CN113538488A - BMS charging port identification method - Google Patents
BMS charging port identification method Download PDFInfo
- Publication number
- CN113538488A CN113538488A CN202110807529.4A CN202110807529A CN113538488A CN 113538488 A CN113538488 A CN 113538488A CN 202110807529 A CN202110807529 A CN 202110807529A CN 113538488 A CN113538488 A CN 113538488A
- Authority
- CN
- China
- Prior art keywords
- arc
- edge
- ellipse
- image
- charging port
- 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
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000001914 filtration Methods 0.000 claims abstract description 21
- 238000012216 screening Methods 0.000 claims abstract description 15
- 238000003708 edge detection Methods 0.000 claims abstract description 11
- 238000009499 grossing Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 16
- 230000008859 change Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 7
- 239000003086 colorant Substances 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a BMS charging port identification method, which comprises the following steps: acquiring an image of a BMS power plug, and converting the image into a gray image through graying and filtering; filtering and smoothing the gray level image to strengthen the edge characteristics of the gray level image, carrying out edge detection on the image by using a Canny edge detection algorithm, and adjusting an edge threshold value by using a slider of an OPENCV (open cell CV) to obtain an edge map; extracting arc sections of the edge graph, and dividing all the extracted arc sections into four types of elliptical arc sections according to the positive and negative of the edge gradient and the concavity and convexity of the edge; and fitting the four types of the divided elliptical arc sections to obtain alternative ellipses, and finally screening out a target ellipse for identifying the charging port from the alternative ellipses. Through the comprehensive arc section selection and screening method, the speed of arc section selection can be accelerated, the effectiveness of arc section selection can be improved, the selected arc section can be guaranteed to be one part of a certain ellipse to a great extent, and the accuracy of the detected ellipse is improved.
Description
Technical Field
The invention belongs to the technical field of battery charging, and particularly relates to a BMS charging port identification method.
Background
There is a great tendency to implement a more rapid and convenient BMS power-on and power-off technology. The plug-in port identification in the automatic charging technology is the most important part in the whole automatic charging technology. In the charging port of the electric vehicle, which is common in the market at present, the identification technology using the ellipse detection is the best method according to the characteristics of the charging port, namely the direct current charging port or the alternating current charging port. Ellipse detection is a very critical part of computer vision and has good application in this respect. Currently, the mainstream methods for ellipse detection are hough transform and its deformation, and least square fitting ellipse and ellipse detection and fitting based on arc segment extraction.
The Hough transform-based ellipse detection utilizes Hough transform to map an image space to a parameter space, but the method is not sensitive to noise, parameters are up to 5-dimensional, and the calculation amount is too large. The predecessors have proposed fitting an ellipse from the angle of a curved arc, and improved algorithms based on various arc segment extractions.
Disclosure of Invention
The present invention is directed to a method for recognizing a charging port of a BMS to overcome the above-mentioned problems. Through the comprehensive arc section selection and screening method, the speed of arc section selection can be accelerated, the effectiveness of arc section selection can be improved, the selected arc section can be guaranteed to be one part of a certain ellipse to a great extent, and the accuracy of the detected ellipse is improved.
The technical purpose of the invention is realized by the following technical scheme:
a method for recognizing a BMS charging port includes the steps of:
acquiring an image of a BMS power plug, and converting the image into a gray image through graying and primary filtering;
carrying out secondary filtering and noise smoothing on the gray level image to strengthen the edge characteristics of the gray level image, carrying out edge detection by using a Canny edge detection algorithm, and adjusting an edge threshold value by using a slider of OPENCV (open ended content correlation) to obtain an edge map;
extracting arc sections of the edge graph, and dividing all the extracted arc sections into four kinds of elliptical arc sections according to the positive and negative of the edge gradient and the concave-convex of the edge;
and fitting the four types of the divided elliptical arc sections to obtain alternative ellipses, and finally screening out a target ellipse for identifying the charging port from the alternative ellipses.
