CN102855649A - Method for splicing high-definition image panorama of high-pressure rod tower on basis of ORB (Object Request Broker) feature point - Google Patents
Method for splicing high-definition image panorama of high-pressure rod tower on basis of ORB (Object Request Broker) feature point Download PDFInfo
- Publication number
- CN102855649A CN102855649A CN2012103038321A CN201210303832A CN102855649A CN 102855649 A CN102855649 A CN 102855649A CN 2012103038321 A CN2012103038321 A CN 2012103038321A CN 201210303832 A CN201210303832 A CN 201210303832A CN 102855649 A CN102855649 A CN 102855649A
- Authority
- CN
- China
- Prior art keywords
- image
- orb
- double points
- matching double
- matching
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 239000011159 matrix material Substances 0.000 claims abstract description 18
- 238000005070 sampling Methods 0.000 claims abstract description 14
- 238000000605 extraction Methods 0.000 claims description 17
- 230000009466 transformation Effects 0.000 claims description 16
- 238000001514 detection method Methods 0.000 claims description 14
- 239000000284 extract Substances 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012217 deletion Methods 0.000 claims description 3
- 230000037430 deletion Effects 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000005562 fading Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 238000012360 testing method Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000004744 fabric Substances 0.000 description 2
- 238000010010 raising Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 244000291564 Allium cepa Species 0.000 description 1
- 206010047571 Visual impairment Diseases 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000010931 gold Substances 0.000 description 1
- 229910052737 gold Inorganic materials 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a method for splicing a high-definition image panorama of a high-pressure rod tower on the basis of an ORB (Object Request Broker) feature point. The method comprises the following steps: 1) reading ultrahigh resolution high-pressure rod tower images of which the sizes are W*H, and sampling and reducing the to-be-spliced ultrahigh resolution images by utilizing a bilinear interpolation method, thereby obtaining a w*h image, wherein W, H, w and h are integers greater than 0 and k is the integer greater than 0; 2) utilizing an ORB algorithm to extract features of all the sampled images; 3) roughly matching the ORB features extracted in the step 2); 4) utilizing matching point pairs extracted in the previous step to extract the ORB features again in an image block in which the matching point pairs of an original ultrahigh resolution image are located, thereby finely matching; 5) calculating a transformational matrix H between adjacent images through the solved matching point pairs; and 6) utilizing a gradually fading method to fuse the adjacent ultrahigh resolution images. According to the method, the seamless splicing for the ultrahigh resolution images is realized, the time for splicing is reduced, the splicing efficiency is increased and the beneficial effect on the high-definition image is achieved.
Description
Technical field
The present invention relates to the clear image panorama joining method of a kind of high pressure stem tower height, relate in particular to the clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point.
Background technology
In recent years, the sustained and rapid development of Chinese national economy has proposed more and more higher requirement to China's power industry.Because China territory is vast, power transmission line corridor is with a varied topography, the limitation of Traditional Man walking operation pattern highlights day by day, adopt unmanned vehicle lift-launch digital imaging apparatus that overhead transmission line is carried out detailed-oriented patrolling and examining and become possibility, although existing digital imaging apparatus resolution has reached careful requirement of seeing the ultra-high-tension power transmission line gold utensil clearly, but because the imaging device visual field is less, the high-definition image that gathers can not comprise high pressure shaft tower armamentarium.
The Panorama Mosaic technology is having a wide range of applications aspect satellite remote sensing detection, meteorology, medical science, military affairs, Aero-Space, the protection of large tracts of land cultural heritage and the virtual scene realization.Overhead transmission line high pressure shaft tower has the characteristics of image of large format, adopts common digital imaging apparatus once to pan and the image of ultrahigh resolution.Utilize the Image Mosaics technology to address the above problem smoothly, successfully realize the synthetic of ultrahigh resolution high pressure shaft tower image.
The Panorama Mosaic technology can be spliced into multiple image that digital imaging apparatus gathers the larger panoramic picture in one width of cloth visual field, and the panoramic picture distortion that obtains at last is less, area-of-interest all centralized displaying on a Zhang Quanjing image.The Panorama Mosaic technology relates generally to feature point extraction, Feature Points Matching and image fusion technology three aspects:, and wherein the extraction effect of unique point directly affects the later image splicing effect.
At present, SIFT and SURF are popular Feature Points Extraction, although above-mentioned two kinds of Feature Points Extraction all have comparatively ripe the application at Image Mosaics and other aspect a lot.But during to the feature point extraction of high-definition picture, just have a large amount of time and be used for feature point extraction.
Summary of the invention
For solving the problem that occurs in the above-mentioned Image Mosaics, the present invention proposes the low and splicing effect of a kind of time complexity well based on the clear image panorama joining method of high pressure stem tower height of ORB unique point.The Feature Points Matching algorithm that it utilizes thick coupling to combine with exact matching has been realized the seamless spliced of ultrahigh resolution image, has reduced the splicing required time, has improved splicing efficient, particularly high-definition image is had good beneficial effect.
