CN112507984B - Conveying material abnormity identification method, device and system based on image identification - Google Patents
Conveying material abnormity identification method, device and system based on image identification Download PDFInfo
- Publication number
- CN112507984B CN112507984B CN202110144098.8A CN202110144098A CN112507984B CN 112507984 B CN112507984 B CN 112507984B CN 202110144098 A CN202110144098 A CN 202110144098A CN 112507984 B CN112507984 B CN 112507984B
- Authority
- CN
- China
- Prior art keywords
- image
- included angle
- angle
- analyzing
- corrected
- 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
- 239000000463 material Substances 0.000 title claims abstract description 83
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000002159 abnormal effect Effects 0.000 claims abstract description 17
- 230000006870 function Effects 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000005856 abnormality Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000010191 image analysis Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 abstract description 4
- 239000000126 substance Substances 0.000 abstract 1
- 230000008569 process Effects 0.000 description 7
- 239000003086 colorant Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
- G06Q10/0832—Special goods or special handling procedures, e.g. handling of hazardous or fragile goods
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Multimedia (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
- Controlling Sheets Or Webs (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The embodiment of the invention relates to image recognition, and discloses a conveying material abnormity recognition method based on image recognition, which is characterized by comprising the following steps: s1: collecting a first video of a first material; s2: analyzing the first video to obtain a first image, and calculating a first included angle between the first material and the conveying belt(ii) a Wherein the content of the first and second substances,the included angles between the directions of the x axis, the y axis and the z axis and the conveying belt are respectively formed; s3: correcting the first included angleTo obtain a second included angle(ii) a S4: a standard image of the first material is taken according to the second included angle
Description
Technical Field
The embodiment of the invention relates to the field of image recognition, in particular to material abnormity detection.
Background
With the wide application of the loading device, the accurate identification and automatic conveying of various materials become the key problems in the fields of automatic loading and transportation. In the loading process, abnormal materials are conveyed into the vehicle, or materials with different specifications of planned goods in the warehouse are conveyed into the vehicle for stacking, so that the stacking of the goods in the vehicle is not uniform, and the risk of sliding is caused in the process of transporting the goods after loading. In the conveying belt process of goods before loading, due to the fact that sliding with the conveying belt exists in different degrees, the goods and the conveying belt exist angle change in the transportation process from time to time, the influence of the angle change caused by sliding on abnormal recognition is avoided, and then whether materials conveyed on the conveying belt conform to materials to be conveyed in a warehouse or not can be rapidly recognized and judged, and the problem in the field is solved.
Disclosure of Invention
In order to solve the technical problem, an embodiment of the present invention provides an image recognition-based transportation material abnormality recognition method, including:
s1: collecting a first video of a first material;
s2: analyzing the first video to obtain a first image, and calculating a first included angle between the first material and the conveying belt(ii) a Wherein,the included angles between the directions of the x axis, the y axis and the z axis and the conveying belt are respectively formed;
S4: a standard image of the first material is taken according to the second included angleCorrecting the standard image of the first material to obtain a corrected image;
s5: and comparing the first image with the corrected image, and if the difference between the first image and the corrected image exceeds a preset condition, judging that the material is abnormal.
Preferably, the S2 specifically includes:
s2.1: analyzing to obtain a vertex coordinate of the first image;
s2.2: obtaining the first included angle based on the included angle between the vertex coordinate and the conveying belt。
Preferably, the S3 specifically includes:
s3.1, analyzing the first video to obtain i second images at the previous time nodes of the first image, analyzing the i second images, and calculating to obtain an included angle(ii) a Wherein i is an integer greater than 2;
s3.2, analyzing the first video to obtain j third images at the later time nodes of the first image, analyzing the j third images, and calculating to obtain included angles(ii) a Wherein j is an integer greater than 2;
s3.3 fitting by means of the least squares method,And the corresponding time node t, and obtaining a fitted function f (t);
s3.4 ifLess than the first threshold, will,Is used as a correction angle, and the correction angle is adopted for correctionThe first included angle of the conveyer beltTo obtain a second included angle;
If it isIf the included angle is larger than or equal to the first threshold value, the moment is reselected as the first image, and the first included angle is obtained through analysisAnd repeating S3.1-S3.3.
