CN111652894B - Annular target self-adaptive detection method for aircraft - Google Patents
Annular target self-adaptive detection method for aircraft Download PDFInfo
- Publication number
- CN111652894B CN111652894B CN202010341673.9A CN202010341673A CN111652894B CN 111652894 B CN111652894 B CN 111652894B CN 202010341673 A CN202010341673 A CN 202010341673A CN 111652894 B CN111652894 B CN 111652894B
- Authority
- CN
- China
- Prior art keywords
- target
- edge
- annular
- ellipse
- target image
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000001914 filtration Methods 0.000 claims abstract description 11
- 238000003708 edge detection Methods 0.000 claims abstract description 8
- 230000009466 transformation Effects 0.000 claims abstract description 8
- 230000000877 morphologic effect Effects 0.000 claims abstract description 6
- 230000008030 elimination Effects 0.000 claims abstract description 4
- 238000003379 elimination reaction Methods 0.000 claims abstract description 4
- 230000001629 suppression Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 3
- 230000007797 corrosion Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 238000012545 processing Methods 0.000 abstract description 2
- 230000003044 adaptive effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002194 synthesizing effect Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/168—Segmentation; Edge detection involving transform domain methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- 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
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- 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
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an annular target self-adaptive detection method for an aircraft, in particular to the field of data processing. The method comprises the following steps: s1: acquiring a target image, and obtaining a candidate region according to the target image; s2: performing edge detection on the target image to obtain a target edge; s3: performing edge enhancement on the target edge by using morphological filtering; s4: performing Hough transformation on the candidate region to obtain a candidate annular target; s5: and performing interference elimination on the annular target to obtain the best fit annular target. The technical problem of how to enhance the detection and tracking effects of the annular targets is solved, and the method is suitable for annular target detection of the aircraft.
Description
Technical Field
The invention relates to the field of data processing, in particular to an annular target self-adaptive detection method for an aircraft.
Background
How to quickly and accurately detect a ring-shaped object in a complex image has been an important issue that researchers have struggled to explore. The method has important application in the fields of biomedical microscopic images, industrial automatic detection, robot vision, space technology, military defense and the like. In the flight process of the miniature flapping rotor wing, effective detection of an annular target is also an extremely important research content, and the follow-up tracking and control are directly influenced, so that the method is a key to success or failure of visual navigation. The rings appear mostly elliptical at different viewing angles, and all ring (ellipse) detection methods rely on algebraic geometrical properties unique to ellipses. Fig. 1 is a mathematical attribute that is often used in ellipse detection. The main ellipse parameters are ellipse center coordinates, ellipse long and short axis lengths, focal length of ellipse and ellipse deflection angle. The characteristics of the ellipse used for detecting the ellipse generally include symmetry of the ellipse, parallel chord theorem, ellipse chord tangent theorem, and the like.
The existing ellipse detection methods can be divided into three types based on their structures: least squares and its optimization methods, clustering-based or voting-based Hough transforms and their variation methods, and related combination methods, such as methods combining statistical analysis, heuristics, or combination techniques, are relied on. The third approach is generally to first fully exploit the fundamental geometric properties of ellipses to reduce complex problems to sub-problems. This method is also referred to as an arc-based ellipse detection method. Generally, the method firstly extracts an elliptic arc and then fits an ellipse by using the elliptic arc.
Circular ring detection under aircraft conditions is poor in performance and prone to false detection due to changes in viewing angles, dynamic motion of the aircraft and interference of complex backgrounds.
Disclosure of Invention
The invention aims to solve the technical problem of enhancing the detection and tracking effects of the annular targets.
The technical scheme for solving the technical problems is as follows: an aircraft-oriented annular target self-adaptive detection method comprises the following steps:
s1: acquiring a target image, and obtaining a candidate region according to the target image;
s2: performing edge detection on the target image to obtain a target edge;
s3: performing edge enhancement on the target edge by using morphological filtering;
s4: performing Hough transformation on the candidate region to obtain a candidate annular target;
s5: and performing interference elimination on the annular target to obtain the best fit annular target.
