CN116503387A - Image detection method, device, equipment, system and readable storage medium - Google Patents
Image detection method, device, equipment, system and readable storage medium Download PDFInfo
- Publication number
- CN116503387A CN116503387A CN202310745475.2A CN202310745475A CN116503387A CN 116503387 A CN116503387 A CN 116503387A CN 202310745475 A CN202310745475 A CN 202310745475A CN 116503387 A CN116503387 A CN 116503387A
- Authority
- CN
- China
- Prior art keywords
- image
- target
- image detection
- characteristic
- detected
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 101
- 238000003860 storage Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 43
- 230000006870 function Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 11
- 239000011159 matrix material Substances 0.000 description 17
- 238000010586 diagram Methods 0.000 description 14
- 230000000694 effects Effects 0.000 description 14
- 238000000605 extraction Methods 0.000 description 12
- 238000003466 welding Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 230000007547 defect Effects 0.000 description 5
- 230000009977 dual effect Effects 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000012512 characterization method Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000011426 transformation method Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006386 memory function Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 229910000679 solder Inorganic materials 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000001131 transforming 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an image detection method, an image detection device, an image detection equipment, an image detection system and a readable storage medium, wherein the image detection method comprises the following steps: acquiring an image to be detected; the image to be detected contains a characteristic target; determining target pixel points in an image to be detected and vector representation and weight of elliptical tangent lines at each target pixel point; according to vector representations and weights corresponding to all ellipse tangents, estimating parameter values of characteristic parameters of a characteristic target, and obtaining optimal parameter values based on an updating strategy; positioning and detecting the characteristic target according to the optimal parameter value; the method and the device can rapidly and accurately estimate the optimal parameter value of the characteristic target in the image, and further can accurately position and detect the characteristic target in the image to be detected.
Description
Technical Field
The present invention relates to the field of machine vision, and in particular, to an image detection method, apparatus, device, system, and readable storage medium.
Background
The circular feature is widely applied to the field of machine vision, camera calibration based on a circular hole target, automatic robot guiding based on the circular feature, object space position and posture measurement, visual navigation, target object identification and the like. The circle is a special ellipse, and perspective projection of the circle is often represented as ellipse features, so that the method for extracting the ellipse features in the research image has important significance.
In practical application of machine vision, it is often necessary to precisely locate an elliptical target in an image, so that the purposes of defect detection, boundary fitting and the like can be achieved. In the prior art for locating an elliptical target in an image, common methods include a centroid method, a Hough transformation method and a method based on boundary point fitting, and the methods are affected by image gray noise or boundary noise, or have higher algorithm complexity, so that the accuracy and efficiency of locating and detecting are reduced.
Disclosure of Invention
The invention aims at providing an image detection method, an image detection device, an image detection equipment, an image detection system and a readable storage medium, which can rapidly and accurately extract the optimal characteristic parameter value of an elliptical target in an image, and can improve the accuracy of positioning and detecting the characteristic target in the image to be detected. Embodiments of the invention may be implemented as follows:
in a first aspect, the present invention provides an image detection method, the method comprising: acquiring an image to be detected; the image to be detected comprises a characteristic target; determining a target pixel point in the image to be detected and vector representations and weights of elliptical tangent lines at the target pixel points; according to the vector representations and the weights corresponding to all the ellipse tangents, estimating the parameter values of the characteristic parameters of the characteristic targets, and obtaining optimal parameter values based on an updating strategy; and positioning and detecting the characteristic target according to the optimal parameter value.
In a second aspect, the present invention provides an image detection apparatus comprising: the acquisition module is used for acquiring the image to be detected; the image to be detected comprises a characteristic target; the determining module is used for determining a target pixel point in the image to be detected and vector representations and weights of elliptical tangent lines at the target pixel points; the estimation module is used for estimating the parameter value of the characteristic parameter of the characteristic target according to the vector representations and the weights corresponding to all the ellipse tangents, and obtaining an optimal parameter value based on an updating strategy; and the positioning and detecting module is used for positioning and detecting the characteristic target according to the optimal parameter value.
In a third aspect, the present invention provides an image detection apparatus comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor being executable to implement the image detection method of the first aspect.
In a fourth aspect, the present invention provides an image detection system comprising an image detection device and a camera platform as described in the previous embodiments; the camera platform is used for acquiring an image to be detected and sending the image to be detected to the image detection device, and the image detection device is used for executing the image detection method according to the first aspect.
In a fifth aspect, the present invention provides a readable storage medium having stored thereon a computer program which, when executed by a processor, implements the image detection method according to the first aspect.
The invention provides an image detection method, an image detection device, an image detection equipment, an image detection system and a readable storage medium, wherein the image detection method comprises the following steps: acquiring an image to be detected; the image to be detected comprises a characteristic target; determining vector representations and weights of target pixel points in the image to be detected and elliptical tangent lines at the target pixel points, wherein the target pixel points are screened out to avoid interference of human factors and camera noise on detection precision, and the weights are set to improve the precision and robustness of detection based on the elliptical tangent lines; and estimating the parameter value of the characteristic parameter of the characteristic target according to the vector representations and the weights corresponding to all the ellipse tangents, obtaining an optimal parameter value based on an updating strategy, and repeatedly iterating until the optimal parameter is obtained based on the updating strategy, so that the estimation precision of the parameter value can be improved, and the accuracy of positioning and detecting the characteristic target in the image to be detected can be improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of an image detection system according to an embodiment of the present invention;
fig. 2 is a block diagram of an image detection apparatus according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of an image detection method according to an embodiment of the present invention;
FIG. 4A is a schematic view of the effect of extracting the characteristic parameters of the simulated ellipse according to the embodiment of the present invention;
FIG. 4B is a partial enlargement of the ellipse in the upper left corner of FIG. 4A;
FIG. 5 is a graph showing a comparison of fitting effects provided by an embodiment of the present invention;
fig. 6 is a functional block diagram of an image detection apparatus according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures.