Preferably, S3.4 adopts the correction included angle to correct the first included angle of the conveying beltTo obtain a second included angleThe method comprises the following steps:
if the first included angleIf the standard deviation of the angle to the correction angle is less than the second threshold, the correction angle is used as the second angle(ii) a If the first included angleThe standard deviation of the angle to the correction is greater than or equal to a second threshold value and smaller than a third threshold value, and the first angle is adjustedTaking the average value of the corrected included angles as a second included angle(ii) a If the first included angleIf the standard deviation of the angle to be corrected is larger than or equal to a third threshold value, the moment is reselected as the first image, and the first angle is obtained through analysisAnd repeating S3.1-S3.3.
Preferably, the S5 includes:
s5.1, calculating the length-width ratio, the length-height ratio and the width-height ratio of the first image, and correcting the length-width ratio, the length-height ratio and the width-height ratio of the image;
s5.2, comparing the length-width ratio of the first image with the length-width ratio of the corrected image, comparing the length-height ratio of the first image with the length-height ratio of the corrected image, and comparing the width-height ratio of the first image with the width-height ratio of the corrected image;
and if the difference value of any one group of proportions exceeds a fourth threshold value, judging that the material is abnormal.
An image recognition-based conveying material abnormality recognition device comprises:
the video acquisition module is used for acquiring a first video of the material;
the image analysis module is used for analyzing the first video to obtain a first image and calculating a first included angle between the first material and the conveying belt(ii) a Wherein,the included angles between the directions of the x axis, the y axis and the z axis and the conveying belt are respectively formed;
a correction module for correcting the first included angleTo obtain a second included angle(ii) a And calling a standard image of the first material according to the second included angleCorrecting the standard image of the first material to obtain a corrected image;
and the judging module compares the first image with the corrected image, and judges that the material is abnormal if the difference between the first image and the corrected image exceeds a preset condition.
analyzing the first video to obtain i second images at the previous time nodes of the first image, analyzing the i second images, and calculating to obtain an included angle(ii) a Wherein i is an integer greater than 2;
analyzing the first video to obtain j third images at the later time nodes of the first image, analyzing the j third images, and calculating to obtain an included angle(ii) a Wherein j is an integer greater than 2;
if it isLess than the first threshold, will,The average value of (1) is used as a correction included angle, and the correction included angle is adopted to correct the first included angle of the conveying beltTo obtain a second included angle;
If it isIf the included angle is larger than or equal to the first threshold value, the moment is reselected as the first image, and the first included angle is obtained through analysis。
An image recognition based transportation material anomaly identification system comprising one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the image recognition based transport material anomaly identification methods described above.
According to the method, through angle correction along with time change, a proper time node is positioned for angle calculation and correction, and identification errors caused by inaccurate angle correction in the sliding process of materials and a conveying belt are avoided; in the material abnormity identification, the aspect ratio and the length-height ratio which are more critical to the transportation are used for replacing image comparison identification, other factors which have no influence on material stacking such as colors and the like are not considered, and the abnormity identification efficiency is improved. In conclusion, the method and the device realize the rapid and accurate abnormity detection of the conveying materials based on the image recognition.
The foregoing description is only an overview of the technical solutions of the present invention, and the embodiments of the present invention are described below in order to make the technical means of the present invention more clearly understood and to make the above and other objects, features, and advantages of the present invention more clearly understandable.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in detail below. However, it will be appreciated by those of ordinary skill in the art that numerous technical details are set forth in order to provide a better understanding of the present application in various embodiments of the present invention. However, the technical solution claimed in the present application can be implemented without these technical details and various changes and modifications based on the following embodiments. The following embodiments are divided for convenience of description, and should not constitute any limitation to the specific implementation manner of the present invention, and the embodiments may be mutually incorporated and referred to without contradiction.
