CN116862881A - Multi-target real-time offset detection method based on image processing - Google Patents
Multi-target real-time offset detection method based on image processing Download PDFInfo
- Publication number
- CN116862881A CN116862881A CN202310856533.9A CN202310856533A CN116862881A CN 116862881 A CN116862881 A CN 116862881A CN 202310856533 A CN202310856533 A CN 202310856533A CN 116862881 A CN116862881 A CN 116862881A
- Authority
- CN
- China
- Prior art keywords
- roi
- offset
- image
- target
- image processing
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 37
- 238000012545 processing Methods 0.000 title claims abstract description 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000005259 measurement Methods 0.000 claims abstract description 16
- 238000010276 construction Methods 0.000 claims abstract description 5
- 238000003708 edge detection Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 6
- 241001292396 Cirrhitidae Species 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 abstract description 6
- 238000009435 building construction Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 7
- 238000012937 correction Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000011897 real-time detection Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—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
- G06T7/11—Region-based segmentation
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a multi-target real-time offset detection method based on image processing, which is used for realizing automatic, all-weather, real-time and accurate offset detection on a plurality of monitoring points; the camera is utilized to continuously collect image data of an application scene, and a series of image processing algorithms are applied to realize high-precision offset measurement of a plurality of monitoring points; the measuring precision of the invention reaches millimeter level, the time calculation error is less than 1 second, the requirements of the fields such as building construction and the like on the precision are met, the requirements of the fields such as building construction and the like on the precision and the instantaneity are met, the offset problem of the target point position is timely corrected by a constructor, and the accuracy and the quality in the construction process are ensured.
Description
Technical Field
The invention belongs to the technical field of offset detection, and particularly relates to a multi-target real-time offset detection method based on image processing.
Background
In many fields, such as construction, assembly of parts, etc., accurate measurement and real-time detection of the offset of multiple target sites becomes particularly critical. Particularly in applications involving high safety and performance requirements, it is important to be able to detect the offset in real time and take measures in time; for example, in the field of building construction, accurate measurement and real-time detection of the deflection of a building structure can ensure the stability and safety of the building. For the part assembly process, the accurate measurement and the real-time detection of the offset of the part can ensure the quality and the accuracy of assembly, and avoid the problems of poor matching or functional failure.
In conventional multi-target offset measurement methods, the use of specific sensors, complex equipment configurations, or manual acquisition and computation is often required. However, these methods have some limitations, such as large measurement error, easy influence from subjective factors, high equipment cost, complex operation flow, inability to achieve multi-objective measurement, inability to perform offset detection in real time, and easy limitation to environmental conditions, and difficulty in meeting the needs of specific scenes.
Disclosure of Invention
The invention aims to provide a multi-target real-time offset detection method based on image processing, which solves the problems of large measurement error, complex operation flow and limited environment in the existing target offset measurement.
The technical scheme adopted by the invention is as follows: the multi-target real-time offset detection method based on image processing is characterized in that a camera is used for continuously collecting image data of an application scene, and a series of image processing algorithms are applied to realize high-precision offset measurement of a plurality of monitoring points.
