CN107463931A - A kind of real-time pointer instrument reading method and device based on ARM platforms - Google Patents
A kind of real-time pointer instrument reading method and device based on ARM platforms Download PDFInfo
- Publication number
- CN107463931A CN107463931A CN201710545000.3A CN201710545000A CN107463931A CN 107463931 A CN107463931 A CN 107463931A CN 201710545000 A CN201710545000 A CN 201710545000A CN 107463931 A CN107463931 A CN 107463931A
- Authority
- CN
- China
- Prior art keywords
- pointer
- image
- dial plate
- real
- line segment
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of real-time pointer instrument reading method and device based on ARM platforms, method comprises the following steps：The preset dial plate center of circle, scale starting point and the total range information of instrument；Dial plate IMAQ, call image capture device collection pointer meters dial plate image；Dial plate image preprocessing, using 3 × 3 Gaussian template to image filtering, eliminate partial noise；Dial plate image binaryzation, coloured image is converted into gray-scale map, carries out binarization operation, while be partitioned into pointer area；Pointer skeletal extraction, refined using the novel framework extraction algorithm based on Euclidean Distance Transform to enter line pointer；Pointer extracting, line segment is extracted using the method that straight line is extracted based on Hough transform；Total indicator reading is obtained, according to the pointer found and the differential seat angle of dial plate original position, calculates the registration pointed by current pointer.The present invention can improve the O＆M efficiency of correlate meter equipment, can be that enterprise or government department save fund and manpower.
Description
Technical field
The present invention relates to Signal and Information Processing technical field, more particularly to a kind of real-time pointer instrument based on ARM platforms
Table reading method and device.
Background technology
Pointer instrument is the important component in modern industry.Because of its high accuracy, high reliability and low cost, obtain
Obtained and be widely applied.At present, the data of instrument, which rely primarily on, is manually distinguished, and low precision, interval time is long, cost is high
It is high.Intelligence instrument reading method can be realized meter reading automatic identification using image analysis algorithm and be transmitted to control centre.
These characteristics based on instrument recognition：It can be that government or enterprise save substantial amounts of labour cost, improve work
Efficiency, reduce entreprise cost.At the same time it can also check meter reading at any time, equipment running status are grasped, pass through long-term data
Collection can also go deep into mining data value.
Therefore, many government departments or enterprise start the intelligence recognition of contact stud instrument now.Current instrument is known
Reading needs to be analyzed the data transfer of pointer meters to control centre mostly, and substantial amounts of view information transmission can cause network
Bandwidth congestion, increase information transfer cost, influence the normal use of instrument recognition system.
To solve above mentioned problem present in existing instrument reading method, invention provides a kind of new, effectively
Solution method.
The content of the invention
In view of the drawbacks described above of prior art, the technical problems to be solved by the invention are to provide one kind and put down based on ARM
The real-time pointer instrument reading method and device of platform, realize that the long-range of instrument registration is read in real time, reduce equipment O＆M cost, side
Equipment operation maintenance personnel is helped to understand equipment state at any time.
To achieve the above object, the invention provides a kind of real-time pointer instrument reading method based on ARM platforms, it is special
Sign is, comprises the following steps：
Step 1: the preset dial plate center of circle, scale starting point and the total range information of instrument；
Step 2: dial plate IMAQ, calls image capture device, the picture of collection is transformed into YCbCr color spaces,
Judge whether to need to open LED light supplement lamp by brightness Y compositions, adjust lens focus, gather pointer meters dial plate image；
Step 3: dial plate image preprocessing, using 3 × 3 Gaussian template to image filtering, eliminates partial noise；
Step 4: dial plate image binaryzation, gray-scale map is converted to by coloured image, using maximum variance between clusters by gray scale
Image carries out binarization operation, while is partitioned into pointer area；
Step 5: pointer skeletal extraction, after Euclidean Distance Transform, obtains the pointer after refinement；
Step 6: pointer extracting, line segment is extracted using the method that straight line is extracted based on Hough transform；
Step 7: obtaining total indicator reading, according to the pointer found and the differential seat angle of dial plate original position, current pointer is calculated
Pointed registration.
Further, the step 3 eliminates in partial noise and eliminates influence of noise using 2 Gaussian Blurs.