To achieve these goals, the present invention adopts following technical scheme:
The clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point, concrete steps are:
The first step: read ultrahigh resolution high pressure shaft tower image, and image sampled dwindle;
Second step: all the imagery exploitation ORB algorithms after sampling dwindled carry out feature extraction;
The 3rd step: the ORB feature of utilize extracting is carried out proximity matching, by the RASANC algorithm matching double points that obtains is screened, and obtains thick matching double points;
The 4th step: go on foot the thick matching double points coordinate of extraction utilizations in, calculate the respective coordinates in original ultrahigh resolution image, and in the image block at the matching double points place of original ultrahigh resolution image, again extract the ORB feature, carry out exact matching;
The 5th step: calculate the transformation matrix H between adjacent image;
The 6th step: utilize to be fade-in gradually to go out method the ultrahigh resolution adjacent image is merged, obtain the ultrahigh resolution panoramic picture, splicing finishes.
In the described first step, the sampling method of dwindling is: utilize bilinear interpolation that ultrahigh resolution image to be spliced is sampled and dwindle, original image is of a size of W * H, and the picture size that obtains is w * h, W wherein, and H, w, h are the integer greater than 0,
K is greater than 0 integer.
The concrete steps of the feature extraction in the described second step are:
(2-1) carry out Oriented FAST feature point detection:
(2-2) generate Rotated BRIEF Feature Descriptor;
Near unique point, choose at random some points right, the synthetic binary string of the size groups of the gray-scale value that these points are right, and with the Feature Descriptor of this binary string as this unique point.
The detailed process of described step (2-2) is:
A generates the BRIEF Feature Descriptor;
B generates Rotated BRIEF Feature Descriptor;
The direction vector that extracts in the Oriented FAST algorithm is joined in the BRIEF feature, be rotated, obtain oriented BRIEF, be referred to as Steered BRIEF; Have high variance and high incoherent steered brief with greedy learning algorithm screening, the result is referred to as rBRIEF; Calculate the distance of each SBRIEF and 0.5, and create container T; First SBRIEF is put into as a result container R, and from container T, remove; From container T, take out next SBRIEF, and and as a result among the container R all SBRIEF compare, if its correlativity less than certain threshold value, then adds as a result among the container R, otherwise abandon;
Repeating step b if be less than 256 SBRIEF among the container R as a result, then changes threshold value, and repeats above step until among the container R 256 SBRIEF are arranged as a result.
The concrete steps in described the 3rd step are as follows:
(3-1) select LSH as proximity matching point to calculating;
(3-2) utilize the RASANC algorithm that the thick matching double points that step (3-1) generates is screened, select and meet the requirements of the namely interior point of matching double points, deletion error matching double points
The detailed process of described step (3-2) is:
(a) some initialization in: in given matching double points, randomly draw 4 pairs of matching double points;
(b) calculate transformation matrix H by interior point;
(c) to remaining matching double points in the matching double points, calculate the distance of they and transformation matrix H, if the result is less than certain threshold value, then it is joined in the interior some set, and according to new interior some set, use least square method to upgrade transformation matrix H, otherwise continue to judge remaining matching double points;
(d) repeated execution of steps (c) is until interior some number no longer increases.
The concrete steps in described the 4th step are as follows:
(4-1) make M
lAnd M
rBe ultrahigh resolution original two adjacent images, m
1And m
rBe respectively two adjacent images after sampling is dwindled, the thick matching double points coordinate that the 3rd step calculated is respectively (x
Li, y
Li) and (x
Rj, y
Rj) 0≤i wherein, j≤n, n are required match point logarithm;
(4-2) respectively with (X
Li, Yy
Li) and (X
Rj, Y
Rj) centered by, the range image piece take γ as radius is respectively I
lAnd I
r, wherein:
(4-3) at image block I
l, I
rThe middle ORB feature of extracting respectively;
(4-4) obtain I
lAnd I
rMatching double points;
(4-5) to all matching double points, repeat above step, generate the matching double points of exact matching.
The concrete steps in described the 6th step are as follows:
(6-1) according to the transformation matrix H between image, corresponding image is carried out conversion, determine the coincidence zone between image;
(6-2) make I
lAnd I
rBe respectively two adjacent images, I is the image after merging:
I(x，y)＝(1-τ(k))×I
l(x，y)+τ(k)×I
r(x，y)+d (1)
Wherein 0≤d≤1 is the fine setting coefficient, and 0≤τ (k)≤1 is weighting function,
Wherein m is overlapping peak width, and k is leftmost pixel count from the overlapping region, and the overlapping region is larger like this, and τ (k) will be milder, so that can seamlessly transit between image.
Beneficial effect of the present invention:
1, utilizes ORB algorithm institute extract minutiae, in Image Mosaics is used, good effect is arranged, and its operation time is than fast two orders of magnitude of SIFT algorithm, than the fast order of magnitude of SURF algorithm;
2, by in falling the employing image, carrying out the ORB feature point extraction, solved the problem of the consuming time serious and low memory that unique point too much causes in the ultrahigh resolution image;
3, in ultrahigh resolution image, utilize the ORB algorithm in the image block of matching double points place, to carry out feature point extraction, and carry out exact matching, solved the error in the Image Mosaics after the sampling;
4, the method for utilizing thick coupling to combine with exact matching, had obvious minimizing its match time, and matching precision also has many raisings;
5, from whole ultrahigh resolution image splicing aspect, its splicing speed has had very large raising.