In the description of the present invention, it should be noted that, if the terms "upper", "lower", "inner", "outer", and the like indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, or the azimuth or the positional relationship in which the inventive product is conventionally put in use, it is merely for convenience of describing the present invention and simplifying the description, and it is not indicated or implied that the apparatus or element referred to must have a specific azimuth, be configured and operated in a specific azimuth, and thus it should not be construed as limiting the present invention.
Furthermore, the terms "first," "second," and the like, if any, are used merely for distinguishing between descriptions and not for indicating or implying a relative importance.
It should be noted that the features of the embodiments of the present invention may be combined with each other without conflict.
The circular feature is widely applied to the field of machine vision, camera calibration based on a circular hole target, automatic robot guiding based on the circular feature, object space position and posture measurement, visual navigation, target object identification and the like. The circle is a special ellipse, and perspective projection of the circle is often represented as ellipse features, so that the method for extracting the ellipse features in the research image has important significance.
Detection accuracy and computational efficiency are two important issues in the extraction of elliptical target features. At present, a large number of ellipse feature extraction methods exist, such as centroid method, hough transformation method and fitting method based on ellipse boundary points, wherein the invariant moment method and the least square method are the most common algorithm for fitting based on ellipse boundary points; however, the invariant moment method can obtain the elliptical center of the sub-pixel level, but is easily affected by image gray noise; the least square algorithm based on the elliptic boundary points must firstly extract the elliptic boundary and then carry out elliptic fitting, so that the complexity of the elliptic fitting algorithm is improved, the influence of boundary noise is extremely easy to be caused, and the precision of elliptic fitting is greatly reduced. Moreover, edge extraction is a complex process, including multiple steps of gradient estimation, non-maximum suppression, threshold selection, and the like, in which numerous uncertain factors exist, which seriously affect the final parameter estimation accuracy.
Therefore, in order to solve the technical problems and improve the feature extraction precision and efficiency of the elliptic target, the image detection method provided by the embodiment of the invention can carry out elliptic parameter estimation based on the dual conic theory model, and ensure the precision of elliptic parameter estimation by using a plurality of parameter constraint modes during parameter estimation, has no edge extraction link in the whole process, effectively avoids errors caused by edge extraction, and improves the efficiency.
Referring to fig. 1, fig. 1 is a block diagram of an image detection system according to an embodiment of the present invention, where an image detection system 10 includes an image detection device 100 and a camera calibration platform 110, and the image detection device 100 and the camera calibration platform 110 may be connected by a wired network or a wireless network.
The camera calibration platform 110 includes a camera for capturing images and a platform for calibrating, where the camera may be fixed on the platform, and a capturing angle of the camera may be adjusted to ensure that an object to be detected can be captured in all directions, and the camera may be, but is not limited to, an industrial camera, and performs image acquisition on the object to be detected, and sends the acquired images to the image detection device 100 for detection, and the object to be detected may be a circuit board, a chip, or the like, which is not limited herein.
Referring to fig. 2, fig. 2 is a block diagram of an image detection apparatus according to an embodiment of the present invention, where the image detection apparatus 100 is configured to perform an image detection method according to an embodiment of the present invention, and includes: the memory 101, the processor 102, the communication interface 103, and the bus 104 are electrically connected directly or indirectly to each other, so as to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.
Alternatively, bus 104 may be a peripheral component interconnect standard @, for examplePCI) bus or extended industry standard architecture (+.>EISA) bus, etc. The buses may be divided into address buses, data buses, control buses, etc. For ease of illustration, only one thick line is shown in fig. 2, but not only one bus or one type of bus.
In an embodiment of the present invention, the processor 102 may be a general purpose processor, a digital signal processor, an application specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component, where the methods, steps, and logic blocks disclosed in the embodiments of the present invention may be implemented or performed. The general purpose processor may be a microprocessor or any conventional processor or the like. The steps of a method disclosed in connection with the embodiments of the present invention may be embodied directly in a hardware processor for execution, or in a combination of hardware and software modules in the processor for execution. The software modules may be located in memory 101 and processor 102 reads the program instructions in memory 101 to perform the steps of the methods described above in connection with its hardware.
In an embodiment of the present invention, the memory 101 may be a nonvolatile memory, such as a hard disk #HDD) or solid state disk (++>SSD), or the like, may also be a volatile memory (++>) Such as RAM. The memory may also be a memory that can be used to carry or store desired programs in the form of instructions or data structuresThe sequence code and any other medium that can be accessed by a computer, but is not limited thereto. The memory in embodiments of the present invention may also be circuitry or any other device capable of performing memory functions for storing instructions and/or data.
The memory 101 may be used to store software programs and modules, such as instructions/modules of the image detection apparatus 400 provided in the embodiment of the present invention, may be stored in the memory 101 in the form of software or firmware (firmware) or may be solidified in the operating system of the image detection device 100OS), the processor 102 executes various functional applications and data processing by executing software programs and modules stored in the memory 101. The communication interface 103 may be used for communication of signaling or data with other node devices.
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.
It is to be understood that the configuration shown in fig. 2 is merely illustrative, and that the image detection apparatus 100 may also include more or fewer components than those shown in fig. 2, or have a different configuration than that shown in fig. 2. The components shown in fig. 2 may be implemented in hardware, software, or a combination thereof.
The image detection device 100 may be any electronic product that can interact with a user, such as a personal computer, a tablet computer, a smart phone, a personal digital assistantPDA), game machine, interactive web tv (++>IPTV), intelligent wearable devices, etc.
The image detection device 100 may also include a network device and/or a user device. Network devices include, but are not limited to, a single network server, a server group of multiple network servers, or a Cloud based Cloud Computing (Cloud Computing) composed of a large number of hosts or network servers.