Further: the arc segment extraction adopts an eight-neighborhood edge tracking method for extraction, and the eight-neighborhood edge tracking method comprises the following steps:
(1) setting pixel points in the edge area of the edge image as foreground colors, setting the rest part as background colors, detecting each pixel point, and when detecting that the current pixel point is the foreground color, predefining the retrieval direction of eight neighborhoods as clockwise or anticlockwise by taking the current pixel point as the center of eight-neighborhood retrieval;
(2) searching according to the searching direction, storing the current pixel point in the step (1), and setting the current pixel point as a background color;
(3) in the retrieval process, when a pixel point is a foreground color again, the pixel point is determined as a new eight-neighborhood retrieval center, the step (2) is repeated until no foreground color exists in the eight-neighborhood retrieved, and all stored pixel points form a set, namely an arc segment;
(4) detecting each pixel point in the edge image, repeating the steps (1) to (3) until the whole edge image is searched, obtaining a plurality of arc sections formed by the pixel points, and screening out short arcs of the arc sections.
Further: the short arc screening process of the arc section in the step (4) comprises the following steps:
determining the length of the corresponding arc segment according to the number of the pixel points, and filtering the arc segment with smaller length;
according to the characteristics of the ellipse, straight arcs without curvature and arc sections with small curvature change in the obtained arc sections are removed.
Further: the judgment method of the arc segment with small curvature change comprises the following steps: marking five pixel points which divide each arc segment into five equal parts, calculating the slope between every two adjacent pixel points, and expressing the change degree of curvature by using the slope change between the five pixel points.
Further: the process of dividing the arc sections into four types of elliptical arc sections is as follows:
taking two end points of an arc section as a connecting line, defining the arc section to be convex when the arc section is positioned above the connecting line, and defining the arc section to be concave when the arc section is positioned below the connecting line; when the gradient of the arc section is larger than 0, the arc section is defined as positive, and when the gradient of the arc section is smaller than 0, the arc section is defined as negative; all the arc segments are divided into four sets of elliptical arc segments.
Further: the process of fitting the elliptical arc segment to obtain the alternative ellipse is as follows:
arranging the points which are combined into all arc sections in each quadrant according to the parameter equation of the known number of the elliptic secondary curve to obtain a set of a series of points, carrying out quartering on the set, taking five endpoints which are divided into quartering as characteristic points to be substituted into the parameter equation to obtain an equation set, and solving the equation set; when the determinant value of the matrix in the coefficients of the equation set is greater than 0, the five unknowns have unique solutions, and when the determinant value is equal to 0, the point is not on an ellipse.
Further: the process of screening the target ellipse in the alternative ellipses comprises the following steps:
calculating the ratio of the major axis to the minor axis of all candidate ellipses, and filtering the candidate ellipses with smaller ratio of the major axis to the minor axis;
calculating the ratio of the major axis of the ellipse to the pixel width in all the candidate ellipses, presetting the value range of the major axis of the ellipse to the pixel width, and filtering the candidate ellipses exceeding the value range;
and arranging the filtered alternative ellipses from small to large according to the size of the Y-axis coordinate, setting the threshold range of the Y-axis coordinate, and removing the alternative ellipses outside the threshold range to obtain the target ellipse for identifying the charging port.
Has the advantages that: according to the method, the edge characteristics of the image are enhanced by utilizing the preprocessing of the image, the edge is obtained by combining the Canny edge detection algorithm, the detected edge is tracked and screened by utilizing the eight-neighborhood edge, and the detected edge is divided into 4 classes of elliptical arc edges according to the positive and negative characteristics of the edge gradient and the concave-convex characteristics of the edge. On the basis, according to a certain limiting condition and an ellipse parameter equation, three sections of elliptical arcs meeting the limiting condition are selected for fitting, a series of alternative ellipses are further obtained, and the required ellipses capable of identifying the charging port are screened out through the relation between characteristic parameters and the relation between target ellipses. Compared with the traditional circular graph algorithm problem extracted based on a simple Hough transform algorithm, the target ellipse of the power socket can be obtained through multiple experiments at multiple angles by the aid of the VS2019 experiment platform on the AMD-based a85 processor. The method can accurately and quickly identify the plugged charging port, and provides a convenient prerequisite for full-automatic power plugging of a battery management system BMS in the new energy automobile.
Drawings
FIG. 1 is an edge map obtained by Canny edge detection at different positions in the present invention;
FIG. 2 is a schematic diagram of FIG. 1 after processing for short arc culling by eight neighborhood edge tracking;
FIG. 3 is a set of two arc segments of FIG. 2, respectively, based on the positive and negative properties of the edge gradient;
fig. 4 is a schematic diagram of fig. 3 after fitting.