Description of drawings
Fig. 1 is algorithm flow chart of the present invention;
Fig. 2,3 is image before the splicing;
Fig. 4,5 is effect exploded view after the splicing.
Embodiment
The invention will be further described below in conjunction with accompanying drawing and embodiment.
As shown in Figure 1, method step of the present invention is as follows:
The first step, read ultrahigh resolution high pressure shaft tower image, be of a size of W * H, utilize bilinear interpolation that ultrahigh resolution image to be spliced is sampled and dwindle, obtain w * h image, W wherein, H, w, h are the integer greater than 0,
K is greater than 0 integer;
Second step, utilize the ORB algorithm to all the sampling after images carry out feature extraction:
The ORB feature has adopted Oriented FAST feature point detection operator and Rotated BRIEF Feature Descriptor.The ORB algorithm not only has the detection effect of SIFT feature, but also has the characteristic that rotation, yardstick convergent-divergent, brightness change the aspects such as unchangeability, the most important thing is that its time complexity has had greatly minimizing than SIFT, so that the ORB algorithm is having very large application prospect aspect high-definition image splicing and the real time video image splicing.
Specifically may further comprise the steps:
2-1) Oriented FAST feature point detection:
The present invention adds direction vector by on the basis of FAST feature point detection, makes it have directivity.
A) utilize FAST feature point detection algorithm fast detecting key point;
B) ask barycenter and the direction of key point place piece:
The extraction of piece barycenter is as follows:
m
pq＝∑
x，yx
py
qI(x，y) (1)
M wherein
PqBe the square of piece, p, q ∈ (0,1), x, y piece, C are required piece barycenter;
The extraction of piece direction:
θ＝atan2(m
01，m
10) （3）
The FAST key point of this belt transect direction just extracts.But the FAST feature point detection can not be processed multi-scale image, but original image can be done pyramid, then each figure is carried out above step, and Oriented FAST just supports multiple dimensioned the variation like this.
2-2) generate Rotated BRI EF Feature Descriptor
The main thought of BRIEF is chosen some points exactly at random near unique point right, the synthetic binary string of the size groups of the gray-scale value that these points are right, and with the Feature Descriptor of this binary string as this unique point.
Its advantage is that arithmetic speed is very fast.
A) generate the BRIEF Feature Descriptor:
A given width of cloth figure;
Image is carried out smoothing processing, reduce picture noise;
Select the region unit p of a SXS pixel at image, 5≤S≤15 wherein, extract the BRIEF feature at p:
Definition τ test, τ measuring and calculation formula is as follows:
X, y are two location of pixels in the p, namely x and y be shape such as the two-dimensional coordinate of [u, v], p (x) and p (y) are the brightness values of x and y pixel;
A BRIEF feature is exactly the binary string that several τ tests form, and specific [x, y] is right for structure, according to following formula, obtains the BRIEF feature
B) generate Rotated BRIEF Feature Descriptor:
The direction vector that extracts in the Oriented FAST algorithm is joined in the BRIEF feature, be rotated, obtain oriented BRIEF, be referred to as Steered BRIEF;
Have high variance and high incoherent steered brief with a kind of greedy learning algorithm screening, the result is referred to as rBRIEF, and algorithm is as follows:
Calculate the distance of each SBRIEF and 0.5, and create container T;
Wherein, greedy algorithm:
First SBRIEF is put into as a result container R, and from container T, remove;
From container T, take out next SBRIEF, and and as a result among the container R all SBRIEF compare, if its correlativity less than certain threshold value, then adds as a result among the container R, otherwise abandon;
Repeating step b) until among the container R 256 SBRIEF are arranged as a result,, then changes (becoming large) threshold value if be less than 256 SBRIEF among the container R as a result, and repeat above step;
The 3rd goes on foot, the ORB feature of extracting in the second step is slightly mated, and concrete steps are as follows:
3-1) the rBRIEF feature is the binary mode feature, selects Locality Sensitive Hashing(LSH) as proximity matching point to calculating;
The matching double points that 3-2) utilizes the RASANC algorithm that the upper step was generated screens:
RANSAC is the abbreviation of " RANdom SAmple Consensus(random sampling is consistent) ", is a kind of Robust estimation method, is proposed by Fischler and Bolles in 1981, and it can estimate from the data centralization of a large amount of exterior points high-precision parameter.Its basic thought is, when carrying out parameter estimation, designs a search engine, utilizes this search engine iteration to filter out the input data consistent with estimated parameter, then utilizes these data to carry out parameter estimation.
The present invention uses the RANSAC algorithm that all matching double points are screened, and selects the matching double points that reaches the parameter model requirement, namely in point, the deletion error matching double points, specific algorithm is as follows:
Interior some initialization: in given matching double points, randomly draw 4 pairs of matching double points;
Calculate transformation matrix H by interior point;
To remaining matching double points in the matching double points, calculate the distance of they and transformation matrix H, if the result is less than certain threshold value, then it is joined in the interior some set, and according to new interior some set, use least square method to upgrade transformation matrix H, otherwise continue to judge remaining matching double points;
Repeat previous step, until interior some number no longer increases.