1st, further,
2nd, in step 5, after Euclidean Distance Transform, it is as follows to obtain the pointer method after refinement：Pass through pixel
The local comparison of 8 field pixel values obtains the pixel vertex type, and thereby determines that the candidate point of skeletal point, according to pixel class
Type, state are that strong point is grown to skeleton；When growth conditions are weak point, all skeletons to be grown out by weak points
Branch touches skeleton edges, then deletes this skeleton branches；Every skeleton branches to grow out perpendicular to generating before
Skeleton, then this skeleton branches is deleted；After obtaining skeletal point by above-mentioned growth regularity, the pointer after refinement is obtained.
Further, the step 6 is specially：Only retain air line distance residing for the center of circle to line segment and be less than 5 pixels
Line segment, more all qualified line segment lengths, it is pointer to choose most long line segment.
Further, the registration pointed by the step 7 calculating current pointer is specially：Judge when time recognition result with
Whether the difference of previous recognition result is more than threshold value, is to give up this result, otherwise exports this recognition result.
A kind of real-time pointer instrument reading device based on ARM platforms, including image capture device, the image being sequentially connected
Processing equipment, data transmission module, remote platform or data collection station, wherein
Image capture device, for gathering pointer meters dial plate image；
Image processing equipment, the pretreatment of its Instrument image recognition service module progress image, image binaryzation, pointer bone
Frame extraction, pointer extracting, angle judges, result is distinguished, and obtains the current registration of instrument；
Data transmission module, for the view data after processing to be transmitted to remote platform or number using Standard general purpose interface
According to acquisition terminal；
Remote platform or data collection station, for the view data after reception processing, do analysis and the profit of later data
With.
Further, when described image processing equipment carries out the pretreatment process of image, 3 × 3 Gaussian template pair is used
Image filtering, partial noise is eliminated, influence of noise is eliminated using 2 Gaussian Blurs.
When described image processing equipment carries out the pointer skeletal extraction flow of image, after Euclidean Distance Transform,
Relatively and the candidate point of skeletal point is quickly determined by local, regrowth obtains skeletal point.
Further, when described image processing equipment carries out the pointer extracting flow of image, carried using based on Hough transform
The method extraction line segment of cut-off line, only retains the line segment that air line distance residing for the center of circle to line segment is less than 5 pixels, relatively more all
Qualified line segment length, it is pointer to choose most long line segment.
Further, when described image processing equipment carries out the result recognition flow of image, according to the pointer and table found
The differential seat angle of disk original position, the registration pointed by current pointer is calculated, judged when time recognition result and previous recognition result
Whether difference is more than threshold value, is to give up this result, otherwise exports this recognition result.
The beneficial effects of the invention are as follows：
The present invention is based on low-power consumption ARM platforms, can improve the O＆M efficiency of correlate meter equipment, can be enterprise or political affairs
Mansion department saves fund and manpower.
Design, concrete structure and the caused technique effect of the present invention are described further below with reference to accompanying drawing, with
It is fully understood from the purpose of the present invention, feature and effect.
Brief description of the drawings
Fig. 1 is the structured flowchart of the real-time pointer instrument reading device based on ARM platforms.
Fig. 2 is the flow chart of the real-time pointer instrument reading method based on ARM platforms.
Embodiment
The present invention is described further below in conjunction with the accompanying drawings.To make the purpose of embodiments of the invention, technical scheme
It is clearer with advantage, simplicity of explanation is done to some nouns being related in the embodiment of the present invention below.
ARM (Acorn RISC Machine, reduced instruction set computer microprocessor), it is that Acorn Co., Ltds of Britain design
First item reduced instruction set computer microprocessor, there is small volume, low-power consumption, low cost, high performance feature, in mobile device market
Have a wide range of applications.
As shown in figure 1, the hardware based image collecting device of the system and ARM processing platforms, have set up real-time pointer instrument
Table reading device.
Low power image processing equipment is mainly set including processor cores, audio-video interface, external storage interface, driving
Standby, power supply etc..Image capture device mainly includes camera lens, LED light supplement lamp, driving equipment, head etc..
As shown in figure 1, the collection behaviour of image capture device instruction progress image is pushed to from low power image processing equipment
Make, the image of collection is output to image processing equipment by image capture device.
As shown in figure 1, in image processing equipment, distinguish service using Instrument image and carry out the pretreatment of image, skeleton
The flows such as extraction, pointer demarcation, angle judgement, result recognition obtain the current registration of instrument.