Example one
The embodiment provides a conveying material abnormity identification method based on image identification, which comprises the following steps:
s1: collecting a first video of a first material;
s2: analyzing the first video to obtain a first image, and calculating a first included angle between the first material and the conveying belt(ii) a Wherein,the included angles between the directions of the x axis, the y axis and the z axis and the conveying belt are respectively formed;
s2.1: analyzing to obtain a vertex coordinate of the first image;
s2.2: obtaining the first included angle based on the included angle between the vertex coordinate and the conveying belt。
S3.1, analyzing the first video to obtain i second images at the previous time nodes of the first image, analyzing the i second images, and calculating to obtain an included angle(ii) a Wherein i is an integer greater than 2;
s3.2, analyzing the first video to obtain j third images at the later time nodes of the first image, analyzing the j third images, and calculating to obtain included angles(ii) a Wherein j is an integer greater than 2;
s3.3 fitting by means of the least squares method,And the corresponding time node t, and obtaining a fitted function f (t);
s3.4 ifLess than the first threshold, will,The average value of (1) is used as a correction included angle, and the correction included angle is adopted to correct the first included angle of the conveying beltTo obtain a second included angle;
If it isIf the included angle is larger than or equal to the first threshold value, the moment is reselected as the first image, and the first included angle is obtained through analysisAnd repeating S3.1-S3.3.
The step acquires the deviation angle in the time period before and after the first included angle at a specific moment, and obtains the included angle deviation before and after a certain moment by adopting a least square fitting function mode. And judging whether the sliding exists in the time period or not through the fitting function. If the value calculated by the fitting function is smaller than the threshold value, the sliding between the materials and the conveyor belt in the time period is considered to be absent, and the included angle in the time period before and after the specific moment is available; if the value calculated by the fitting function is larger than or equal to the threshold value, the material and the conveyor belt in the time period are considered to have obvious sliding, the included angle of the specific time possibly has errors, the time is selected again, and the angle in the time period is adopted for correction after the condition that the obvious sliding does not exist is judged. The angle correction algorithm in the time periods before and after the specific moment effectively avoids the error identification caused by the sliding between the materials and the conveyor belt when the pictures are collected, and improves the accuracy of abnormal material identification.
S3.4 adopt the correction included angle to correct the conveying belt and the first included angleTo obtain a second included angleThe method comprises the following steps:
if the first included angleIf the standard deviation of the angle to the correction angle is less than the second threshold, the correction angle is used as the second angle(ii) a If the first included angleThe standard deviation of the angle to the correction is greater than or equal to a second threshold value and smaller than a third threshold value, and the first angle is adjustedTaking the average value of the corrected included angles as a second included angle(ii) a If the first included angleIf the standard deviation of the angle to be corrected is larger than or equal to a third threshold value, the moment is reselected as the first image, and the first angle is obtained through analysisAnd repeating S3.1-S3.3.
S4: a standard image of the first material is taken according to the second included angleCorrecting the standard image of the first material to obtain a corrected image;
s5: and comparing the first image with the corrected image, and if the difference between the first image and the corrected image exceeds a preset condition, judging that the material is abnormal.
S5.1, calculating the length-width ratio, the length-height ratio and the width-height ratio of the first image, and correcting the length-width ratio, the length-height ratio and the width-height ratio of the image;
s5.2, comparing the length-width ratio of the first image with the length-width ratio of the corrected image, comparing the length-height ratio of the first image with the length-height ratio of the corrected image, and comparing the width-height ratio of the first image with the width-height ratio of the corrected image;
and if the difference value of any one group of proportions exceeds a fourth threshold value, judging that the material is abnormal.
According to the traditional material abnormal conveying method based on image comparison, images are directly compared one by one, the calculated amount is large, and the abnormal material identification efficiency is low. In fact, when materials are conveyed and subsequently stacked in the vehicle, information such as colors and patterns has no effect on stacking the materials, and the length, width and height ratio of the materials is an important factor for preventing the materials from being subsequently stacked in the vehicle, particularly the falling caused by emergency braking of the vehicle in the operation process. Therefore, the method for identifying abnormal materials based on images provided by the embodiment does not compare information such as colors and patterns, and only focuses on key factors: aspect ratio, length-to-height ratio have effectively improved unusual recognition efficiency, and do not influence subsequent sign indicating number material and loading.