The 4th the step, by above-mentioned three steps, can calculate the transformation matrix H between the rear adjacent image of sampling, and can carry out by certain fusion method the splicing of image, but the Current Transform matrix H is calculated in the image after sampling, if be directly used in the ultrahigh resolution original image, doubling of the image zone not necessarily can be very accurate after the splicing, has the error of sampling quantity rank pixel coordinate.The present invention utilizes the matching double points that the step extracts, and again extracts the ORB feature in the image block at the matching double points place of original ultrahigh resolution image, carries out exact matching again, has solved the problem that occurs above.Concrete steps are as follows:
4-1) make M
lAnd M
rBe ultrahigh resolution original two adjacent images, m
lAnd m
rBe respectively two adjacent images after sampling is dwindled, the matching double points coordinate that the 3rd step calculated is respectively (x
Li, y
Li) and (x
Rj, y
Rj), 0≤i wherein, j≤n, n are required match point logarithm;
4-2) respectively with (X
Li, Yy
Li) and (X
Rj, Y
Rj) centered by, the range image piece take γ as radius is respectively I
lAnd I
r, γ is the integer of any 9≤γ≤100 scopes here, wherein:
4-3) at image block I
l, I
rThe middle ORB feature of extracting respectively;
4-4) obtain I
lAnd I
rMatching double points;
4-5) to all matching double points, repeat above step, generate the matching double points of exact matching.
The 5th goes on foot, passes through top required matching double points, calculates the transformation matrix H between adjacent image;
The 6th step, utilize to be fade-in and gradually go out method the ultrahigh resolution adjacent image is merged, concrete steps are as follows:
6-1) according to the transformation matrix H between image, can carry out conversion to corresponding image, determine the coincidence zone between image;
6-2) make I
lAnd I
rBe respectively two adjacent images, I is the image after merging:
I(x，y)＝(1-τ(k))×I
l(x，y)+τ(k)×I
r(x，y)+d (1)
Wherein 0≤d≤1 is the fine setting coefficient, and 0≤τ (k)≤1 is weighting function,
Wherein m is overlapping peak width, and k is leftmost pixel count from the overlapping region, and the overlapping region is larger like this, and τ (k) will be milder, so that can seamlessly transit between image.
In order to check the beneficial effect of the present invention in ultrahigh resolution, in experiment, the present invention carries out the splicing effect test to 5 groups of ultrahigh resolution high pressure shaft tower images, and experiment condition is as follows: CPU is Intel Core i32.27GHz, the 2G internal memory.To be ORB compare at time complexity with popular now feature point detecting method table 1, used picture size size is 5184X3456, as can be seen from Table 1, ORB feature point detection algorithm time complexity obviously is better than SURF and SIFT feature detection algorithm, than the fast nearly order of magnitude of SURF, than SIFT fast nearly two orders of magnitude; Table 2 is directly to utilize the ORB algorithm to splice and the first comparison of piecemeal stitching algorithm on time complexity of thick rear essence on original ultrahigh resolution image, as can be seen from the table, joining method of the present invention is than the method for directly utilizing the ORB algorithm to splice on original ultrahigh resolution image fast nearly 150%.In conjunction with above two experimental results, the present invention has not only improved detection efficiency at the unique point examination phase, and greatly reduce time complexity, and aspect the integral body splicing, the present invention utilizes the first block image joining method of thick rear essence, equally greatly reduce the time complexity of splicing, for the splicing of ultrahigh resolution image improves splicing efficient greatly.
Each feature point detection algorithm contrast detection time of table 1.
Table 2. direct splicing and the contrast of piecemeal splicing time
Although above-mentionedly by reference to the accompanying drawings the specific embodiment of the present invention is described; but be not limiting the scope of the invention; one of ordinary skill in the art should be understood that; on the basis of technical scheme of the present invention, those skilled in the art do not need to pay various modifications that creative work can make or distortion still in protection scope of the present invention.
Claims (8)
1. the clear image panorama joining method of the high pressure stem tower height based on the ORB unique point is characterized in that, concrete steps are:
The first step: read ultrahigh resolution high pressure shaft tower image, and image sampled dwindle;
Second step: all the imagery exploitation ORB algorithms after sampling dwindled carry out feature extraction;
The 3rd step: the ORB feature of utilize extracting is carried out proximity matching, by the RASANC algorithm matching double points that obtains is screened, and obtains thick matching double points;
The 4th step: go on foot the thick matching double points coordinate of extraction utilizations in, calculate the respective coordinates in original ultrahigh resolution image, and in the image block at the matching double points place of original ultrahigh resolution image, again extract the ORB feature, carry out exact matching;
The 5th step: calculate the transformation matrix H between adjacent image;
The 6th step: utilize to be fade-in gradually to go out method the ultrahigh resolution adjacent image is merged, obtain the ultrahigh resolution panoramic picture, splicing finishes.
2. the clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point as claimed in claim 1, it is characterized in that, in the described first step, the method that sampling is dwindled is: utilize bilinear interpolation that ultrahigh resolution image to be spliced is sampled and dwindle, original image is of a size of W * H, the picture size that obtains is w * h, W wherein, H, w, h is the integer greater than 0
K is greater than 0 integer.
