CN116697897B - Method and system for detecting position of shielding object - Google Patents
Method and system for detecting position of shielding object Download PDFInfo
- Publication number
- CN116697897B CN116697897B CN202310994645.0A CN202310994645A CN116697897B CN 116697897 B CN116697897 B CN 116697897B CN 202310994645 A CN202310994645 A CN 202310994645A CN 116697897 B CN116697897 B CN 116697897B
- Authority
- CN
- China
- Prior art keywords
- edge
- virtual
- analysis
- point
- determining
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004458 analytical method Methods 0.000 claims abstract description 87
- 238000001514 detection method Methods 0.000 claims abstract description 74
- 230000000007 visual effect Effects 0.000 claims abstract description 63
- 238000013507 mapping Methods 0.000 claims abstract description 11
- 239000000523 sample Substances 0.000 claims description 31
- 238000003708 edge detection Methods 0.000 claims description 24
- 238000011156 evaluation Methods 0.000 claims description 15
- 230000009467 reduction Effects 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000033228 biological regulation Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- 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
- G06T2207/10048—Infrared image
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application discloses a method and a system for detecting the edge position of a shielding object, which relate to the technical field of shielding object wide detection, dynamically generate a virtual analysis map, set infrared detection points for mapping positions of each infrared sensor, determine first edge position points of the edge of the shielding object relative to the virtual analysis map according to the infrared detection points mapped by two infrared sensors, connect every two adjacent first edge position points in the first edge position points in a first edge position array to generate a virtual first edge line, perform visual analysis on the virtual analysis map according to a preset visual analysis strategy, determine a plurality of second edge position points according to visual analysis, correct the virtual first edge line according to the second edge position points to generate a second edge line.
Description
Technical Field
The application relates to the technical field of shielding object wide detection, in particular to a shielding object position detection method and system.
Background
In the existing production line, especially a cloth production line, a plate production line or other production lines with wide requirements on production products, a multipoint infrared detection device is used for detecting the wide of the products, and further compliance of the products is guaranteed, however, because a certain distance exists between infrared sensors of the multipoint infrared detection device, the edges of the products just between the two infrared sensors cannot be accurately determined, and the product requirements with high accuracy requirements cannot be met.
Disclosure of Invention
The application aims to provide a detection method and a detection system capable of improving the wide detection accuracy.
The application discloses a method for detecting the edge position of a shielding object, which comprises the following steps:
driving a camera to shoot a shielding object in real time to dynamically generate a virtual analysis map, wherein the center of the virtual analysis map is overlapped with the center of the multi-point infrared detection device;
mapping the position of each infrared sensor on the virtual analysis map according to the position difference of the infrared sensor of the multi-point infrared detection device relative to the center of the multi-point infrared detection device, and setting an infrared detection point for the mapping position of each infrared sensor;
driving a multipoint infrared detection device to scan and analyze the edge of the shielding object, determining two infrared sensors corresponding to the edge of the shielding object, determining a first edge position point of the edge of the shielding object relative to a virtual analysis map according to infrared detection points mapped by the two infrared sensors, generating a first edge position array according to detection frequencies of the infrared sensors, and connecting every two adjacent first edge position points in the first edge position array to generate a virtual first edge line;
performing visual analysis on the virtual analysis map according to a preset visual analysis strategy, and determining a plurality of second edge position points according to the visual analysis;
correcting the virtual first edge line according to the second edge position point to generate a second edge line;
and determining the edge of the shielding object according to the second edge line.
In some embodiments of the application, a method of generating a virtual analysis map includes:
analyzing a real-time image of a shielding object shot by a camera in real time, and intercepting the real-time image based on a preset intercepting range to generate a reference image;
graying and noise reduction processing is carried out on the reference image, the edge of the shielding object is determined according to the edge detection technology, and the range of the shielding object is calibrated on the reference image based on the determined edge of the shielding object, so that a virtual analysis map is generated.
In some embodiments of the application, a method of determining a first edge location point includes:
establishing a plane coordinate system aiming at the virtual analysis map;
and acquiring coordinates of infrared detection points mapped by the two infrared sensors corresponding to the edge of the shielding object, calculating intermediate coordinates between the two coordinates, and recognizing the intermediate coordinates as a first edge position point.
