pixel and road dictionary D are solved respectively1Difference E1With each pixel and background dictionary D2Difference
E2, according to the two differences E1And E2Classify to pixel, tentatively judge that pixel belongs to road area or background area
Domain.
The sample of input is solved and road dictionary D respectively by equation below1Difference E1With with background dictionary D2Difference
Value E2：
Wherein, x is the test sample of input,For road dictionary D1K-th of atom, p represents dictionary D1In atom
Number；For background dictionary D2L-th of atom, q represents dictionary D2In atom number；
Classify by comparing the size of two differences to the pixel of test sample, obtain the preliminary knot of Road Detection
Fruit：
If E1-E2＜ 0, represent test sample pixel and road area Atomic Correlations it is stronger, then be tentatively judged to picture
Vegetarian refreshments belongs to road area；
If E1-E2>=0, represent test sample pixel and background area Atomic Correlations it is stronger, then be tentatively judged to picture
Vegetarian refreshments belongs to background area；
The Preliminary detection that this step obtains is as shown in Figure 6.
Step 7：Result optimizing.
The general outline of road can be obtained by Preliminary detection, how real road is therefrom determined, and excludes void
Alert interference, is a very crucial step.According to the characteristics of road itself, i.e., road is leptosomatic the present invention, and profile is one
Closed curve, closer to slender type, area is smaller for the shape of this curve, the characteristics of more meeting road, former according to integration
Reason propose following area perimeter than optimization algorithm, effectively to exclude false-alarm region.
With reference to Fig. 2, the realization of this step is as follows：
A Preliminary detection result figure I to be optimized 7a) is inputted, referring to Fig. 6, size is m × n, with Preliminary detection knot
The center of fruit figure I is fixed point, and it is (m+2) × (n+2) that the size of image, which is expanded, will expand border out and be both configured to 0, i.e.,
For background, the image after expansion isInitialize the number S of the pixel in connected domain for road*=0 and the perimeter of connected domain
L*=0；
7b) to the image after expansionStart to scan from pixel (2,2), skip all boundary points, until running into
The pixel (x, y) that one pixel value is 1, makes S*=1, the pixel value of pixel (x, y) is set to 3；
It 7c) takes its 4 neighborhoods to pixel (x, y), i.e., in the window of the 3*3 put centered on (x, y), searches up and down
Pixel value is the number m of 0 point in 4 neighborhoods, uses L*The value update L of+m*；
Its 8 neighborhoods 7d) are taken to pixel (x, y), i.e., search 8 neighborhood of surrounding in the window of the 3*3 put centered on (x, y)
Interior pixel value is the number n of 1 point, uses S*The value update S of+n*, this n pixel value is changed to 3 from 1 one by one, and records these pictures
Position where vegetarian refreshments；
7e) to step 7d) in record n pixel, repeat step 7c one by one) and step 7d), until pixel
It can not find the point that pixel point value is 1 in (x, y) and its 8 neighborhoods, i.e., a connected domain traveled through one time, recorded in this connected domain
For the number S of the pixel of road*And the perimeter L of connected domain*If the length of side of pixel is set as 1, pixel number
S*It is equivalent to the area of road in connected domain；
Threshold T 7f) is set, with updated S*With updated L*It calculates road and approaches rateAgain by road
Rate is approached compared with threshold value：If road P*＞ T, then step 7d) inner recorded pixel value be 3 those points be all changed to
0, it is otherwise constant, reinitialize S*=0, L*=0；
The setting of threshold value is the value of a floating, is flexibly selected according to the requirement of detection, if the value setting of T is smaller,
It is also better to remove the effect of false-alarm, but the higher of omission factor meeting simultaneously, if the value setting of T is larger, the road of detection is relatively more
Add whole, but the removal effect of false-alarm is relatively poor, this example sets threshold T as 0.35；
7g) to the image after expansionStart to scan from pixel (x+1, y+1), repeat step 7b) arrive step 7f),
Until the last one point pixel (m, n) of Preliminary detection result images；The image after all expansionsMiddle pixel value is 3
Point value is changed to 1 again, and the border after expansion is removed, and just obtains after the optimization of image to be detected Road Detection as a result, such as Fig. 7.
The effect of the present invention can be further illustrated by following simulation result.
1. simulated conditions
The present invention is under the programmed environment of Visual Studio 2010 and combination MFC technologies carry out emulation experiment.
The size for being detected SAR image is that 329 × 329, resolution ratio is 4 meters, as shown in Figure 4.