The network on which the image detection apparatus 100 is located includes, but is not limited to, the internet, a wide area network, a metropolitan area network, a local area network, and a virtual private networkVPN), etc.
In the embodiment of the invention, the camera calibration platform can be utilized to shoot the IC circuit board, the shot image is sent to the image detection device 100, the image detection device 100 can execute the image detection device provided by the embodiment of the invention to detect the characteristic parameters of the welding spots welded on the IC circuit board, and the boundary fitting is carried out based on the obtained characteristic parameters, so that the positions of the welding spots in the image are determined, and the defect detection of the welding spots can be carried out according to the fitting result.
The following describes an image detection method provided by an embodiment of the present invention with the image detection apparatus 100 in fig. 1 as an execution subject, referring to fig. 3, fig. 3 is a schematic flowchart of the image detection method provided by the embodiment of the present invention, and may include the following steps:
s301: acquiring an image to be detected; the image to be detected contains a characteristic target;
s302: determining target pixel points in an image to be detected and vector representation and weight of elliptical tangent lines at each target pixel point;
s303: according to vector representations and weights corresponding to all ellipse tangents, estimating parameter values of characteristic parameters of a characteristic target, and obtaining optimal parameter values based on an updating strategy;
s304: and positioning and detecting the characteristic target according to the optimal parameter value.
In the technical solutions of steps S301 to S304, the target pixel point is screened after the image to be detected is obtained, interference of human factors and camera noise on detection precision can be avoided, then vector representation and weight corresponding to an elliptical tangent line at the target pixel point are obtained, precision and robustness of detection based on the elliptical tangent line can be improved by setting weight, parameter estimation is performed according to the obtained vector representation and weight of all elliptical tangent lines, a parameter value of an elliptical target characteristic parameter is obtained, in order to determine whether the parameter value is an optimal parameter value, repeated iteration is obtained based on an updating strategy, an optimal parameter value is obtained, estimation precision of the parameter value is improved, and accuracy of positioning and detection of the characteristic target in the image to be detected can be improved.
In an alternative embodiment, the characteristic target is an elliptical target, and the characteristic parameters may include coordinates of a central point, a rotation angle, a major axis value and a minor axis value of the elliptical target, and then the target position of the elliptical target in the image to be detected may be determined according to the central coordinates; and curve fitting is carried out at the target position according to the rotation angle, the major axis value and the minor axis value to obtain an elliptic boundary, and compared with the actual boundary of the characteristic target, the fitted elliptic boundary has smaller error and higher accuracy.
The above steps are described in detail below.
In step S301, the image to be detected may be an image received in real time by the image detection apparatus or a pre-stored image, and the image to be detected has a feature target therein, the feature target having an elliptical feature. For example, the image to be detected is an image obtained by photographing an IC circuit board, wherein the elliptical target is a solder joint on the IC circuit board.
In step S302, a vector representation of the target pixel points in the image to be detected and the ellipse tangent at each target pixel point, as well as the weights, are determined.
In the embodiment of the present invention, the screening of the target pixel point from the target to be detected can avoid the interference of human factors and camera noise on the detection precision, the setting of the weight can improve the precision and the robustness of the detection based on the ellipse tangent, and in order to achieve the above technical effects, the step S302 may include the following sub-steps:
Sub-step 1: converting the image to be detected into a gradient image;
sub-step 2: and determining vector representation and weight of the target pixel point and the ellipse tangent according to the gradient amplitude of each pixel point in the gradient image.
It will be appreciated that the image gradient calculates the degree to which the pixels of the image change. For the edge part of the image, the gray value change is larger, and the gradient value is larger; for the smoother part of the image, the gray value change is smaller, the corresponding gradient value is also smaller, so that the image gradient calculates the edge information of the image, and therefore, in order to realize the positioning of the elliptical target, the boundary position information of the elliptical target can be determined to improve the positioning precision, so that the embodiment of the invention can construct an elliptical tangent line through the gradient information, thereby solving the parameter value of the characteristic parameter of the elliptical target, carrying out boundary fitting under the constraint of the parameter value, and obtaining the fitting result conforming to the actual situation, and after the image to be detected is obtained, converting the image to be detected into the gradient image, thereby obtaining the information such as the gradient amplitude of the elliptical boundary pixel point. The conversion mode of the gradient image is the prior art, and is not described herein.
In the embodiment of the invention, considering that the conventional ellipse parameter estimation method usually extracts the boundary of the ellipse first, then uses a numerical method to fit the extracted boundary into the required ellipse parameter. The reason why the edge extraction step exists is that the ellipse characteristic is defined in the form of a point conic, as shown in equation (1):
wherein,,is a coefficient in the quadratic curve expression, is also a characteristic parameter of an elliptic target, and is a point on the quadratic curve +.>There is equation (2):
(2)
in the middle of、/>Is the i pixel point->Horizontal and vertical coordinates of (a).
By the dual relationship of points and lines, an ellipse can also be represented by a tangent line in its dual space, and a tangent line on an ellipseWherein->Is tangential->Coefficients of the corresponding standard equation, equation (3) also exists:
(3)
in the middle ofIs->Is>Characteristic parameters of->Form as equation (4):
theoretically, the characteristic parameters can be uniquely determined only by knowing exactly 5 elliptical tangents at different positions. Therefore, as known from the dual conic theory, the parameter value of the characteristic parameter of the elliptic target must be obtained first, the image gradient at the elliptic boundary not only can distinguish the image, but also can represent the normal direction of the image edge.