In some embodiments of the present application, a method for performing visual analysis on a virtual analysis map according to a preset visual analysis strategy includes:
constructing a visual analysis strategy according to a preset visual analysis frequency, a visual analysis range and a position probe point density inserted during visual analysis;
determining analysis frequency of the virtual analysis map according to the visual analysis frequency in the visual analysis strategy;
determining the length of the edge analysis of the shelter in the virtual analysis map according to the visual analysis range in the visual analysis strategy, and defining an edge detection interval for the shelter according to the determined length of the edge of the shelter;
determining the distance between the position probe points of the edge detection interval according to the position probe point density in the visual analysis strategy;
and determining the position of the position probe point according to the determined interval between the edge detection interval and the position probe point, and determining the position of the position probe point as the position of the second edge position point.
In some embodiments of the present application, the method for detecting the edge position of the obstruction further includes: the accuracy evaluation is carried out on the second edge line, and the method for carrying out the accuracy evaluation on the second edge line comprises the following steps:
aiming at analysis frequency of the virtual analysis map, constructing a frequency precision influence operator;
constructing a length accurate influence operator aiming at the length of the edge analysis of the shielding object in the virtual analysis map;
constructing a distance influencing operator aiming at the distance between position probe points of an edge detection interval in the virtual analysis map;
determining a precision evaluation corresponding value of the second edge line based on the frequency precision influence operator, the length precision influence operator and the interval influence operator;
the expression for calculating the accuracy evaluation corresponding value of the second edge line is:
;
wherein j is the corresponding value of the precision evaluation of the second edge line,for the analysis frequency of the virtual analysis map,for the distance between the position probe points of the edge detection interval in the virtual analysis map, +.>For the first adjustment constant, +.>For length of the occlusion edge analysis in the virtual analysis map, +.>For the second adjustment constant, +.>For the first adjustment of the conversion factor, < >>For the second adjustment of the conversion factor,>normalizing the coefficients for the first conversion,/>Is the second-order conversion coefficient.
In some embodiments of the present application, a method for correcting a virtual first edge line according to a second edge position point, and generating a second edge line includes:
establishing an edge comparison line aiming at the edge regulation trend of the shielding object, starting from the position of the second edge position point according to the position of the second edge position point, establishing a connecting line for vertically connecting the edge comparison line, and determining the intersection point of the connecting line and the first edge line as a first adjusting point;
and adjusting the first adjusting point of the first edge line to the position of the second edge position point, carrying out smooth accompanying adjustment on a line segment with a first preset length beside the first edge line, and determining the adjusted first edge line as the second edge line.
In some embodiments of the present application, a method of determining a first preset length includes:
calculating a first distance between the second edge position points and the first edge line, and determining a first credibility factor of the second edge position points by combining the consistency of the first distance between the adjacent second edge position points;
determining a second confidence factor based on the sum of the analysis frequencies of the virtual analysis patterns and the distance between the probe points;
and determining a first preset length according to the first credibility factor and the second credibility factor.
In some embodiments of the present application, the expression for calculating the first preset length is:
;
wherein, l is a first preset length,for a first distance, +>Is the correspondence value of the first distance between adjacent second edge position points, +.>For the third adjustment constant, +.>For the analysis frequency of the virtual analysis pattern, < +.>For the distance between the position probe points of the edge detection interval in the virtual analysis map, +.>Return a coefficient for the third transition, +.>For the fourth conversion factor, +.>For the fourth adjustment constant, +.>For the third adjustment of the conversion factor,>the conversion factor is adjusted for the fourth.
