CN105069461B - Based on image characteristic point collinearly with the insulator chain automatic positioning method of iso-distance constraint - Google Patents
Based on image characteristic point collinearly with the insulator chain automatic positioning method of iso-distance constraint Download PDFInfo
- Publication number
- CN105069461B CN105069461B CN201510443073.2A CN201510443073A CN105069461B CN 105069461 B CN105069461 B CN 105069461B CN 201510443073 A CN201510443073 A CN 201510443073A CN 105069461 B CN105069461 B CN 105069461B
- Authority
- CN
- China
- Prior art keywords
- insulator chain
- image
- conllinear
- point
- curvature
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses it is a kind of based on image characteristic point collinearly with the insulator chain automatic positioning method of iso-distance constraint, including the extraction of image preprocessing, curvature scale space angle point grid, conllinear equidistant points, hierarchical clustering and insulator chain positioning step.The present invention is simple, practical, utilize the conllinear and iso-distance constraint of insulator chain curvature scale space angle point, it can realize the automatic positioning of the insulator chain of arbitrary major axes orientation in complicated, noisy, low resolution Aerial Images, and it takes few, to partial occlusion and fall string with robustness, solves the problems, such as that current insulator chain positioning method accuracy is low, accidentally positioning and computation complexity are high.
Description
Technical field
Overhaul field the invention belongs to power transmission and transforming equipment operating status, more particularly to it is a kind of based on image characteristic point collinearly with
The insulator chain automatic positioning method of iso-distance constraint.
Background technology
Insulator is element indispensable in transmission line of electricity, has the functions such as mechanical support and electric insulation.Once absolutely
Edge is damaged, and just loses its useful effect, causes irremediable massive losses.Therefore, insulator is examined in time
Survey is necessary.And from be automatically positioned out in Aerial Images insulator chain be realize its state-detection and fault diagnosis it is important before
It carries.Insulator chain automatic positioning method of taking photo by plane at present can be generally divided into 4 classes：(1) method based on segmentation, by original image point
For multiple regions, and mark interested region；(2) method based on edge detection finds the profile of interesting target, realizes
Positioning；(3) method based on texture analyzes the textural characteristics of interesting target, and extracts target location as criterion
Come；(4) it is based on matched method, the feature for extracting template and test image is matched, the region in indicia matched.
Method positioning accuracy based on segmentation is low, and cannot correctly handle image similar in gray feature, is not suitable for multiple
Miscellaneous, noisy, low resolution Aerial Images.Based on the method at edge to noise-sensitive, the similar puppet in edge can not be correctly handled
Target, and background is complicated, the numerous images of edge variation can alleviative method significantly the speed of service.Method based on texture calculates
Complexity is high, can not solve insulator chain and background texture difference it is little when insulator chain orientation problem, and for certain
It is difficult to differentiate between with pseudo- target similar in insulator chain textural characteristics.There is strong dependency to template based on matched method, and big
The template of amount can substantially reduce the feature extracting and matching speed of template and test image.
In complicated, noisy, low resolution Aerial Images, that there are precision is low for existing insulator chain localization method, accidentally
The limitations such as positioning, computation complexity height, and do not account for shape feature of the insulator chain in bianry image.Insulator chain with
The targets such as shaft tower, circuit have obvious shape difference in bianry image.
Invention content
The technical problem to be solved by the present invention is to：It provides a kind of collinearly exhausted with taking photo by plane for iso-distance constraint based on image characteristic point
Edge substring automatic positioning method.
The technical solution used in the present invention is：
It is a kind of based on image characteristic point collinearly with the insulator chain automatic positioning method of taking photo by plane of iso-distance constraint, including following step
Suddenly：
Step a：Image preprocessing：Image comprising the insulator chain of taking photo by plane is pre-processed, obtains filtering out noise
The smooth bianry image of back edge；
Step b：Curvature scale space angle point grid：The edge image for extracting the bianry image, from the edge image
Middle extraction contour curve；In the lower curvature for calculating each pixel on the contour curve in scale σ=3, local curvature's maximum point
As candidate angular；If the curvature value of the candidate angular is more than preset curvature threshold value, and is more than its neighborhood local minimum
2 times when, then be correct angle point；In artwork, curvature scale space angle point corresponding with the correct angle point is accurately positioned.