Detailed Description
In the description of the present invention, unless otherwise specified, the terms "upper", "lower", "left", "right", "front", "rear", and the like, indicate orientations or positional relationships only for the purpose of describing the present invention and simplifying the description, but do not indicate or imply that the designated device or structure must have a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
As shown in fig. 1 to 4, the method for recognizing a BMS charging port according to the present invention includes the steps of:
s1, acquiring an image of the BMS power plug, and converting the image into a gray image through graying and primary filtering;
s2, carrying out secondary filtering and noise smoothing on the gray level image to strengthen the edge characteristics of the gray level image, carrying out edge detection by using a Canny edge detection algorithm, and adjusting an edge threshold value by using a slider of an OPENCV to obtain an edge image;
s3, extracting arc segments of the edge graph, and dividing all the extracted arc segments into four types of elliptical arc segments according to the positivity and negativity of the edge gradient and the concavity and convexity of the edge;
and S4, fitting the four types of the divided elliptical arc sections to obtain alternative ellipses, and finally screening out a target ellipse for identifying the charging port from the alternative ellipses.
In the S3, the arc segment extraction is performed by using an eight-neighborhood edge tracking method, where the eight-neighborhood edge tracking method includes the steps of:
(1) setting pixel points in the edge area of the edge image as foreground colors (white), setting the rest parts as background colors (black), detecting each pixel point, and when detecting that the current pixel point is the foreground color, predefining the retrieval direction of eight neighborhoods as clockwise or anticlockwise by taking the current pixel point as the center of eight-neighborhood retrieval;
(2) searching according to the searching direction, storing the current pixel point in the step (1), and setting the current pixel point as a background color;
(3) in the retrieval process, when a pixel point is a foreground color again, the pixel point is determined as a new eight-neighborhood retrieval center, the step (2) is repeated until no foreground color exists in the eight-neighborhood retrieved, and all stored pixel points form a set, namely an arc segment;
(4) detecting each pixel point in the edge image, and repeating the steps (1) to (3) until the whole edge image is searched, thus obtaining a plurality of arc sections consisting of the pixel points; and (4) screening out short arcs of the arc sections.
Wherein, the process of short arc screening out is carried out to the arc section in step (4): determining the length of the corresponding arc segment according to the number of the pixel points, and filtering the arc segment with smaller length; according to the characteristics of the ellipse, straight arcs without curvature and arc sections with small curvature change in the obtained arc sections are removed.
Further, the method for judging the arc segment with small curvature change comprises the following steps: marking five pixel points which divide each arc segment into five equal parts, calculating the slope between every two adjacent pixel points, and expressing the change degree of curvature by using the slope change between the five pixel points.
Further, in step S3, the process of dividing the arc segments into four types of elliptical arc segments is as follows:
taking two end points of an arc section as a connecting line, defining the arc section to be convex when the arc section is positioned above the connecting line, and defining the arc section to be concave when the arc section is positioned below the connecting line; when the gradient of the arc section is positive, defining the arc section as positive direction, and when the gradient of the arc section is negative, defining the arc section as negative direction; all the arc segments are divided into four sets of elliptical arc segments.
Further, in step S4, the process of fitting the elliptical arc segments to obtain the candidate ellipses includes:
arranging the points which are combined into all arc sections in each quadrant according to the parameter equation of the known number of the elliptic secondary curve to obtain a set of a series of points, carrying out quartering on the set, taking five endpoints which are divided into quartering as characteristic points to be substituted into the parameter equation to obtain an equation set, and solving the equation set; when the determinant value of the matrix in the coefficients of the equation set is greater than 0, the five unknowns have unique solutions, and when the determinant value is equal to 0, the point is not on an ellipse.
Further, in step S4, the process of screening the target ellipse in the candidate ellipses is as follows:
calculating the ratio of the major axis to the minor axis of all candidate ellipses, and filtering the candidate ellipses with smaller ratio of the major axis to the minor axis;
calculating the ratio of the major axis of the ellipse to the pixel width in all the candidate ellipses, presetting the value range of the major axis of the ellipse to the pixel width, and filtering the candidate ellipses exceeding the value range;
when concentric circle condition is detected: according to the position of the X-axis coordinate and the Y-axis coordinate of the central point of the ellipse, regarding the central X-axis coordinate and the Y-axis coordinate which are close as the ellipse of the same center, and filtering to remove the smaller concentric circles of the major axis and the minor axis;
and arranging the filtered alternative ellipses from small to large according to the size of the Y-axis coordinate, setting the threshold range of the Y-axis coordinate, and removing the alternative ellipses outside the threshold range to obtain the target ellipse for identifying the charging port.