The beneficial effects of the invention are as follows: aiming at the defects of poor detection performance and poor robustness of the traditional Hough detection method in a complex dynamic environment, the invention designs a rapid ellipse detection method based on edge detection and Hough transformation. Firstly, an improved Canny edge detection method is provided, and edge information is effectively reserved while noise is removed; then, morphological filtering is utilized to strengthen the edge of the target, so that the robustness of the method is improved; further carrying out Hough transformation on the candidate region, and extracting a candidate annular target; and finally, effectively eliminating the interference target by a voting mechanism based on the fitting degree, and detecting the optimal annular target. Experimental results show that the method has good robustness for complex background and motion scene, and can reliably detect and stably track the annular target, so that the technical problem of how to enhance the detection and tracking effects of the annular target is solved.
On the basis of the technical scheme, the invention can be improved as follows.
Further, the step S2 specifically includes:
s21: image denoising the target image by using Gaussian filtering;
s22: obtaining the gradient amplitude and the gradient direction of the target image after filtering according to the finite difference of the first-order partial derivatives;
s23: performing non-maximum suppression on the gradient amplitude;
s24: and obtaining a high threshold and a low threshold, finding out the outline of the image edge in the target image according to the high threshold, and connecting the edge break points of the outline according to the low threshold until the whole outline is closed, so as to obtain the target edge.
The further scheme has the advantages that in order to better detect edges in the later period and reduce the influence of noise on results, gaussian smoothing denoising is firstly carried out on an original image; the traditional Canny operator only extracts gradients in the x direction and the y direction and then calculates the gradients, but some important edge information, especially some information in the oblique direction, can still be lost. Calculating gradient information in two oblique directions of the image, and finally synthesizing original gradient information and information in the oblique directions to obtain a final edge image; the larger the gradient value of a point in the image, the larger the gradient magnitude corresponding thereto. But not necessarily all the true edge points of the image for points with larger gradient magnitudes. Therefore, to determine the edges, local gradient maximum points must be preserved, i.e., non-maximum suppression of gradient magnitude. By utilizing gradient angle information, a method for keeping local gradient maximum value by comparing local gradient values is adopted to inhibit non-maximum value; .
Further, the step S3 specifically includes:
s31: acquiring a structural element, and performing corrosion operation on the target image according to the structural element;
s32: and performing expansion operation on the target image by using the structural elements with smaller sizes to obtain a connected domain.
The adoption of the further scheme has the beneficial effects that isolated noise points can be eliminated after the structural elements are corroded, and the cavity can be filled to form a connected domain after the target image is expanded, so that the effect of edge enhancement is achieved.
Further, the step S4 specifically includes:
s41: selecting a major axis endpoint of the ellipse, and calculating a center coordinate, a semi-major axis and an included angle theta between the major axis of the ellipse and an x axis;
s42: calculating the length of the short axis to obtain an elliptic equation;
s43: and obtaining candidate annular targets according to the equation of the ellipse.
Further, step S42 specifically includes:
s421: taking edge points in any connected domain, and marking the edge points as m points;
s422: repeating the step A421, and obtaining a corresponding beta value according to each m point;
s423: counting the number of times of occurrence of each calculated beta value, and setting a threshold T according to the number of times;
s424: when the beta value corresponding to the m point accords with the threshold T, an ellipse { O is obtained x ,O y ,α,β,θ}。
The above further scheme has the advantages that if the point pairs to be selected are two ends of the major axis of the ellipse, the point m is also the point on the ellipse, the value of the beta calculated each time is the same, the point m on the ellipse is many, the number of times of the beta reaches a peak value, a threshold value T is set, if the accumulation (the number of times of the occurrence) of a certain beta exceeds T, the assumed major axis end point is considered to be correct, and the ellipse exists at the position.
Further, the step S5 specifically includes:
s51: according to the ellipse { O } x ,O y Alpha, beta, theta to obtain the fitting degree dis of the pixels i =exp(-abs(Er 1 +Er 2 -1)), wherein:
Er 1 =((P ix -O ix )·cos(θ i )+(P iy -O iy )·sin(θ i )) 2 /α i 2 ,
Er 2 =(-(P ix -O ix )·sin(θ i )+(P iy -O iy )·cos(θ i )) 2 /β i 2 ;
s52: for all dis in the connected domain i Voting pixels less than 0.5, and taking the fitting degree as a weight;
s53: obtaining the connected domain with the maximum ticket value as the best fitting annular target
Additional aspects of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
FIG. 1 is a method flow diagram of an embodiment of an aircraft-oriented annular target adaptive detection method of the present invention;
FIG. 2 is a schematic view of ellipse parameters of other embodiments of the present invention for an aircraft-oriented annular target adaptive detection method;
FIG. 3 is a schematic view of any point on an ellipse of another embodiment of an aircraft-oriented annular target adaptive detection method of the present invention.