Therefore, in order to avoid interference of human factors and camera noise on detection accuracy in the embodiment of the present invention, the embodiment of the present invention provides a threshold segmentation method to screen out a target pixel point for parameter estimation, that is, the implementation of the sub-step 1 may be: determining a boundary neighborhood of the feature target in the gradient image; and determining the pixel point with the gradient amplitude larger than a preset threshold value as a target pixel point at the boundary neighborhood.
The boundary neighborhood may be understood as an area formed by adjacent pixels of the boundary pixel points of the elliptical target in eight directions, and a preset multiple of an average value of gradient magnitudes corresponding to the pixels in the boundary neighborhood is determined as a preset threshold, for example, the preset multiple is 2 times or 3 times, and the target pixel points can be screened out from the boundary neighborhood through the preset threshold.
In order to determine the vector representation and the weights of the ellipse tangent at each target pixel point, for the sub-step 2 described above, the implementation manner provided by the embodiment of the present invention may be:
and taking a vector formed by the product of the horizontal gradient amplitude of the target pixel point in the horizontal direction, the vertical gradient amplitude of the target pixel point in the vertical direction, the gradient amplitude of the negative gradient direction and the coordinates of the target pixel point as a vector representation, and taking the modulus value of the gradient corresponding to the target pixel point as the weight of an ellipse tangent.
In an embodiment of the present invention, the gradient of the pixel point at the boundary neighborhood can be expressed asWherein, the method comprises the steps of, wherein,horizontal ladder for ith pixel point respectivelyDegree amplitude and vertical gradient amplitude, then ellipse tangent l at that pixel point i The vector representation of (2) is as in equation (5):
(5)
wherein,,the coordinate representation of the ith pixel point; the negative sign indicates the negative direction of the gradient, the normal to the straight line direction points to the gradient direction of the i-th pixel, and the elliptical focus is in the straight line normal.
In order to improve detection precision and robustness, a modulus value of a gradient amplitude of each target pixel point is used as a weight of an ellipse tangent, in general, the ellipse tangent with a large gradient modulus value is located on an ellipse boundary with a larger probability, and the importance of the ellipse boundary with the large gradient modulus value to characteristic parameter estimation of an ellipse target is far greater than that of the ellipse boundary with a small gradient modulus value.
After a set of ellipse tangents are obtained, step S303 is described in detail below.
In the technical solution of step S303, first, parameter value estimation is performed on the feature parameters of the feature target according to vector representations and weights corresponding to all ellipse tangents, which may include the following steps:
step 1: constructing a function to be solved about the characteristic parameters according to the vector representation and the weights;
as shown in the above equations (1) and (4), it can be seen that the characteristic parameters to be solved in the embodiment of the present invention are coefficients of quadratic curves corresponding to ellipses, and the characteristic parameter vector to be solved is recorded asThen->For each ellipse tangent line l i Weight of it is set to +.>Then the functional form to be solved is as in equation (6):
(6)
wherein,,characterization of the i-th ellipse tangent, shaped as +.>;/>Is->Vector parameters of (a); />、/>Is->Horizontal gradient magnitude and vertical gradient magnitude of target pixel at>Characterizing the product of the negative directional gradient and the coordinates of the target pixel point; r represents a set of ellipse tangents; />Characterization of->Weights of ellipse tangents; />Characterizing a feature parameter vector to be solved; />Characterizing the function to be solved, it can be seen that the function to be solved is constructed based on the feature parameter vector to be solved, the vector representation of the ellipse tangent and the weight.
Step 2: and solving the function to be solved to obtain parameter values of the characteristic parameters except the normal parameters.
In the embodiment of the invention, a characteristic parameter with a constant value exists in the elliptic conic equation, namely F in the characteristic parameter vector, so that before solving a function to be solved, the parameter value of a constant parameter in the characteristic parameter vector to be solved can be set as a first value, the function to be solved is converted based on the parameter value of the constant parameter, and the converted function to be solved is solved based on a least square method, so that the parameter values of the residual characteristic parameters except the constant parameter are obtained.
Considering uncertainty in the linear scale, for each ellipse tangentCan be made to satisfyThus achieving the effect of the linear normalization, the above equation (6) can be changed to equation (7):
(7)
wherein,,consists of parameters of an ellipse tangent and +.>。
In the prior art, it is common to have a constraintUnder the limitation of (1), the function to be solved is directly solved by SVD decomposition method to obtain the parameter value of each characteristic parameter.
However, the process is not limited to the above-described process,the actual parameters of the ellipse are not satisfied, and the calculated ellipse parameters are often biased estimates of the ellipse. Therefore, the embodiment of the invention does not adopt the method to calculate the least square solution of the ellipse parameters. Owing to the discriminant of ellipse +. >. Equation (8) is observed:
in the aboveFor symmetrical positive definite matrix ++>Thus->Necessarily greater than 0. In the embodiment of the present invention, the two sides of the formula (3) are multiplied by the non-zero scale factor simultaneously, so that +.>=1. Thus formula (7) can be written as:
wherein,,by->The parameter composition of (C) is as follows->;/>By->Is formed by combining partial parameters of (a) as +.>. Equation (9) is the converted function to be solved according to the embodiment of the present invention ++> 。At this time, the equation (9) is solved by the least square method, and a least square solution satisfying the elliptic base discriminant, that is, the parameter value of the characteristic parameter can be obtained.
After obtaining the parameter value of the feature parameter, to determine whether the parameter value is an optimal parameter value, the parameter value may be updated based on an update policy, and in an implementation process, the method may include the following steps:
step 3: and determining the central coordinate variance of the characteristic target under the constraint of the estimated parameter value.