Instrument is distinguished result and is pushed to data transmission module with Instrument image by image processing equipment, then passes through data transfer
Module sends data to remote platform or data collection station using Standard general purpose interface.
The real-time pointer instrument reading method flow of the present invention is as shown in Fig. 2 the dial plate center of circle preset first, scale starting point
With the total range information of instrument, and only need it is preset once.
The collection of Instrument image is carried out using image capture device, in order to ensure that whole day can be adopted normally for 24 hours
Collection, the present apparatus employs the design of LED light supplement lamp, and instrument and the distance of camera lens are about 15cm or so, and frequency acquisition is every 5
1 width picture of second, resolution ratio CIF, form .jpg.
Then, the pretreatment of image is carried out, in the image of collection, the problems such as pollution reflective due to the change of bright and dark light
Light and shade inequality high level noise can be produced, using 3 × 3 Gaussian template to image filtering, elimination portion before entering line pointer and reading
Divide noise, the present apparatus eliminates influence of noise using 2 Gaussian Blurs.Then, testing image is converted into gray scale using formula (1)
Image：
G=0.299R+0.587G+0.114B (1)
After Instrument image is got, in order to be advantageous to follow-up pointer extracting, it is necessary to by background and some light and shade spots
Point is separated, because the general local environment of pointer meters is not very fixed, because the change dial plate gray value of light has change
Change, split and do not had applicability using fixed threshold method, maximum variance between clusters are then used in the present apparatus
Carry out the segmentation of image-region.In the case of generating shade around pointer, maximum variance between clusters remain able to relatively good
Ground Split goes out pointer area.
Because the later gauge pointer of binaryzation has one fixed width, if in this case directly using classical
Hough transform extracts pointer, it may appear that the straight line extracted is not in the feelings of coincidence status with straight line where pointer skeleton
Condition, pointer is first then subjected to refinement in the present apparatus and extracts pointer skeleton, then obtains pointer angle again.The present apparatus uses base
Enter line pointer refinement in the novel framework extraction algorithm of Euclidean Distance Transform.
After Euclidean Distance Transform, relatively and the candidate point of skeletal point is quickly determined by local, regrowth obtains
Skeletal point, it ensure that the connectedness that can keep skeleton while real-time as far as possible.
In terms of pointer is extracted, there is employed herein the method based on Hough transform extraction straight line, classical Hough changes
It is the straight line information that will pass through a bit (x, y) in cartesian coordinate system, is converted to the straight line normal in polar coordinate space
(ρ, θ) information, its formula are：
ρ=xcos θ+ysin θ (2)
Then to doing cumulative mark by the comprehensive straight line of effective pixel points, the information of every line segment is obtained, due to referring to
Straight line where pin, so only retaining the line segment that air line distance residing for the center of circle to line segment is less than 5 pixels, compares institute by the center of circle
There is qualified line segment length, it is pointer to choose most long line segment.
Finally, according to the pointer found and the differential seat angle of dial plate original position, the registration pointed by current pointer is calculated.Sentence
Whether the disconnected difference for working as time recognition result and previous recognition result is more than threshold value, is to give up this result, otherwise exports this
Distinguish result.Then data transmission module will distinguish result and instrument picture passes through Standard general purpose interface and broadband network, 4G-
LTE or WIFI network are transmitted to remote platform or data collection station.The data that equipment operation maintenance personnel is fed back according to instrument judge
Equipment current state, decision support is provided for system regular maintenance.
Preferred embodiment of the invention described in detail above.It should be appreciated that one of ordinary skill in the art without
Creative work can is needed to make many modifications and variations according to the design of the present invention.Therefore, all technologies in the art
Personnel are available by logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Technical scheme, all should be in the protection domain being defined in the patent claims.
Claims (10)
1. a kind of real-time pointer instrument reading method based on ARM platforms, it is characterised in that comprise the following steps：
Step 1: the preset dial plate center of circle, scale starting point and the total range information of instrument；
Step 2: dial plate IMAQ, calls image capture device, the picture of collection is transformed into YCbCr color spaces, passed through
Brightness Y compositions judge whether to need to open LED light supplement lamp, adjust lens focus, gather pointer meters dial plate image；
Step 3: dial plate image preprocessing, using 3 × 3 Gaussian template to image filtering；
Step 4: dial plate image binaryzation, gray-scale map is converted to by coloured image, using maximum variance between clusters by gray level image
Binarization operation is carried out, while is partitioned into pointer area；
Step 5: pointer skeletal extraction, after Euclidean Distance Transform, obtains the pointer after refinement；
Step 6: pointer extracting, line segment is extracted using the method that straight line is extracted based on Hough transform；
Step 7: obtaining total indicator reading, according to the pointer found and the differential seat angle of dial plate original position, it is signified to calculate current pointer
To registration.