Detailed Description
The principles and features of the present invention are described below with reference to the drawings, the examples are illustrated for the purpose of illustrating the invention and are not to be construed as limiting the scope of the invention.
An example is substantially as shown in figure 1:
the annular target self-adaptive detection method facing the aircraft in the embodiment comprises the following steps of:
s1: acquiring a target image, and obtaining a candidate region according to the target image;
s2: performing edge detection on the target image to obtain a target edge;
s3: edge enhancement is carried out on the target edge by morphological filtering;
s4: performing Hough transformation on the candidate region to obtain a candidate annular target;
s5: and performing interference elimination on the annular target to obtain the best fit annular target.
The beneficial effects of the invention are as follows: aiming at the defects of poor detection performance and poor robustness of the traditional Hough detection method in a complex dynamic environment, the invention designs a rapid ellipse detection method based on edge detection and Hough transformation. Firstly, an improved Canny edge detection method is provided, and edge information is effectively reserved while noise is removed; then, morphological filtering is utilized to strengthen the edge of the target, so that the robustness of the method is improved; further carrying out Hough transformation on the candidate region, and extracting a candidate annular target; and finally, effectively eliminating the interference target by a voting mechanism based on the fitting degree, and detecting the optimal annular target. Experimental results show that the method has good robustness for complex background and motion scene, and can reliably detect and stably track the annular target, so that the technical problem of how to enhance the detection and tracking effects of the annular target is solved.
On the basis of the technical scheme, the invention can be improved as follows.
Optionally, in some other embodiments, step S2 specifically includes:
s21: image denoising is carried out on the target image by utilizing Gaussian filtering;
s22: obtaining the gradient amplitude and direction of the filtered target image according to the finite difference of the first-order partial derivatives;
s23: performing non-maximum suppression on the gradient amplitude;
s24: and obtaining a high threshold and a low threshold, finding out the outline of the image edge in the target image according to the high threshold, and connecting the edge break points of the outline according to the low threshold until the whole outline is closed, thereby obtaining the target edge.
In order to better detect edges in the later period and reduce the influence of noise on results, firstly, gaussian smoothing denoising is carried out on an original image; the traditional Canny operator only extracts gradients in the x direction and the y direction and then calculates the gradients, but some important edge information, especially some information in the oblique direction, can still be lost. Calculating gradient information in two oblique directions of the image, and finally synthesizing original gradient information and information in the oblique directions to obtain a final edge image; the larger the gradient value of a point in the image, the larger the gradient magnitude corresponding thereto. But not necessarily all the true edge points of the image for points with larger gradient magnitudes. Therefore, to determine the edges, local gradient maximum points must be preserved, i.e., non-maximum suppression of gradient magnitude. By utilizing gradient angle information, a method for keeping local gradient maximum value by comparing local gradient values is adopted to inhibit non-maximum value; .
Optionally, in some other embodiments, step S3 specifically includes:
s31: acquiring a structural element, and performing corrosion operation on the target image according to the structural element, wherein the size of the structural element in the embodiment can be 5×5 pixels in general;
s32: the target image is expanded by using the structural element with smaller size to obtain the connected domain, and the structural element with smaller size in the embodiment can be about 3×3 pixels, and the error is 1 pixel.
After the structural elements are corroded, isolated noise points can be eliminated, and after the target image is expanded, the cavity can be filled to form a connected domain, so that the effect of edge enhancement is achieved.
As shown in fig. 2 and 3, optionally, in some other embodiments, step S4 specifically includes:
s41: selecting a major axis endpoint of the ellipse, and calculating a center coordinate, a semi-major axis and an included angle theta between the major axis of the ellipse and an x axis;
s42: calculating the length of the short axis to obtain an elliptic equation;
s43: and obtaining candidate annular targets according to the equation of the ellipse.