Step c：Conllinear equidistant points extraction：Select any two described in curvature scale space angle point, using collinearly with etc.
It is found thirdly away from constraint, if in the presence of being all thirdly curvature scale space angle point, judges that be conllinear equidistant points at 3 points.
Step d：Hierarchical clustering：Hierarchical clustering is carried out to the directions of all conllinear equidistant points so that conllinear etc. in per class
It is less than preset direction threshold value away from direction change, selects the maximum a kind of conllinear equidistant point set as insulator chain of quantity.
Step e：Insulator chain positions：The conllinear equidistant point set of the insulator chain is marked with minimum enclosed rectangle, to
It takes photo by plane described in realization the automatic positioning of insulator chain.
It is as follows in the step a：
Step a-1：Binary conversion treatment is carried out to the image comprising the insulator chain of taking photo by plane, obtains insulator chain binary map
Picture；
Step a-2：Morphological erosion and expansion are carried out to the insulator chain bianry image, obtain filtered insulator
String bianry image；
Step a-3：Filter out the cell that area in the filtered insulator chain bianry image is less than preset area threshold value
Domain obtains pre-processed results image.
It is as follows in the step b：
Step b-1：The edges canny in the pre-processed results image are extracted, edge image is generated；
Step b-2：Extract contour curve from the edge image, by the contour curve be expressed as at scale σ with
Arc length μ is the functional form Γ (μ, σ) of parameter：
Γ (μ, σ)=(x (μ, σ), y (μ, σ)) (1)
Wherein g (μ, σ) be scale be σ Gaussian function, x (μ), y (μ) be using arc length μ as the coordinate representation form of parameter,For convolution operation；
Step b-3：In the lower curvature for calculating each pixel on the contour curve in scale σ=3, local curvature's maximum is found out
Point, as candidate angular；
Wherein,
The single order and second dervative of g (μ, σ) are indicated respectively,For convolution operation.
Step b-4：If the curvature value of the candidate angular is more than preset curvature threshold value, and is more than its neighborhood Local Minimum
When 2 times of value, the candidate angular is correct angle point；
Step b-5：In artwork, curvature scale space angle point corresponding with the correct angle point is accurately positioned.
It is as follows in the step c：
Step c-1：Two-dimensional array A (N, 2) is established, N is the number of angle point, and array element is original image mean curvature scale
The coordinate of space angle point；
Step c-2：Assign each array element in the array A to point (x in orderp,yp), (xp,yp) ∈ A, and to every
A bit (xp,yp), repeat step c-3~c-4；
Step c-3：(x is different to eachp,yp) point (xq,yq) ∈ A, calculate (xp,yp) and (xq,yq) between distance
dpqWith direction opq；
Step c-4：It takes successively and is different from (xp,yp) and (xq,yq) point (x, y) ∈ A, calculate (x, y) and (xp,yp) between
Distance dpWith direction opIf meeting dpAnd dpqThe minimum value ε of the small Mr. Yu of relative mistake1, opAnd opqThe minimum value of the small Mr. Yu of absolute difference
ε2：
Then judge three point X={ (xp,yp),(xq,yq), (x, y) } it is conllinear equidistant points, step c-3 is turned to, is otherwise repeated
Execute step c-4.
It is as follows in the step d：
Step d-1：To every group of conllinear equidistant points Xj={ (xj1,yj1),(xj2,yj2),(xj3,yj3), 1≤j≤M is calculated
Its direction oj, M is conllinear equidistant points group number；
Step d-2：By each group of conllinear equidistant points XjIt is set as cluster；
Step d-3：The root mean square between arbitrary two cluster is calculated, the distance matrix O={ o in direction are obtainedij},1≤i,j≤M；
oij=oi-oj (8)
Step d-4：By oijCorresponding two clusters of minimum value merge into a new cluster；
Step d-5：Step d-3~d-4 is repeated, when the difference of the maxima and minima in the direction of conllinear equidistant points in cluster is big
When preset direction threshold value, ending cluster merges.
It is using advantageous effect caused by above-mentioned technical proposal：
1, the present invention utilizes the conllinear and iso-distance constraint of insulator chain curvature scale space angle point, realizes complicated Aerial Images
In arbitrary major axes orientation insulator chain automatic and accurate positioning, it is low, accidentally to solve existing insulator chain positioning method accuracy
Positioning and the high problem of computation complexity；
2, the present invention takes few, and to partial occlusion and falls string with robustness, can improve positioning accuracy, improve automatic
Change performance.