The multi-target real-time offset detection method based on image processing is implemented by the following steps:
step 1, image data acquisition and enhancement processing;
step 2, original image data are saved, and initial states of a reference point and a monitoring point are recorded;
step 3, detecting the reference point and the monitoring point ROI in the image processed in the step 1;
step 4, expanding and cutting the ROI area obtained in the step 3;
step 5, eliminating non-target communication areas in the cut image;
step 6, obtaining the coordinates of the center point and the pixel size of the target through edge detection;
step 7, comparing the obtained pixel size proportion with the original data to determine the distortion degree and correct, and recalculating the geometric center point pixel coordinates;
step 8, calculating the relative distance between the monitoring point and the reference point, and converting the relative distance into an actual relative distance through the pixel scale parameter;
step 9, comparing the calculated relative distance with the original data, and calculating an offset value of the monitoring point;
step 10, circularly and repeatedly executing the step 1 and the steps 3 to 9 so as to detect the target in real time;
wherein the step 1 specifically comprises the following steps:
step 1.1, acquiring image data of a construction site in real time by using a fixed camera;
step 1.2, improving contrast and detail definition of the low-illumination image by utilizing a brightness channel enhancement technology, then removing noise in the image, and highlighting the whole structure and detail;
the step 3 specifically comprises the following steps: realizing template matching by utilizing a Halcon algorithm, and positioning and extracting the ROI areas of the reference point and the monitoring point in the detection image;
the expansion and clipping of the ROI area in the step 4 are specifically as follows:
according to a predefined expansion factor, performing region expansion of the ROI to cover the whole range of the target, and recording the coordinate point of the upper left corner of the clipping region and the width and height of the clipping region:
new ROI upper left-corner abscissa=original ROI upper left-corner abscissa-expansion factor original ROI width;
new ROI upper left ordinate = original ROI upper left ordinate-expansion factor original ROI height;
new ROI width = original ROI width +2 expansion factor original ROI width;
new ROI height = original ROI height +2 expansion factor original ROI height;
wherein the step 5 is specifically implemented according to the following steps:
step 5.1, searching for connected domains, searching for all connected domains of the ROI by using an OpenCV algorithm, and calculating the area of the non-background connected domain;
step 5.2, screening connected domains, and filtering the non-background connected domains in the cut image area by means of mean filtering, wherein the largest area is a target area, and the area of the part is smaller than the largest connected domain;
wherein the step 7 is specifically implemented according to the following steps:
step 7.1, analyzing the distortion degree of the image by comparing the size of the extracted target area with the original size, and calculating a distortion coefficient;
step 7.2, calculating corrected center point coordinates as follows:
in (x) u ,y u ) Is the corrected center coordinates, (x) c ,y c ) To the central coordinate before correction, k n Is a distortion coefficient;
wherein the step 8 is specifically implemented according to the following steps:
step 8.1, calculating the relative distance between the monitoring point and the reference point, and calculating the relative pixel distance by using the coordinate difference of the two points;
step 8.2, determining a pixel scale coefficient by calculating the proportional relation between the pixel size of the reference point in the image and the actual physical size, and multiplying the relative pixel distance by the coefficient to obtain the actual relative distance;
wherein, the step 9 is specifically implemented as the following steps:
step 9.1, comparing the calculated relative distance with a reference value in the original data, and determining an offset value of the monitoring point through comparing the difference between the calculated relative distance and the reference value;
step 9.2, judging the direction and degree of the offset according to the positive and negative values of the offset value, and if the offset values of the X axis and the Y axis are positive, indicating that the monitoring point is offset rightwards or upwards relative to the reference point; if the X-axis offset value and the Y-axis offset value are negative, the monitoring point is offset leftwards or downwards relative to the reference value; the greater the absolute value of the offset value, the greater the degree of offset.
The beneficial effects of the invention are as follows:
the multi-target real-time offset detection method based on image processing utilizes the camera to collect the image data of the application scene, the measuring and offset calculating processes are automatically completed by a computer, the operation flow is simple and easy to operate, and operators do not need to have professional technical knowledge; meanwhile, the invention integrates advanced edge detection technology, and calculates by dividing a pixel into dozens of sub-pixels, thereby doubling the edge recognition effect and reducing offset errors caused by inaccurate pixel position and pixel size extraction; in order to overcome the problem of picture distortion caused by factors such as light refraction, the degree of distortion of an image is estimated by comparing a reference point with original geometric data, geometric correction is carried out according to the degree of distortion, and accurate and reliable offset measurement results of all coordinate axes are ensured; in addition, the invention has less computer resources, can rapidly process a large amount of image data, and performs offset calculation in real time, thereby providing timely offset information for application scenes and helping operators to take necessary corrective measures in time.
Drawings
FIG. 1 is a diagram of the detection effect of the image processing-based multi-target real-time offset detection method of the present invention;
FIG. 2 is a comparison graph of non-target connected region elimination effect of the multi-target real-time offset detection method based on image processing of the present invention;
fig. 3 is a graph comparing geometric correction effects of the multi-target real-time offset detection method based on image processing according to the present invention.
Detailed Description
The invention will be described in detail below with reference to the drawings and the detailed description.
The invention provides a multi-target real-time offset detection method based on image processing, which is used for realizing automatic, all-weather, real-time and accurate offset detection on a plurality of monitoring points; the camera is utilized to continuously collect image data of an application scene, and a series of image processing algorithms are applied to realize high-precision offset measurement of a plurality of monitoring points; firstly, preprocessing image data, including image enhancement operations such as high lifting and noise removal, so as to improve the quality and contrast of images; matching and cutting out areas where the reference points and the monitoring points are located from the images by using a template matching technology; then, an edge detection algorithm is applied to accurately position the cut region, and the position of the target is accurately found. The pixel distance between the monitoring point and the reference point is converted into an actual distance by combining the pixel scale parameters; and finally, obtaining the accurate offset by comparing the calculation result with the original data.
Example 1
The embodiment is a multi-target real-time offset detection method based on image processing, which specifically comprises the following steps:
step 1, selecting a reference point and a monitoring point, firstly, determining a fixed reference point which can be a known position or a relatively stable characteristic point, and then selecting a target point position needing to detect offset, which is usually a structure which is not finished in engineering projects or a position needing special attention;
step 2, image acquisition and preprocessing, wherein image data of a target scene are continuously acquired through a camera; preprocessing the acquired image data, including graying, noise removal, image enhancement and the like, so as to improve the image quality and definition and prepare for subsequent template matching and offset calculation;
and 3, target positioning and position extraction, and analyzing and processing the preprocessed image. Locating the areas where the reference points and the monitoring points in the image are located through feature extraction and matching, and further accurately extracting the geometric center coordinates and the pixel size of the target object through an edge detection technology;
step 4, calculating and analyzing the offset, and calculating the offset of the target point position relative to the reference point by utilizing the position relation between the reference point and the monitoring point; converting the pixel distance into an actual relative distance through the pixel scale parameter, and comparing and calculating with the original data to obtain an accurate offset value;
step 5, displaying and feeding back results, and outputting an offset result in an intuitive and visual mode by calibrating and processing the image; the operator can clearly know the deviation condition of the target point position and take timely correction measures according to the displayed result.
Example 2
The embodiment is a multi-target real-time offset detection method based on image processing, which specifically comprises the following steps:
as shown in fig. 1, the detection effect diagram of the multi-target real-time offset detection method based on image processing in this embodiment is shown, the circle is marked as a reference point (white background and black circle), the rectangular frame is a monitoring point (black background and white circle), and the triangular frame is a monitoring point with offset;
step 1, image data acquisition and enhancement processing;
step 2, saving original image data;
step 3, template matching, namely detecting a reference point and a monitoring point ROI area respectively;
step 4, expanding and cutting the ROI area;
step 5, eliminating non-target communication areas in the cut image;
step 6, edge detection, namely acquiring the coordinates of the central point and the pixel size of the target;
step 7, comparing the obtained pixel size proportion with the original data to determine the distortion degree and correct, and recalculating the geometric center point pixel coordinates;
step 8, calculating the relative distance between the monitoring point and the reference point, and converting the relative distance into an actual relative distance through the pixel scale parameter;
step 9, comparing the calculated relative distance with the original data, and calculating an offset value of the monitoring point;
step 10, the steps 1 and 3-9 are repeatedly executed in a circulating way so as to detect the real-time offset of the target.