Optionally, in some other embodiments, step S42 specifically includes:
s421: taking edge points in any connected domain, and marking the edge points as m points;
s422: repeating the step A421, and obtaining a corresponding beta value according to each m point;
s423: counting the number of times of occurrence of each calculated beta value, and setting a threshold T according to the number of times, wherein the threshold T in the embodiment is 60;
s424: when the beta value corresponding to the m point accords with the threshold T, an ellipse { O is obtained x ,O y ,α,β,θ}。
In this embodiment, the β value is a short radius of the ellipse, if the point pair to be selected is the two end points of the major axis of the ellipse, the m points are also points on the ellipse, the β value calculated each time is the same, the m points on the ellipse are many, the number of occurrences of β reaches a peak value, a threshold T is set, and if the accumulation (number of occurrences) of a certain β exceeds T, the assumed major axis end point is considered to be correct, and the ellipse exists at this position.
Optionally, in some other embodiments, step S5 specifically includes:
s51: according to ellipse { O x ,O y Alpha, beta, theta to obtain the fitting degree dis of the pixels i =exp(-abs(Er 1 +Er 2 -1)), wherein:
Er 1 =((P ix -O ix )·cos(θ i )+(P iy -O iy )·sin(θ i )) 2 /α i 2 ,
Er 2 =(-(P ix -O ix )·sin(θ i )+(P iy -O iy )·cos(θ i )) 2 /β i 2 ;
s52: for all dis in the connected domain i Voting the pixels less than 0.5, and taking the fitting degree as a weight;
s53: obtaining the connected domain with the maximum ticket value as the best fitting annular target
On the basis of the technical scheme, the invention can be improved as follows.
It should be noted that, the foregoing embodiments are product embodiments corresponding to the foregoing method embodiments, and description of each structural device and an optional implementation manner in this embodiment may refer to corresponding description in the foregoing method embodiments, which is not repeated herein.
The reader will appreciate that in the description of this specification, a description of terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the apparatus and units described above may refer to corresponding procedures in the foregoing method embodiments, which are not described herein again.
The present invention is not limited to the above embodiments, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the present invention, and these modifications and substitutions are intended to be included in the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (1)
1. The annular target self-adaptive detection method for the aircraft is characterized by comprising the following steps of:
s1: acquiring a target image, and obtaining a candidate region according to the target image;
s2: performing edge detection on the target image to obtain a target edge, and specifically comprising the following steps:
s21: image denoising the target image by using Gaussian filtering;
s22: obtaining the gradient amplitude and the gradient direction of the target image after filtering according to the finite difference of the first-order partial derivatives;
s23: performing non-maximum suppression on the gradient amplitude;
s24: acquiring a high threshold and a low threshold, finding out the outline of the image edge in the target image according to the high threshold, and connecting the edge break points of the outline according to the low threshold until the whole outline is closed, so as to obtain the target edge;
s3: edge enhancement is carried out on the target edge by morphological filtering, and the method specifically comprises the following steps:
s31: acquiring a structural element, and performing corrosion operation on the target image according to the structural element;
s32: performing expansion operation on the target image by using the structural elements with smaller sizes to obtain a connected domain;
s4: performing Hough transformation on the candidate region to obtain a candidate annular target, wherein the method specifically comprises the following steps of:
s41: selecting a major axis endpoint of the ellipse, and calculating a center coordinate, a semi-major axis and an included angle theta between the major axis of the ellipse and an x axis;
s42: calculating the length of the short axis to obtain an elliptic equation, which specifically comprises the following steps:
s421: taking edge points in any connected domain, and marking the edge points as m points;
s422: repeating the step A421, and obtaining a corresponding beta value according to each m point;
s423: counting the number of times of occurrence of each calculated beta value, and setting a threshold T according to the number of times;
s424: when the beta value corresponding to the m point accords with the threshold T, an ellipse { O is obtained x ,O y ,α,β,θ};