3, the method for the present invention is simple, practical, and achieves higher positioning accuracy, and required time is shorter, is not necessarily to
It is artificial to participate in.
Description of the drawings
Fig. 1 is the flow chart of the present invention；
Fig. 2 is the conllinear and iso-distance constraint schematic diagram of the curvature scale space angle point of insulator chain image of the present invention；
Fig. 3 is that the embodiment of the present invention 1 is taken photo by plane insulator chain image；
Fig. 4 is 1 curvature scale space angle point grid result of the embodiment of the present invention；
Fig. 5 is 1 conllinear equidistant points of embodiment of the present invention extraction result；
Fig. 6 is 1 hierarchical clustering handling result of the embodiment of the present invention；
Fig. 7 is 1 minimum enclosed rectangle mark frame of the embodiment of the present invention；
Fig. 8 is 1 positioning result of the embodiment of the present invention.
Specific implementation mode
The invention will be further described with reference to the accompanying drawings and examples.
Embodiment 1：
As shown in Figure 1, it is a kind of based on image characteristic point collinearly with the insulator chain automatic positioning method of taking photo by plane of iso-distance constraint,
Include the following steps：
Step a：Image preprocessing：Image comprising the insulator chain of taking photo by plane is pre-processed, obtains filtering out noise
The smooth bianry image of back edge；
Step b：Curvature scale space angle point grid：The edge image for extracting the bianry image, from the edge image
Middle extraction contour curve；In the lower curvature for calculating each pixel on the contour curve in scale σ=3, local curvature's maximum point
As candidate angular；If the curvature value of the candidate angular is more than preset curvature threshold value, and is more than its neighborhood local minimum
2 times when, then be correct angle point；In artwork, curvature scale space angle point corresponding with the correct angle point is accurately positioned.
Step c：Conllinear equidistant points extraction：Select any two described in curvature scale space angle point, using collinearly with etc.
It is found thirdly away from constraint, if in the presence of being all thirdly curvature scale space angle point, judges that be conllinear equidistant points at 3 points.With 3
For a umbrella disk, as shown in Fig. 2, l is insulator chain major axes orientation, A, B, C are insulator chain curvature scale space angle point, dAB,
dBCDistance between respectively AB, BC.A, B, C are located approximately at straight line l1On, and l1It is parallel with l；dAB, dBCApproximately equal.Cause
This judgement A, B, C are conllinear equidistant points.
Step d：Hierarchical clustering：Hierarchical clustering is carried out to the directions of all conllinear equidistant points so that conllinear etc. in per class
It is less than preset direction threshold value away from direction change, selects the maximum a kind of conllinear equidistant point set as insulator chain of quantity.
Step e：Insulator chain positions：The conllinear equidistant point set of the insulator chain is marked with minimum enclosed rectangle, to
It takes photo by plane described in realization the automatic positioning of insulator chain.
It is as follows in the step a：
Step a-1：Binary conversion treatment is carried out to the image comprising the insulator chain of taking photo by plane, obtains insulator chain binary map
Picture；
Step a-2：Morphological erosion and expansion are carried out to the insulator chain bianry image, obtain filtered insulator
String bianry image；
Step a-3：Filter out the cell that area in the filtered insulator chain bianry image is less than preset area threshold value
Domain obtains pre-processed results image.
It is as follows in the step b：
Step b-1：The edges canny in the pre-processed results image are extracted, edge image is generated；
Step b-2：Extract contour curve from the edge image, by the contour curve be expressed as at scale σ with
Arc length μ is the functional form Γ (μ, σ) of parameter：
Γ (μ, σ)=(x (μ, σ), y (μ, σ)) (1)
Wherein g (μ, σ) be scale be σ Gaussian function, x (μ), y (μ) be using arc length μ as the coordinate representation form of parameter,For convolution operation；
Step b-3：In the lower curvature for calculating each pixel on the contour curve in scale σ=3, local curvature's maximum is found out
Point, as candidate angular；
Wherein,
The single order and second dervative of g (μ, σ) are indicated respectively,For convolution operation.
