CN110458044A - A kind of judgement ground immersion method based on image recognition - Google Patents
A kind of judgement ground immersion method based on image recognition Download PDFInfo
- Publication number
- CN110458044A CN110458044A CN201910660724.1A CN201910660724A CN110458044A CN 110458044 A CN110458044 A CN 110458044A CN 201910660724 A CN201910660724 A CN 201910660724A CN 110458044 A CN110458044 A CN 110458044A
- Authority
- CN
- China
- Prior art keywords
- ground
- soaked
- water
- image
- judgement
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
Abstract
The judgement ground immersion method based on image recognition that the present invention relates to a kind of, when solving using touch sensor, there are measurement result inaccuracy, sensor are easy to damage, and sensor the problems such as being not easy to the laying of circuit when being mounted on ground, judgement ground immersion method based on image recognition, comprising the following steps: smeared on ground to be identified and meet water allochroic paint;Monitoring device is arranged in the top on ground to be identified;Acquire ground realtime graphic;Ground realtime graphic is sent to the image analysis module of monitoring device, image analysis module compares ground realtime graphic with pre-set image;Similarity between ground realtime graphic and pre-set image is less than preset threshold, shows that similarity is lower, i.e., ground to be identified is not soaked in water;Similarity between ground realtime graphic and pre-set image is greater than preset threshold, shows that similarity is higher, i.e., ground to be identified has been soaked in water.
Description
Technical field
The present invention relates to a kind of judgement ground immersion methods, and in particular to a kind of judgement ground immersion based on image recognition
Method.
Background technique
Building can be soaked in water because of the region that the reasons such as leakage, pipe valve damage, flood, rainfall cause part to need waterproof.
Immersion problem not only upsets normal life, the work production order, but also influences whether that equipment and building are just in wetted areas
It is often used, in turn results in even more serious consequence.
The generation of adverse consequences in order to prevent, by using real time monitoring, issues in time when ground is soaked in water
Alarm signal.Currently used for mostly using the touch sensors such as capacitor, resistance, optical fiber greatly to Hquid monitoring, work as sensor
The electric parameter of sensor can be changed later by touching water, so that electric signal changes.But above-mentioned touch sensor
It needs to be directly installed on monitored ground.Since ground rolling and interfere vulnerable to pedestrian, vehicle, lead to measurement result
Inaccuracy, sensor is also easy to damage, and when sensor is mounted on ground is not easy to the laying of circuit.
Summary of the invention
When in order to solve in above-mentioned background technique using touch sensor monitoring, sensor is mounted directly on the ground easily
By the interference for arriving pedestrian, vehicle, cause measurement result inaccuracy, sensor also easy to damage, and when sensor is mounted on ground
The problems such as being not easy to the laying of circuit, the judgement ground immersion method based on image recognition that the present invention provides a kind of.
The technical solution of the invention is as follows the following steps are included:
A kind of judgement ground immersion method based on image recognition, is characterized in that, comprising the following steps:
S1 is smeared on ground to be identified and is met water allochroic paint;
S2, by monitoring device setting it is to be identified above the ground;
S3 acquires ground realtime graphic;
Ground realtime graphic, is sent to the image analysis module of monitoring device by S4, and image analysis module is real-time by ground
Image is compared with pre-set image;
S5, similarity between ground realtime graphic and pre-set image are less than preset threshold, show that similarity is lower, i.e., to
The ground of identification is not soaked in water;
Similarity between ground realtime graphic and pre-set image is greater than preset threshold, shows that similarity is higher, i.e., wait know
Other ground has been soaked in water.
Further, the shape at setting is smeared with chance water allochroic paint on ground to be identified.
Further, the shape set is arrow shaped.
Further, monitoring device includes that camera, image analysis module, wireless communication module, master control borad, power supply connect
Head;
The data output end of camera is connect with main control board data input terminal;
The data input pin and output end of image analysis module are connect with main control board data output end and input terminal respectively;
The data input pin of wireless communication module is connect with main control board data output end;
Power connection is connect with external power supply equipment.
Further, the result after module analyzes image analysis module by wireless communication is sent to supervision department.
Further, when ground is not soaked in water, meeting water allochroic paint is white, when ground has been soaked in water, meets water and becomes
Color coating is colourless.
Further, the chance water allochroic paint is that thousand discolorations meet water color shifting ink 601A series.
The present invention has the advantages that
The characteristics of the present invention is based on coating meets water discoloration simultaneously combines image-recognizing method, realizes non-contact detection, no
But fast response time, at low cost, high reliablity.And without placing any device or equipment on ground, avoid vulnerable to row
The interference of people, vehicle lead to measurement result inaccuracy, sensor also problem easy to damage.
Image Acquisition is carried out by installing pinnacled camera, the region not only monitored is big, and quick and easy for installation,
So that application prospect of the present invention is extensive.
Detailed description of the invention
Fig. 1 is the schematic diagram being soaked in water using method monitoring ground of the invention;
Fig. 2 is the schematic diagram not being soaked in water using method monitoring ground of the invention;
Fig. 3 is to meet water allochroic paint normal condition schematic diagram;
Fig. 4 is to meet water allochroic paint to be soaked in water status diagram;
Fig. 5 is the outside drawing of monitoring device.
Appended drawing reference is as follows:
1- monitoring device, 2- meet water allochroic paint, 3- water.
Specific embodiment
The contents of the present invention are described in further detail below in conjunction with the drawings and specific embodiments:
As shown in Figures 1 to 5, should be soaked method based on the judgement ground of image recognition, comprising the following steps:
S1 is smeared in the chance water allochroic paint 2 of ground white to be identified into arrow shaped;As shown in figure 3, after smearing
Face is white arrow, when water 3 is met on ground, as shown in figure 4, white arrow becomes colorless (transparent) on ground;
It meets water allochroic paint 2 to belong to water-soluble silk screen coating usually itself is white, may be set to be other colors, meet water
Bleach after 3 restores after dry, realizes colour change function with this.Can be added in the case where meeting water allochroic paint 2 specific color (as it is red,
Yellow, blue) or shape and pattern (various geometries or trade mark) after again on it smear meet water allochroic paint 2.In this way
The chance water allochroic paint 2 on ground is white under the drying regime of ground, meets 2 bleach of water allochroic paint, Jin Erxian after being submerged by water 3
Reveal the specific color of lower layer and the pattern of shape.
Water allochroic paint 2 is met in ground partial smearing to be identified, when water 3 collects on ground to be identified, is smeared
The field color for meeting water allochroic paint 2 can change, and sagittate smearing mode may make color change interval feature more obvious,
Convenient for the further analysis of image analysis module, while avoiding entire ground to be detected and smearing chance water allochroic paint 2;
It meets water allochroic paint 2 to be widely used in weaving, manufacture and engineering field at present, chance water discoloration applies
Expect 2 technical maturities, can satisfy the demand of the method for the present invention.
The top on ground to be identified is arranged in monitoring device 1 by S2, is taken the photograph by the image information adjustment of cam feedback
As brilliance degree, guarantee that ground to be identified can be completely covered in camera shooting area;
S3 acquires ground realtime graphic by camera in monitoring device 1;
Ground realtime graphic, is sent to the image analysis module of monitoring device 1 by S4, and image analysis module is real-time by ground
Image is compared with pre-set image;
Pre-set image is that image when ground to be identified is soaked by water 3 can apply after comparing with realtime graphic according to the two
The color difference in region is smeared to judge whether ground soaks 3.
It is avoidable because the reasons such as weather make light change by setting the preset threshold of two image similarities,
Lead to the color difference of the image appearance of shooting and the problem of error analysis occurs.
S5, similarity between ground realtime graphic and pre-set image are less than preset threshold, show that similarity is lower, i.e., to
It is not soaked by water 3 on the ground of identification;
Similarity between ground realtime graphic and pre-set image is greater than preset threshold, shows that similarity is higher, i.e., wait know
It is soaked by water 3 on other ground;
Shoot ground to be identified under different light, the image after shooting be compared, find out under ordinary ray
Image, and the image minimum with image similarity under ordinary ray.
