CN113345036B - HSV (hue, saturation, value) feature transformation based indicator lamp state identification method - Google Patents
HSV (hue, saturation, value) feature transformation based indicator lamp state identification method Download PDFInfo
- Publication number
- CN113345036B CN113345036B CN202110567003.3A CN202110567003A CN113345036B CN 113345036 B CN113345036 B CN 113345036B CN 202110567003 A CN202110567003 A CN 202110567003A CN 113345036 B CN113345036 B CN 113345036B
- Authority
- CN
- China
- Prior art keywords
- indicator light
- indicator
- hsv
- image
- status
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 230000009466 transformation Effects 0.000 title claims abstract description 19
- 238000005286 illumination Methods 0.000 claims description 15
- 238000012937 correction Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 5
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000007689 inspection Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001131 transforming effect Effects 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
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
-
- G06T5/80—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—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
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—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
- G06T2207/20112—Image segmentation details
- G06T2207/20132—Image cropping
Abstract
The invention discloses an indicator light state identification method based on HSV (hue, saturation, value) feature transformation, which comprises the following steps of: acquiring an image of an indicator light area to be identified, and correcting and dividing the image to obtain a single indicator light area; positioning the indicator lamps in the single indicator lamp area by using an S component clustering method of an HSV space; and identifying the state of the indicator lamp based on the HSV threshold value and the proportion and the distribution condition of each color component. The invention has better positioning effect and strong robustness. Has good stability. A new way is provided for the realization of the state recognition engineering of the protection indicator lamp of the electrical control cabinet in the relay protection room of the transformer substation.
Description
Technical Field
The invention relates to the technical field of monitoring of working states of equipment in a transformer substation, in particular to an indicator lamp state identification method based on HSV (hue, saturation and value) feature transformation.
Background
The indicating lamp is used as an important indicating device in the operation of the power system, the opening and closing positions of the circuit breaker of the transformer substation are mainly displayed, the green indicating lamp is lightened to indicate that the circuit breaker is at the opening position, the red indicating lamp is lightened to indicate that the circuit breaker is at the closing position, and the routing inspection becomes an important work of power operation and maintenance. Because the number of indicating lamps is large in the inspection process, the working characteristics are complex, and more attention is paid to replacing manual inspection with machine vision. When machine vision replaces artifical the patrolling and examining, the operating condition discernment rate of accuracy of pilot lamp is especially crucial, in case discernment is wrong, can the operating condition of erroneous judgement transformer substation's circuit breaker, probably arouses serious consequence.
The identification of the working state of the indicating lamp of the circuit breaker is the identification of the color of the indicating lamp. In the prior art, one way is to select the RGB space to extract the indicator lights, and to use the shape to extract the indicator lights and set the red, yellow and green color thresholds in the RGB space for recognition. Or mapping the input indicating lamp image from an original RGB color space to an 11-dimensional color attribute space, effectively extracting color features, finding out the position of the signal indicating lamp through the color and shape features of the indicating lamp, and finally, identifying the state of the indicating lamp through comparing pixels at the center position of the indicating lamp with edge pixels. The method can extract a multi-color target, but due to the correlation of R, G, B three elements in an RGB space, the value difference of RGB values under different illumination environments is large, so that the segmentation result is poor, and the identification accuracy is reduced.
Disclosure of Invention
The invention aims to provide an indicator light state identification method based on HSV (hue, saturation, value) feature transformation, which can solve the problems of poor segmentation result and low identification accuracy when an RGB (red, green and blue) space is selected to extract and identify an indicator light in the prior art.
The purpose of the invention is realized by the following technical scheme:
the method for identifying the state of the indicator lamp based on HSV feature transformation comprises the following steps:
acquiring an image of an indicator light area to be identified, and correcting and dividing the image to obtain a single indicator light area;
positioning the indicator lamps in the single indicator lamp area by using an S component clustering method of an HSV space;
and identifying the state of the indicator light based on the combination of the HSV threshold value and the proportion and the distribution condition of each color component.
Further, the correcting and dividing the image into regions includes:
adopting a Gaussian high-pass filter to carry out illumination enhancement processing on the image;
distortion correction is carried out on the image by adopting a perspective transformation technology to obtain a corrected image;
and dividing the corrected image by taking a single indicator light as a unit.
Further, the segmenting the corrected image by using a single indicator light as a unit includes:
carrying out S-component clustering segmentation on the complete indicator light region image to extract the indicator light and converting the indicator light into a binary image;
performing horizontal projection and vertical projection on the binary image, and respectively counting the number of projection peak values;
describing projection coordinate values of the pixels by accumulating sums of horizontal and vertical pixels respectively;
and acquiring the number of peak points of the projection coordinate values, and dividing the complete indicator light area into a plurality of single indicator light areas by taking the peak points as a division reference.
Further, when the single indicator light area comprises the switch, and the switch and the indicator light are respectively positioned on the upper half part and the lower half part of the single indicator light area, the single indicator light area is divided into two parts from the middle, the part where the indicator light is positioned is reserved, and the part where the switch is positioned is removed.
Further, after the part where the switch is located is removed, the method further comprises the step of removing the signboard: and judging the roundness of the connected domain in the single indicator lamp area, when the roundness of the connected domain is greater than 0.8, reserving the connected domain, otherwise, deleting the connected domain.
Further, the identifying the status of the indicator light based on the HSV threshold value in combination with the proportion and the distribution of the color components includes:
indicator light color tracking for each individual indicator light zone separately;
and respectively identifying the indicator light state of each single indicator light area.
Further, the indicator light color tracking for each individual indicator light region respectively comprises: and performing HSV color transformation on the indicator lamps in three states of normal lighting, normally extinguishing and abnormal lighting, dividing the HSV space into color intervals with the step length of 1, and calculating H, S, V the number of pixels of each component falling in the interval.
Further, the state of the indicator light is identified according to the number of pixels of the H, S, V in which each component falls in the interval.
Further, the calculation formula for identifying the state of the indicator light is as follows:
wherein S is o Representing the number of orange pixels, S y Denotes the number of yellow pixels, S r Indicating the number of red pixels, open indicating the status of the indicator light is on, and close indicating the status of the indicator light is off.
Further, the state of the indicator light is on and comprises a normal lighting state and an abnormal lighting state, and when S is detected y When > 0, it indicates an abnormally bright state, S y When 0, it indicates a normally bright state.
According to the HSV feature transformation-based indicator light state identification method, homomorphic filtering is used for enhancing and distortion correcting an acquired image, an RGB threshold segmentation method is used for carrying out primary positioning on an indicator light, line projection is carried out on a primary positioning result, the peak value of a projection curve is extracted, the array identification of multiple lines of indicator lights is converted into unit state identification, and finally, the intelligent judgment of the state of the indicator light is carried out by combining the proportion and the distribution condition of each color component. The secondary positioning of the indicator lamp is completed through S component clustering of the HSV space, so that the positioning effect is good, and the robustness is strong. Has good stability. A new way is provided for the realization of the state recognition engineering of the protection indicator lamp of the electrical control cabinet in the relay protection room of the transformer substation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a diagram of steps of an HSV feature transformation based indicator light status identification method of the present invention;
FIG. 2 is an image of an indicator light region to be identified before distortion correction;
FIG. 3 is an image of an indicator light region to be identified after distortion correction;
FIG. 4 is a schematic diagram of converting an indicator light region image into a binary image;
FIG. 5 is a schematic diagram of a horizontal projection of a binary image;
FIG. 6 is a schematic diagram of a vertical projection of a binary image;
FIG. 7 is a schematic view of a single indicator light area after segmentation;
fig. 8 is a diagram illustrating the number of pixels in the interval where H, S, V components fall under three conditions.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure of the present disclosure. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The invention discloses an indicating lamp state identification method based on HSV (hue, saturation and value) feature transformation, which comprises the following steps of:
and step S1, acquiring the image of the indicator light area to be identified, and correcting and dividing the image into areas to obtain a single indicator light area.
Because the pilot lamp receives the installation environment in the collection process, the influence of factors such as illumination leads to the picture of acquireing to produce the phenomenon of certain degree illumination inhomogeneous and shape distortion, and the pilot lamp of transformer substation arranges comparatively densely in addition, leads to the shadow to produce easily, and all above all kinds of circumstances can lead to the pilot lamp to meet the obstacle in location and identification process, finally influence the accuracy of discernment. Therefore, in order to improve the accuracy of the post-image recognition, it is necessary to perform enhancement and correction processing on the image with uneven illumination. For this purpose, the application selects a Gaussian high-pass filter to perform illumination enhancement processing on the image.