Step b-4：If the curvature value of the candidate angular is more than preset curvature threshold value, and is more than its neighborhood Local Minimum
When 2 times of value, the candidate angular is correct angle point；
Step b-5：In artwork, curvature scale space angle point corresponding with the correct angle point is accurately positioned.
It is as follows in the step c：
Step c-1：Two-dimensional array A (N, 2) is established, N is the number of angle point, and array element is original image mean curvature scale
The coordinate of space angle point；
Step c-2：Assign each array element in the array A to point (x in orderp,yp), (xp,yp) ∈ A, and to every
A bit (xp,yp), repeat step c-3~c-4；
Step c-3：(x is different to eachp,yp) point (xq,yq) ∈ A, calculate (xp,yp) and (xq,yq) between distance
dpqWith direction opq；
Step c-4：It takes successively and is different from (xp,yp) and (xq,yq) point (x, y) ∈ A, calculate (x, y) and (xp,yp) between
Distance dpWith direction opIf meeting dpAnd dpqThe minimum value ε of the small Mr. Yu of relative mistake1, opAnd opqThe minimum value of the small Mr. Yu of absolute difference
ε2：
Then judge three point X={ (xp,yp),(xq,yq), (x, y) } it is conllinear equidistant points, step c-3 is turned to, is otherwise repeated
Execute step c-4.
It is as follows in the step d：
Step d-1：To every group of conllinear equidistant points Xj={ (xj1,yj1),(xj2,yj2),(xj3,yj3), 1≤j≤M is calculated
Its direction oj, M is conllinear equidistant points group number；
Step d-2：By each group of conllinear equidistant points XjIt is set as cluster；
Step d-3：The root mean square between arbitrary two cluster is calculated, the distance matrix O={ o in direction are obtainedij},1≤i,j≤M；
oij=oi-oj (8)
Step d-4：By oijCorresponding two clusters of minimum value merge into a new cluster；
Step d-5：Step d-3~d-4 is repeated, when the difference of the maxima and minima in the direction of conllinear equidistant points in cluster is big
When preset direction threshold value, ending cluster merges.
In the present embodiment, single insulator string string is taken photo by plane shown in original image such as Fig. 3 (a), and double insulator string string is taken photo by plane original
Shown in beginning image such as Fig. 3 (b).After being pre-processed respectively to two images, its curvature scale space angle point such as Fig. 4 (a) is extracted
With shown in 4 (b), it can be seen that the angle point contains abundant local feature and shape information, can tentatively describe shape feature.
It is distinctive collinearly with iso-distance constraint condition using insulator chain, the angle point not satisfied the constraint is removed, extraction meets the constraint
Conllinear equidistant points, as shown in Fig. 5 (a) and 5 (b).Maximum kind, and the side of the conllinear equidistant points of maximum kind are obtained using hierarchical clustering
To approximate with major axes orientation consistent, as shown in Fig. 6 (a) and 6 (b).Finally, the conllinear of insulator chain is marked with minimum enclosed rectangle
Equidistant points, as shown in Fig. 7 (a) and 7 (b)；Include realizing insulator chain automatic positioning knot in original image by rectangle posting
Fruit such as Fig. 8 (a) and 8 (b) are shown.
The foregoing is only a preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims
Subject to.
Claims (5)
1. it is a kind of based on image characteristic point collinearly with the insulator chain automatic positioning method of taking photo by plane of iso-distance constraint, including following step
Suddenly：
Step a：Image preprocessing：Image comprising the insulator chain of taking photo by plane is pre-processed, obtains filtering out noise back
The smooth bianry image of edge, as pre-processed results image；
Step b：Curvature scale space angle point grid：The edge image for extracting the bianry image is carried from the edge image
Contouring curve；In the lower curvature for calculating each pixel on the contour curve in scale σ=3, using local curvature's maximum point as
Candidate angular；If the curvature value of the candidate angular is more than preset curvature threshold value, and more than 2 times of its neighborhood local minimum
When, then it is correct angle point；In artwork, curvature scale space angle point corresponding with the correct angle point is accurately positioned；
Step c：Conllinear equidistant points extraction：Select the curvature scale space angle point described in any two, using it is conllinear with it is equidistant about
Beam is found thirdly, if in the presence of being all thirdly curvature scale space angle point, judges that be conllinear equidistant points at 3 points；
Step d：Hierarchical clustering：Hierarchical clustering is carried out to the direction of all conllinear equidistant points so that the conllinear equidistant points in per class
Direction change is less than preset direction threshold value, selects the maximum a kind of conllinear equidistant point set as insulator chain of quantity；
Step e：Insulator chain positions：The conllinear equidistant point set that the insulator chain is marked with minimum enclosed rectangle, to realize
The automatic positioning of the insulator chain of taking photo by plane.