2. emulation content
Emulation 1 carries out PPB drop spots with present invention SAR image shown in Fig. 4 and handles, as a result such as Fig. 5.It can be bright from Fig. 5
Aobvious to find out, the image after spot drops in the present invention becomes apparent from, and roadway characteristic is more obvious, this can be accurate to next step extraction
The feature for representing road is laid a good foundation；
Emulation 2 classifies to each pixel of image such as Fig. 5 after drop spot with the present invention, obtains Preliminary detection knot
Fruit is schemed, such as Fig. 6.In terms of Fig. 6 testing results, tentatively the general outline and trend of road are detected, but still deposited
By non-rice habitats point error detection into road waypoint the problem of, so taking being post-processed to Preliminary detection result for optimization algorithm
It is necessary；
The characteristics of emulation 3, the present invention combines road itself, i.e., road is all leptosomatic linear target, with area perimeter
The optimization algorithm of ratio optimizes Preliminary detection result figure as shown in Figure 6, with effectively remove isolated noise spot and
Block-like false-alarm region, as a result such as Fig. 7.Testing result from the result of Fig. 7 as can be seen that after optimization algorithm eliminates
Some noise spots of Preliminary detection result figure and block-like false-alarm region；
Fig. 7 is compared with the standard drawing of corresponding test image shown in Fig. 8, it can be seen that road inspection of the invention
It surveys result and the degree that is consistent of standard drawing is very high, show that the present invention has good Road Detection effect.
Claims (6)
1. a kind of SAR image Approach for road detection based on ratio feature, including：
(1) SAR image to be detected is read in, and drop spot pretreatment is carried out to SAR image；
(2) gray level co-occurrence matrixes are constructed point by point to the image after drop spot, and energy, entropy, comparison is calculated with gray level co-occurrence matrixes
Degree, average, variance, correlation, non-similarity, unfavourable balance away from 9 kinds of textural characteristics of uniformity；
(3) the 9 kinds of textural characteristics extracted above are optimized and screened according to Bhattacharyya range indexs, only chosen
Can be respectively effectively to the feature of 3 kinds of Road Detection in SAR image and classification contribution maximum：Average, variance and comparison
Degree；
(4) ratio feature is extracted：
(4a) extracts two kinds of ratio features, i.e., the comparison ratio feature between road and two side areas point by point to the image after drop spot
Similar ratio feature R2 between R1 and both sides of the road region；
3 kinds of textural characteristics of extraction in step (3) and step (4a) are extracted two kinds of ratio features and are normalized by (4b), are obtained
5 dimensional feature vectors of each pixel；
(5) pixel of part tape label is randomly choosed as sample, including road waypoint and non-rice habitats point, is gone out with the sample architecture
Road dictionary D1With background dictionary D2；
(6) Preliminary detection：
(6a) solves each pixel and road dictionary D respectively1Difference E1With each pixel and background dictionary D2Difference E2；
(6b) is according to the two differences E1And E2Classify to pixel：If E1-E2＜ 0, represent test sample pixel and
The Atomic Correlations of road area are stronger, then are tentatively judged to pixel and belong to road area；If E1-E2>=0, represent test sample
Pixel and background area Atomic Correlations it is stronger, then be tentatively judged to pixel and belong to background area；
(7) Preliminary detection that obtains for step (6) as a result, leptosomatic feature further according to road, with area perimeter than
Optimization algorithm excludes false-alarm region, obtains the final result of Road Detection.
2. according to the method described in claim 1, according to Bhattacharyya range indexs to step (2) wherein in step (3)
9 kinds of textural characteristics of extraction optimize screening, are to optimize screening to each by following range formula：
Wherein, BD represents Bhattacharyya range indexs, μ1、σ1First kind atural object on same texture template image is represented respectively
The average and variance of pixel value；μ2、σ2The average of the second class atural object pixel value and side on same texture template image are represented respectively
Difference.
3. according to the method described in claim 1, wherein calculating comparison ratio feature R1 in step (4), carry out as follows：
4a) extract 15 × 15 image block Q point by point to the image after drop spot；
4b) in the center image block P of image block Q center extractions 7 × 7, feelings of the road width for 1,2,3 pixel are calculated respectively
Condition obtains 3 comparison ratio features, and takes maximum therein, and temporarily the comparison ratio as image block P central pixel points is special
Sign；
22.5 degree 4c) are rotated counterclockwise centered on central pixel point to image block Q, return to step 4b), a corotating 7 times obtains
To 8 comparison ratio features；
Maximum 4d) is found out from 8 comparison ratio features, the comparison ratio feature R1 as image block P central pixel points：
R1=min (max (u3/u1,u1/u3),max(u2/u1,u1/u2)),
Wherein, u1Represent the average of pixel in region 1, u2Represent the average of pixel in region 2, u3Represent pixel in region 3
The average of point.