In some embodiments of the application, a correspondence value of the first distance between the second edge location points is determinedThe method of (1) comprises:
accumulating and summing the first distances corresponding to other second edge position points of the preset scanning number near the second edge position point, and calculating to obtain a first distance average value;
respectively comparing the distance difference between the first distance corresponding to the second edge position point and the average value of the first distance, recording the condition that the distance difference is larger than a preset value, and according to the distance differenceDetermining a corresponding value of continuity for occurrence times of cases in which the difference is larger than a preset value。
In some embodiments of the present application, there is also disclosed a system for detecting an edge position of a shutter, including:
the map generation module is used for driving the camera to shoot the shielding object in real time to dynamically generate a virtual analysis map, the center of the virtual analysis map is overlapped with the center of the multi-point infrared detection device, the position of each infrared sensor is mapped on the virtual analysis map according to the position difference of the infrared sensor of the multi-point infrared detection device relative to the center of the multi-point infrared detection device, and an infrared detection point is set for the mapping position of each infrared sensor;
the virtual first edge line determining module is used for driving the multi-point infrared detection device to scan and analyze the edge of the shielding object, determining two infrared sensors corresponding to the edge of the shielding object, determining first edge position points of the edge of the shielding object relative to a virtual analysis map according to infrared detection points mapped by the two infrared sensors, generating a first edge position array according to detection frequencies of the infrared sensors, and connecting every two adjacent first edge position points in the first edge position array to generate a virtual first edge line;
the correction module is used for carrying out visual analysis on the virtual analysis map according to a preset visual analysis strategy, determining a plurality of second edge position points according to the visual analysis, correcting the virtual first edge line according to the second edge position points, generating a second edge line, and determining the edge of the shelter according to the second edge line.
The application discloses a method for detecting the edge position of a shielding object, which relates to the technical field of shielding object wide detection, dynamically generates a virtual analysis map, sets infrared detection points for the mapping positions of each infrared sensor, determines the first edge position points of the edge of the shielding object relative to the virtual analysis map according to the infrared detection points mapped by two infrared sensors, connects every two adjacent first edge position points in the first edge position points in a first edge position array to generate a virtual first edge line, performs visual analysis on the virtual analysis map according to a preset visual analysis strategy, determines a plurality of second edge position points according to visual analysis, corrects the virtual first edge line according to the second edge position points to generate a second edge line, and effectively improves the accuracy of the edge position detection of the shielding object by performing secondary adjustment on the detection result of an infrared detection device through a visual analysis method.
The technical scheme of the application is further described in detail through the drawings and the embodiments.
Drawings
Fig. 1 is a method step diagram of a method for detecting a position of a shielding object according to an embodiment of the present application.
Detailed Description
The technical scheme of the application is further described below through the attached drawings and the embodiments.
The technical solution of the present application will be clearly and completely described below with reference to the accompanying drawings and specific embodiments, it being understood that the preferred embodiments described herein are for illustrating and explaining the present application only and are not to be construed as limiting the scope of the present application, and that some insubstantial modifications and adaptations can be made by those skilled in the art in light of the following disclosure. In the present application, unless explicitly specified and defined otherwise, technical terms used in the present application should be construed in a general sense as understood by those skilled in the art to which the present application pertains.
Examples:
the application aims to provide a detection method and a detection system capable of improving the wide detection accuracy.
The application discloses a method for detecting the edge position of a shielding object, referring to fig. 1, comprising the following steps:
and S100, driving a camera to shoot a shielding object in real time so as to dynamically generate a virtual analysis map, wherein the center of the virtual analysis map is overlapped with the center of the multi-point infrared detection device.
It should be understood that dynamically generating a virtual analysis map may be understood as intermittently intercepting video captured in real time.
Step S200, mapping the position of each infrared sensor on the virtual analysis map according to the difference of the positions of the infrared sensors of the multi-point infrared detection device relative to the center of the multi-point infrared detection device, and setting an infrared detection point for the mapped position of each infrared sensor.
Step S300, a multi-point infrared detection device is driven to scan and analyze the edge of the shielding object, two infrared sensors corresponding to the edge of the shielding object are determined, first edge position points of the edge of the shielding object relative to a virtual analysis map are determined according to infrared detection points mapped by the two infrared sensors, a first edge position array is generated according to detection frequencies of the infrared sensors, and each two adjacent first edge position points in the first edge position array are connected to generate a virtual first edge line.
It should be understood that, when the multi-point infrared detection device is used to scan and analyze the edge of the shielding object, the shielding object and the multi-point infrared detection device need to be relatively displaced, so that the first edge position array needs to be generated according to the detection frequency of the infrared sensor, and the first edge position array can be understood as a set of first edge position points when the infrared sensor is at different positions of the edge of the shielding object.
And step S400, performing visual analysis on the virtual analysis map according to a preset visual analysis strategy, and determining a plurality of second edge position points according to the visual analysis.
And S500, correcting the virtual first edge line according to the second edge position point to generate a second edge line.
Step S600, determining the edge of the shielding object according to the second edge line.