Firstly, under the constraint that a function to be solved is equal to zero, transforming a characteristic parameter vector to be solved to obtain an observation residual vector of the characteristic parameter; then, constructing a weight square matrix according to all weights, calculating a transpose of an observation residual vector, a product matrix of the weight square matrix and the observation residual vector, calculating a product between the product matrix and the transpose of the product matrix, dividing the product by the difference between the preset observation times and the number of parameter values of the residual characteristic parameters, and obtaining a variance matrix corresponding to the characteristic parameters; finally, in the variance matrix, the variance of the abscissa is calculated according to the relation between the abscissa of the center coordinate and the corresponding characteristic parameter and the covariance propagation law, and the variance of the ordinate is calculated according to the relation between the ordinate of the center coordinate and the corresponding characteristic parameter and the covariance propagation law.
The above embodimentIn which the accuracy of the parameter value of the estimated characteristic parameter is determined by using the probability statistics knowledge, and in the probability statistics, the observation residual matrix of the parameter is set as,/>Is a coefficient matrix->Is a parameter matrix->Is a constant matrix; the weighting matrix of the parameters is +.>The method comprises the steps of carrying out a first treatment on the surface of the The observation times are->The number of parameters is->. At this time, unit weight variance of the defined parameter>The form is as equation (10):
for parameter matrixThe variance of the parameter matrix is defined as equation (11):
thus, in combination with the probability statistics described above, embodiments of the present invention assume that equation (4) above is equal to zero, i.e., that the given fitting data is error-free, meaning that in equation (4)The part is equal to zero, and the part of expression is unfolded by combining the vector representation of the elliptic tangent, so that the observation residual vector of the characteristic parameters can be obtained, and the observation residual vector is formed as follows: the shape is as follows:the method comprises the steps of carrying out a first treatment on the surface of the n represents the total number of ellipse tangents; />The shape is as follows: />,/>Characterizing the characteristic parameter vector after solving.
From the above, the number of feature parameters to be estimated is 5, and the number of observations is set toTherefore, assume thatIs->Square matrix of construction, variance matrix corresponding to characteristic parameter ∈>As a 5x5 square matrix, it can be calculated by equation (10):
(12)
From the epipolar geometry theory, the coordinates of the center of the ellipseMatrix of characteristic parameters>The following relational expression (13) is satisfied: i.e., a polar line constructed from points on an ellipse, whose infinity is the center location of the ellipse:
(13)
from the above relation (13), the ellipse center is knownAnd->Through covariance propagation law, a calculation equation of the variance of the center of the ellipse can be obtained as equation (14):
(14)
wherein,,is the abscissa variance of the center coordinates of the elliptical target, +.>Is the ordinate variance of the center coordinates of the elliptical target, +.>Is the variance of the characteristic parameter D; />Is the variance of the characteristic parameter E.
By calculating the variance of the center coordinates of the elliptical target, the fitting accuracy of the ellipse can be quantitatively evaluated, see step 4.
Step 4: and determining an optimal parameter value according to a comparison result of the central coordinate variance and a preset precision threshold.
In the embodiment of the invention, if the variance of the central coordinate is smaller than the preset precision threshold, the parameter value is used as the optimal parameter value, otherwise, the estimated parameter is not the optimal estimation of the current elliptical target, the weight of the elliptical tangent is updated, the parameter value of the characteristic parameter is updated based on the updated weight, and the parameter estimation is performed again based on the updated weight until the variance of the central coordinate is smaller than the preset precision threshold or reaches the upper limit of the set iteration times, so as to obtain the optimal parameter value.
In the embodiment of the present invention, an implementation manner of updating the weight of the ellipse tangent is provided, that is, the distance between all the pixel points and the current ellipse parameter is calculated, if the distance is greater than the set distance threshold, the tangent weight corresponding to the pixel point is set to be 0, so that the method can be performed according to the following steps:
step a: a conic equation of the elliptical target is obtained according to the parameter values of all the characteristic parameters;
step b: substituting the coordinate value of each target pixel point into a quadratic curve equation to obtain an equation solution corresponding to each target pixel point;
step c: and updating the weight of the elliptic tangent corresponding to the target pixel point with the equation solution larger than the preset equation solution to zero.
It can be understood that, for any point on the conic, when the coordinate value of the point is brought into the conic equation, the equation result is zero, otherwise the equation result is not zero, so in the embodiment of the invention, the preset equation is solved to zero, under the constraint of the estimated parameter value, if the coordinate values of all the target pixel points are brought into the conic equation to be zero, it is proved that the target pixel points are on the boundary of the elliptic target, the elliptic target can be accurately fitted according to the parameter value, otherwise, the weight of the corresponding elliptic tangent of the target pixel point which cannot make the conic equation equal to zero is updated to zero, and then parameter estimation is returned.
In step 304, the feature object is an elliptical object; the parameter values of the characteristic parameters comprise coordinates of a central point, a rotation angle, a major axis value and a minor axis value of the elliptical target, and the characteristic targets are positioned and detected according to the optimal parameter values, and the method comprises the following steps: determining the target position of the characteristic target in the image to be detected according to the center point coordinates; and performing curve fitting on the target position according to the rotation angle, the long axis value and the short axis value to obtain the boundary of the characteristic target, thereby realizing the positioning and detection effects of the characteristic target.
According to the embodiment, based on the dual quadratic curve theoretical model, constraint conditions such as threshold segmentation, weight distribution, linear normalization and ellipse discriminant are added in ellipse parameter solving, and compared with simple point constraint, the embodiment of the invention can rapidly and accurately estimate the parameter value of the ellipse target characteristic parameter, and through experimental verification, the ellipse parameter fitting precision of the embodiment of the invention is 0.03pixel; in addition, when the parameter value of the characteristic parameter is estimated, ellipse contour data do not need to be extracted in advance, so that the efficiency of ellipse parameter estimation is greatly improved; and carrying out precision evaluation on the ellipse fitting result, carrying out fitting iteration based on the precision evaluation result, and still obtaining a precise and stable fitting result under the condition that the ellipse has defects.