Example two
An image recognition-based conveying material abnormality recognition device comprises:
the video acquisition module is used for acquiring a first video of the material;
the image analysis module is used for analyzing the first video to obtain a first image and calculating a first included angle between the first material and the conveying belt(ii) a Wherein,the included angles between the directions of the x axis, the y axis and the z axis and the conveying belt are respectively formed;
a correction module for correcting the first included angleTo obtain a second included angle(ii) a And taking the first materialAccording to the second included angleCorrecting the standard image of the first material to obtain a corrected image;
and the judging module compares the first image with the corrected image, and judges that the material is abnormal if the difference between the first image and the corrected image exceeds a preset condition.
analyzing the first video to obtain i second images at the previous time nodes of the first image, analyzing the i second images, and calculating to obtain an included angle(ii) a Wherein i is an integer greater than 2;
analyzing the first video to obtain j third images at the later time nodes of the first image, analyzing the j third images, and calculating to obtain an included angle(ii) a Wherein j is an integer greater than 2;
if it isLess than the first threshold, will,The average value of (1) is used as a correction included angle, and the correction included angle is adopted to correct the first included angle of the conveying beltTo obtain a second included angle;
If it isIf the included angle is larger than or equal to the first threshold value, the moment is reselected as the first image, and the first included angle is obtained through analysis。
The embodiment also provides a conveying material abnormity identification system based on image identification, which comprises one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for performing any of the image recognition based transport material anomaly identification methods described above.
In the embodiment, through angle correction which changes along with time, a proper time node is positioned for angle calculation and correction, and identification errors caused by inaccurate angle correction in the sliding process of materials and a conveying belt are avoided; in the material abnormity identification, the aspect ratio and the length-height ratio which are more critical to the transportation are used for replacing image comparison identification, other factors which have no influence on material stacking such as colors and the like are not considered, and the abnormity identification efficiency is improved. In conclusion, the embodiment realizes the rapid and accurate abnormity detection of the conveying materials based on the image recognition.
It will be understood by those of ordinary skill in the art that the foregoing embodiments are specific examples for carrying out the invention, and that various changes in form and details may be made therein without departing from the spirit and scope of the invention in practice.
Claims (5)
1. A conveying material abnormity identification method based on image identification is characterized by comprising the following steps:
s1: collecting a first video of a first material;
s2: analyzing the first video to obtain a first image, and calculating a first included angle between the first material and the conveying belt(ii) a Wherein,the included angles between the directions of the x axis, the y axis and the z axis and the conveying belt are respectively formed;
S4: a standard image of the first material is taken according to the second included angleCorrecting the standard image of the first material to obtain a corrected image;
s5: comparing the first image with the corrected image, and if the difference between the first image and the corrected image exceeds a preset condition, judging that the material is abnormal;
the S3 specifically includes:
s3.1, analyzing the first video to obtain i second images at the previous time nodes of the first image, analyzing the i second images, and calculating to obtain an included angle(ii) a Wherein i is an integer greater than 2;
s3.2, analyzing the first video to obtain j third images at the later time nodes of the first image, analyzing the j third images, and calculating to obtain included angles(ii) a Wherein j is an integer greater than 2;
s3.3 fitting by means of the least squares method,And the corresponding time node t, and obtaining a fitted function f (t);
s3.4 ifLess than the first threshold, will,The average value of (1) is used as a correction included angle, and the correction included angle is adopted to correct the first included angle of the conveying beltTo obtain a second included angle;
If it isIf the time is larger than or equal to the first threshold, the moment is reselected as the first image, and the first image is analyzed to obtain a first imageIncluded angleAnd repeating S3.1-S3.3;
the S5 includes:
s5.1, calculating the length-width ratio, the length-height ratio and the width-height ratio of the first image, and correcting the length-width ratio, the length-height ratio and the width-height ratio of the image;
s5.2, comparing the length-width ratio of the first image with the length-width ratio of the corrected image, comparing the length-height ratio of the first image with the length-height ratio of the corrected image, and comparing the width-height ratio of the first image with the width-height ratio of the corrected image;
and if the difference value of any one group of proportions exceeds a fourth threshold value, judging that the material is abnormal.