Further, in a preferred embodiment of the present application, the correcting and dividing the image into regions includes:
and step S101, carrying out illumination enhancement processing on the image by adopting a Gaussian high-pass filter.
The application is not limited to the specific process of the illumination enhancement treatment. After the image is subjected to illumination enhancement processing, the illumination uniformity of the image is enhanced, the shadow is basically removed, and the color characteristic is more obvious.
And S102, carrying out distortion correction on the image by adopting a perspective transformation technology to obtain a corrected image.
Besides the illumination influence, the image is distorted to a certain extent, so that the positioning difficulty of the indicator lamp is increased, and the identification accuracy is influenced. Therefore, distortion correction of the image after the illumination enhancement processing is required. And taking four corner points of the image as correction reference points, and transforming the distorted image by a perspective transformation technology to obtain a corrected image. After the distortion correction of the image, the unnecessary part of the corrected image is cut off to obtain a complete indicator light area, as shown in fig. 3. Fig. 2 is an image before distortion correction.
And step S103, dividing the corrected image by taking a single indicator lamp as a unit.
The complete indicator light regions are observed and analyzed, and the indicator lights are arranged densely, so that great difficulty is brought to overall identification of the indicator lights, the difficulty of the algorithm is increased to a great extent, and the identification rate of the algorithm is greatly reduced. However, the arrangement of the indicator lamps of the equipment in the relay protection room of the transformer substation has a certain rule, and the indicator lamp area can be divided into the individual indicator lamps according to the arrangement rule.
Further, the segmenting the corrected image in units of a single indicator light includes:
step S1031, roughly extracting the indicator lights by performing an S-component clustering segmentation method on the complete indicator light region image and converting the indicator lights into a binary image, as shown in fig. 4.
Step S1032, horizontal and vertical projection is carried out on the binary image, the number of projection peak values is counted respectively, namely the number of the projection peak values is the number of rows and columns of the indicator light, and the complete indicator light area is divided according to the number of the projection peak values. The projection curves are shown in fig. 5 (row projection) and fig. 6 (column projection), respectively.
Step S1033, for the image with size M × N, the projection coordinate values are described by the cumulative sum of horizontal and vertical pixels, respectively, and expressed as a projection formula:
wherein P is H Representing a transverse projection function; p V Representing a longitudinal projection function; f (x, y) represents the gray scale value of each point in the image.
And S1034, acquiring the number of peak points of the projection coordinate values, and dividing the complete indicator light region into a plurality of single indicator light regions by taking the peak points as a division reference.
The single indicator light zone is shown in fig. 7, which includes indicator lights and switches, which are located in the upper and lower halves of the single indicator light zone, respectively. The single indicator light area is divided into two parts from the middle, and the upper part is the indicator light part.
And step S2, positioning the indicator lamps in the single indicator lamp area by using an S component clustering method of the HSV space.
After the individual indicator light regions are divided, the specific position of each indicator light is located. In general, the indicator lamp has 3 operating states: normally on, off, and abnormally on. The S clustering method can well describe the positions of all the indicator lamps, and has better effect and stronger applicability. Therefore, the S clustering method is selected to position the indicator lamps in the single indicator lamp area, and the positioning result does not generate too large difference due to the on-off state of the lamps. However, after S component clustering is used, the influence of the signboard exists in part of the indicator lamps, therefore, the signboard is removed by using a roundness method, the roundness of the connected domain in a single indicator lamp area is judged because the shape of the indicator lamp is circular and the signboard is square, when the roundness of the connected domain is greater than 0.8, the connected domain is reserved, otherwise, the connected domain is deleted. Besides the signboard, a small part of interference of a small area region exists, so that the area screening is further carried out, and the small area irrelevant region is deleted by an area method.
And step S3, identifying the state of the indicator light based on the combination of the HSV threshold value and the proportion and the distribution condition of each color component.
Further, in a preferred embodiment of the present application, identifying the status of the indicator light based on the HSV threshold in combination with the ratio and distribution of the color components includes:
and S301, respectively tracking the color of the indicator light of each single indicator light area.
After the indicator lamp is positioned in step S2, the position of the indicator lamp is partially cut, HSV color transformation is performed on the indicator lamp in three states of normally on, normally off, and abnormally on, an HSV space is divided into color intervals with a step length of 1, and the number of pixels in each component falling into the interval is calculated H, S, V, and the result is shown in fig. 8.
In fig. 8, the abscissa is H, S, V and the ordinate is the number of pixels in the image satisfying the value of the abscissa H, S, V after normalization, and it can be seen from fig. 8 that the indicator light images H, S, V in different states have different attribute values, and the threshold values of the indicator light images H, S, V in the three states are shown in table 1.
TABLE 1H, S, V threshold values for the indicator light for three states
And step S302, respectively identifying the indicator lamp state of each single indicator lamp area.
According to the comparison analysis of H, S, V threshold values of the indicator light in the three states in the table 1 and the HSV color distribution range in the table 2, when the indicator light is in an off state, the color is red; when the indicator light is in a normal bright state, the color shows red and orange superposition; when the indicator light is in an abnormal lighting state, the colors are represented by the superposition of four colors of red, orange, yellow and green. Therefore, the states of the indicator lamps can be identified by setting the threshold values of the three states of the indicator lamps according to table 1, as shown in formula (3).
In the formula, S o Representing the number of orange pixels, S y Denotes the number of yellow pixels, S r The number of red pixels is shown, when the sum of the numbers of orange and yellow pixels is more than 0.35, the state of the indicator light is shown to be on, otherwise, the indicator light is in the off state.
When the indicator light is on, and S y When > 0, it indicates an abnormally bright state, S y When 0, it indicates a normally bright state.
TABLE 2 HSV model color Range distribution
In order to verify the beneficial effects of the present application, specific experimental data are described below.
Taking an indicator lamp of a secondary control cabinet in a relay protection room of a certain transformer substation as an example, under different illumination and shooting conditions, 200 small indicator lamp images (including the same indicator lamp panel and different indicator lamp panels acquired under different illumination conditions) are selected, and the comparison result is shown in table 3 by using the method of the invention and a popular SVM classification algorithm in the prior art and using a V component method under the same data set.
TABLE 3 comparison of the results of the different tests
As can be seen from Table 3, the identification rate of the indicator lamp by the method reaches 98.5%, compared with an SVM algorithm and a V component judgment method, the identification rate of the method is better, the mistaken identification indicator lamp of each method is selected for analysis, and the V component judgment method has the main problem that the V component and the brightness in an HSV space have a certain relation but do not have an absolute relation, so that the identification has errors. For the algorithm, the main reason for identifying the wrong indicator lamp is that the indicator lamp which is originally in the closed state is judged to be in the bright state mainly due to the fact that the brightness of the adjacent indicator lamp is too bright, but the total identification result error is not large. Therefore, the algorithm has high recognition effect.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and the like.
The above description is for illustrative purposes only and is not intended to limit the present invention, and any modifications, equivalents, improvements, etc. within the spirit and scope of the present invention should be included within the scope of the present invention as defined by the appended claims.
Claims (8)
1. An indicator lamp state identification method based on HSV feature transformation is characterized by comprising the following steps:
acquiring an image of an indicator light area to be identified, and correcting and dividing the image to obtain a single indicator light area;
positioning the indicator lamps in the single indicator lamp area by using an S component clustering method of an HSV space;
identifying the state of the indicator light based on the combination of the HSV threshold value and the proportion and the distribution condition of each color component;
the correcting and dividing the image comprises:
adopting a Gaussian high-pass filter to carry out illumination enhancement processing on the image;
distortion correction is carried out on the image by adopting a perspective transformation technology to obtain a corrected image;
dividing the corrected image by taking a single indicator lamp as a unit;
the dividing of the corrected image by taking a single indicator lamp as a unit comprises the following steps:
carrying out S-component clustering segmentation on the complete indicator light region image to extract the indicator light and converting the indicator light into a binary image;
performing horizontal projection and vertical projection on the binary image, and respectively counting the number of projection peak values;
describing projection coordinate values of the pixels by accumulating sums of horizontal and vertical pixels respectively;
and acquiring the number of peak points of the projection coordinate values, and dividing the complete indicator light region into a plurality of single indicator light regions by taking the peak points as a division reference.
2. An HSV feature-transformation-based status recognition method according to claim 1, wherein when the single indicator light zone includes a switch, and the switch and the indicator light are respectively located in the upper half and the lower half of the single indicator light zone, the single indicator light zone is divided into two parts from the middle, the part where the indicator light is located is reserved, and the part where the switch is located is removed.
3. The method of claim 2, further comprising the step of removing the sign after removing the portion of the switch: and judging the roundness of the connected domain in the single indicator lamp area, when the roundness of the connected domain is greater than 0.8, retaining the connected domain, otherwise, deleting the connected domain.
4. The method of claim 1, wherein the identifying the status of the indicator based on the HSV threshold in combination with the ratio and distribution of the color components comprises:
indicator light color tracking for each individual indicator light zone separately;
and respectively identifying the indicator light state of each single indicator light area.
5. An HSV feature transform-based indicator light status identification method according to claim 4, wherein said indicator light color tracking for each individual indicator light zone separately comprises: and performing HSV color transformation on the indicator lamps in three states of normal lighting, normally extinguishing and abnormal lighting, dividing the HSV space into color intervals with the step length of 1, and calculating H, S, V the number of pixels of each component falling in the interval.
6. An HSV feature transformation-based indicator light state identification method according to claim 5, wherein the indicator light state is identified according to the number of pixels of which the components of H, S, V fall within an interval.
7. An HSV feature transformation based indicator light status identification method according to claim 6, wherein said identification indicator light status is calculated by the formula:
wherein S is o Representing the number of orange pixels, S y Denotes the number of yellow pixels, S r Indicating the number of red pixels, open indicating the status of the indicator light is on, and close indicating the status of the indicator light is off.
8. The method of claim 7, wherein the status of the indicator comprises a normally on status and an abnormally on status, and when S is asserted, the status of the indicator is changed y When > 0, it indicates an abnormally bright state, S y When 0, it indicates a normally bright state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567003.3A CN113345036B (en) | 2021-05-24 | 2021-05-24 | HSV (hue, saturation, value) feature transformation based indicator lamp state identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110567003.3A CN113345036B (en) | 2021-05-24 | 2021-05-24 | HSV (hue, saturation, value) feature transformation based indicator lamp state identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113345036A CN113345036A (en) | 2021-09-03 |
| CN113345036B true CN113345036B (en) | 2022-09-27 |
Family
ID=77471133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110567003.3A Active CN113345036B (en) | 2021-05-24 | 2021-05-24 | HSV (hue, saturation, value) feature transformation based indicator lamp state identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113345036B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114217118B (en) * | 2021-12-09 | 2023-05-16 | 福建省海峡智汇科技有限公司 | Method and system for recognizing state of high-voltage live display of indoor substation |
| CN116863333A (en) * | 2023-06-28 | 2023-10-10 | 深圳市名通科技股份有限公司 | AI intelligent detection method for FSU equipment working state |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101908271A (en) * | 2010-06-28 | 2010-12-08 | 青岛海信网络科技股份有限公司 | Signal lamp color identification method and device |
| CN102496282A (en) * | 2011-12-16 | 2012-06-13 | 湖南工业大学 | Traffic intersection signal light state identification method based on RGB color transformation |
| CN103325124A (en) * | 2012-03-21 | 2013-09-25 | 东北大学 | Target detecting and tracking system and method using background differencing method based on FPGA |
| CN108357418A (en) * | 2018-01-26 | 2018-08-03 | 河北科技大学 | A kind of front truck driving intention analysis method based on taillight identification |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729899B (en) * | 2016-08-11 | 2019-12-20 | 杭州海康威视数字技术股份有限公司 | License plate number recognition method and device |
| US10650257B2 (en) * | 2017-02-09 | 2020-05-12 | SMR Patents S.à.r.l. | Method and device for identifying the signaling state of at least one signaling device |
| CN107341806A (en) * | 2017-06-02 | 2017-11-10 | 青岛克路德机器人有限公司 | Based on the detection of the indoor indicator lamp of color and shape facility and condition discrimination method |
| CN107578035B (en) * | 2017-09-30 | 2020-06-16 | 深圳市颐通科技有限公司 | Human body contour extraction method based on super-pixel-multi-color space |