In order to verify the accuracy and robustness of the algorithm proposed by the embodiment of the present invention, the image detection system 10 shown in fig. 1 may be used for verification, and the hardware of the system includes: 1 MV-CE200-11GM type industrial camera. Wherein, the size of the camera pixel is 2.4 2.4/>The method comprises the steps of carrying out a first treatment on the surface of the Resolution is 2688%> 1520/>. The lens size is 4.8->. Is provided with megapixels 25->Industrial camera lens with focal length and outer diameter of 120 +.>Is a blue ring-shaped light source.
Before the calibration experiment, an ellipse fitting experiment is performed first, ellipse parameter extraction is performed on an analog image, and comparison is performed with a traditional Sobel operator. The simulated image was drawn into large circles on 4 calibration plates by PhotoShop software. Considering the smoothing effect of an actual CMOS sensor and an optical system on an image, carrying out ellipse parameter estimation on the generated image after neighborhood smoothing, verifying the accuracy of an algorithm, simulating an experimental image and the result of the ellipse parameter estimation as shown in fig. 4A and 4B. Fig. 4A is a schematic diagram illustrating an effect of extracting a characteristic parameter of a simulated ellipse provided by the embodiment of the present invention, and fig. 4B is a schematic diagram illustrating an effect of locally amplifying an ellipse in an upper left corner in fig. 4A, which obviously shows that an ellipse parameter estimated by an image detection method provided by the embodiment of the present invention can be accurately fitted to a real ellipse, and has high accuracy.
In order to quantitatively verify the detection accuracy of the embodiment of the invention, the result of center coordinate extraction of the elliptical target is compared with a true value, and the comparison result is shown as an elliptical center extraction result in a simulation image in table 1.
TABLE 1
As can be seen from the table, the mean value of the abscissa error of the centers of the four ellipses is 0.028The mean value of the ordinate error is 0.027 +.>. Therefore, the accuracy of the characteristic parameters extracted by the image detection method provided by the embodiment of the invention can reach 0.03Compared with the extraction result of the Sobel operator, the embodiment of the invention greatly improves the extraction precision of the ellipse parameters. />
In a service scene of detecting welding spots in an IC board, the image detection method provided by the embodiment of the invention can accurately detect and position welding spots, for example, welding spots are arranged in a chip image obtained by image acquisition of a chip, for example, one welding spot is selected, the image detection method provided by the prior art and the embodiment of the invention is used for fitting, the fitting effect is shown in fig. 5, wherein the left graph is the fitting effect of the prior art, the right graph is the fitting effect of the embodiment of the invention, and it can be obviously seen that the fitting result of the embodiment of the invention can avoid the influence of defects, which indicates that the image detection method provided by the embodiment of the invention can stably and accurately extract ellipse parameters when ellipses have defects, and the fitting accuracy and the robustness can be higher by using the parameter value.
Based on the same inventive concept, an embodiment of the present invention further provides an image detection apparatus, as shown in fig. 6, fig. 6 is a functional block diagram of the image detection apparatus according to the embodiment of the present invention, and the image detection apparatus 400 may include: the acquisition module 410, the determination module 420, the estimation module 430, the positioning and detection module 440.
An acquisition module 410, configured to acquire an image to be detected; the image to be detected contains a characteristic target;
a determining module 420, configured to determine a target pixel point in the image to be detected and a vector representation and a weight of an ellipse tangent at each target pixel point;
the estimation module 430 is configured to perform parameter value estimation on the feature parameters of the feature target according to the vector representations and weights corresponding to all ellipse tangents, and obtain an optimal parameter value based on an update policy;
the positioning and detecting module 440 is configured to position and detect the feature object according to the optimal parameter value.
It is appreciated that the acquisition module 410, the determination module 420, the estimation module 430, and the positioning and detection module 440 may cooperatively perform the steps of fig. 3 to achieve corresponding technical effects.
In alternative embodiments, the determining module 420 may be specifically configured to perform the embodiments of the sub-steps 1 and 2 and each of the sub-steps 1 and 2, so as to achieve the corresponding technical effects.
In an alternative implementation manner, the estimation module 430 may be specifically configured to perform steps 1 to 4 and steps a to c in the embodiment of the present invention to achieve corresponding technical effects.
In an alternative embodiment, the positioning and detecting module 440 is specifically configured to determine a target position of the elliptical target in the image to be detected according to the center coordinates; and performing curve fitting according to the rotation angle, the major axis value and the minor axis value at the target position to obtain an elliptical boundary.
It should be noted that, in the above embodiments of the present application, the division of the modules is merely schematic, and there may be another division manner in actual implementation, and in addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or may exist separately and physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all or part of the technical solution contributing to the prior art or in the form of a software product stored in a storage medium, including several instructions to cause an image detection device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: u disk, mobile hard disk and ROM ROM), random access memory (>RAM), magnetic or optical disk, or the like, and can store program codes.
Based on the above embodiments, the present application also provides a storage medium in which a computer program is stored, which when executed by a computer, causes the computer to execute the image detection method provided in the above embodiments.
Based on the above embodiments, the present invention also provides a computer program, which when run on a computer, causes the computer to execute the image detection method provided in the above embodiments.
Based on the above embodiments, the present invention further provides a chip, where the chip is configured to read a computer program stored in a memory, and is configured to perform the image detection method provided in the above embodiments.
Embodiments of the present invention also provide a computer program product comprising instructions which, when run on a computer, cause the computer to perform the image detection method provided in the above embodiments.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by instructions. These instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The present invention is not limited to the above embodiments, and any changes or substitutions that can be easily understood by those skilled in the art within the technical scope of the present invention 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 (12)
1. An image detection method, the method comprising:
acquiring an image to be detected; the image to be detected comprises a characteristic target;
determining a target pixel point in the image to be detected and vector representations and weights of elliptical tangent lines at the target pixel points;
according to the vector representations and the weights corresponding to all the ellipse tangents, estimating the parameter values of the characteristic parameters of the characteristic targets, and obtaining optimal parameter values based on an updating strategy;
and positioning and detecting the characteristic target according to the optimal parameter value.