2. The method for identifying the abnormality of the transported material based on the image identification as claimed in claim 1, wherein the S2 specifically includes:
s2.1: analyzing to obtain a vertex coordinate of the first image;
3. The method for identifying abnormality of conveyed material based on image identification as claimed in claim 1, wherein said S3.4 corrects said first angle of said conveyor belt by using said corrected angleTo obtain a second included angleThe method comprises the following steps:
if the first included angleIf the standard deviation of the angle to the correction angle is less than the second threshold, the correction angle is used as the second angle(ii) a If the first included angleThe standard deviation of the angle to the correction is greater than or equal to a second threshold value and smaller than a third threshold value, and the first angle is adjustedTaking the average value of the corrected included angles as a second included angle(ii) a If the first included angleIf the standard deviation of the angle to be corrected is larger than or equal to a third threshold value, the moment is reselected as the first image, and the first angle is obtained through analysisAnd repeating S3.1-S3.3.
4. An unusual recognition device of transported material based on image recognition, its characterized in that includes:
the video acquisition module is used for acquiring a first video of the material;
the image analysis module is used for analyzing the first video to obtain a first image and calculating a first included angle between the first material and the conveying belt(ii) a Wherein,respectively as the included angles between the directions of the x axis, the y axis and the z axis and the conveyer belt;
A correction module for correcting the first included angleTo obtain a second included angle(ii) a And calling a standard image of the first material according to the second included angleCorrecting the standard image of the first material to obtain a corrected image;
the judging module is used for comparing the first image with the corrected image, and judging that the material is abnormal if the difference between the first image and the corrected image exceeds a preset condition; the second included angle of the correction moduleThe calculation method is as follows:
analyzing the first video to obtain i second images at the previous time nodes of the first image, analyzing the i second images, and calculating to obtain an included angle(ii) a Wherein i is an integer greater than 2;
analyzing the first video to obtain j third images at the later time nodes of the first image, analyzing the j third images, and calculating to obtain an included angle(ii) a Wherein j is an integer greater than 2;
if it isLess than the first threshold, will,The average value of (1) is used as a correction included angle, and the correction included angle is adopted to correct the first included angle of the conveying beltTo obtain a second included angle;
If it isIf the included angle is larger than or equal to the first threshold value, the moment is reselected as the first image, and the first included angle is obtained through analysis;
The judgment module executes: calculating the length-width ratio, the length-height ratio and the width-height ratio of the first image, and correcting the length-width ratio, the length-height ratio and the width-height ratio of the image;
comparing the aspect ratio of the first image with the aspect ratio of the corrected image, and comparing the aspect ratio of the first image with the aspect ratio of the corrected image;
and if the difference value of any one group of proportions exceeds a fourth threshold value, judging that the material is abnormal.