In order to verify the application of the proposed arc-segment-based ellipse detection method to charging port identification, a direct-current charging port is photographed from multiple angles under the condition that a light source is ensured, and an experiment is performed based on VS2019 by using the proposed method, so as to verify whether a target ellipse of the charging port can be detected accurately, namely, an insertion interface is detected accurately. In order to better simulate the situation that the new energy automobile cannot be stopped all the time when actually stopped, three positions of left-inclined, right-inclined and right-centered are respectively oriented to simulate three situations of left-inclined, right-inclined and right-stopped automobile bodies when the automobile is stopped. The Canny edge detection results after the pretreatment under the three positions are shown in fig. 1; FIG. 2 is a schematic diagram of FIG. 1 after an eight-neighborhood edge tracking process has been performed to remove short arcs; taking the leftmost diagram in fig. 2 as an example, fig. 3 is a diagram for dividing the edge into two cases, namely, a gradient greater than 0 and a gradient less than 0, so as to prepare for extracting the valid edge point in the next step. Fig. 4 shows the situation of the ellipse obtained by point fitting, which shows that the target ellipse to be detected can be detected, and the ellipses of other parts on the charging port can also be detected, but those ellipses are not beneficial to the subsequent ellipse pose estimation. By adopting the filtering criteria formulated according to the characteristic parameters, the filtering graphs at the three positions can achieve good filtering effects, and the target ellipse is obtained.
In order to make the objects, technical solutions and advantages of the present invention more concise and clear, the present invention is described with the above specific embodiments, which are only used for describing the present invention, and should not be construed as limiting the scope of the present invention. It should be understood that any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (7)
1. A method for recognizing a BMS charging port, comprising the steps of:
acquiring an image of a BMS power plug, and converting the image into a gray image through graying and primary filtering;
carrying out secondary filtering and noise smoothing on the gray level image to strengthen the edge characteristics of the gray level image, carrying out edge detection by using a Canny edge detection algorithm, and adjusting an edge threshold value by using a slider of OPENCV (open ended content correlation) to obtain an edge map;
extracting arc sections of the edge graph, and dividing all the extracted arc sections into four kinds of elliptical arc sections according to the positive and negative of the edge gradient and the concave-convex of the edge;
and fitting the four types of the divided elliptical arc sections to obtain alternative ellipses, and finally screening out a target ellipse for identifying the charging port from the alternative ellipses.
2. The method of recognizing a BMS charging port according to claim 1, wherein: the arc segment extraction adopts an eight-neighborhood edge tracking method for extraction, and the eight-neighborhood edge tracking method comprises the following steps:
(1) setting pixel points in the edge area of the edge image as foreground colors, setting the rest part as background colors, detecting each pixel point, and when detecting that the current pixel point is the foreground color, predefining the retrieval direction of eight neighborhoods as clockwise or anticlockwise by taking the current pixel point as the center of eight-neighborhood retrieval;
(2) searching according to the searching direction, storing the current pixel point in the step (1), and setting the current pixel point as a background color;
(3) in the retrieval process, when a pixel point is a foreground color again, the pixel point is determined as a new eight-neighborhood retrieval center, the step (2) is repeated until no foreground color exists in the eight-neighborhood retrieved, and all stored pixel points form a set, namely an arc segment;
(4) detecting each pixel point in the edge image, repeating the steps (1) to (3) until the whole edge image is searched, obtaining a plurality of arc sections formed by the pixel points, and screening out short arcs of the arc sections.
3. The method of recognizing a BMS charging port according to claim 2, wherein: the short arc screening process in the step (4) comprises the following steps:
determining the length of the corresponding arc segment according to the number of the pixel points, and filtering the arc segment with smaller length;
according to the characteristics of the ellipse, straight arcs without curvature and arc sections with small curvature change in the obtained arc sections are removed.
4. The method of recognizing a BMS charging port according to claim 3, wherein: the judgment method of the arc segment with small curvature change comprises the following steps: marking five pixel points which divide each arc segment into five equal parts, calculating the slope between every two adjacent pixel points, and expressing the change degree of curvature by using the slope change between the five pixel points.