It should be appreciated that the method of analyzing edges using visual analysis techniques includes:
image preprocessing: first, the original image is subjected to preprocessing including graying and noise reduction processing. Converting a color image to a gray image can simplify the calculation and make the edges more visible. Appropriate noise reduction techniques, such as gaussian filtering or median filtering, are then applied to reduce noise in the image.
Calculating the gradient: the gradient operator (e.g., sobel, prewitt or Roberts operator) is used to calculate the gradient for each pixel in the image. Gradients represent the direction and magnitude of the image intensity change. A common approach is to calculate gradient values in the horizontal and vertical directions by applying convolution operations on the image.
Edge strength calculation: the edge intensity of each pixel is calculated from the gradient values. The magnitude of the gradient is typically used to represent the intensity of the edge, i.e., the square root of the magnitude of the horizontal and vertical gradients for each pixel is calculated.
Non-maximum suppression: in the edge detection process, in order to make the detected edge finer and more accurate, a non-maximum suppression method is generally employed. The method can compare the edge intensities in the gradient direction, only the local maximum value points are reserved, and the non-edge area is restrained.
Double thresholding and edge connection: double thresholding is applied on the edge intensity map to divide the pixels into three categories, strong edges, weak edges, and non-edges. Typically, the strong edge pixels are determined by setting appropriate thresholds and the complete edge is formed by connecting the weak edge pixels with the strong edge pixels. This may be achieved using some connectivity algorithm, such as pixel neighborhood based connectivity detection or using an edge tracking algorithm (such as Canny edge detection).
Edge post-treatment: according to application requirements, edge post-processing steps such as edge refinement, edge filling, edge smoothing and the like can be performed to further optimize the result of edge detection.
In some embodiments of the application, a method of generating a virtual analysis map includes:
the method comprises the steps of firstly, analyzing a real-time image of a shielding object shot by a camera in real time, and intercepting the real-time image based on a preset intercepting range to generate a reference image.
And secondly, carrying out graying and noise reduction treatment on the reference image, determining the edge of the shielding object according to an edge detection technology, calibrating the range of the shielding object on the reference image based on the determined edge of the shielding object, and generating a virtual analysis map.
In some embodiments of the application, a method of determining a first edge location point includes:
first, a plane coordinate system is established for the virtual analysis map.
And secondly, acquiring coordinates of infrared probe points mapped by two infrared sensors corresponding to the edge of the shielding object, calculating intermediate coordinates between the two coordinates, and recognizing the intermediate coordinates as first edge position points.
In some embodiments of the present application, a method for performing visual analysis on a virtual analysis map according to a preset visual analysis strategy includes:
firstly, constructing a visual analysis strategy according to preset visual analysis frequency, visual analysis range and the density of the inserted position probe points during visual analysis.
And secondly, determining the analysis frequency of the virtual analysis map according to the visual analysis frequency in the visual analysis strategy.
And thirdly, determining the length of the edge analysis of the shielding object in the virtual analysis map according to the visual analysis range in the visual analysis strategy, and defining an edge detection interval for the shielding object according to the determined length of the edge of the shielding object.
And fourthly, determining the distance between the position probe points of the edge detection interval according to the position probe point density in the visual analysis strategy.
And fifthly, determining the position of the position probe point according to the determined interval between the edge detection interval and the position probe point, and determining the position of the position probe point as the position of the second edge position point.
In some embodiments of the present application, the method for detecting the edge position of the obstruction further includes: the accuracy evaluation is carried out on the second edge line, and the method for carrying out the accuracy evaluation on the second edge line comprises the following steps:
the first step, aiming at the analysis frequency of the virtual analysis map, a frequency accurate influence operator is constructed.
Secondly, constructing a length accurate influence operator aiming at the length of the edge analysis of the shielding object in the virtual analysis map.
Thirdly, constructing a distance influencing operator aiming at the distance between position probe points of an edge detection interval in the virtual analysis map.
And fourthly, determining a precision evaluation corresponding value of the second edge line based on the frequency precision influence operator, the length precision influence operator and the interval influence operator.
The expression for calculating the accuracy evaluation corresponding value of the second edge line is:
。
wherein j is the corresponding value of the precision evaluation of the second edge line,for the analysis frequency of the virtual analysis map,for the distance between the position probe points of the edge detection interval in the virtual analysis map, +.>For the first adjustment constant, +.>For length of the occlusion edge analysis in the virtual analysis map, +.>For the second adjustment constant, +.>For the first adjustment of the conversion factor, < >>For the second adjustment of the conversion factor,>for the first transformation, return a coefficient, +.>Is the second-order conversion coefficient.