The image block Q in corresponding direction when retaining comparison ratio feature R1 maximums simultaneously, as closest to the direction of road.
4. according to the method described in claim 1, wherein calculating likelihood ratio value tag R2 in step (4), carry out as follows：
7 × 7 center image block P 4e) is extracted in the image block Q retained from step (4d)；
4f) calculate situation of the road width for 1,2,3 pixel respectively, obtain 3 similar ratio features, and take it is therein most
Small value, the similar ratio feature R2 as image block P central pixel points：
R2=max (u3/u2,u2/u3),
Wherein, u2Represent the average of pixel in region 2, u3Represent the average of pixel in region 3.
5. according to the method described in claim 1, wherein solve each pixel and road dictionary D1Difference E1With each pixel
Point and background dictionary D2Difference E2, carried out respectively with equation below：
Wherein, x is the test sample of input,For road dictionary D1K-th of atom, p represents dictionary D1In atom number；For background dictionary D2L-th of atom, q represents dictionary D2In atom number.
6. according to the method described in claim 1, wherein in step (7) with area perimeter than optimization algorithm exclude false-alarm area
Domain carries out as follows：
Preliminary detection result images I 7a) is inputted, size is m × n, using the center of Preliminary detection result images I as fixed point,
It is (m+2) × (n+2) that the size of image, which is expanded, will expand border out and be both configured to 0, as background, the image after expansion
ForInitialize the number S of the pixel in connected domain for road*=0 and the perimeter L of connected domain*=0；
7b) to image after expansionStart to scan from pixel (2,2), skip all boundary points, until running into first pixel
It is worth the pixel (x, y) for 1, makes S*=1, the pixel value of pixel (x, y) is set to 3；
Its 4 neighborhoods 7c) are taken to pixel (x, y), the number m for the point that pixel value in 4 neighborhoods is 0 is searched, uses L*The value update of+m
L*；
Its 8 neighborhoods 7d) are taken to pixel (x, y), the number n for the point that pixel value in 8 neighborhoods is 1 is searched, uses S*The value update of+n
S*, the pixel value of this n point is changed to 3 one by one, and records the position where these pixel values；
Step 7c 7e) is repeated to above-mentioned n point) and step 7d), it can not find until in pixel (x, y) and its 8 neighborhoods
Pixel value is 1 point, obtains the number S of the pixel in this connected domain for road*And the perimeter L of connected domain*；
Threshold T 7f) is set, with updated S*With updated L*It calculates road and approaches rateRoad is approached into rate again
Compared with threshold value：If road P*＞ T, then step 7d) inner recorded pixel value be 3 those points be all changed to 0, otherwise
It is constant, reinitialize S*=0, L*=0；
7g) to image after expansionStart to scan from pixel (x+1, y+1), repeat step 7b) arrive step 7f), Zhi Daochu
The last one pixel (m, n) of testing result image I is walked, image after all expansionsMiddle pixel value is the value weight of 3 point
1 newly is changed to, removes image after expansionBorder, obtain the final optimization pass result of Road Detection.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711415934.1A CN108109156B (en) | 2017-12-25 | 2017-12-25 | SAR image Approach for road detection based on ratio feature |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711415934.1A CN108109156B (en) | 2017-12-25 | 2017-12-25 | SAR image Approach for road detection based on ratio feature |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108109156A true CN108109156A (en) | 2018-06-01 |
| CN108109156B CN108109156B (en) | 2019-10-11 |
Family
ID=62212580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711415934.1A Active CN108109156B (en) | 2017-12-25 | 2017-12-25 | SAR image Approach for road detection based on ratio feature |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108109156B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188889A (en) * | 2019-04-28 | 2019-08-30 | 温州市兴海市政建设有限公司 | A kind of urban road surfaces maintenance management system based on preventative maintenance |
| CN117809052A (en) * | 2024-03-01 | 2024-04-02 | 海豚乐智科技(成都)有限责任公司 | Block target detection and feature extraction method, device and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101739667A (en) * | 2009-12-04 | 2010-06-16 | 西安电子科技大学 | Non-downsampling contourlet transformation-based method for enhancing remote sensing image road |
| CN101982835A (en) * | 2010-11-12 | 2011-03-02 | 西安电子科技大学 | Level set method for edge detection of SAR images of airport roads |
| CN102592114A (en) * | 2011-12-26 | 2012-07-18 | 河南工业大学 | Method for extracting and recognizing lane line features of complex road conditions |
| CN102915441A (en) * | 2012-08-30 | 2013-02-06 | 杭州电子科技大学 | Method for detecting unstructured road on basis of Haar texture |