3. the clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point as claimed in claim 1 is characterized in that, the concrete steps of the feature extraction in the described second step are:
(2-1) carry out Oriented FAST feature point detection:
(2-2) generate Rotated BRIEF Feature Descriptor;
Near unique point, choose at random some points right, the synthetic binary string of the size groups of the gray-scale value that these points are right, and with the Feature Descriptor of this binary string as this unique point.
4. the clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point as claimed in claim 3 is characterized in that, the detailed process of described step (2-2) is:
A generates BRI EF Feature Descriptor;
B generates Rotated BRIEF Feature Descriptor;
The direction vector that extracts in the Oriented FAST algorithm is joined in the BRIEF feature, be rotated, obtain oriented BRIEF, be referred to as Steered BRIEF; Have high variance and high incoherent steered brief with greedy learning algorithm screening, the result is referred to as rBRIEF; Calculate the distance of each SBRIEF and 0.5, and create container T; First SBRIEF is put into as a result container R, and from container T, remove; From container T, take out next SBRIEF, and and as a result among the container R all SBRIEF compare, if its correlativity less than certain threshold value, then adds as a result among the container R, otherwise abandon;
Repeating step b if be less than 256 SBRIEF among the container R as a result, then changes threshold value, and repeats above step until among the container R 256 SBRIEF are arranged as a result.
5. the clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point as claimed in claim 1 is characterized in that, the concrete steps in described the 3rd step are as follows:
(3-1) select LSH as proximity matching point to calculating;
(3-2) utilize the RASANC algorithm that the matching double points that step (3-1) generates is screened, select and meet the requirements of the namely interior point of matching double points, deletion error matching double points.
6. the clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point as claimed in claim 5 is characterized in that, the detailed process of described step (3-2) is:
(a) some initialization in: in given matching double points, randomly draw 4 pairs of matching double points;
(b) calculate transformation matrix H by interior point;
(c) to remaining matching double points in the matching double points, calculate the distance of they and transformation matrix H, if the result is less than certain threshold value, then it is joined in the interior some set, and according to new interior some set, use least square method to upgrade transformation matrix H, otherwise continue to judge remaining matching double points;
(d) repeated execution of steps (c) is until interior some number no longer increases.
7. the clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point as claimed in claim 1 is characterized in that, the concrete steps in described the 4th step are as follows:
(4-1) make M
lAnd M
rBe ultrahigh resolution original two adjacent images, m
lAnd m
rBe respectively two adjacent images after sampling is dwindled, the thick matching double points coordinate that the 3rd step calculated is respectively (x
Li, y
Li) and (x
Rj, y
Rj) 0≤i wherein, j≤n, n are required match point logarithm;
(4-2) respectively with (X
Li, Yy
Li) and (X
Rj, Y
Rj) centered by, the range image piece take γ as radius is respectively I
lAnd I
r, wherein:
(4-3) at image block I
l, I
rThe middle ORB feature of extracting respectively;
(4-4) obtain I
lAnd I
rMatching double points;
(4-5) to all matching double points, repeat above step, generate the matching double points of exact matching.
8. the clear image panorama joining method of a kind of high pressure stem tower height based on the ORB unique point as claimed in claim 1 is characterized in that, the concrete steps in described the 6th step are as follows:
(6-1) according to the transformation matrix H between image, corresponding image is carried out conversion, determine the coincidence zone between image;
(6-2) make I
lAnd I
rBe respectively two adjacent images, I is the image after merging:
I(x，y)＝(1-τ(k))×I
l(x，y)+τ(k)×I
r(x，y)+d (1)
Wherein 0≤d≤1 is the fine setting coefficient, and 0≤τ (k)≤1 is weighting function,
Wherein m is overlapping peak width, and k is leftmost pixel count from the overlapping region, and the overlapping region is larger like this, and τ (k) will be milder, so that can seamlessly transit between image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210303832.1A CN102855649B (en) | 2012-08-23 | 2012-08-23 | Method for splicing high-definition image panorama of high-pressure rod tower on basis of ORB (Object Request Broker) feature point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210303832.1A CN102855649B (en) | 2012-08-23 | 2012-08-23 | Method for splicing high-definition image panorama of high-pressure rod tower on basis of ORB (Object Request Broker) feature point |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102855649A true CN102855649A (en) | 2013-01-02 |