5. An image recognition-based transportation material anomaly identification system, characterized in that the image recognition-based transportation material anomaly identification system comprises one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the method of any of claims 1-3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110144098.8A CN112507984B (en) | 2021-02-03 | 2021-02-03 | Conveying material abnormity identification method, device and system based on image identification |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110144098.8A CN112507984B (en) | 2021-02-03 | 2021-02-03 | Conveying material abnormity identification method, device and system based on image identification |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112507984A CN112507984A (en) | 2021-03-16 |
CN112507984B true CN112507984B (en) | 2021-05-11 |
Family
ID=74952854
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110144098.8A Active CN112507984B (en) | 2021-02-03 | 2021-02-03 | Conveying material abnormity identification method, device and system based on image identification |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112507984B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102055959A (en) * | 2009-10-29 | 2011-05-11 | 株式会社日立制作所 | Central monitoring system based on a plurality of monitoring cameras and central monitoring method |
CN103839373A (en) * | 2013-03-11 | 2014-06-04 | 成都百威讯科技有限责任公司 | Sudden abnormal event intelligent identification alarm device and system |
CN110054121A (en) * | 2019-04-25 | 2019-07-26 | 北京极智嘉科技有限公司 | A kind of intelligent forklift and container pose bias detecting method |
CN111160339A (en) * | 2019-12-24 | 2020-05-15 | 浙江大华技术股份有限公司 | License plate correction method, image processing equipment and device with storage function |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101173565B1 (en) * | 2009-12-24 | 2012-08-13 | 한국과학기술원 | Container detecting method using image processing |
CN105157626B (en) * | 2015-09-29 | 2018-01-02 | 中国民用航空总局第二研究所 | A kind of fixed road face detection means and method using structure light |
CN108932479A (en) * | 2018-06-06 | 2018-12-04 | 上海理工大学 | A kind of human body anomaly detection method |
-
2021
- 2021-02-03 CN CN202110144098.8A patent/CN112507984B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102055959A (en) * | 2009-10-29 | 2011-05-11 | 株式会社日立制作所 | Central monitoring system based on a plurality of monitoring cameras and central monitoring method |
CN103839373A (en) * | 2013-03-11 | 2014-06-04 | 成都百威讯科技有限责任公司 | Sudden abnormal event intelligent identification alarm device and system |
CN110054121A (en) * | 2019-04-25 | 2019-07-26 | 北京极智嘉科技有限公司 | A kind of intelligent forklift and container pose bias detecting method |
CN111160339A (en) * | 2019-12-24 | 2020-05-15 | 浙江大华技术股份有限公司 | License plate correction method, image processing equipment and device with storage function |
Also Published As
Publication number | Publication date |
---|---|
CN112507984A (en) | 2021-03-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111553951B (en) | Parcel processing apparatus and parcel processing method | |
US8631922B2 (en) | System, apparatus, and method for object edge detection | |
CN115953373B (en) | Glass defect detection method, device, electronic equipment and storage medium | |
CN115065708B (en) | Industrial Internet of things system based on machine vision detection and control method thereof | |
CN116309565A (en) | High-strength conveyor belt deviation detection method based on computer vision | |
CN112507984B (en) | Conveying material abnormity identification method, device and system based on image identification | |
CN113095444A (en) | Image labeling method, device and storage medium | |
WO2023109557A1 (en) | Connector inspection method, electronic device and storage medium | |
CN112464785A (en) | Target detection method and device, computer equipment and storage medium | |
CN117055249A (en) | Sampling quality inspection analysis system for liquid crystal display screen assembly processing line | |
CN113192061B (en) | Extraction method and device of LED package appearance detection image, electronic equipment and storage medium | |
US20230294134A1 (en) | Parcel singulation yield correcting system and method | |
CN116777894B (en) | Method and device for detecting surface defects of chip | |
CN116468373B (en) | Power plant equipment warehouse management system based on Internet of things | |
CN114638888B (en) | Position determination method and device, electronic equipment and readable storage medium | |
CN116128853A (en) | Production line assembly detection method, system, computer and readable storage medium | |
CN112767397B (en) | Workpiece detection method, workpiece detection device, and storage medium | |
CN115631125A (en) | Parcel detection method and parcel processing apparatus | |
CN110031474B (en) | Foreign matter detection method and foreign matter detection device | |
JPH07243808A (en) | Method and apparatus for inspection of label as well as lebel image processor | |
CN109388983B (en) | Bar code classification method, classification device, electronic equipment and storage medium | |
CN112200976B (en) | Medicine detection method and device, electronic terminal and storage medium | |
US20230351578A1 (en) | Method, program, apparatus, and system for abnormality detection | |
CN116402841B (en) | Cross-animal flow offset detection method and related device based on machine vision | |
JP2004318488A (en) | Product inspection method and product inspection device |
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 |