2. it is according to claim 1 based on image characteristic point collinearly with the insulator chain automatic positioning side that takes photo by plane of iso-distance constraint
Method, it is characterised in that：It is as follows in the step a：
Step a-1：Binary conversion treatment is carried out to the image comprising the insulator chain of taking photo by plane, obtains insulator chain bianry image；
Step a-2：Morphological erosion and expansion are carried out to the insulator chain bianry image, obtain filtered insulator chain two
It is worth image；
Step a-3：The zonule that area in the filtered insulator chain bianry image is less than preset area threshold value is filtered out, is obtained
To pre-processed results image.
3. according to it is described in claim 1 based on image characteristic point collinearly with the insulator chain automatic positioning side that takes photo by plane of iso-distance constraint
Method, it is characterised in that：It is as follows in the step b：
Step b-1：The edges canny in the pre-processed results image are extracted, edge image is generated；
Step b-2：Contour curve is extracted from the edge image, the contour curve is expressed as at scale σ with arc length μ
For the functional form Γ (μ, σ) of parameter：
Γ (μ, σ)=(x (μ, σ), y (μ, σ)) (1)
Wherein g (μ, σ) be scale be σ Gaussian function, x (μ), y (μ) be using arc length μ as the coordinate representation form of parameter,For
Convolution operation；
Step b-3：In the lower curvature for calculating each pixel on the contour curve in scale σ=3, local curvature's maximum point is found out,
As candidate angular；
Wherein,
The single order and second dervative of g (μ, σ) are indicated respectively,For convolution operation；
Step b-4：If the curvature value of the candidate angular is more than preset curvature threshold value, and is more than its neighborhood local minimum 2
Times when, the candidate angular be correct angle point；
Step b-5：In artwork, curvature scale space angle point corresponding with the correct angle point is accurately positioned.
4. according to it is described in claim 1 based on image characteristic point collinearly with the insulator chain automatic positioning side that takes photo by plane of iso-distance constraint
Method, it is characterised in that：It is as follows in the step c：
Step c-1：Two-dimensional array A (N, 2) is established, N is the number of angle point, and array element is original image mean curvature scale space
The coordinate of angle point；
Step c-2：Assign each array element in the array A to point (x in orderp,yp), (xp,yp) ∈ A, and to every bit
(xp,yp), repeat step c-3~c-4；
Step c-3：(x is different to eachp,yp) point (xq,yq) ∈ A, calculate (xp,yp) and (xq,yq) between distance dpqWith
Direction opq；
Step c-4：It takes successively and is different from (xp,yp) and (xq,yq) point (x, y) ∈ A, calculate (x, y) and (xp,yp) between distance
dpWith direction opIf meeting dpAnd dpqThe minimum value ε of the small Mr. Yu of relative mistake1, opAnd opqThe minimum value ε of the small Mr. Yu of absolute difference2：
Then judge three point X={ (xp,yp),(xq,yq), (x, y) } it is conllinear equidistant points, step c-3 is turned to, step is otherwise repeated
Rapid c-4.