| CN102855649B CN102855649B (en) | 2015-07-15 |
Family
ID=47402210
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210303832.1A Active CN102855649B (en) | 2012-08-23 | 2012-08-23 | Method for splicing high-definition image panorama of high-pressure rod tower on basis of ORB (Object Request Broker) feature point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102855649B (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236050A (en) * | 2013-05-06 | 2013-08-07 | 电子科技大学 | Auxiliary bank note and worn coin reestablishing method based on graph clustering |
| CN103336963A (en) * | 2013-07-08 | 2013-10-02 | 天脉聚源(北京)传媒科技有限公司 | Method and device for image feature extraction |
| CN103700069A (en) * | 2013-12-11 | 2014-04-02 | 武汉工程大学 | ORB (object request broker) operator-based reference-free video smoothness evaluation method |
| CN103761721A (en) * | 2013-12-30 | 2014-04-30 | 西北工业大学 | Stereoscopic vision fast image stitching method suitable for space tether-robot |
| CN104200487A (en) * | 2014-08-01 | 2014-12-10 | 广州中大数字家庭工程技术研究中心有限公司 | Target tracking method based on ORB characteristics point matching |
| CN104462820A (en) * | 2014-12-10 | 2015-03-25 | 广东电网有限责任公司电力科学研究院 | Method for detecting errors of coordinates of towers of power grids |
| CN104881841A (en) * | 2015-05-20 | 2015-09-02 | 南方电网科学研究院有限责任公司 | Aerial high voltage electric tower image splicing method based on edge characteristics and point characteristics |
| CN105007397A (en) * | 2015-04-30 | 2015-10-28 | 南方电网科学研究院有限责任公司 | Video compensation method of eliminating line segment cross mismatching point |
| CN105223957A (en) * | 2015-09-24 | 2016-01-06 | 北京零零无限科技有限公司 | A kind of method and apparatus of gesture manipulation unmanned plane |
| CN103700069B (en) * | 2013-12-11 | 2016-11-30 | 武汉工程大学 | A kind of evaluation methodology of smoothness without reference video based on ORB operator |
| CN106657816A (en) * | 2016-11-07 | 2017-05-10 | 湖南源信光电科技有限公司 | ORB algorithm based multipath rapid video splicing algorithm with image registering and image fusion in parallel |
| CN106909877A (en) * | 2016-12-13 | 2017-06-30 | 浙江大学 | A kind of vision based on dotted line comprehensive characteristics builds figure and localization method simultaneously |
| CN107580175A (en) * | 2017-07-26 | 2018-01-12 | 济南中维世纪科技有限公司 | A kind of method of single-lens panoramic mosaic |
| CN107656613A (en) * | 2017-09-08 | 2018-02-02 | 国网山东省电力公司电力科学研究院 | A kind of man-machine interactive system and its method of work based on the dynamic tracking of eye |
| CN107703956A (en) * | 2017-09-28 | 2018-02-16 | 山东鲁能智能技术有限公司 | A kind of virtual interaction system and its method of work based on inertia capturing technology |
| CN107886100A (en) * | 2017-12-04 | 2018-04-06 | 西安思源学院 | A kind of BRIEF Feature Descriptors based on order array |
| CN108455228A (en) * | 2017-12-29 | 2018-08-28 | 长春师范大学 | The automatic Load System of tire |
| CN109064385A (en) * | 2018-06-20 | 2018-12-21 | 何中 | 360 degree of panorama bandwagon effect Core Generators and delivery system |
| CN109376773A (en) * | 2018-09-30 | 2019-02-22 | 福州大学 | Crack detecting method based on deep learning |
| CN109961078A (en) * | 2017-12-22 | 2019-07-02 | 展讯通信（上海）有限公司 | Images match and joining method, device, system, readable medium |
| CN110866863A (en) * | 2018-08-27 | 2020-03-06 | 天津理工大学 | Automobile A-pillar perspective algorithm |
| CN110986889A (en) * | 2019-12-24 | 2020-04-10 | 国网河南省电力公司检修公司 | High-voltage substation panoramic monitoring method based on remote sensing image technology |
| CN111869198A (en) * | 2018-03-15 | 2020-10-30 | 株式会社村上开明堂 | Synthetic image creation device, synthetic image creation method, and synthetic image creation program |
| CN113673283A (en) * | 2020-05-14 | 2021-11-19 | 惟亚(上海)数字科技有限公司 | Smooth tracking method based on augmented reality |
| CN113724177A (en) * | 2021-09-07 | 2021-11-30 | 北京大学深圳医院 | Pulmonary nodule information fusion method, device, equipment and storage medium thereof |
| CN114373153A (en) * | 2022-01-12 | 2022-04-19 | 北京拙河科技有限公司 | Video imaging optimization system and method based on multi-scale array camera |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1901228A1 (en) * | 2005-06-08 | 2008-03-19 | Fujitsu Ltd. | Image processor |
| CN101345843A (en) * | 2008-08-28 | 2009-01-14 | 中兴通讯股份有限公司 | Method and system for implementing full view video of visible mobile terminal |
| CN101877140A (en) * | 2009-12-18 | 2010-11-03 | 北京邮电大学 | Panorama-based panoramic virtual tour method |
-
2012
- 2012-08-23 CN CN201210303832.1A patent/CN102855649B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1901228A1 (en) * | 2005-06-08 | 2008-03-19 | Fujitsu Ltd. | Image processor |
| CN101345843A (en) * | 2008-08-28 | 2009-01-14 | 中兴通讯股份有限公司 | Method and system for implementing full view video of visible mobile terminal |
| CN101877140A (en) * | 2009-12-18 | 2010-11-03 | 北京邮电大学 | Panorama-based panoramic virtual tour method |
Non-Patent Citations (2)
| Title |
|---|
| ETHAN RUBLEE等: "Orb: an efficient alternative to sift or surf", 《COMPUTER VISION-ICCV》 * |