Example 3
The multi-target real-time offset detection method based on image processing provided by the embodiment is characterized in that:
firstly, real-time offset detection is realized by continuously collecting image data, and the offset detection method can be used for timely finding the offset condition of the target point position, so that corrective measures can be quickly taken when the offset occurs, and potential problems and risks can be avoided;
secondly, the invention automatically calculates the offset by a computer through collecting image data by a camera without specific sensors or complex equipment configuration. The system operation is more automatic, the requirements for manual intervention and complex operation are reduced, and therefore the convenience and efficiency of operation are improved. An operator can realize full-automatic offset detection only by easily setting system parameters and monitoring flow, so that manpower resources and time cost are greatly saved;
thirdly, high-precision offset calculation is carried out, the method can accurately position the target in the region, high-precision offset calculation is realized, the measurement precision reaches millimeter level, and the error range can be controlled within 1 milli-terminal;
fourthly, by referring to the fixed point, the influence of camera shake on measurement is reduced, and the accuracy and reliability of the measurement result are ensured; in the measuring process, the reference point is used as a stable reference, and the relative distance between the monitoring point and the reference point is calculated, so that the influence of camera shake on measurement is eliminated, and the measuring precision and reliability are improved; the method is implemented by the following steps:
the image data acquisition and enhancement processing in the step 1 is specifically implemented according to the following steps:
step 1.1, acquiring image data of a construction site in real time by using a fixed camera;
step 1.2, the image enhancement is implemented according to the following steps:
step 1.2.1, improving contrast and detail definition of the low-illumination image by utilizing a brightness channel enhancement technology;
step 1.2.2, removing noise in the image by using methods such as gray processing, gaussian filtering, sharpening filtering and the like, and simultaneously highlighting the whole structure and details;
step 2, original image data are saved, and the method is implemented according to the following steps:
step 2.1, saving the original data of the image, recording the initial states of the reference point and the monitoring point, and skipping and not repeatedly executing if the step is already executed;
step 3, template matching is carried out, namely detecting the ROI (region of interest) of the reference point and the monitoring point respectively, and the method is implemented according to the following steps:
step 3.1, realizing template matching by utilizing a Halcon algorithm, and positioning and extracting ROI areas of a reference point and a monitoring point in a detection image;
and 4, expanding and cutting the region of the ROI, wherein the method is implemented by the following steps of:
step 4.1, the ROI area is expanded, and due to a certain deviation of the ROI area, the ROI area needs to be properly expanded according to a predefined expansion factor to cover the whole range of the target, and the upper left corner coordinate point of the clipping area and the width and height of the clipping area are recorded:
new ROI upper left-corner abscissa=original ROI upper left-corner abscissa-expansion factor original ROI width;
new ROI upper left ordinate = original ROI upper left ordinate-expansion factor original ROI height;
new ROI width = original ROI width +2 expansion factor original ROI width;
new ROI height = original ROI height +2 expansion factor original ROI height;
step 5, eliminating non-target connected areas in the cut image, and specifically implementing the following steps:
step 5.1, searching for connected domains, searching for all connected domains of the ROI by using an OpenCV algorithm, and calculating the area of the non-background connected domain;
step 5.2, screening connected domains, and for the part, with the largest area being a target area and smaller than the largest connected domain, of the cut image area, filtering by applying mean filtering, wherein the step is helpful for reducing interference of fine noise on a subsequent edge detection process, and the effect is shown in fig. 2;
step 6, edge detection, namely obtaining the geometric center coordinates and the pixel size of the target, wherein the method is implemented according to the following steps:
and 6.1, carrying out edge detection on the image by using a Canny algorithm, extracting an accurate target area, and calculating the pixel coordinates and the pixel size of the geometric center point of the target.
And 7, comparing the obtained pixel size proportion with original data to determine the distortion degree and correct, and recalculating the geometric center point coordinates, wherein the method is implemented according to the following steps:
step 7.1, analyzing the distortion degree of the image by comparing the size of the extracted target area with the original size, and calculating a distortion coefficient;
step 7.2, calculating corrected center point coordinates as follows:
in (x) u ,y u ) Is the corrected center coordinates, (x) c ,y c ) To the central coordinate before correction, k n As the distortion coefficient, the corrected effect is shown in fig. 3;
step 8, calculating the relative distance between the monitoring point and the reference point, and converting the relative distance into an actual relative distance through the pixel scale parameter, wherein the method is implemented according to the following steps:
step 8.1, calculating the relative distance between the monitoring point and the reference point, and calculating the relative pixel distance by using the coordinate difference of the two points;
and 8.2, determining a pixel scale coefficient by calculating the proportional relation between the pixel size of the reference point in the image and the actual physical size, and multiplying the relative pixel distance by the coefficient to obtain the actual relative distance.
And 9, comparing the calculated relative distance with original data, and calculating an offset value of the monitoring point, wherein the method is implemented according to the following steps:
step 9.1, comparing the calculated relative distance with a reference value in the original data, and determining an offset value of the monitoring point through comparing the difference between the calculated relative distance and the reference value;
step 9.2, judging the direction and degree of the offset according to the positive and negative values of the offset value, and if the offset values of the X axis and the Y axis are positive, indicating that the monitoring point is offset rightwards or upwards relative to the reference point; if the X-axis offset value and the Y-axis offset value are negative, the monitoring point is offset leftwards or downwards relative to the reference value; the greater the absolute value of the offset value, the greater the degree of offset.
Claims (9)
1. The multi-target real-time offset detection method based on image processing is characterized in that a camera is used for continuously collecting image data of an application scene, and a series of image processing algorithms are applied to realize high-precision offset measurement of a plurality of monitoring points.
2. The image processing-based multi-target real-time offset detection method according to claim 1, wherein the method is implemented specifically as follows:
step 1, image data acquisition and enhancement processing;
step 2, original image data are saved, and initial states of a reference point and a monitoring point are recorded;
step 3, detecting the reference point and the monitoring point ROI in the image processed in the step 1;
step 4, expanding and cutting the ROI area obtained in the step 3;
step 5, eliminating non-target communication areas in the cut image;
step 6, obtaining the coordinates of the center point and the pixel size of the target through edge detection;
step 7, comparing the obtained pixel size proportion with the original data to determine the distortion degree and correct, and recalculating the geometric center point pixel coordinates;
step 8, calculating the relative distance between the monitoring point and the reference point, and converting the relative distance into an actual relative distance through the pixel scale parameter;
step 9, comparing the calculated relative distance with the original data, and calculating an offset value of the monitoring point;
step 10, the steps 1 and 3-9 are repeatedly executed in a circulating way so as to detect the real-time offset of the target.
3. The image processing-based multi-target real-time offset detection method according to claim 2, wherein the step 1 specifically comprises:
step 1.1, acquiring image data of a construction site in real time by using a fixed camera;
and 1.2, improving the contrast and detail definition of the low-illumination image by utilizing a brightness channel enhancement technology, then removing noise in the image, and simultaneously highlighting the whole structure and detail.
4. The image processing-based multi-target real-time offset detection method according to claim 2, wherein the step 3 specifically comprises: and (3) realizing template matching by utilizing a Halcon algorithm, and positioning and extracting the ROI areas of the reference point and the monitoring point in the detection image.
5. The image processing-based multi-target real-time offset detection method according to claim 2, wherein the ROI region expansion and clipping in step 4 is specifically:
according to a predefined expansion factor, performing region expansion of the ROI to cover the whole range of the target, and recording the coordinate point of the upper left corner of the clipping region and the width and height of the clipping region:
new ROI upper left-corner abscissa=original ROI upper left-corner abscissa-expansion factor original ROI width;
new ROI upper left ordinate = original ROI upper left ordinate-expansion factor original ROI height;
new ROI width = original ROI width +2 expansion factor original ROI width;
new ROI height = original ROI height +2 expansion factor original ROI height.
6. The image processing-based multi-target real-time offset detection method according to claim 2, wherein the step 5 is specifically implemented as follows:
step 5.1, searching for connected domains, searching for all connected domains of the ROI by using an OpenCV algorithm, and calculating the area of the non-background connected domain;
and 5.2, screening connected domains, and filtering the non-background connected domains in the cut image area by means of mean filtering, wherein the largest area is a target area, and the area of the part is smaller than the largest connected domain.
7. The image processing-based multi-target real-time offset detection method according to claim 2, wherein the step 7 is specifically implemented as follows:
step 7.1, analyzing the distortion degree of the image by comparing the size of the extracted target area with the original size, and calculating a distortion coefficient;
step 7.2, calculating corrected center point coordinates as follows:
in (x) u ,y u ) Is the corrected center coordinates, (x) c ,y c ) To the middle before correctionHeart coordinates, k n Is a distortion coefficient.
8. The image processing-based multi-target real-time offset detection method according to claim 2, wherein the step 8 is specifically implemented as follows:
step 8.1, calculating the relative distance between the monitoring point and the reference point, and calculating the relative pixel distance by using the coordinate difference of the two points;
and 8.2, determining a pixel scale coefficient by calculating the proportional relation between the pixel size of the reference point in the image and the actual physical size, and multiplying the relative pixel distance by the coefficient to obtain the actual relative distance.
9. The image processing-based multi-target real-time offset detection method according to claim 2, wherein the step 9 is specifically implemented as follows:
step 9.1, comparing the calculated relative distance with a reference value in the original data, and determining an offset value of the monitoring point through comparing the difference between the calculated relative distance and the reference value;
step 9.2, judging the direction and degree of the offset according to the positive and negative values of the offset value, and if the offset values of the X axis and the Y axis are positive, indicating that the monitoring point is offset rightwards or upwards relative to the reference point; if the X-axis offset value and the Y-axis offset value are negative, the monitoring point is offset leftwards or downwards relative to the reference value; the greater the absolute value of the offset value, the greater the degree of offset.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310856533.9A CN116862881A (en) | 2023-07-13 | 2023-07-13 | Multi-target real-time offset detection method based on image processing |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310856533.9A CN116862881A (en) | 2023-07-13 | 2023-07-13 | Multi-target real-time offset detection method based on image processing |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116862881A true CN116862881A (en) | 2023-10-10 |
Family
ID=88230106
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310856533.9A Pending CN116862881A (en) | 2023-07-13 | 2023-07-13 | Multi-target real-time offset detection method based on image processing |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116862881A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117579790A (en) * | 2024-01-16 | 2024-02-20 | 金钱猫科技股份有限公司 | Construction site monitoring method and terminal |
-
2023
- 2023-07-13 CN CN202310856533.9A patent/CN116862881A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117579790A (en) * | 2024-01-16 | 2024-02-20 | 金钱猫科技股份有限公司 | Construction site monitoring method and terminal |
CN117579790B (en) * | 2024-01-16 | 2024-03-22 | 金钱猫科技股份有限公司 | Construction site monitoring method and terminal |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108921176B (en) | Pointer instrument positioning and identifying method based on machine vision | |
US8660349B2 (en) | Screen area detection method and screen area detection system | |
CN109489566B (en) | Lithium battery diaphragm material slitting width detection method, detection system and device | |
CN112613429B (en) | Pointer type instrument reading method suitable for multi-view images based on machine vision | |
CN108960237B (en) | Reading identification method for pointer type oil level indicator | |
CN111879241A (en) | Mobile phone battery size measuring method based on machine vision | |
CN109815822B (en) | Patrol diagram part target identification method based on generalized Hough transformation | |
CN112308854B (en) | Automatic detection method and system for chip surface flaws and electronic equipment | |
CN115096206B (en) | High-precision part size measurement method based on machine vision | |
CN112270320B (en) | Power transmission line tower coordinate calibration method based on satellite image correction | |
CN111160477B (en) | Image template matching method based on feature point detection | |
CN114219773B (en) | Pre-screening and calibrating method for bridge crack detection data set | |
CN116862881A (en) | Multi-target real-time offset detection method based on image processing | |
CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
CN110555373A (en) | Concrete vibration quality real-time detection method based on image recognition | |
CN114529610A (en) | Millimeter wave radar data labeling method based on RGB-D camera | |
CN117434568A (en) | Intelligent positioning system based on remote sensing satellite | |
CN113408519A (en) | Method and system for reading pointer instrument based on template rotation matching | |
CN116596987A (en) | Workpiece three-dimensional size high-precision measurement method based on binocular vision | |
CN116758266A (en) | Reading method of pointer type instrument | |
CN114092695B (en) | ROI extraction method and device based on segmentation model | |
CN113592953B (en) | Binocular non-cooperative target pose measurement method based on feature point set | |
CN113011417B (en) | Target matching method based on intersection ratio coverage rate loss and repositioning strategy | |
CN114998571A (en) | Image processing and color detection method based on fixed-size marker | |
CN114663681A (en) | Method for reading pointer type meter and related product |
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 |