CN112287853A - Dynamic intelligent image recognition algorithm based on IT equipment indicator light and equipment model - Google Patents
Dynamic intelligent image recognition algorithm based on IT equipment indicator light and equipment model Download PDFInfo
- Publication number
- CN112287853A CN112287853A CN202011204261.7A CN202011204261A CN112287853A CN 112287853 A CN112287853 A CN 112287853A CN 202011204261 A CN202011204261 A CN 202011204261A CN 112287853 A CN112287853 A CN 112287853A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- equipment
- points
- point
- comparison
- 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
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 239000003086 colorant Substances 0.000 claims description 11
- 230000004913 activation Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 238000003825 pressing Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 abstract description 15
- 238000007689 inspection Methods 0.000 abstract description 14
- 238000000034 method Methods 0.000 abstract description 12
- 238000012544 monitoring process Methods 0.000 abstract description 8
- 230000008569 process Effects 0.000 abstract description 8
- 238000009826 distribution Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 11
- 238000007726 management method Methods 0.000 description 10
- 238000013473 artificial intelligence Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013523 data management Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013439 planning Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000272194 Ciconiiformes Species 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/64—Analysis of geometric attributes of convexity or concavity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a dynamic intelligent image recognition algorithm based on IT equipment indicator lights and equipment models, which comprises the following steps: the identification algorithm is a YoloV3 identification algorithm based on native darknet53, and is used for respectively extracting the characteristics of two input pictures by taking a convolutional neural network as a characteristic extraction network; and a comparison algorithm, namely generating convex polygons of the two input pictures according to the extracted features by using a convex hull algorithm in the computational geometry, and comparing the convex polygons. Has the advantages that: the method and the system realize the automatic IT operation and maintenance management process, make the condition of equipment assets in the machine room clearly visible, realize the monitoring performance of the operation and maintenance process of the machine room, improve the manual distribution of the machine room and reduce the manual inspection task.
Description
Technical Field
The invention relates to the technical field of image recognition algorithms, in particular to a dynamic intelligent image recognition algorithm based on IT equipment indicator lamps and equipment models.
Background
The development of the national penguin and the national enterprise is closely related to the national civilization, industrial production and economic development, and how to ensure the normal development of business is an important task of enterprises. The normal work of IT-related equipment is the basis for the normal development of business, so the management of the IT equipment in a machine room is an important daily work of an operation and maintenance department.
The traditional machine room operation and maintenance is carried out manually, the safety and stability of the machine room are required to be high, the service continuity of personnel is high, and the problems of more equipment and fewer operation and maintenance personnel exist in the practical situation. Therefore, the following situations are easy to occur in the inspection management mode: 1. the in-place condition of the routing inspection and the recorded data cannot be used for mastering the authenticity of the data; 2. a large amount of routing inspection information is inconvenient to store, easy to lose and labor-consuming; 3. the information is inconvenient to query, and the data cannot be effectively utilized to make auxiliary decisions on equipment such as defect analysis and model selection; 4. the inspection workload is large, the repeatability is high, the working strength is high, and a large amount of working time of operation and maintenance personnel is occupied; 5. the inspection frequency is low due to the fact that the inspection personnel are insufficient.
In recent years, with the support and the advocated of the country, the artificial intelligence technology has been developed vigorously, and the artificial intelligence technology finds good landing scenes in various industries, wherein intelligent operation and maintenance is one of the scenes. In the noisy environment of computer lab, the radiation is heavy, still considerable to fortune dimension personnel's health injury, so intelligent fortune dimension becomes the mainstream that can become computer lab fortune dimension afterwards. The image recognition technology of artificial intelligence can just replace manual inspection, and can accurately recognize related equipment and indicator lights. If the alarm exists, the comparison algorithm gives an alarm in real time. Therefore, the invention provides a dynamic intelligent image recognition algorithm based on the IT equipment indicator light and the equipment model.
Disclosure of Invention
Aiming at the problems in the related art, the invention provides a dynamic intelligent image recognition algorithm based on IT equipment indicator lights and equipment models, so as to overcome the technical problems in the prior related art.
Therefore, the invention adopts the following specific technical scheme:
based on a dynamic intelligent image recognition algorithm for IT equipment indicator lights and equipment models, the dynamic intelligent image recognition algorithm comprises the following steps:
the identification algorithm is a YoloV3 identification algorithm based on native darknet53, and is used for respectively extracting the characteristics of two input pictures by taking a convolutional neural network as a characteristic extraction network;
and a comparison algorithm, namely generating convex polygons of the two input pictures according to the extracted features by using a convex hull algorithm in the computational geometry, and comparing the convex polygons.
Further, the recognition algorithm uses a leak ReLU as an activation function, a batch normalization as a regularization, and the recognition algorithm is a multi-scale training end-to-end recognition algorithm.
Further, the comparison algorithm uses a convex hull algorithm in the computational geometry to generate convex polygons of the two input pictures according to the extracted features, and the comparison specifically comprises the following steps:
generating convex polygons of the two input pictures by using a convex hull algorithm according to the extracted features;
and comparing the two groups of convex polygons sequentially through outer layer point comparison, inner layer point comparison and color comparison.
Further, the convex hull algorithm specifically includes the following steps:
finding the point with the smallest ordinate y among all the points of the input picture, namely the lowest point among all the points, and recording the point as p0；
Then calculating the cosine values of included angles between connecting lines of the rest points and the point and the x axis, sequencing the points from large to small according to the sine value of the points to the lowest point, and marking the sequenced points as p1，p2，p3，…pn；
The lowest point p0And the first point p of the sorted points1Push into stack, then from p2Starting calculation, calculating whether vectors of two points at the top of the stack and three points at the point rotate anticlockwise, if so, pressing the point into the stack, otherwise, pushing out elements at the top of the stack;
the last element in the stack is the point at the periphery of all convex hulls.
Further, the step of judging whether the rotation is counterclockwise specifically includes the following steps:
setting the two points at the top of the stack and the p2The coordinates of the points are respectively A (a)x，ay)、B(bx，by)、C(cx，cy)；
According to the formula area ═ bx-ax)*(cy-ay)-(by-ay)*(cx-ax) Calculating the value of area when area>0, A-B-C counterclockwise rotation, area<0, A-B-C rotates clockwise, area is 0, and A-B-C is on a straight line.
Further, the algorithm principle of the outer layer point comparison is as follows: when the shapes of the two groups of convex polygons are completely the same, indicating lamps on the periphery are completely the same; and when the shapes of the two groups of convex polygons are different, indicating that the indicator lamp is turned off, sending abnormal information and giving an alarm.
Further, the algorithm principle of the inner layer point comparison is as follows: respectively taking a triangle formed by any two external points and internal points in the two groups of convex polygons, calculating the side length proportion of two adjacent sides in the triangle and the included angle formed by the two sides, and comparing; if the side length ratio is equal to the included angle, the internal point exists, if the side length ratio is not equal to the included angle, the internal point does not exist, abnormal information is sent, and an alarm is given.
Further, the algorithm principle of the color comparison is as follows: comparing the colors of the indicator lights in the two groups of convex polygons, and if the colors are the same, indicating that the indicator lights are not abnormal, and not giving an alarm; if the colors are different, the indication lamp is abnormal, abnormal information is sent, and an alarm is given.
The invention has the beneficial effects that:
1) the indicating lamp of various colours in the computer lab equipment can be discerned through utilizing artificial intelligence, machine vision, topological technique to distinguish the colour of indicating lamp, can also utilize the graphics algorithm to contrast the indicating lamp, if detect the indicating lamp warning, for example extinguish, turn red, can report to the police at once, can give the effectual loss stopping of user.
2) By establishing an intelligent identification project system, an automatic IT operation and maintenance management process is realized, the condition of equipment assets of a machine room is clear and visible, and the monitoring performance of the operation and maintenance process of the machine room is realized.
3) Through improving basic data management, unified with the rack with wherein the data rule of patrolling and examining of equipment, through the integrated automatic transmission that realizes IT fortune dimension basic data to ITACS, guarantee the accuracy of data, the promptness to the management mode of managing and controlling is concentrated to fortune dimension basic data has been established.
4) Through improving the IT operation and maintenance management mode, the automatic systematic management from monitoring room monitoring to machine room equipment is realized, an automatic plan task is established, the machine room inspection plan mode which is automatically executed improves the manual distribution of the machine room, and the manual inspection task is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart of a dynamic intelligent image recognition algorithm based on indication lights and device models of IT devices according to an embodiment of the present invention;
FIG. 2 is a block diagram of a YoloV3 recognition algorithm in a dynamic intelligent image recognition algorithm based on indicators and device models for IT devices, according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a convex hull algorithm in a dynamic intelligent image recognition algorithm based on indicators and device models of IT devices, according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a principle of determining whether the IT device indicator light and the device model rotate counterclockwise in a dynamic intelligent image recognition algorithm according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of the principle of comparing the outer layer points in the dynamic intelligent image recognition algorithm based on the indication lamps and the model numbers of the IT equipment according to the embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating the principle of comparing inner layer points in a dynamic intelligent image recognition algorithm based on the indication lamps and the model numbers of IT devices according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an input picture in a dynamic intelligent image recognition algorithm based on indicators and device models for IT devices, according to an embodiment of the present invention;
FIG. 8 is a diagram of an original image of a comparison algorithm in a dynamic intelligent image recognition algorithm based on indicators and device models of IT devices according to an embodiment of the present invention;
fig. 9 is a schematic diagram of a convex hull algorithm test picture in a dynamic intelligent image recognition algorithm based on the IT device indicator light and the device model according to an embodiment of the present invention.
Detailed Description
For further explanation of the various embodiments, the drawings which form a part of the disclosure and which are incorporated in and constitute a part of this specification, illustrate embodiments and, together with the description, serve to explain the principles of operation of the embodiments, and to enable others of ordinary skill in the art to understand the various embodiments and advantages of the invention, and, by reference to these figures, reference is made to the accompanying drawings, which are not to scale and wherein like reference numerals generally refer to like elements.
According to the embodiment of the invention, a dynamic intelligent image recognition algorithm based on the IT equipment indicator light and the equipment model is provided.
Referring to the drawings and the detailed description, the present invention will be further described, as shown in fig. 1 to 9, a dynamic intelligent image recognition algorithm based on the indication lights and the device models of the IT devices according to an embodiment of the present invention, the dynamic intelligent image recognition algorithm includes the following steps:
step S1: the identification algorithm is a YoloV3 identification algorithm based on native darknet53, and is used for respectively extracting the characteristics of two input pictures by taking a convolutional neural network as a characteristic extraction network;
specifically, the whole picture is divided into cells for detection, the algorithm uses a leave ReLU as an activation function, batch normalization as regularization, and an end-to-end recognition algorithm for multi-scale training.
Fig. 2 shows a block diagram of YoloV3 recognition algorithm, because real-time detection is required in the machine room inspection, and the indicator light in the equipment is very small. Compared with the current recognition algorithm based on deep learning, the algorithm can meet the requirements of real time and detection of small targets, and only the YoloV3 is met, so the algorithm is adopted.
Step S2: and a comparison algorithm, namely generating convex polygons of the two input pictures according to the extracted features by using a convex hull algorithm in the computational geometry, and comparing the convex polygons.
Wherein, step S2 specifically includes the following steps:
generating convex polygons of the two input pictures by using a convex hull algorithm according to the extracted features;
in particular, in graphics, a convex hull is a very important concept. Briefly, given N points in a plane, a convex polygon is found, which consists of some points as vertices, that just encloses all N points. The convex hull algorithm is also called Graham Scan method. Point ordering time complexity o (nlogn), examining each point o (n), and integrating time complexity o (nlogn). As shown in fig. 3, a schematic diagram of a convex hull algorithm is shown, where the convex hull algorithm specifically includes the following steps:
finding the point with the smallest ordinate y among all the points of the input picture, namely the lowest point among all the points, and recording the point as p0；
Then calculating the cosine values of included angles between connecting lines of the rest points and the point and the x axis, sequencing the points from large to small according to the sine value of the points to the lowest point, and marking the sequenced points as p1，p2，p3，…pn；
The lowest point p0And the first point p of the sorted points1Push into stack, then from p2Starting calculation, calculating whether vectors of two points at the top of the stack and three points at the point rotate anticlockwise, if so, pressing the point into the stack, otherwise, pushing out elements at the top of the stack;
the last element in the stack is the point at the periphery of all convex hulls.
As shown in fig. 4, the schematic diagram of determining whether the rotation is counterclockwise rotation, and further, determining whether the rotation is counterclockwise rotation specifically includes the following steps:
setting the two points at the top of the stack and the p2The coordinates of the points are respectively A (a)x，ay)、B(bx，by)、C(cx，cy)；
According to the formula area ═ bx-ax)*(cy-ay)-(by-ay)*(cx-ax) Calculating the value of area when area>0, A-B-C counterclockwise rotation, area<0, A-B-C rotates clockwise, area is 0, and A-B-C is on a straight line.
And comparing the two groups of convex polygons sequentially through outer layer point comparison, inner layer point comparison and color comparison.
Specifically, the algorithm principle of the outer layer point comparison is as follows: when the shapes of the two groups of convex polygons are completely the same, indicating lamps on the periphery are completely the same; when the shapes of the two groups of convex polygons are different, indicating that an indicator lamp is turned off, and sending abnormal information and giving an alarm as shown in fig. 5;
the algorithm principle of the inner layer point comparison is as follows: respectively taking a triangle formed by any two external points and internal points in the two groups of convex polygons, calculating the side length proportion of two adjacent sides in the triangle and the included angle formed by the two sides, and comparing; if the side length ratio is equal to the included angle, the internal point exists, if the side length ratio is not equal to the included angle, the internal point does not exist, and as shown in fig. 6, abnormal information is sent and an alarm is given;
the algorithm principle of the color comparison is as follows: comparing the colors of the indicator lights in the two groups of convex polygons, and if the colors are the same, indicating that the indicator lights are not abnormal, and not giving an alarm; if the colors are different, the indication lamp is abnormal, abnormal information is sent, and an alarm is given.
In addition, fig. 7 is an input picture, i.e. an identification picture, according to an embodiment of the present invention; FIG. 8 is an original picture of the alignment algorithm; fig. 9 is a convex hull algorithm test picture (the point indicated by the arrow disappears).
The invention of the embodiment is as follows: the intelligent identification algorithm and the intelligent comparison algorithm use artificial intelligence and the intelligent identification algorithm to identify the small target indicator lamp. And comparing by using a comparison algorithm indicator light;
the innovation points of the embodiment are as follows: the comparison is performed using the convex hull algorithm of the graph structure. The algorithm is first used in China and is applied to the intelligent inspection robot. The comparison speed is high, and the comparison accuracy is high.
For the convenience of understanding the above technical solutions of the present invention, the following detailed descriptions are provided for the identification and comparison processes of the present invention in the practical process.
And starting identification, wherein after the robot is started, an identification comparison algorithm is started, and a port is monitored. This port is used to receive 3 parameters for identification and comparison (storage path of picture, whether it is the first shot, whether json file is downloaded).
And when the robot runs to the cabinet, the camera shoots and the pictures are stored under the corresponding path. And then the Android end sends the parameters to a monitoring port of the recognition algorithm. The method is divided into two parts:
and when the second parameter is True or not, and False or not, starting an identification algorithm and generating a reference library normal.json file, wherein the json file mainly comprises a cabinet name (used for comparing an indicator lamp for the next time), a picture ID (used for comparing the indicator lamp for the next time), an identified picture storage path (used for downloading an Android terminal), coordinates of the indicator lamp (used for displaying an ITACSS terminal) and a color of the indicator lamp (used for comparing the indicator lamp for the next time), and then uploading the identified picture storage path to the Android terminal to wait for the next identification comparison.
And when the second parameter is that whether the first shooting is False or not and whether the json file downloaded is True or not, starting an identification comparison algorithm and generating a resize.
Resize.json, and downloaded normal.json files. And comparing the cabinet name, the picture ID, the coordinates of the indicating lamp and the color of the indicating lamp. When a certain indicator lamp in the cabinet is turned off or the color is changed, a comparison algorithm is applied to generate comparison information, a comparison result is stored in resize.
In summary, according to the technical scheme of the invention, by using artificial intelligence, machine vision and topology technology, the indicator lights of various colors in the equipment in the machine room can be identified and distinguished, and the indicator lights can be compared by using a graphical algorithm, if the indicator lights are detected to give an alarm, such as being turned off and turned red, the alarm can be given immediately, and the loss can be effectively prevented for users.
In addition, the invention realizes the automatic IT operation and maintenance management process by establishing an intelligent identification project system; the condition of equipment assets in the machine room is clearly visible, and the monitoring performance of the operation and maintenance process of the machine room is realized; by improving basic data management, the inspection data rules of the cabinet and equipment therein are unified; the automatic transmission of IT operation and maintenance basic data to the ITACS is realized through integration, the accuracy and the timeliness of the data are ensured, and a management mode for carrying out centralized control on the operation and maintenance basic data is established; by improving an IT operation and maintenance management mode, the automatic systematic management from monitoring of a monitoring room to equipment in a machine room is realized; establishing an automatic planning task and automatically executing a machine room inspection planning mode; improve the manual work distribution of computer lab, reduce the manual work task of patrolling and examining.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (8)
1. The dynamic intelligent image recognition algorithm based on the IT equipment indicator light and the equipment model is characterized by comprising the following steps of:
the identification algorithm is a YoloV3 identification algorithm based on native darknet53, and is used for respectively extracting the characteristics of two input pictures by taking a convolutional neural network as a characteristic extraction network;
and a comparison algorithm, namely generating convex polygons of the two input pictures according to the extracted features by using a convex hull algorithm in the computational geometry, and comparing the convex polygons.
2. The dynamic intelligent image recognition algorithm for IT equipment indicator lights and equipment models according to claim 1, characterized in that the recognition algorithm uses leakage ReLU as an activation function, batch normalization as regularization, and is a multi-scale trained end-to-end recognition algorithm.
3. The dynamic intelligent image recognition algorithm for the IT equipment indicator lights and the equipment models as claimed in claim 1, wherein the comparison algorithm uses a convex hull algorithm in computational geometry to generate two convex polygons of the input pictures according to the extracted features, and the comparison specifically comprises the following steps:
generating convex polygons of the two input pictures by using a convex hull algorithm according to the extracted features;
and comparing the two groups of convex polygons sequentially through outer layer point comparison, inner layer point comparison and color comparison.
4. The dynamic intelligent image recognition algorithm for the IT equipment indicator lights and the equipment models as claimed in claim 3, wherein the convex hull algorithm specifically comprises the following steps:
finding the point with the smallest ordinate y among all the points of the input picture, namely the lowest point among all the points, and recording the point as p0；
Then calculating the cosine values of included angles between connecting lines of the rest points and the point and the x axis, sequencing the points from large to small according to the sine value of the points to the lowest point, and marking the sequenced points as p1，p2，p3，…pn；
The lowest point p0And the first point p of the sorted points1Push into stack, then from p2Starting to calculate whether vectors of two points at the top of the stack and three points at the point rotate anticlockwise or not, and if so, pressing the point into the stackIf not, pushing out the stack top element;
the last element in the stack is the point at the periphery of all convex hulls.
5. The algorithm for identifying dynamic intelligent images of IT equipment indicator lights and equipment models as claimed in claim 4, wherein said determining whether the rotation is counterclockwise specifically comprises the steps of:
setting the two points at the top of the stack and the p2The coordinates of the points are respectively A (a)x，ay)、B(bx，by)、C(cx，cy)；
According to the formula area ═ bx-ax)*(cy-ay)-(by-ay)*(cx-ax) Calculating the value of area when area>0, A-B-C counterclockwise rotation, area<0, A-B-C rotates clockwise, area is 0, and A-B-C is on a straight line.
6. The dynamic intelligent image recognition algorithm for the IT equipment indicator lights and the equipment models as claimed in claim 3, wherein the algorithm principle of the outer layer point comparison is as follows: when the shapes of the two groups of convex polygons are completely the same, indicating lamps on the periphery are completely the same; and when the shapes of the two groups of convex polygons are different, indicating that the indicator lamp is turned off, sending abnormal information and giving an alarm.
7. The dynamic intelligent image recognition algorithm for the IT equipment indicator lights and the equipment models as claimed in claim 3, wherein the algorithm principle of the inner layer point comparison is as follows: respectively taking a triangle formed by any two external points and internal points in the two groups of convex polygons, calculating the side length proportion of two adjacent sides in the triangle and the included angle formed by the two sides, and comparing; if the side length ratio is equal to the included angle, the internal point exists, if the side length ratio is not equal to the included angle, the internal point does not exist, abnormal information is sent, and an alarm is given.
8. The dynamic intelligent image recognition algorithm for the IT equipment indicator lights and the equipment models as claimed in claim 3, wherein the color comparison algorithm principle is as follows: comparing the colors of the indicator lights in the two groups of convex polygons, and if the colors are the same, indicating that the indicator lights are not abnormal, and not giving an alarm; if the colors are different, the indication lamp is abnormal, abnormal information is sent, and an alarm is given.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011204261.7A CN112287853A (en) | 2020-11-02 | 2020-11-02 | Dynamic intelligent image recognition algorithm based on IT equipment indicator light and equipment model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011204261.7A CN112287853A (en) | 2020-11-02 | 2020-11-02 | Dynamic intelligent image recognition algorithm based on IT equipment indicator light and equipment model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112287853A true CN112287853A (en) | 2021-01-29 |
Family
ID=74354198
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011204261.7A Pending CN112287853A (en) | 2020-11-02 | 2020-11-02 | Dynamic intelligent image recognition algorithm based on IT equipment indicator light and equipment model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112287853A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107357428A (en) * | 2017-07-07 | 2017-11-17 | 京东方科技集团股份有限公司 | Man-machine interaction method and device based on gesture identification, system |
| CN108566534A (en) * | 2018-04-23 | 2018-09-21 | Oppo广东移动通信有限公司 | Alarm method, device, terminal based on video monitoring and storage medium |
| CN109492651A (en) * | 2018-11-01 | 2019-03-19 | 国网山东省电力公司青岛供电公司 | A kind of intelligent identification Method of device signal lamp |
| CN110288661A (en) * | 2019-06-19 | 2019-09-27 | 深圳市睿智龙电子科技有限公司 | Location regulation method, device, computer equipment and the storage medium of operating lamp |
| CN111784587A (en) * | 2020-06-30 | 2020-10-16 | 杭州师范大学 | Invoice photo position correction method based on deep learning network |
-
2020
- 2020-11-02 CN CN202011204261.7A patent/CN112287853A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107357428A (en) * | 2017-07-07 | 2017-11-17 | 京东方科技集团股份有限公司 | Man-machine interaction method and device based on gesture identification, system |
| CN108566534A (en) * | 2018-04-23 | 2018-09-21 | Oppo广东移动通信有限公司 | Alarm method, device, terminal based on video monitoring and storage medium |
| CN109492651A (en) * | 2018-11-01 | 2019-03-19 | 国网山东省电力公司青岛供电公司 | A kind of intelligent identification Method of device signal lamp |
| CN110288661A (en) * | 2019-06-19 | 2019-09-27 | 深圳市睿智龙电子科技有限公司 | Location regulation method, device, computer equipment and the storage medium of operating lamp |
| CN111784587A (en) * | 2020-06-30 | 2020-10-16 | 杭州师范大学 | Invoice photo position correction method based on deep learning network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11380232B2 (en) | Display screen quality detection method, apparatus, electronic device and storage medium | |
| KR102229594B1 (en) | Display screen quality detection method, device, electronic device and storage medium | |
| US11615524B2 (en) | Product defect detection method and apparatus, electronic device and storage medium | |
| CN111259892B (en) | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp | |
| WO2020007118A1 (en) | Display screen peripheral circuit detection method and device, electronic equipment and storage medium | |
| WO2017088553A1 (en) | Method and system for rapidly identifying and marking electronic component polarity direction | |
| CN111401419A (en) | Improved RetinaNet-based employee dressing specification detection method | |
| CN110738164B (en) | Part abnormity detection method, model training method and device | |
| CN105740774A (en) | Text region positioning method and apparatus for image | |
| CN115131283A (en) | Defect detection and model training method, device, equipment and medium for target object | |
| CN109711375B (en) | Signal lamp identification method and device | |
| CN110866915A (en) | Circular inkstone quality detection method based on metric learning | |
| CN109086781A (en) | A kind of cabinet lamp state identification method based on deep learning | |
| CN112287853A (en) | Dynamic intelligent image recognition algorithm based on IT equipment indicator light and equipment model | |
| CN112711603A (en) | Workpiece detection method and system based on cloud and computer-readable storage medium | |
| CN117037059A (en) | Equipment management method and device based on inspection monitoring and electronic equipment | |
| CN109470708A (en) | Quality determining method, device, server and the storage medium of plastic foam cutlery box | |
| CN115358981A (en) | Glue defect determining method, device, equipment and storage medium | |
| JP7167990B2 (en) | Method, device, system and program for controlling robot, and storage medium | |
| TW202138785A (en) | Classification method and a classification system | |
| Zhang et al. | Color-strip Recognition Based Information Management System: Implementation on OBD Management | |
| CN116883880B (en) | Crane identification method and device based on AR technology and electronic equipment | |
| Enkhbaatar et al. | Automatic Visual Monitoring System for Data Center Device Management | |
| CN116433958A (en) | Cone racetrack boundary classification method system, device and storage medium | |
| CN116229051A (en) | Detection method of panel status lamp |
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 |