| 杨红喆: "基于特征点的全景图生成技术的研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103236050A (en) * | 2013-05-06 | 2013-08-07 | 电子科技大学 | Auxiliary bank note and worn coin reestablishing method based on graph clustering |
| CN103236050B (en) * | 2013-05-06 | 2015-08-12 | 电子科技大学 | A kind of auxiliary bank note worn coin method for reconstructing based on figure cluster |
| CN103336963A (en) * | 2013-07-08 | 2013-10-02 | 天脉聚源(北京)传媒科技有限公司 | Method and device for image feature extraction |
| CN103700069A (en) * | 2013-12-11 | 2014-04-02 | 武汉工程大学 | ORB (object request broker) operator-based reference-free video smoothness evaluation method |
| CN103700069B (en) * | 2013-12-11 | 2016-11-30 | 武汉工程大学 | A kind of evaluation methodology of smoothness without reference video based on ORB operator |
| CN103761721B (en) * | 2013-12-30 | 2016-10-05 | 西北工业大学 | One is applicable to space rope system machine human stereo vision fast image splicing method |
| CN103761721A (en) * | 2013-12-30 | 2014-04-30 | 西北工业大学 | Stereoscopic vision fast image stitching method suitable for space tether-robot |
| CN104200487A (en) * | 2014-08-01 | 2014-12-10 | 广州中大数字家庭工程技术研究中心有限公司 | Target tracking method based on ORB characteristics point matching |
| CN104462820A (en) * | 2014-12-10 | 2015-03-25 | 广东电网有限责任公司电力科学研究院 | Method for detecting errors of coordinates of towers of power grids |
| CN104462820B (en) * | 2014-12-10 | 2017-10-27 | 广东电网有限责任公司电力科学研究院 | A kind of method of power network shaft tower coordinate error detection |
| CN105007397B (en) * | 2015-04-30 | 2018-06-19 | 南方电网科学研究院有限责任公司 | A kind of video comfort method eliminated line segment and intersect Mismatching point |
| CN105007397A (en) * | 2015-04-30 | 2015-10-28 | 南方电网科学研究院有限责任公司 | Video compensation method of eliminating line segment cross mismatching point |
| CN104881841A (en) * | 2015-05-20 | 2015-09-02 | 南方电网科学研究院有限责任公司 | Aerial high voltage electric tower image splicing method based on edge characteristics and point characteristics |
| CN104881841B (en) * | 2015-05-20 | 2019-01-04 | 南方电网科学研究院有限责任公司 | High-tension electricity pylon image split-joint method of taking photo by plane based on edge feature and point feature |
| CN105223957A (en) * | 2015-09-24 | 2016-01-06 | 北京零零无限科技有限公司 | A kind of method and apparatus of gesture manipulation unmanned plane |
| US10261507B2 (en) | 2015-09-24 | 2019-04-16 | Beijing Zero Zero Infinity Technology Co., Ltd | Method and device for controlling unmanned aerial vehicle with gesture |
| CN106657816A (en) * | 2016-11-07 | 2017-05-10 | 湖南源信光电科技有限公司 | ORB algorithm based multipath rapid video splicing algorithm with image registering and image fusion in parallel |
| CN106909877A (en) * | 2016-12-13 | 2017-06-30 | 浙江大学 | A kind of vision based on dotted line comprehensive characteristics builds figure and localization method simultaneously |
| CN106909877B (en) * | 2016-12-13 | 2020-04-14 | 浙江大学 | Visual simultaneous mapping and positioning method based on dotted line comprehensive characteristics |
| CN107580175A (en) * | 2017-07-26 | 2018-01-12 | 济南中维世纪科技有限公司 | A kind of method of single-lens panoramic mosaic |
| CN107656613B (en) * | 2017-09-08 | 2020-12-18 | 国网智能科技股份有限公司 | Human-computer interaction system based on eye movement tracking and working method thereof |
| CN107656613A (en) * | 2017-09-08 | 2018-02-02 | 国网山东省电力公司电力科学研究院 | A kind of man-machine interactive system and its method of work based on the dynamic tracking of eye |
| CN107703956A (en) * | 2017-09-28 | 2018-02-16 | 山东鲁能智能技术有限公司 | A kind of virtual interaction system and its method of work based on inertia capturing technology |
| CN107886100B (en) * | 2017-12-04 | 2020-10-30 | 西安思源学院 | BRIEF feature descriptor based on rank array |
| CN107886100A (en) * | 2017-12-04 | 2018-04-06 | 西安思源学院 | A kind of BRIEF Feature Descriptors based on order array |
| CN109961078A (en) * | 2017-12-22 | 2019-07-02 | 展讯通信（上海）有限公司 | Images match and joining method, device, system, readable medium |
| CN110490271A (en) * | 2017-12-22 | 2019-11-22 | 展讯通信（上海）有限公司 | Images match and joining method, device, system, readable medium |
| CN110490271B (en) * | 2017-12-22 | 2021-09-21 | 展讯通信（上海）有限公司 | Image matching and splicing method, device, system and readable medium |
| CN108455228A (en) * | 2017-12-29 | 2018-08-28 | 长春师范大学 | The automatic Load System of tire |
| CN108455228B (en) * | 2017-12-29 | 2023-07-28 | 长春师范大学 | Automatic tire loading system |
| CN111869198B (en) * | 2018-03-15 | 2021-12-14 | 株式会社村上开明堂 | Synthetic image creating device, synthetic image creating method, and recording medium |
| CN111869198A (en) * | 2018-03-15 | 2020-10-30 | 株式会社村上开明堂 | Synthetic image creation device, synthetic image creation method, and synthetic image creation program |
| CN109064385A (en) * | 2018-06-20 | 2018-12-21 | 何中 | 360 degree of panorama bandwagon effect Core Generators and delivery system |
| CN110866863A (en) * | 2018-08-27 | 2020-03-06 | 天津理工大学 | Automobile A-pillar perspective algorithm |
| CN109376773A (en) * | 2018-09-30 | 2019-02-22 | 福州大学 | Crack detecting method based on deep learning |
| CN110986889A (en) * | 2019-12-24 | 2020-04-10 | 国网河南省电力公司检修公司 | High-voltage substation panoramic monitoring method based on remote sensing image technology |