5. The method of recognizing a BMS charging port according to claim 1, wherein: the process of dividing the arc sections into four types of elliptical arc sections is as follows:
taking two end points of an arc section as a connecting line, defining the arc section to be convex when the arc section is positioned above the connecting line, and defining the arc section to be concave when the arc section is positioned below the connecting line; when the gradient of the arc section is larger than 0, the arc section is defined as positive, and when the gradient of the arc section is smaller than 0, the arc section is defined as negative; all the arc segments are divided into four sets of elliptical arc segments.
6. The method of recognizing a BMS charging port according to claim 1, wherein: the process of fitting the elliptical arc segment to obtain the alternative ellipse is as follows:
arranging the points which are combined into all arc sections in each quadrant according to the parameter equation of the known number of the elliptic secondary curve to obtain a set of a series of points, carrying out quartering on the set, taking five endpoints which are divided into quartering as characteristic points to be substituted into the parameter equation to obtain an equation set, and solving the equation set; when the determinant value of the matrix in the coefficients of the equation set is greater than 0, the five unknowns have unique solutions, and when the determinant value is equal to 0, the point is not on an ellipse.
7. The method of claim 1, wherein the process of screening the target ellipse among the candidate ellipses is as follows:
calculating the ratio of the major axis to the minor axis of all candidate ellipses, and filtering the candidate ellipses with smaller ratio of the major axis to the minor axis;
calculating the ratio of the major axis of the ellipse to the pixel width in all the candidate ellipses, presetting the value range of the major axis of the ellipse to the pixel width, and filtering the candidate ellipses exceeding the value range;
and arranging the filtered alternative ellipses from small to large according to the size of the Y-axis coordinate, setting the threshold range of the Y-axis coordinate, and removing the alternative ellipses outside the threshold range to obtain the target ellipse for identifying the charging port.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110807529.4A CN113538488A (en) | 2021-07-16 | 2021-07-16 | BMS charging port identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110807529.4A CN113538488A (en) | 2021-07-16 | 2021-07-16 | BMS charging port identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113538488A true CN113538488A (en) | 2021-10-22 |
Family
ID=78099794
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110807529.4A Pending CN113538488A (en) | 2021-07-16 | 2021-07-16 | BMS charging port identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113538488A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116630315A (en) * | 2023-07-24 | 2023-08-22 | 山东东阿亿福缘阿胶制品有限公司 | Intelligent beverage packaging defect detection method based on computer vision |
CN116958793A (en) * | 2023-07-24 | 2023-10-27 | 国网江苏省电力有限公司泰州供电分公司 | Device and method for evaluating visual recognition of charging robot based on illumination condition |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1996041312A1 (en) * | 1995-06-07 | 1996-12-19 | University Of Florida Research Foundation, Inc. | Automated method for digital image quantitation |
CN106845444A (en) * | 2017-02-15 | 2017-06-13 | 西安交通大学 | A kind of vehicle well cover detection method combined based on acnode |
CN107492094A (en) * | 2017-07-21 | 2017-12-19 | 长安大学 | A kind of unmanned plane visible detection method of high voltage line insulator |
CN107742301A (en) * | 2017-10-25 | 2018-02-27 | 哈尔滨理工大学 | Transmission line of electricity image processing method under complex background based on image classification |
US20180056797A1 (en) * | 2016-08-31 | 2018-03-01 | Faraday&Future Inc. | Systems and methods for providing an intelligent charge handle for charging a vehicle battery |
CN110390696A (en) * | 2019-07-03 | 2019-10-29 | 浙江大学 | A kind of circular hole pose visible detection method based on image super-resolution rebuilding |
CN111192326A (en) * | 2020-01-02 | 2020-05-22 | 上海电气集团股份有限公司 | Method and system for visually identifying direct-current charging socket of electric automobile |
CN111402316A (en) * | 2020-03-09 | 2020-07-10 | 东华大学 | Method for rapidly detecting ellipse in image based on false link removal |
WO2021027070A1 (en) * | 2019-08-09 | 2021-02-18 | 清华大学 | Deep learning-based ellipse recognition method |