In some embodiments of the present application, a method for correcting a virtual first edge line according to a second edge position point, and generating a second edge line includes:
the first step, aiming at the edge regulation trend of the shielding object, establishing an edge comparison line, starting from the position of the second edge position point according to the position of the second edge position point, establishing a connecting line for vertically connecting the edge comparison line, and determining the intersection point of the connecting line and the first edge line as a first adjusting point.
And secondly, adjusting a first adjusting point of the first edge line to the position of a second edge position point, carrying out smooth concomitant adjustment on a line segment with a first preset length beside the first edge line, and determining the adjusted first edge line as the second edge line.
In some embodiments of the present application, a method of determining a first preset length includes:
the first step is to calculate the first distance between the second edge position point and the first edge line, and combine the consistency of the first distance between the adjacent second edge position points to determine the first credibility factor of the second edge position point.
And a second step of determining a second credibility factor based on the analysis frequency of the virtual analysis map and the distance between the probe points.
And thirdly, determining a first preset length according to the first credible factor and the second credible factor.
In some embodiments of the present application, the expression for calculating the first preset length is:
。
wherein, l is a first preset length,for a first distance, +>Is the correspondence value of the first distance between adjacent second edge position points, +.>For the third adjustment constant, +.>For the analysis frequency of the virtual analysis pattern, < +.>For the distance between the position probe points of the edge detection interval in the virtual analysis map, +.>Return a coefficient for the third transition, +.>For the fourth conversion factor, +.>For the fourth adjustment constant, +.>For the third adjustment of the conversion factor,>the conversion factor is adjusted for the fourth.
In some embodiments of the application, a correspondence value of the first distance between the second edge location points is determinedThe method of (1) comprises:
accumulating and summing the first distances corresponding to other second edge position points of the preset scanning number near the second edge position point, and calculating to obtain a first distance average value;
respectively comparing the second edge position point pairsRecording the distance difference between the first distance and the average value of the first distance, and determining a consistency corresponding value according to the occurrence frequency of the distance difference larger than the preset value。
In some embodiments of the present application, there is also disclosed a system for detecting an edge position of a shutter, including:
the map generation module is used for driving the camera to shoot the shielding object in real time so as to dynamically generate a virtual analysis map, the center of the virtual analysis map is overlapped with the center of the multi-point infrared detection device, the position of each infrared sensor is mapped on the virtual analysis map according to the position difference of the infrared sensor of the multi-point infrared detection device relative to the center of the multi-point infrared detection device, and the infrared detection point is set for the mapping position of each infrared sensor.
The virtual first edge line determining module is used for driving the multi-point infrared detection device to scan and analyze the edge of the shielding object, determining two infrared sensors corresponding to the edge of the shielding object, determining first edge position points of the edge of the shielding object relative to a virtual analysis map according to infrared detection points mapped by the two infrared sensors, generating a first edge position array according to detection frequencies of the infrared sensors, and connecting every two adjacent first edge position points in the first edge position array to generate a virtual first edge line.
The correction module is used for carrying out visual analysis on the virtual analysis map according to a preset visual analysis strategy, determining a plurality of second edge position points according to the visual analysis, correcting the virtual first edge line according to the second edge position points, generating a second edge line, and determining the edge of the shelter according to the second edge line.
From the above description of the embodiments, it will be clear to those skilled in the art that the present application may be implemented in hardware, or may be implemented by means of software plus necessary general hardware platforms. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present application.
The application discloses a method for detecting the edge position of a shielding object, which relates to the technical field of shielding object wide detection, dynamically generates a virtual analysis map, sets infrared detection points for the mapping positions of each infrared sensor, determines the first edge position points of the edge of the shielding object relative to the virtual analysis map according to the infrared detection points mapped by two infrared sensors, connects every two adjacent first edge position points in the first edge position points in a first edge position array to generate a virtual first edge line, performs visual analysis on the virtual analysis map according to a preset visual analysis strategy, determines a plurality of second edge position points according to visual analysis, corrects the virtual first edge line according to the second edge position points to generate a second edge line, and effectively improves the accuracy of the edge position detection of the shielding object by performing secondary adjustment on the detection result of an infrared detection device through a visual analysis method.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application and not for limiting it, and although the present application has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that: the technical scheme of the application can be modified or replaced by the same, and the modified technical scheme cannot deviate from the spirit and scope of the technical scheme of the application.