5. according to it is described in claim 1 based on image characteristic point collinearly with the insulator chain automatic positioning side that takes photo by plane of iso-distance constraint
Method, it is characterised in that：It is as follows in the step d：
Step d-1：To every group of conllinear equidistant points Xj={ (xj1,yj1),(xj2,yj2),(xj3,yj3), 1≤j≤M calculates its direction
oj, M is conllinear equidistant points group number；
Step d-2：By each group of conllinear equidistant points XjIt is set as cluster；
Step d-3：The root mean square between arbitrary two cluster is calculated, the distance matrix O={ o in direction are obtainedij},1≤i,j≤M；
oij=oi-oj (8)
Step d-4：By oijCorresponding two clusters of minimum value merge into a new cluster；
Step d-5：Step d-3~d-4 is repeated, when the difference of the maxima and minima in the direction of conllinear equidistant points in cluster is more than in advance
When set direction threshold value, ending cluster merges.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510443073.2A CN105069461B (en) | 2015-07-24 | 2015-07-24 | Based on image characteristic point collinearly with the insulator chain automatic positioning method of iso-distance constraint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510443073.2A CN105069461B (en) | 2015-07-24 | 2015-07-24 | Based on image characteristic point collinearly with the insulator chain automatic positioning method of iso-distance constraint |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105069461A CN105069461A (en) | 2015-11-18 |
| CN105069461B true CN105069461B (en) | 2018-11-06 |
Family
ID=54498822
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510443073.2A Active CN105069461B (en) | 2015-07-24 | 2015-07-24 | Based on image characteristic point collinearly with the insulator chain automatic positioning method of iso-distance constraint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105069461B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107369162B (en) * | 2017-07-21 | 2020-07-10 | 华北电力大学（保定） | Method and system for generating insulator candidate target area |
| CN115512252B (en) * | 2022-11-18 | 2023-02-21 | 东北电力大学 | Unmanned aerial vehicle-based power grid inspection automation method and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714342A (en) * | 2013-12-20 | 2014-04-09 | 华北电力大学（保定） | An aerial-photo insulator chain automatic positioning method based on binary image shape features |
| CN104021394A (en) * | 2014-06-05 | 2014-09-03 | 华北电力大学（保定） | Insulator image recognition method based on Adaboost algorithm |
-
2015
- 2015-07-24 CN CN201510443073.2A patent/CN105069461B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103714342A (en) * | 2013-12-20 | 2014-04-09 | 华北电力大学（保定） | An aerial-photo insulator chain automatic positioning method based on binary image shape features |
| CN104021394A (en) * | 2014-06-05 | 2014-09-03 | 华北电力大学（保定） | Insulator image recognition method based on Adaboost algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 《一种航拍绝缘子串图像自动定位方法》;赵振兵;《仪器仪表学报》;20140331;第35卷(第3期);全文 * |
| 《航拍绝缘子图像的检测与识别方法研究》;严凯等;《贵州电子技术》;20151031;第18卷(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105069461A (en) | 2015-11-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109598290A (en) | A kind of image small target detecting method combined based on hierarchical detection | |
| CN104134234B (en) | A kind of full automatic three-dimensional scene construction method based on single image | |
| CN103295232B (en) | Based on the SAR image registration method in straight line and region | |
| CN103745498B (en) | A kind of method for rapidly positioning based on image | |
| CN109712143B (en) | Rapid image segmentation method based on superpixel multi-feature fusion | |
| CN106340010B (en) | A kind of angular-point detection method based on second order profile difference | |
| CN109344820A (en) | Digital electric meter Recognition of Reading method based on computer vision and deep learning | |
| CN109712112A (en) | Taking photo by plane based on local feature is insulated the localization method of subgraph | |
| CN104123554A (en) | SIFT image characteristic extraction method based on MMTD | |
| CN103971377A (en) | Building extraction method based on prior shape level set segmentation | |
| CN110443295A (en) | Improved images match and error hiding reject algorithm | |
| Cao et al. | Sharp feature extraction in point clouds | |
| CN105069461B (en) | Based on image characteristic point collinearly with the insulator chain automatic positioning method of iso-distance constraint | |
| CN105069459B (en) | One kind is directed to High Resolution SAR Images type of ground objects extracting method | |
| CN105354547A (en) | Pedestrian detection method in combination of texture and color features | |
| Wang et al. | A region-line primitive association framework for object-based remote sensing image analysis | |
| CN107369162A (en) | A kind of generation method and system of insulator candidate target region | |
| CN104036295A (en) | Road center line auto-detection method employing multispectral remote sensing images | |
| Zhang et al. | Recognition and detection of wolfberry in the natural background based on improved YOLOv5 network | |
| Su et al. | Effective target extraction of automatic target-scoring system | |
| CN111354003B (en) | Pig segmentation method based on depth image | |
| Li et al. | Low-cost 3D building modeling via image processing | |
| Wang et al. | Improved glove defect detection algorithm based on YOLOv5 framework | |
| Liu et al. | Adaptive ideal image reconstruction for bacteria colony detection | |
| Xia et al. | Application of an improved watershed algorithm in the insulator contamination monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |