CN114820468A - Accumulated water detection method based on color-changing paper and image recognition - Google Patents
Accumulated water detection method based on color-changing paper and image recognition Download PDFInfo
- Publication number
- CN114820468A CN114820468A CN202210359923.0A CN202210359923A CN114820468A CN 114820468 A CN114820468 A CN 114820468A CN 202210359923 A CN202210359923 A CN 202210359923A CN 114820468 A CN114820468 A CN 114820468A
- Authority
- CN
- China
- Prior art keywords
- color
- paper
- target image
- water
- hsv
- 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
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 46
- 238000001514 detection method Methods 0.000 title claims description 16
- 238000000034 method Methods 0.000 claims abstract description 11
- 238000009825 accumulation Methods 0.000 description 7
- 239000007788 liquid Substances 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 239000002352 surface water Substances 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 241000519995 Stachys sylvatica Species 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000007704 transition 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- 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
Abstract
The invention discloses a method for detecting accumulated water based on color-changing paper and image recognition, which comprises the following steps: step 1, collecting a target image of water-encountering color-changing paper pasted on the ground of a pre-accumulated water area; step 2, converting the target image from an RGB color space to an HSV color space; step 3, acquiring an HSV component value range of the designated color based on a preset HSV component value range comparison table; the specified color is a color which is obtained by changing the color-changeable paper when the paper meets water; step 4, identifying the target image based on the value range of the HSV component of the designated color, judging whether the designated color is identified, if so, entering step 5, and if not, entering step 1; and 5, performing alarm operation. The invention solves the problems that the accumulated water is difficult to accurately identify under the conditions that the ground is reflective, the ground color is close to the color of water, the spot on the ground cannot distinguish whether the accumulated water exists or not and the like.
Description
Technical Field
The invention belongs to the technical field of image recognition, and particularly relates to a water accumulation detection method based on color-changeable paper and image recognition.
Background
Currently, for water accumulation identification, it is a common practice to directly perform surface water accumulation identification by using a liquid level sensor and image identification. The liquid level sensor monitors the surface accumulated water by acquiring liquid level data; the image identification method adopts the direct identification of the image of the surface water accumulation to monitor the surface water accumulation. The existing image recognition method mainly utilizes machine vision to extract the characteristics of surface ponding so as to achieve the aim of ponding recognition.
The accumulated water monitoring is carried out through the liquid level sensor, the monitoring purpose can be achieved only when a certain amount of accumulated water exists on the ground, the monitoring device is used in a special scene sensitive to the accumulated water on the ground, and the monitoring effect cannot meet the requirement on monitoring precision. When the machine vision method is used for accumulated water identification, under partial scenes, such as the conditions that the ground has serious reflection, the ground color is close to the color of water, stains on the ground cannot distinguish whether accumulated water exists or not, and the like, accurate detection is difficult to achieve by only depending on image identification.
Disclosure of Invention
The invention aims to solve the technical problem that the accumulated water detection method based on the color-changeable paper and the image recognition is provided aiming at the defects in the prior art, and the problem that the accumulated water is difficult to accurately recognize under the conditions that the ground is reflective, the ground color is close to the color of water, stains exist on the ground, whether the accumulated water exists or not can not be distinguished is solved.
In order to solve the technical problems, the invention adopts the technical scheme that: a method for detecting accumulated water based on color-changeable paper and image recognition comprises the following steps:
step 1, collecting a target image of water-encountering color-changing paper pasted on the ground of a pre-accumulated water area;
step 2, converting the target image from an RGB color space to an HSV color space;
step 3, acquiring an HSV component value range of the designated color based on a preset HSV component value range comparison table; the specified color is a color which is obtained by changing the color-changeable paper when the paper meets water;
step 4, identifying the target image based on the value range of the HSV (hue, saturation and value) component of the designated color, judging whether the designated color is identified, if so, entering step 5, and if not, entering step 1;
and 5, performing alarm operation.
The accumulated water detection method based on the color-changeable paper and the image recognition comprises the following step 3:
and 3-1, setting an H, S, V component threshold of the water-encountering color-changing paper, and removing the interference background item on the periphery of the water-encountering color-changing paper by identifying HSV space color values of all pixel points in the target image.
The accumulated water detection method based on the color-changeable paper and the image recognition comprises the following step 3:
and 3-2, after the step 3-1 is executed, carrying out binarization processing on the target image.
The accumulated water detection method based on the color-changeable paper and the image recognition comprises the following step 3:
and 3-3, after the step 3-2 is executed, performing opening operation processing on the target image to highlight the area to be detected.
According to the accumulated water detection method based on the color-changeable paper and the image recognition, when the target image is recognized in the step 4, the corresponding region to be detected of the target image before binarization processing is recognized according to the region to be detected after processing in the step 3-3, HSV space color values of the region to be detected are obtained, and whether the specified color is recognized or not is judged based on the HSV space color values and the value range of the HSV component of the specified color.
In the seeper detection method based on the color-changeable paper and the image recognition, when the target image is recognized in the step 4, the area S of the region where the specified color is located is calculated.
Compared with the prior art, the invention has the following advantages: according to the invention, the water-encountering color-changing paper is pasted on the ground of the pre-water-accumulating area, so that the water accumulation condition can be reflected through the water-encountering color-changing paper, and the difficulty of subsequent image recognition is reduced; in addition, the target image is converted from the RGB color space to the HSV color space, so that the interference of light and the like is reduced, and the subsequent color identification is more accurate.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
FIG. 2 is a chart of HSV component value range.
Detailed Description
As shown in fig. 1, a method for detecting standing water based on color-changeable paper and image recognition includes the following steps:
step 1, collecting a target image of water-encountering color-changing paper pasted on the ground of a pre-accumulated water area;
in practice, for example, in order to monitor water accumulated on the ground in a comprehensive pump room of a power plant, color-changeable paper which changes color when meeting water (for example, the color is close to white when dry and changes to red when meeting water) is fixed on the ground at the bottom of a valve position where water leakage easily occurs, and a high-definition camera is erected in a matched manner to acquire a real-time video of the position of the color-changeable paper in a target area;
step 2, converting the target image from an RGB color space to an HSV color space;
step 3, acquiring the value range of the HSV component of the designated color based on a preset HSV component value range comparison table (shown in figure 2); the specified color is a color obtained by changing the color-changeable paper when the water meets the water;
if the designated color is red, the value range of the HSV component is H between 0 and 10 and 156-180, S between 43 and 255 and V between 46 and 255;
step 4, identifying the target image based on the value range of the HSV component of the designated color, judging whether the designated color is identified, if so, entering step 5, and if not, entering step 1;
supposing that the HSV space color values of all pixel points of the water-encountering color-variable paper are identified to be H (53), S (15) and V (233), referring the values of the three parameters to an HSV component value range comparison table, and giving the color of white; if no water is accumulated, the step 1 is carried out, and the target image of the next frame is collected continuously; otherwise, entering step 5;
and 5, performing alarm operation.
In this embodiment, step 3 further includes:
step 3-1, setting an H, S, V component threshold of the water-encountering color-changing paper, and removing interference background items on the periphery of the water-encountering color-changing paper by identifying HSV space color values of all pixel points in the target image;
it should be noted that, in practice, because the target image is obtained by shooting, there is an area of the water-non-contact color-changeable paper in the target image inevitably, so that the H, S, V component threshold of the water-contact color-changeable paper is set to remove the interfering background item on the periphery of the water-contact color-changeable paper;
step 3-2, after the step 3-1 is executed, carrying out binarization processing on the target image;
it should be noted that the Image Binarization (Image Binarization) is a process of setting the gray level of a pixel point on an Image to 0 or 255, that is, making the whole target Image exhibit an obvious black-and-white effect. The binarization of the target image greatly reduces the data volume in the image, so that the outline of the target can be highlighted, and the target at the position refers to a color block newly generated on the target image after meeting water, namely a to-be-detected area needing to be processed next.
And 3-3, after the step 3-2 is executed, performing opening operation processing on the target image to highlight the area to be detected.
Performing opening operation, corroding and then expanding to eliminate white spots outside the area, so that the color of the water-contact color-changeable paper is changed when contacting water and then is subjected to transition treatment with the color of the surrounding environment, and the influence of the color value in the non-detection area on the area to be detected is avoided;
in this embodiment, when the target image is identified in step 4, according to the to-be-detected region processed in step 3-3, the to-be-detected region corresponding to the target image before binarization processing is identified, so as to obtain HSV spatial color values of the to-be-detected region, and based on the HSV spatial color values and the HSV component value range of the designated color, whether the designated color is identified is determined.
For example, if the color of the water-variable color paper changes, a group of color component values H-5, S-243 and V-210 is obtained, and according to the HSV component value range comparison table, the identified color is red, and water accumulation is proved at the moment.
In this embodiment, when the target image is identified in step 4, the method further includes calculating an area S of the area where the identified designated color is located. Specifically, the area S is calculated according to the number of pixel points in the area where the designated color is located, and the larger the area is, the more serious the accumulated water is, so that the accumulated water condition can be judged by a worker.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and all simple modifications, changes and equivalent structural changes made to the above embodiment according to the technical spirit of the present invention still fall within the protection scope of the technical solution of the present invention.
Claims (6)
1. A ponding detection method based on color-changing paper and image recognition is characterized in that: the method comprises the following steps:
step 1, collecting a target image of water-encountering color-changing paper pasted on the ground of a pre-accumulated water area;
step 2, converting the target image from an RGB color space to an HSV color space;
step 3, acquiring an HSV component value range of the designated color based on a preset HSV component value range comparison table; the specified color is a color which is obtained by changing the color-changeable paper when the paper meets water;
step 4, identifying the target image based on the value range of the HSV component of the designated color, judging whether the designated color is identified, if so, entering step 5, and if not, entering step 1;
and 5, performing alarm operation.
2. The seeper detection method based on the color-changeable paper and the image recognition is characterized in that: the step 3 further comprises:
and 3-1, setting an H, S, V component threshold of the water-encountering color-changing paper, and removing the interference background item on the periphery of the water-encountering color-changing paper by identifying HSV space color values of all pixel points in the target image.
3. The method for detecting standing water based on color-changeable paper and image recognition according to claim 2, wherein: the step 3 further comprises:
and 3-2, after the step 3-1 is executed, carrying out binarization processing on the target image.
4. The seeper detection method based on the color-changeable paper and the image recognition is characterized by comprising the following steps: the step 3 further comprises:
and 3-3, after the step 3-2 is executed, performing opening operation processing on the target image to highlight the area to be detected.
5. The seeper detection method based on the color-changeable paper and the image recognition is characterized in that: and 4, when the target image is identified in the step 3, identifying the corresponding to-be-detected region of the target image before binarization processing according to the to-be-detected region processed in the step 3-3, obtaining HSV space color values of the to-be-detected region, and judging whether the designated color is identified or not based on the HSV space color values and the designated color HSV component value range.
6. The seeper detection method based on the color-changeable paper and the image recognition is characterized in that: and 4, when the target image is identified, calculating the area S of the area where the identified designated color is located.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210359923.0A CN114820468A (en) | 2022-04-06 | 2022-04-06 | Accumulated water detection method based on color-changing paper and image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210359923.0A CN114820468A (en) | 2022-04-06 | 2022-04-06 | Accumulated water detection method based on color-changing paper and image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114820468A true CN114820468A (en) | 2022-07-29 |
Family
ID=82534569
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210359923.0A Pending CN114820468A (en) | 2022-04-06 | 2022-04-06 | Accumulated water detection method based on color-changing paper and image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114820468A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116740577A (en) * | 2023-08-10 | 2023-09-12 | 瞳见科技有限公司 | Road ponding identification method, system, terminal and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809131A (en) * | 2016-03-08 | 2016-07-27 | 宁波裕兰信息科技有限公司 | Method and system for carrying out parking space waterlogging detection based on image processing technology |
| CN106780428A (en) * | 2016-11-11 | 2017-05-31 | 北京理工大学珠海学院 | A kind of number of chips detection method and system based on colour recognition |
| US20200116858A1 (en) * | 2018-10-11 | 2020-04-16 | Furuno Electric Co., Ltd. | Underwater detection apparatus and underwater detection method |
| CN112541887A (en) * | 2020-12-02 | 2021-03-23 | 中国华能集团有限公司南方分公司 | Method for detecting water leakage defect of multi-pipeline equipment operation site of thermal power plant |
| CN112862821A (en) * | 2021-04-01 | 2021-05-28 | 中国工商银行股份有限公司 | Water leakage detection method and device based on image processing, computing equipment and medium |
| CN113034624A (en) * | 2021-05-06 | 2021-06-25 | 湖州云电笔智能科技有限公司 | Temperature early warning image identification method, system, equipment and storage medium based on temperature sensing color-changing adhesive tape |
| CN113741291A (en) * | 2021-09-09 | 2021-12-03 | 孙梦瑶 | Household water leakage prevention intelligent detection system based on Internet of things and working method thereof |
| CN114229641A (en) * | 2021-12-20 | 2022-03-25 | 苏州汇川控制技术有限公司 | Method, device and equipment for determining water level of elevator shaft and readable storage medium |
-
2022
- 2022-04-06 CN CN202210359923.0A patent/CN114820468A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105809131A (en) * | 2016-03-08 | 2016-07-27 | 宁波裕兰信息科技有限公司 | Method and system for carrying out parking space waterlogging detection based on image processing technology |
| CN106780428A (en) * | 2016-11-11 | 2017-05-31 | 北京理工大学珠海学院 | A kind of number of chips detection method and system based on colour recognition |
| US20200116858A1 (en) * | 2018-10-11 | 2020-04-16 | Furuno Electric Co., Ltd. | Underwater detection apparatus and underwater detection method |
| CN112541887A (en) * | 2020-12-02 | 2021-03-23 | 中国华能集团有限公司南方分公司 | Method for detecting water leakage defect of multi-pipeline equipment operation site of thermal power plant |
| CN112862821A (en) * | 2021-04-01 | 2021-05-28 | 中国工商银行股份有限公司 | Water leakage detection method and device based on image processing, computing equipment and medium |
| CN113034624A (en) * | 2021-05-06 | 2021-06-25 | 湖州云电笔智能科技有限公司 | Temperature early warning image identification method, system, equipment and storage medium based on temperature sensing color-changing adhesive tape |
| CN113741291A (en) * | 2021-09-09 | 2021-12-03 | 孙梦瑶 | Household water leakage prevention intelligent detection system based on Internet of things and working method thereof |
| CN114229641A (en) * | 2021-12-20 | 2022-03-25 | 苏州汇川控制技术有限公司 | Method, device and equipment for determining water level of elevator shaft and readable storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 贾维: "分布式配电室智能监控系统设计与实现", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116740577A (en) * | 2023-08-10 | 2023-09-12 | 瞳见科技有限公司 | Road ponding identification method, system, terminal and storage medium |
| CN116740577B (en) * | 2023-08-10 | 2024-01-12 | 瞳见科技有限公司 | Road ponding identification method, system, terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022062812A1 (en) | Screen defect detection method, apparatus, and electronic device | |
| CN116721106B (en) | Profile flaw visual detection method based on image processing | |
| CN106680287B (en) | Visual detection method for step defects of bearing rivet | |
| AU2014346263B2 (en) | Complex background-oriented optical character recognition method and device | |
| CN106097368B (en) | A kind of recognition methods in veneer crack | |
| CN105915840B (en) | A method of the factory smoke discharge based on vision signal monitors automatically | |
| CN109447011B (en) | Real-time monitoring method for infrared leakage of steam pipeline | |
| CN113298776B (en) | Method for detecting appearance defects of metal closed water pump impeller | |
| CN114820468A (en) | Accumulated water detection method based on color-changing paper and image recognition | |
| CN106228541A (en) | The method and device of screen location in vision-based detection | |
| CN111047624A (en) | Image dim target detection method, device, equipment and storage medium | |
| WO2021000948A1 (en) | Counterweight weight detection method and system, and acquisition method and system, and crane | |
| CN112669287A (en) | Electrical equipment temperature monitoring method based on image recognition | |
| CN113533372B (en) | Paper defect detection method, system, device and computer storage medium | |
| CN109387524A (en) | Thread defect detection method and device based on linearly polarized photon | |
| CN110490872B (en) | Foreign matter detection method and system for processing equipment | |
| CN106530292B (en) | A kind of steel strip surface defect image Fast Identification Method based on line scan camera | |
| CN111008960B (en) | Aluminum electrolytic capacitor bottom appearance detection method and device based on machine vision | |
| CN110322508B (en) | Auxiliary positioning method based on computer vision | |
| KR101712489B1 (en) | Method for measuring a pollution level of spot welding electrode tip using images | |
| Xiang et al. | Research on target detection method based on HSV fusion Gaussian mixture model | |
| CN115409803A (en) | Oil level identification method, system and medium for transformer in power distribution room | |
| CN114140417A (en) | Cigarette filter stick identification method and system based on machine vision | |
| CN115457459A (en) | Machine vision system capable of effectively improving detection efficiency | |
| CN113504250A (en) | Peanut aflatoxin detection device and method based on prism type RGB color extraction |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220729 |