Claims (10)
1. A method for detecting the edge position of a shielding object, comprising the steps of:
driving a camera to shoot a shielding object in real time to dynamically generate a virtual analysis map, wherein the center of the virtual analysis map is overlapped with the center of the multi-point infrared detection device;
mapping the position of each infrared sensor on the virtual analysis map according to the position difference of the infrared sensor of the multi-point infrared detection device relative to the center of the multi-point infrared detection device, and setting an infrared detection point for the mapping position of each infrared sensor;
driving a multipoint infrared detection device to scan and analyze the edge of the shielding object, determining two infrared sensors corresponding to the edge of the shielding object, determining a first edge position point of the edge of the shielding object relative to a virtual analysis map according to infrared detection points mapped by the two infrared sensors, generating a first edge position array according to detection frequencies of the infrared sensors, and connecting every two adjacent first edge position points in the first edge position array to generate a virtual first edge line;
performing visual analysis on the virtual analysis map according to a preset visual analysis strategy, and determining a plurality of second edge position points according to the visual analysis;
correcting the virtual first edge line according to the second edge position point to generate a second edge line;
and determining the edge of the shielding object according to the second edge line.
2. The method for detecting the edge position of an obstruction according to claim 1, wherein the method for generating a virtual analysis map comprises:
analyzing a real-time image of a shielding object shot by a camera in real time, and intercepting the real-time image based on a preset intercepting range to generate a reference image;
graying and noise reduction processing is carried out on the reference image, the edge of the shielding object is determined according to the edge detection technology, and the range of the shielding object is calibrated on the reference image based on the determined edge of the shielding object, so that a virtual analysis map is generated.
3. The method for detecting the edge position of an obstruction according to claim 1, wherein the method for determining the first edge position point comprises:
establishing a plane coordinate system aiming at the virtual analysis map;
and acquiring coordinates of infrared detection points mapped by the two infrared sensors corresponding to the edge of the shielding object, calculating intermediate coordinates between the two coordinates, and recognizing the intermediate coordinates as a first edge position point.
4. The method for detecting the edge position of an obstruction according to claim 1, wherein the method for performing visual analysis on the virtual analysis map according to a preset visual analysis strategy comprises:
constructing a visual analysis strategy according to a preset visual analysis frequency, a visual analysis range and a position probe density inserted during visual analysis;
determining analysis frequency of the virtual analysis map according to the visual analysis frequency in the visual analysis strategy;
determining the length of the edge analysis of the shelter in the virtual analysis map according to the visual analysis range in the visual analysis strategy, and defining an edge detection interval for the shelter according to the determined length of the edge of the shelter;
determining the distance between the position probe points of the edge detection interval according to the position probe point density in the visual analysis strategy;
and determining the position of the position probe point according to the determined interval between the edge detection interval and the position probe point, and determining the position of the position probe point as the position of the second edge position point.
5. The method for detecting the edge position of a shutter according to claim 4, further comprising: the accuracy evaluation is carried out on the second edge line, and the method for carrying out the accuracy evaluation on the second edge line comprises the following steps:
aiming at analysis frequency of the virtual analysis map, constructing a frequency precision influence operator;
constructing a length accurate influence operator aiming at the length of the edge analysis of the shielding object in the virtual analysis map;
constructing a distance influencing operator aiming at the distance between position probe points of an edge detection interval in the virtual analysis map;
determining a precision evaluation corresponding value of the second edge line based on the frequency precision influence operator, the length precision influence operator and the interval influence operator;
the expression for calculating the accuracy evaluation corresponding value of the second edge line is:
;
wherein j is the corresponding value of the precision evaluation of the second edge line,for the analysis frequency of the virtual analysis pattern, < +.>For the distance between the position probe points of the edge detection interval in the virtual analysis map, +.>For the first adjustment constant, +.>For length of the occlusion edge analysis in the virtual analysis map, +.>For the second adjustment constant, +.>For the first adjustment of the conversion factor, < >>For the second adjustment of the conversion factor,>for the first transformation, return a coefficient, +.>Is the second-order conversion coefficient.