S43: obtaining candidate annular targets according to the equation of the ellipse;
s5: the interference elimination is carried out on the annular target to obtain the best fitting annular target, and the method specifically comprises the following steps:
s51: according to the ellipse { O } x ,O y Alpha, beta, theta to obtain the fitting degree dis of the pixels i =exp(-abs(Er 1 +Er 2 -1)), wherein:
Er 1 =((P ix -O ix )·cos(θ i )+(P iy -O iy )·sin(θ i )) 2 /α i 2 ,
Er 2 =(-(P ix -O ix )·sin(θ i )+(P iy -O iy )·cos(θ i )) 2 /β i 2 ;
s52: for all dis in the connected domain i Voting pixels less than 0.5, and taking the fitting degree as a weight;
s53: the connected domain with the maximum ticket value is obtained as the best fitting annular target t=argmax Σdis.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010341673.9A CN111652894B (en) | 2020-04-27 | 2020-04-27 | Annular target self-adaptive detection method for aircraft |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010341673.9A CN111652894B (en) | 2020-04-27 | 2020-04-27 | Annular target self-adaptive detection method for aircraft |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111652894A CN111652894A (en) | 2020-09-11 |
CN111652894B true CN111652894B (en) | 2023-11-14 |
Family
ID=72342920
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010341673.9A Active CN111652894B (en) | 2020-04-27 | 2020-04-27 | Annular target self-adaptive detection method for aircraft |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111652894B (en) |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2002183739A (en) * | 2000-12-14 | 2002-06-28 | Tsubakimoto Chain Co | Ellipse detection method and ellipse detection device |
RU2419150C1 (en) * | 2010-03-10 | 2011-05-20 | Федеральное Государственное Унитарное Предприятие "Государственный Рязанский Приборный Завод" | Method to process sequence of images to detect and follow air objects |
DE102015205505A1 (en) * | 2015-03-26 | 2016-09-29 | Mando Corporation | Method and apparatus for detecting elliptical structures in an image |
US9934578B2 (en) * | 2016-08-15 | 2018-04-03 | Macau University Of Science And Technology | Method for edge detection |
CN106951820B (en) * | 2016-08-31 | 2019-12-13 | 江苏慧眼数据科技股份有限公司 | Passenger flow statistical method based on annular template and ellipse fitting |
-
2020
- 2020-04-27 CN CN202010341673.9A patent/CN111652894B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN111652894A (en) | 2020-09-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110543837B (en) | Visible light airport airplane detection method based on potential target point | |
CN110349207B (en) | Visual positioning method in complex environment | |
CN106530347B (en) | Stable high-performance circle feature detection method | |
CN108663026B (en) | Vibration measuring method | |
JPH10208056A (en) | Line detection method | |
CN110222661B (en) | Feature extraction method for moving target identification and tracking | |
CN106327522A (en) | Infrared small target detection method based on multi-direction morphological filtering complex cloud background | |
CN114331879A (en) | Visible light and infrared image registration method for equalized second-order gradient histogram descriptor | |
CN111127546B (en) | Circular target center positioning method and system based on polar coordinate transformation | |
CN103745236A (en) | Texture image identification method and texture image identification device | |
Wang et al. | Hand posture recognition from disparity cost map | |
CN109064473B (en) | 2.5D ultrasonic panoramic image segmentation method | |
CN113095385B (en) | Multimode image matching method based on global and local feature description | |
CN111652894B (en) | Annular target self-adaptive detection method for aircraft | |
CN105574860A (en) | Method for identifying deflection polarity of rudder slice | |
Hashmani et al. | A survey on edge detection based recent marine horizon line detection methods and their applications | |
CN115953399B (en) | Industrial part structural defect detection method based on contour features and SVDD | |
CN111626236A (en) | Rapid ellipse target detection method | |
Luo et al. | Improved Harris corner detection algorithm based on canny edge detection and Gray difference preprocessing | |
CN112132849A (en) | Spatial non-cooperative target corner extraction method based on Canny edge detection | |
CN115205564B (en) | Unmanned aerial vehicle-based hull maintenance inspection method | |
Zhao et al. | Principal direction-based Hough transform for line detection | |
Huang et al. | An automatic detection and recognition method for pointer-type meters in natural gas stations | |
CN113793372A (en) | Optimal registration method and system for different-source images | |
CN106650717B (en) | Accurate positioning method for round object with thickness interference |
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 |