| CN108009555A (en) * | 2017-12-15 | 2018-05-08 | 上海索广电子有限公司 | A kind of LED light Color Recognition System |
| CN109117764A (en) * | 2018-07-29 | 2019-01-01 | 国网上海市电力公司 | Using the method for color threshold method identification target object region electrical symbol in power monitoring |
| CN111259892B (en) * | 2020-01-19 | 2023-07-04 | 福建升腾资讯有限公司 | Inspection method, inspection device, inspection equipment and inspection medium for state of indicator lamp |
| CN111666824B (en) * | 2020-05-14 | 2023-12-15 | 浙江工业大学 | Indicator light identification method of mobile robot based on color attribute and machine learning |
| CN112001299B (en) * | 2020-08-21 | 2024-02-02 | 浙江省机电设计研究院有限公司 | Tunnel vehicle finger device and lighting lamp fault identification method |
| CN112364780A (en) * | 2020-11-11 | 2021-02-12 | 许继集团有限公司 | Method for identifying state of indicator lamp |
-
2021
- 2021-05-24 CN CN202110567003.3A patent/CN113345036B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101908271A (en) * | 2010-06-28 | 2010-12-08 | 青岛海信网络科技股份有限公司 | Signal lamp color identification method and device |
| CN102496282A (en) * | 2011-12-16 | 2012-06-13 | 湖南工业大学 | Traffic intersection signal light state identification method based on RGB color transformation |
| CN103325124A (en) * | 2012-03-21 | 2013-09-25 | 东北大学 | Target detecting and tracking system and method using background differencing method based on FPGA |
| CN108357418A (en) * | 2018-01-26 | 2018-08-03 | 河北科技大学 | A kind of front truck driving intention analysis method based on taillight identification |
Non-Patent Citations (5)
| Title |
|---|
| 一种面向设备系统指示灯的状态识别方法;张永合等;《计算机仿真》;20090315(第03期);第227-230页 * |
| 基于图像处理的交通灯检测技术;吴国庆等;《现代电子技术》;20170415(第08期);第103-106页 * |
| 基于颜色属性的信号指示灯检测识别;胡灿林等;《现代计算机(专业版)》;20180305(第07期);第77-91页 * |
| 基于颜色提取方法的仪表彩色指针识别;冀辰宇等;《东北电力大学学报》;20120615(第03期);第79-82页 * |
| 皮肤黑素细胞肿瘤图像综合分割方法研究;田庆飞等;《中国体视学与图像分析》;20070925(第03期);第207-211页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113345036A (en) | 2021-09-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113345036B (en) | HSV (hue, saturation, value) feature transformation based indicator lamp state identification method | |
| CN107103330A (en) | A kind of LED status recognition methods and device | |
| CN109636784A (en) | Saliency object detection method based on maximum neighborhood and super-pixel segmentation | |
| CN106780440A (en) | Destruction circuit plate relic image automatic comparison recognition methods | |
| CN105913441A (en) | Shadow removal method for improving target detection performance in video | |
| CN108319966A (en) | The method for identifying and classifying of equipment in a kind of substation's complex background infrared image | |
| CN109087363B (en) | HSV color space-based sewage discharge detection method | |
| CN105894015B (en) | A kind of banister state analysis method and system | |
| CN110619623B (en) | Automatic identification method for heating of joint of power transformation equipment | |
| CN105868683A (en) | Channel logo identification method and apparatus | |
| CN103996045A (en) | Multi-feature fused smoke identification method based on videos | |
| CN111311670B (en) | Cooling bed punching recognition method, system and equipment based on image recognition | |
| CN113298077A (en) | Transformer substation foreign matter identification and positioning method and device based on deep learning | |
| CN113449639A (en) | Non-contact data acquisition method for instrument by gateway of Internet of things | |
| CN113225461A (en) | System and method for detecting video monitoring scene switching | |
| CN111695373B (en) | Zebra stripes positioning method, system, medium and equipment | |
| CN114332781A (en) | Intelligent license plate recognition method and system based on deep learning | |
| CN113033548A (en) | Image recognition method for unit running state judgment and monitoring point alignment | |
| CN113344047A (en) | Platen state identification method based on improved K-means algorithm | |
| CN115841731A (en) | Infrared-monitoring park fire early warning method | |
| CN109598713A (en) | A kind of method for detecting abnormality based on image recognition | |
| CN113657175A (en) | Intelligent identification method, system, storage medium and equipment for switch state of power distribution cabinet | |
| Kim | License plate location method unaffected by variation in size and aspect ratio | |
| CN112036392B (en) | Automatic identification method for states of UPS (uninterrupted Power supply) indicator lamps of production station of shale gas field | |
| CN109389079A (en) | A kind of traffic lights recognition methods |
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 |