2. The image detection method according to claim 1, wherein determining a vector representation and a weight of a target pixel point in the image to be detected and an ellipse tangent at each of the target pixel points, comprises:
converting the image to be detected into a gradient image;
and determining vector representations and weights of the target pixel points and the ellipse tangent according to the gradient amplitude of each pixel point in the gradient image.
3. The image detection method according to claim 2, wherein determining the vector representation of the target pixel and the ellipse tangent and the weights according to the gradient magnitude of each pixel in the gradient image comprises:
Determining a boundary neighborhood of the feature object in the gradient image;
determining the pixel point with the gradient amplitude larger than a preset threshold value as the target pixel point at the boundary neighborhood;
and taking a vector formed by the product of the horizontal gradient amplitude of the target pixel point in the horizontal direction, the vertical gradient amplitude of the target pixel point in the vertical direction and the product of the gradient amplitude of the negative gradient direction and the coordinates of the target pixel point as the vector representation, and taking the modulus value of the gradient corresponding to the target pixel point as the weight of the ellipse tangent.
4. The image detection method according to claim 1, wherein estimating the parameter value of the feature parameter of the feature object based on the vector representations and the weights corresponding to all the ellipse tangents, comprises:
constructing a function to be solved about the characteristic parameters according to the vector representation and the weights;
and solving the function to be solved to obtain parameter values of the characteristic parameters except the normal parameters.
5. The image detection method according to claim 1, wherein obtaining the optimal parameter value based on the update policy comprises:
Determining the central coordinate variance of the characteristic target under the constraint of the estimated parameter value;
and determining the optimal parameter value according to a comparison result of the central coordinate variance and a preset precision threshold.
6. The image detection method according to claim 5, wherein determining the optimal parameter value according to the comparison result of the center coordinate variance and a preset accuracy threshold value comprises:
and if the central coordinate variance is smaller than the preset precision threshold, taking the parameter value as an optimal parameter value, otherwise, updating the weight of the elliptical tangent line, and updating the parameter value of the characteristic parameter based on the updated weight until the central coordinate variance is smaller than the preset precision threshold or reaches the upper limit of the set iteration times, so as to obtain the optimal parameter value.
7. The image detection method according to claim 6, wherein updating the weight of the ellipse tangent includes:
obtaining a conic equation of the characteristic target according to the parameter values of all the characteristic parameters;
substituting the coordinate value of each target pixel point into the quadratic curve equation to obtain an equation solution corresponding to each target pixel point;
And updating the weight of the ellipse tangent corresponding to the target pixel point with the equation solution larger than the preset equation solution to zero.
8. The image detection method according to claim 1, wherein the feature object is an elliptical object; the parameter values of the characteristic parameters comprise center point coordinates, rotation angles, major axis values and minor axis values of the elliptical targets, and the characteristic targets are positioned and detected according to the optimal parameter values, and the method comprises the following steps:
determining the target position of the characteristic target in the image to be detected according to the center point coordinates;
and performing curve fitting on the target position according to the rotation angle, the long axis value and the short axis value to obtain the boundary of the characteristic target.
9. An image detection apparatus, comprising:
the acquisition module is used for acquiring the image to be detected; the image to be detected comprises a characteristic target;
the determining module is used for determining a target pixel point in the image to be detected and vector representations and weights of elliptical tangent lines at the target pixel points;
the estimation module is used for estimating the parameter value of the characteristic parameter of the characteristic target according to the vector representations and the weights corresponding to all the ellipse tangents, and obtaining an optimal parameter value based on an updating strategy;
And the positioning and detecting module is used for positioning and detecting the characteristic target according to the optimal parameter value.
10. An image detection apparatus comprising a processor and a memory, the memory storing a computer program executable by the processor, the processor being executable to implement the image detection method of any one of claims 1 to 8.
11. An image detection system comprising the image detection device of claim 10 and a camera platform; the camera platform is used for acquiring an image to be detected and sending the image to be detected to the image detection device, and the image detection device is used for executing the image detection method as claimed in any one of claims 1 to 8.