| CN113673283A (en) * | 2020-05-14 | 2021-11-19 | 惟亚(上海)数字科技有限公司 | Smooth tracking method based on augmented reality |
| CN113724177A (en) * | 2021-09-07 | 2021-11-30 | 北京大学深圳医院 | Pulmonary nodule information fusion method, device, equipment and storage medium thereof |
| CN113724177B (en) * | 2021-09-07 | 2023-12-15 | 北京大学深圳医院 | Lung nodule information fusion method, device, equipment and storage medium thereof |
| CN114373153A (en) * | 2022-01-12 | 2022-04-19 | 北京拙河科技有限公司 | Video imaging optimization system and method based on multi-scale array camera |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102855649B (en) | 2015-07-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102855649B (en) | Method for splicing high-definition image panorama of high-pressure rod tower on basis of ORB (Object Request Broker) feature point | |
| CN104200461B (en) | The remote sensing image registration method of block and sift features is selected based on mutual information image | |
| CN103279939B (en) | A kind of image mosaic disposal system | |
| Juan et al. | SURF applied in panorama image stitching | |
| CN111080529A (en) | Unmanned aerial vehicle aerial image splicing method for enhancing robustness | |
| KR101470112B1 (en) | Daisy descriptor generation from precomputed scale - space | |
| US10621446B2 (en) | Handling perspective magnification in optical flow processing | |
| Trulls et al. | Dense segmentation-aware descriptors | |
| CN104134200B (en) | Mobile scene image splicing method based on improved weighted fusion | |
| CN103034982B (en) | Image super-resolution rebuilding method based on variable focal length video sequence | |
| CN107851196B (en) | Image pattern matching method and device | |
| CN104809731B (en) | A kind of rotation Scale invariant scene matching method based on gradient binaryzation | |
| CN106991695A (en) | A kind of method for registering images and device | |
| CN105761233A (en) | FPGA-based real-time panoramic image mosaic method | |
| CN105100640A (en) | Local registration parallel video stitching method and local registration parallel video stitching system | |
| Cai et al. | Guided attention network for object detection and counting on drones | |
| Wu et al. | Remote sensing image super-resolution via saliency-guided feedback GANs | |
| CN107516322A (en) | A kind of image object size based on logarithm pole space and rotation estimation computational methods | |
| CN105631872A (en) | Remote sensing image registration method based on multiple feature points | |
| CN103093226B (en) | A kind of building method of the RATMIC descriptor for characteristics of image process | |
| Du et al. | GPU based parallel optimization for real time panoramic video stitching | |
| Zhang et al. | Real-Time object detection for 360-degree panoramic image using CNN | |
| Tao et al. | F-pvnet: Frustum-level 3-d object detection on point–voxel feature representation for autonomous driving | |
| Dehnavi et al. | Cost and power efficient FPGA based stereo vision system using directional graph transform | |
| CN105894494A (en) | Three-line-array stereo aerial survey camera parallel spectrum band registration method based on GPU technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 250002, No. 1, South Second Ring Road, Shizhong District, Shandong, Ji'nan Co-patentee after: State Grid Corporation of China Patentee after: Electric Power Research Institute of State Grid Shandong Electric Power Company Address before: 250002, No. 1, South Second Ring Road, Shizhong District, Shandong, Ji'nan Co-patentee before: State Grid Corporation of China Patentee before: Electric Power Research Institute of Shandong Electric Power Corporation |
|
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20130102 Assignee: National Network Intelligent Technology Co., Ltd. Assignor: Electric Power Research Institute of State Grid Shandong Electric Power Company Contract record no.: X2019370000006 Denomination of invention: Method for splicing high-definition image panorama of high-pressure rod tower on basis of ORB (Object Request Broker) feature point Granted publication date: 20150715 License type: Exclusive License Record date: 20191014 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201029 Address after: 250101 Electric Power Intelligent Robot Production Project 101 in Jinan City, Shandong Province, South of Feiyue Avenue and East of No. 26 Road (ICT Industrial Park) Patentee after: National Network Intelligent Technology Co.,Ltd. Address before: 250002, No. 1, South Second Ring Road, Shizhong District, Shandong, Ji'nan Patentee before: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Patentee before: STATE GRID CORPORATION OF CHINA |
|
| TR01 | Transfer of patent right | ||
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: National Network Intelligent Technology Co.,Ltd. Assignor: ELECTRIC POWER RESEARCH INSTITUTE OF STATE GRID SHANDONG ELECTRIC POWER Co. Contract record no.: X2019370000006 Date of cancellation: 20210324 |
|
| EC01 | Cancellation of recordation of patent licensing contract |