6. The method for detecting the edge position of an obstruction of claim 4, wherein the method for correcting the virtual first edge line according to the second edge position point to generate the second edge line comprises:
establishing an edge comparison line aiming at the edge regulation trend of the shielding object, starting from the position of the second edge position point according to the position of the second edge position point, establishing a connecting line for vertically connecting the edge comparison line, and determining the intersection point of the connecting line and the first edge line as a first adjusting point;
and adjusting the first adjusting point of the first edge line to the position of the second edge position point, carrying out smooth accompanying adjustment on a line segment with a first preset length beside the first edge line, and determining the adjusted first edge line as the second edge line.
7. The method for detecting the edge position of a covering according to claim 6, wherein the method for determining the first preset length includes:
calculating a first distance between the second edge position points and the first edge line, and determining a first credibility factor of the second edge position points by combining the consistency of the first distance between the adjacent second edge position points;
determining a second confidence factor based on the sum of the analysis frequencies of the virtual analysis patterns and the distance between the probe points;
and determining a first preset length according to the first credibility factor and the second credibility factor.
8. The method for detecting the edge position of a covering according to claim 7, wherein the expression for calculating the first preset length is:
;
wherein, l is a first preset length,for a first distance, +>Is the correspondence value of the first distance between adjacent second edge position points, +.>For the third adjustment constant, +.>For the analysis frequency of the virtual analysis pattern, < +.>For the distance between the position probe points of the edge detection interval in the virtual analysis map, +.>Return a coefficient for the third transition, +.>For the fourth conversion factor, +.>For the fourth adjustment constant, +.>For the third adjustment of the conversion factor,>the conversion factor is adjusted for the fourth.
9. The method of claim 8, wherein determining a correspondence value of the first distance between the second edge position pointsThe method of (1) comprises:
accumulating and summing the first distances corresponding to other second edge position points of the preset scanning number near the second edge position point, and calculating to obtain a first distance average value;
respectively comparing the distance difference between the first distance corresponding to the second edge position point and the average value of the first distance, recording the situation that the distance difference is larger than a preset value, and determining a consistency corresponding value according to the occurrence times of the situation that the distance difference is larger than the preset value。
10. A shade edge position detection system, comprising:
the map generation module is used for driving the camera to shoot the shielding object in real time to dynamically generate a virtual analysis map, the center of the virtual analysis map is overlapped with the center of the multi-point infrared detection device, the position of each infrared sensor is mapped on the virtual analysis map according to the position difference of the infrared sensor of the multi-point infrared detection device relative to the center of the multi-point infrared detection device, and an infrared detection point is set for the mapping position of each infrared sensor;
the virtual first edge line determining module is used for driving the multi-point infrared detection device to scan and analyze the edge of the shielding object, determining two infrared sensors corresponding to the edge of the shielding object, determining first edge position points of the edge of the shielding object relative to a virtual analysis map according to infrared detection points mapped by the two infrared sensors, generating a first edge position array according to detection frequencies of the infrared sensors, and connecting every two adjacent first edge position points in the first edge position array to generate a virtual first edge line;
the correction module is used for carrying out visual analysis on the virtual analysis map according to a preset visual analysis strategy, determining a plurality of second edge position points according to the visual analysis, correcting the virtual first edge line according to the second edge position points, generating a second edge line, and determining the edge of the shelter according to the second edge line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310994645.0A CN116697897B (en) | 2023-08-09 | 2023-08-09 | Method and system for detecting position of shielding object |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310994645.0A CN116697897B (en) | 2023-08-09 | 2023-08-09 | Method and system for detecting position of shielding object |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116697897A CN116697897A (en) | 2023-09-05 |