The lines curvature of every its attribute of piece image has the characteristic point of oneself, these characteristic points characterize image lines curvature
Important some positions (image actual features), more commonly used characteristic point have the terminal etc. of angle point, line segment.Pass through image
The Curvature varying of lines come extract the characteristic point in image (such as straightway be continuous zero curvature but line segment endpoint curvature
Can mutate, camber line is continuous curvature different from zero, angle point is local maxima curvature) judge the similarities of two images.
Characteristic point in two images is compared, if similar characteristic point number is more, it is considered that this
The similarity degree of two images is higher.
The minimum image of similarity and normal picture are compared, calculate similar characteristic point number, which can be used as two
The preset threshold of width image similarity;
When image to be detected and normal picture compare, if the feature that similar characteristic point number is greater than preset threshold is counted
Mesh shows that image similarity to be detected is higher, i.e., ground to be identified is soaked by water 3;Conversely, image to be detected is similar
Spend lower, i.e., ground to be identified is not soaked by water 3.
Two images similarity whether with higher, the algorithm are judged by the similar feature point number of two images
Benefit be image that the same object is shot under different angle, can still find many match points, i.e. this method has
There is lesser error.
The result after analysis is sent to supervision department by wireless communication module in monitoring device 1;
As shown in Fig. 2, wireless communication module sends the message that do not soaked by water 3 in the state that ground is not soaked by water 3
To supervision department;As shown in Figure 1, the coatings area color that ground is covered by water 3 occurs in the state that ground is soaked by water 3
Variation, the message that wireless communication module transmission is soaked by water 3 to supervision department.
As shown in figure 5, the monitoring device 1 includes camera, image analysis module, wireless communication module, master control borad, electricity
The data output end of source connector, camera is connect with main control board data input terminal;The data output end of image analysis module and defeated
Enter end to connect with main control board data input terminal and output end respectively;The data input pin of wireless communication module and main control board data are defeated
Outlet connection;Power connection is that monitoring device 1 is powered and connect with external power supply equipment.
The above description is only an embodiment of the present invention, and it is not intended to limit the protection scope of the present invention, all to utilize the present invention
Equivalent structure transformation made by specification and accompanying drawing content, is applied directly or indirectly in other relevant technical fields, and wraps
It includes in scope of patent protection of the invention.
Claims (7)
- A kind of method 1. judgement ground based on image recognition is soaked, which comprises the following steps:S1 is smeared on ground to be identified and is met water allochroic paint (2);S2, by monitoring device (1) setting it is to be identified above the ground;S3 acquires ground realtime graphic;Ground realtime graphic, is sent to the image analysis module of monitoring device (1) by S4, and image analysis module schemes on ground in real time As being compared with pre-set image;S5, the similarity between ground realtime graphic and pre-set image is less than preset threshold, shows that similarity is lower, i.e., to be identified Ground do not soaked by water (3);Similarity between ground realtime graphic and pre-set image is greater than preset threshold, shows that similarity is higher, i.e., to be identified It is soaked by water (3) on ground.
- The method 2. a kind of judgement ground based on image recognition according to claim 1 is soaked, it is characterised in that: wait know The shape at setting is smeared with chance water allochroic paint (2) in other ground.
- The method 3. a kind of judgement ground based on image recognition according to claim 2 is soaked, it is characterised in that: described to set Fixed shape is arrow shaped.
- The method 4. a kind of judgement ground based on image recognition according to claim 3 is soaked, it is characterised in that: monitoring is set Standby (1) includes camera, image analysis module, wireless communication module, master control borad, power connection;The data output end of camera is connect with main control board data input terminal;The data input pin and output end of image analysis module are connect with main control board data output end and input terminal respectively;The data input pin of wireless communication module is connect with main control board data output end;Power connection is connect with external power supply equipment.
- The method 5. a kind of judgement ground based on image recognition according to claim 4 is soaked, it is characterised in that: pass through nothing Result after line communication module analyzes image analysis module is sent to supervision department.