| US8805118B2 (en) * | 2007-01-19 | 2014-08-12 | Google Inc. | Method for automatic alignment of raster data with vector data in a geographic information system |
| CN104331873A (en) * | 2013-07-22 | 2015-02-04 | 浙江大学 | Method for detecting road from single image |
| CN104392212A (en) * | 2014-11-14 | 2015-03-04 | 北京工业大学 | Method for detecting road information and identifying forward vehicles based on vision |
-
2017
- 2017-12-25 CN CN201711415934.1A patent/CN108109156B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8805118B2 (en) * | 2007-01-19 | 2014-08-12 | Google Inc. | Method for automatic alignment of raster data with vector data in a geographic information system |
| CN101739667A (en) * | 2009-12-04 | 2010-06-16 | 西安电子科技大学 | Non-downsampling contourlet transformation-based method for enhancing remote sensing image road |
| CN101982835A (en) * | 2010-11-12 | 2011-03-02 | 西安电子科技大学 | Level set method for edge detection of SAR images of airport roads |
| CN102592114A (en) * | 2011-12-26 | 2012-07-18 | 河南工业大学 | Method for extracting and recognizing lane line features of complex road conditions |
| CN102915441A (en) * | 2012-08-30 | 2013-02-06 | 杭州电子科技大学 | Method for detecting unstructured road on basis of Haar texture |
| CN104331873A (en) * | 2013-07-22 | 2015-02-04 | 浙江大学 | Method for detecting road from single image |
| CN104392212A (en) * | 2014-11-14 | 2015-03-04 | 北京工业大学 | Method for detecting road information and identifying forward vehicles based on vision |
Non-Patent Citations (3)
| Title |
|---|
| WUJALIN等: "Detection of roads in aerial images by using edge information", 《2012 5TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING》 * |
| 伏晨荣: "基于SAR图像的道路损毁信息提取技术研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》 * |
| 张玺锐: "基于SAR图像的道路损毁信息提取方法研究", 《中国优秀硕士学位论文全文数据库（电子期刊）》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188889A (en) * | 2019-04-28 | 2019-08-30 | 温州市兴海市政建设有限公司 | A kind of urban road surfaces maintenance management system based on preventative maintenance |
| CN117809052A (en) * | 2024-03-01 | 2024-04-02 | 海豚乐智科技(成都)有限责任公司 | Block target detection and feature extraction method, device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108109156B (en) | 2019-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210463B (en) | Precise ROI-fast R-CNN-based radar target image detection method | |
| Ao et al. | Detection and discrimination of ship targets in complex background from spaceborne ALOS-2 SAR images | |
| CN110378308B (en) | Improved port SAR image near-shore ship detection method based on fast R-CNN | |
| CN108596055B (en) | Airport target detection method of high-resolution remote sensing image under complex background | |
| CN112446327B (en) | Remote sensing image target detection method based on non-anchor frame | |
| Rani et al. | Road Identification Through Efficient Edge Segmentation Based on Morphological Operations. | |
| Lechner et al. | Remote sensing of small and linear features: Quantifying the effects of patch size and length, grid position and detectability on land cover mapping | |
| CN111476159B (en) | Method and device for training and detecting detection model based on double-angle regression | |
| CN112183432B (en) | Building area extraction method and system based on medium-resolution SAR image | |
| CN108830870B (en) | Satellite image high-precision farmland boundary extraction method based on multi-scale structure learning | |
| CN108898065B (en) | Deep network ship target detection method with candidate area rapid screening and scale self-adaption | |
| Tao et al. | Scene context-driven vehicle detection in high-resolution aerial images | |
| CN110929607A (en) | Remote sensing identification method and system for urban building construction progress | |
| CN109871875B (en) | Building change detection method based on deep learning | |
| CN111639587B (en) | Hyperspectral image classification method based on multi-scale spectrum space convolution neural network | |
| Yang et al. | Classified road detection from satellite images based on perceptual organization | |
| Chen et al. | Geospatial transformer is what you need for aircraft detection in SAR Imagery | |
| CN103761526A (en) | Urban area detecting method based on feature position optimization and integration | |
| CN106295498A (en) | Remote sensing image target area detection apparatus and method | |
| Liu et al. | 13 Population Estimation and Interpolation Using Remote Sensing | |
| CN114241332A (en) | Deep learning-based solid waste field identification method and device and storage medium | |
| CN108109156B (en) | SAR image Approach for road detection based on ratio feature | |
| CN108073940A (en) | A kind of method of 3D object instance object detections in unstructured moving grids | |
| Huang et al. | Superpixel-based change detection in high resolution sar images using region covariance features | |
| CN112348750B (en) | SAR image change detection method based on threshold fusion and neighborhood voting |
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 |