CN116697897B true CN116697897B (en) | 2023-11-03 |
Family
ID=87829804
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310994645.0A Active CN116697897B (en) | 2023-08-09 | 2023-08-09 | Method and system for detecting position of shielding object |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116697897B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS63201514A (en) * | 1987-02-17 | 1988-08-19 | Toshiba Mach Co Ltd | Method for measuring plastic sheet width |
CN111526258A (en) * | 2019-02-04 | 2020-08-11 | 京瓷办公信息系统株式会社 | Image forming apparatus with a toner supply device |
CN113487639A (en) * | 2021-07-14 | 2021-10-08 | 北京金山云网络技术有限公司 | Image processing method and device, electronic equipment and storage medium |
CN113551598A (en) * | 2021-07-20 | 2021-10-26 | 钛玛科(北京)工业科技有限公司 | Infrared wide sensor detection device and position detection method of shielding object |
CN114998283A (en) * | 2022-06-17 | 2022-09-02 | 云知声智能科技股份有限公司 | Lens blocking object detection method and device |
CN115890897A (en) * | 2022-11-17 | 2023-04-04 | 北新集团建材股份有限公司 | System for automatically adjusting gypsum board edge type |
CN116202561A (en) * | 2023-03-31 | 2023-06-02 | 钛玛科(北京)工业科技有限公司 | Correction method for linear error of infrared sensor |
-
2023
- 2023-08-09 CN CN202310994645.0A patent/CN116697897B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS63201514A (en) * | 1987-02-17 | 1988-08-19 | Toshiba Mach Co Ltd | Method for measuring plastic sheet width |
CN111526258A (en) * | 2019-02-04 | 2020-08-11 | 京瓷办公信息系统株式会社 | Image forming apparatus with a toner supply device |
CN113487639A (en) * | 2021-07-14 | 2021-10-08 | 北京金山云网络技术有限公司 | Image processing method and device, electronic equipment and storage medium |
CN113551598A (en) * | 2021-07-20 | 2021-10-26 | 钛玛科(北京)工业科技有限公司 | Infrared wide sensor detection device and position detection method of shielding object |
CN114998283A (en) * | 2022-06-17 | 2022-09-02 | 云知声智能科技股份有限公司 | Lens blocking object detection method and device |
CN115890897A (en) * | 2022-11-17 | 2023-04-04 | 北新集团建材股份有限公司 | System for automatically adjusting gypsum board edge type |
CN116202561A (en) * | 2023-03-31 | 2023-06-02 | 钛玛科(北京)工业科技有限公司 | Correction method for linear error of infrared sensor |
Non-Patent Citations (1)
Title |
---|
仿人型假手指尖三维力触觉传感器及动态抓取研究;张庭;中国博士学位论文全文数据库 信息科技辑(第1期);第18页 * |
Also Published As
Publication number | Publication date |
---|---|
CN116697897A (en) | 2023-09-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109146930B (en) | Infrared and visible light image registration method for electric power machine room equipment | |
US8660349B2 (en) | Screen area detection method and screen area detection system | |
CN109741356B (en) | Sub-pixel edge detection method and system | |
CN111696107B (en) | Molten pool contour image extraction method for realizing closed connected domain | |
CN111308448B (en) | External parameter determining method and device for image acquisition equipment and radar | |
CN111080661B (en) | Image-based straight line detection method and device and electronic equipment | |
CN111811784A (en) | Laser spot center coordinate determination method, device and equipment | |
CN111968144A (en) | Image edge point acquisition method and device | |
JP2013089234A (en) | Image processing system | |
CN111462066A (en) | Thread parameter detection method based on machine vision | |
CN115205286B (en) | Method for identifying and positioning bolts of mechanical arm of tower-climbing robot, storage medium and terminal | |
CN106157329A (en) | A kind of adaptive target tracking method and device | |
US9014426B2 (en) | Method and device for the detection of moving objects in a video image sequence | |
TWI383690B (en) | Method for image processing | |
CN117764983A (en) | Visual detection method for binocular identification of intelligent manufacturing production line | |
CN117764989B (en) | Visual-aided display screen defect detection method | |
CN109671084B (en) | Method for measuring shape of workpiece | |
CN116697897B (en) | Method and system for detecting position of shielding object | |
CN117611525A (en) | Visual detection method and system for abrasion of pantograph slide plate | |
CN113269732B (en) | Linear object detection method based on characteristic scanning image | |
CN114964032A (en) | Blind hole depth measuring method and device based on machine vision | |
CN113052833A (en) | Non-vision field imaging method based on infrared thermal radiation | |
CN110097507B (en) | Depth map optimization system and optimization method | |
KR101007149B1 (en) | Method for extracting warping point for calibration of wide angle camera and method for aquiring top view of vehicle | |
KR101615733B1 (en) | Particle inspection method for the visualization of surface between the lens and the infrared filter in the camera module |
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 |