-
2021
- 2021-07-16 CN CN202110807529.4A patent/CN113538488A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO1996041312A1 (en) * | 1995-06-07 | 1996-12-19 | University Of Florida Research Foundation, Inc. | Automated method for digital image quantitation |
US20180056797A1 (en) * | 2016-08-31 | 2018-03-01 | Faraday&Future Inc. | Systems and methods for providing an intelligent charge handle for charging a vehicle battery |
CN106845444A (en) * | 2017-02-15 | 2017-06-13 | 西安交通大学 | A kind of vehicle well cover detection method combined based on acnode |
CN107492094A (en) * | 2017-07-21 | 2017-12-19 | 长安大学 | A kind of unmanned plane visible detection method of high voltage line insulator |
CN107742301A (en) * | 2017-10-25 | 2018-02-27 | 哈尔滨理工大学 | Transmission line of electricity image processing method under complex background based on image classification |
CN110390696A (en) * | 2019-07-03 | 2019-10-29 | 浙江大学 | A kind of circular hole pose visible detection method based on image super-resolution rebuilding |
WO2021027070A1 (en) * | 2019-08-09 | 2021-02-18 | 清华大学 | Deep learning-based ellipse recognition method |
CN111192326A (en) * | 2020-01-02 | 2020-05-22 | 上海电气集团股份有限公司 | Method and system for visually identifying direct-current charging socket of electric automobile |
CN111402316A (en) * | 2020-03-09 | 2020-07-10 | 东华大学 | Method for rapidly detecting ellipse in image based on false link removal |
Non-Patent Citations (1)
Title |
---|
项博良 等: "基于椭圆检测的充电口识别", 计算机技术与发展, vol. 30, no. 4, pages 1 - 5 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116630315A (en) * | 2023-07-24 | 2023-08-22 | 山东东阿亿福缘阿胶制品有限公司 | Intelligent beverage packaging defect detection method based on computer vision |
CN116630315B (en) * | 2023-07-24 | 2023-09-29 | 山东东阿亿福缘阿胶制品有限公司 | Intelligent beverage packaging defect detection method based on computer vision |
CN116958793A (en) * | 2023-07-24 | 2023-10-27 | 国网江苏省电力有限公司泰州供电分公司 | Device and method for evaluating visual recognition of charging robot based on illumination condition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111488756B (en) | Face recognition-based living body detection method, electronic device, and storage medium | |
CN113538488A (en) | BMS charging port identification method | |
CN110517265B (en) | Method and device for detecting surface defects of product and storage medium | |
CN106709500B (en) | Image feature matching method | |
CN109447117B (en) | Double-layer license plate recognition method and device, computer equipment and storage medium | |
CN111695373B (en) | Zebra stripes positioning method, system, medium and equipment | |
CN105320946A (en) | MATLAB based fingerprint identification method | |
CN101114335A (en) | Full angle rapid fingerprint identification method | |
CN107480662B (en) | Mould image identification method and device | |
CN104537650A (en) | Polarity direction judging method and device for aluminum electrolytic capacitor | |
CN113724243B (en) | Image processing method, image processing device, electronic equipment and storage medium | |
CN105447489B (en) | A kind of character of picture OCR identifying system and background adhesion noise cancellation method | |
CN114240978B (en) | Cell edge segmentation method and device based on adaptive morphology | |
CN109409181A (en) | A kind of finger lower edges independent detection method referring to vein image for low quality | |
CN111950654B (en) | Magic cube color block color reduction method based on SVM classification | |
CN111192326A (en) | Method and system for visually identifying direct-current charging socket of electric automobile | |
CN110032946A (en) | A kind of aluminium based on machine vision/aluminium blister package tablet identification and localization method | |
Frejlichowski | Pre-processing, extraction and recognition of binary erythrocyte shapes for computer-assisted diagnosis based on MGG images | |
CN112435272A (en) | High-voltage transmission line connected domain removing method based on image contour analysis | |
CN116703909A (en) | Intelligent detection method for production quality of power adapter | |
CN112418226B (en) | Method and device for identifying opening and closing states of fisheyes | |
Wang et al. | Lane detection algorithm based on density clustering and RANSAC | |
CN112329572B (en) | Rapid static living body detection method and device based on frame and flash point | |
CN110619273B (en) | Efficient iris recognition method and recognition device | |
CN112329556A (en) | Traffic sign detection method and device, electronic equipment and storage medium |
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 |