- The method 6. a kind of judgement ground based on image recognition according to claim 3 is soaked, it is characterised in that: ground is not When being soaked by water (3), meeting water allochroic paint (2) is white, and when ground is soaked by water (3), meeting water allochroic paint (2) is nothing Color.
- The method 7. a kind of judgement ground based on image recognition according to claim 3 is soaked, it is characterised in that: the chance Water allochroic paint (2) is that thousand discolorations meet water color shifting ink 601A series.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910660724.1A CN110458044A (en) | 2019-07-22 | 2019-07-22 | A kind of judgement ground immersion method based on image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910660724.1A CN110458044A (en) | 2019-07-22 | 2019-07-22 | A kind of judgement ground immersion method based on image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110458044A true CN110458044A (en) | 2019-11-15 |
Family
ID=68481646
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910660724.1A Pending CN110458044A (en) | 2019-07-22 | 2019-07-22 | A kind of judgement ground immersion method based on image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110458044A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN114842629A (en) * | 2022-05-18 | 2022-08-02 | 国家电投集团东方新能源股份有限公司热力分公司 | Water immersion alarm method, device and system for heating station |
Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1844952A (en) * | 2006-05-10 | 2006-10-11 | 北京好望角医学影像技术有限公司 | Land cover change detection method based on remote sensing image processing |
CN102279081A (en) * | 2011-04-26 | 2011-12-14 | 同济大学 | Method and device for detecting water seepage of tunnel |
CN102589808A (en) * | 2012-01-16 | 2012-07-18 | 苏州临点三维科技有限公司 | Large-scale tunnel seepage point measuring method |
CN102776904A (en) * | 2012-07-19 | 2012-11-14 | 同济大学 | Method for fast predicting side wall leakage of underground diaphragm wall using infrared thermal fields |
CN104614299A (en) * | 2015-02-11 | 2015-05-13 | 上海同标质量检测技术有限公司 | Concrete impermeability test system and method employing color-change ink |
US20170017862A1 (en) * | 2014-03-14 | 2017-01-19 | Omron Corporation | Image recognition device, image sensor, and image recognition method |
CN107833221A (en) * | 2017-11-29 | 2018-03-23 | 武汉大学 | A kind of water leakage monitoring method based on multi-channel feature fusion and machine learning |
CN108810269A (en) * | 2018-06-04 | 2018-11-13 | 努比亚技术有限公司 | Alarm method, mobile terminal and the computer readable storage medium of battery immersion |
CN108974044A (en) * | 2018-08-09 | 2018-12-11 | 铁路愿景欧洲有限公司 | Railroad track assets survey system |
CN109268928A (en) * | 2018-09-12 | 2019-01-25 | 长安大学 | A kind of heat supply monitoring system |
CN109443812A (en) * | 2018-09-21 | 2019-03-08 | 同济大学 | Hvac equipment fault diagnosis method and system based on view data |
CN109580109A (en) * | 2018-12-20 | 2019-04-05 | 国网福建省电力有限公司 | A kind of method that soft straight converter valve tower cooler water leak monitors automatically |
CN109858441A (en) * | 2019-01-30 | 2019-06-07 | 广州轨道交通建设监理有限公司 | A kind of monitoring abnormal state method and apparatus for construction site |
-
2019
- 2019-07-22 CN CN201910660724.1A patent/CN110458044A/en active Pending
Patent Citations (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1844952A (en) * | 2006-05-10 | 2006-10-11 | 北京好望角医学影像技术有限公司 | Land cover change detection method based on remote sensing image processing |
CN102279081A (en) * | 2011-04-26 | 2011-12-14 | 同济大学 | Method and device for detecting water seepage of tunnel |
CN102589808A (en) * | 2012-01-16 | 2012-07-18 | 苏州临点三维科技有限公司 | Large-scale tunnel seepage point measuring method |
CN102776904A (en) * | 2012-07-19 | 2012-11-14 | 同济大学 | Method for fast predicting side wall leakage of underground diaphragm wall using infrared thermal fields |
US20170017862A1 (en) * | 2014-03-14 | 2017-01-19 | Omron Corporation | Image recognition device, image sensor, and image recognition method |
CN104614299A (en) * | 2015-02-11 | 2015-05-13 | 上海同标质量检测技术有限公司 | Concrete impermeability test system and method employing color-change ink |
CN107833221A (en) * | 2017-11-29 | 2018-03-23 | 武汉大学 | A kind of water leakage monitoring method based on multi-channel feature fusion and machine learning |
CN108810269A (en) * | 2018-06-04 | 2018-11-13 | 努比亚技术有限公司 | Alarm method, mobile terminal and the computer readable storage medium of battery immersion |
CN108974044A (en) * | 2018-08-09 | 2018-12-11 | 铁路愿景欧洲有限公司 | Railroad track assets survey system |
CN109268928A (en) * | 2018-09-12 | 2019-01-25 | 长安大学 | A kind of heat supply monitoring system |
CN109443812A (en) * | 2018-09-21 | 2019-03-08 | 同济大学 | Hvac equipment fault diagnosis method and system based on view data |
CN109580109A (en) * | 2018-12-20 | 2019-04-05 | 国网福建省电力有限公司 | A kind of method that soft straight converter valve tower cooler water leak monitors automatically |
CN109858441A (en) * | 2019-01-30 | 2019-06-07 | 广州轨道交通建设监理有限公司 | A kind of monitoring abnormal state method and apparatus for construction site |
Non-Patent Citations (2)
Title |
---|
PETER M. BACH 等: "Reliability of Infrared Thermography in Detecting Leaks in Buried Water Reticulation Pipes", 《 IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING》 * |
彭斌 等: "基于全景展开图像的隧道衬砌渗漏水数字化识别方法研究", 《现代隧道技术》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
CN113741291B (en) * | 2021-09-09 | 2024-04-05 | 孙梦瑶 | Household water leakage prevention intelligent detection system based on Internet of things and working method thereof |
CN114842629A (en) * | 2022-05-18 | 2022-08-02 | 国家电投集团东方新能源股份有限公司热力分公司 | Water immersion alarm method, device and system for heating station |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110458044A (en) | A kind of judgement ground immersion method based on image recognition | |
CN102137272B (en) | Method for calibrating colors of multiple cameras in open environment | |
CN113551775B (en) | Equipment fault on-line monitoring alarm method and system based on infrared thermal imaging | |
CN111882810B (en) | Fire identification and early warning method and system | |
CN102831393A (en) | Rapid image recognizing method of power tower pole outline | |
CN106204602B (en) | The anti-part detection method of element and system | |
CN107576269B (en) | Power transmission line forest fire positioning method | |
CN110135343A (en) | A kind of street lamp intelligent measurement and night status judgment method | |
CN106705884A (en) | Product dimension detection method | |
CN111707237A (en) | Building exterior wall surface spraying method based on visual measurement | |
CN112906602B (en) | Automatic identification device and identification method for electric quantity meter of power distribution cabinet based on image processing | |
CN111854939A (en) | Online detection method for LED flexible light bar | |
CN112560574A (en) | River black water discharge detection method and recognition system applying same | |
CN108961305B (en) | Sea wave climbing monitoring method based on image recognition | |
CN111119419A (en) | Building roof waterproof system and waterproof monitoring method thereof | |
CN207923747U (en) | A kind of textile cloth cloth surface detection system | |
CN110910597A (en) | Real-time monitoring and alarming system for transformer substation personnel | |
CN110782431B (en) | High-voltage wire icing area detection method based on deep learning | |
CN108346252A (en) | A kind of integrated forest fire protection information system excavated based on big data | |
CN109961428A (en) | Non-negative Matrix Factorization electrically molten magnesia industry fault detection method based on manifold | |
CN113225525B (en) | Indoor monitoring method and system | |
KR20230047833A (en) | System for sensing fire of electrical installations | |
CN209433223U (en) | A kind of controller for optical cross box status monitoring | |
CN113850133A (en) | Ship line-crossing detection method and system for ship lock video monitoring | |
CN106168467A (en) | A kind of three-dimensional detection device and method |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191115 |