12. A readable storage medium having stored thereon a computer program, which when executed by a processor implements the image detection method according to any of claims 1 to 8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310745475.2A CN116503387B (en) | 2023-06-25 | 2023-06-25 | Image detection method, device, equipment, system and readable storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310745475.2A CN116503387B (en) | 2023-06-25 | 2023-06-25 | Image detection method, device, equipment, system and readable storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116503387A true CN116503387A (en) | 2023-07-28 |
CN116503387B CN116503387B (en) | 2024-03-26 |
Family
ID=87318651
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310745475.2A Active CN116503387B (en) | 2023-06-25 | 2023-06-25 | Image detection method, device, equipment, system and readable storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116503387B (en) |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020150280A1 (en) * | 2000-12-04 | 2002-10-17 | Pingshan Li | Face detection under varying rotation |
JP2006350553A (en) * | 2005-06-14 | 2006-12-28 | Kyoto Univ | Corresponding point retrieval method, mutual location method, three-dimensional image measurement method, corresponding point retrieval device, mutual location device, three-dimensional image measurement device, corresponding point retrieval program and computer-readable recording medium with its program recorded |
CN107209849A (en) * | 2015-01-07 | 2017-09-26 | 微软技术许可有限责任公司 | Eyes are tracked |
CN107301638A (en) * | 2017-05-27 | 2017-10-27 | 东南大学 | A kind of ellipse detection method based on arc support line segment |
CN109086734A (en) * | 2018-08-16 | 2018-12-25 | 新智数字科技有限公司 | The method and device that pupil image is positioned in a kind of pair of eye image |
CN110276324A (en) * | 2019-06-27 | 2019-09-24 | 北京万里红科技股份有限公司 | The elliptical method of pupil is determined in a kind of iris image |
CN110781956A (en) * | 2019-10-24 | 2020-02-11 | 精硕科技(北京)股份有限公司 | Target detection method and device, electronic equipment and readable storage medium |
CN111626236A (en) * | 2020-05-29 | 2020-09-04 | 常州工学院 | Rapid ellipse target detection method |
CN112967281A (en) * | 2021-04-07 | 2021-06-15 | 洛阳伟信电子科技有限公司 | Ellipse detection algorithm based on arc support growth |
US20220172393A1 (en) * | 2019-04-05 | 2022-06-02 | Airbus Defence And Space Sas | Method for locating a target from an elliptical contour |
CN114648544A (en) * | 2022-03-22 | 2022-06-21 | 聚时领臻科技(浙江)有限公司 | Sub-pixel ellipse extraction method |
CN115423870A (en) * | 2022-08-29 | 2022-12-02 | 中汽创智科技有限公司 | Pupil center positioning method and device |
CN115457063A (en) * | 2022-08-23 | 2022-12-09 | 武汉海微科技有限公司 | Method, device and equipment for extracting edge of circular hole of PCB (printed Circuit Board) and storage medium |
-
2023
- 2023-06-25 CN CN202310745475.2A patent/CN116503387B/en active Active
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020150280A1 (en) * | 2000-12-04 | 2002-10-17 | Pingshan Li | Face detection under varying rotation |
JP2006350553A (en) * | 2005-06-14 | 2006-12-28 | Kyoto Univ | Corresponding point retrieval method, mutual location method, three-dimensional image measurement method, corresponding point retrieval device, mutual location device, three-dimensional image measurement device, corresponding point retrieval program and computer-readable recording medium with its program recorded |
CN107209849A (en) * | 2015-01-07 | 2017-09-26 | 微软技术许可有限责任公司 | Eyes are tracked |
CN107301638A (en) * | 2017-05-27 | 2017-10-27 | 东南大学 | A kind of ellipse detection method based on arc support line segment |
CN109086734A (en) * | 2018-08-16 | 2018-12-25 | 新智数字科技有限公司 | The method and device that pupil image is positioned in a kind of pair of eye image |
US20220172393A1 (en) * | 2019-04-05 | 2022-06-02 | Airbus Defence And Space Sas | Method for locating a target from an elliptical contour |
CN110276324A (en) * | 2019-06-27 | 2019-09-24 | 北京万里红科技股份有限公司 | The elliptical method of pupil is determined in a kind of iris image |
CN110781956A (en) * | 2019-10-24 | 2020-02-11 | 精硕科技(北京)股份有限公司 | Target detection method and device, electronic equipment and readable storage medium |
CN111626236A (en) * | 2020-05-29 | 2020-09-04 | 常州工学院 | Rapid ellipse target detection method |
CN112967281A (en) * | 2021-04-07 | 2021-06-15 | 洛阳伟信电子科技有限公司 | Ellipse detection algorithm based on arc support growth |
CN114648544A (en) * | 2022-03-22 | 2022-06-21 | 聚时领臻科技(浙江)有限公司 | Sub-pixel ellipse extraction method |
CN115457063A (en) * | 2022-08-23 | 2022-12-09 | 武汉海微科技有限公司 | Method, device and equipment for extracting edge of circular hole of PCB (printed Circuit Board) and storage medium |
CN115423870A (en) * | 2022-08-29 | 2022-12-02 | 中汽创智科技有限公司 | Pupil center positioning method and device |
Also Published As
Publication number | Publication date |
---|---|
CN116503387B (en) | 2024-03-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP3735344B2 (en) | Calibration apparatus, calibration method, and calibration program | |
CN112232279B (en) | Personnel interval detection method and device | |
CN111445531B (en) | Multi-view camera navigation method, device, equipment and storage medium | |
CN107038443B (en) | Method and device for positioning region of interest on circuit board | |
CN107980138A (en) | A kind of false-alarm obstacle detection method and device | |
CN108447094B (en) | Method and system for estimating attitude of monocular color camera | |
CN112270719B (en) | Camera calibration method, device and system | |
CN114862973B (en) | Space positioning method, device and equipment based on fixed point location and storage medium | |
CN111681186A (en) | Image processing method and device, electronic equipment and readable storage medium | |
CN113763478B (en) | Unmanned vehicle camera calibration method, device, equipment, storage medium and system | |
CN112348909A (en) | Target positioning method, device, equipment and storage medium | |
CN111353325A (en) | Key point detection model training method and device | |
CN111383264A (en) | Positioning method, positioning device, terminal and computer storage medium | |
WO2019123554A1 (en) | Image processing device, image processing method, and recording medium | |
KR101188296B1 (en) | Weighted-based target decision method for strapdown dual mode imaging seeker and system thereof | |
CN116503387B (en) | Image detection method, device, equipment, system and readable storage medium | |
CN115272482A (en) | Camera external reference calibration method and storage medium | |
CN112270693B (en) | Method and device for detecting motion artifact of time-of-flight depth camera | |
CN114648544A (en) | Sub-pixel ellipse extraction method | |
EP4054187A1 (en) | Calibration method of a portable electronic device | |
CN111223139B (en) | Target positioning method and terminal equipment | |
CN113587895A (en) | Binocular distance measuring method and device | |
CN114415129A (en) | Visual and millimeter wave radar combined calibration method and device based on polynomial model | |
CN116958931B (en) | Method and computing device for vehicle collision early warning in warehouse | |
CN111586299B (en) | Image processing method and related equipment |
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 |