A kind of 2. real-time pointer instrument reading method based on ARM platforms as claimed in claim 1, it is characterised in that step
In three, influence of noise is eliminated using 2 Gaussian Blurs.
A kind of 3. real-time pointer instrument reading method based on ARM platforms as claimed in claim 1, it is characterised in that：Step
In five, after Euclidean Distance Transform, it is as follows to obtain the pointer method after refinement：Pass through the field pixel value of pixel 8
It is local relatively to obtain the pixel vertex type, and the candidate point of skeletal point is thereby determined that, according to pixel vertex type, state strong
Point be grown to skeleton；When growth conditions are weak point, all skeleton branches to be grown out by weak points touch skeleton
Edge, then this skeleton branches is deleted；Every skeleton branches to grow out are perpendicular to the skeleton generated before, then by this bone
Frame branch deletes；After obtaining skeletal point by above-mentioned growth regularity, the pointer after refinement is obtained.
A kind of 4. real-time pointer instrument reading method based on ARM platforms as claimed in claim 1, it is characterised in that step
In six, specific method is：Only retain the line segment that air line distance residing for the center of circle to line segment is less than 5 pixels, more all symbols
The line segment length of conjunction condition, it is pointer to choose most long line segment.
A kind of 5. real-time pointer instrument reading method based on ARM platforms as claimed in claim 1, it is characterised in that step
Seven, calculating the registration specific method pointed by current pointer is：Judge when the difference of time recognition result and previous recognition result is
It is no to be more than threshold value, it is to give up this result, otherwise exports this recognition result.
6. a kind of real-time pointer instrument reading device based on ARM platforms, it is characterised in that including the IMAQ being sequentially connected
Equipment, image processing equipment, data transmission module, remote platform or data collection station, wherein
Image capture device, for gathering pointer meters dial plate image；
Image processing equipment, the pretreatment of its Instrument image recognition service module progress image, image binaryzation, pointer skeleton carry
Take, pointer extracting, angle judge, result recognition, the acquisition current registration of instrument；
Data transmission module, adopted for the view data after processing to be transmitted to remote platform or data using Standard general purpose interface
Collect terminal；
Remote platform or data collection station, for the view data after reception processing, do the analysis and utilization of later data.
7. a kind of real-time pointer instrument reading device based on ARM platforms as claimed in claim 6, it is characterised in that described
When image processing equipment carries out the pretreatment process of image, using 3 × 3 Gaussian template to image filtering, 2 Gaussian modes are used
Paste to eliminate influence of noise.
8. a kind of real-time pointer instrument reading device based on ARM platforms as claimed in claim 6, it is characterised in that described
When image processing equipment carries out the pointer skeletal extraction flow of image, after Euclidean Distance Transform, by local relatively and true
Determine the candidate point of skeletal point, regrowth obtains skeletal point.
9. a kind of real-time pointer instrument reading device based on ARM platforms as claimed in claim 6, it is characterised in that described
When image processing equipment carries out the pointer extracting flow of image, line segment is extracted using the method that straight line is extracted based on Hough transform,
Only retain the line segment that air line distance residing for the center of circle to line segment is less than 5 pixels, more all qualified line segment lengths, choosing
It is pointer to take most long line segment.
10. a kind of real-time pointer instrument reading device based on ARM platforms as claimed in claim 6, it is characterised in that described
When image processing equipment carries out the result recognition flow of image, according to the pointer found and the differential seat angle of dial plate original position, meter
The registration pointed by current pointer is calculated, whether the difference for judging to work as time recognition result and previous recognition result is more than threshold value, is then
Give up this result, otherwise export this recognition result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710545000.3A CN107463931A (en) | 2017-07-06 | 2017-07-06 | A kind of real-time pointer instrument reading method and device based on ARM platforms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710545000.3A CN107463931A (en) | 2017-07-06 | 2017-07-06 | A kind of real-time pointer instrument reading method and device based on ARM platforms |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107463931A true CN107463931A (en) | 2017-12-12 |
Family
ID=60546631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710545000.3A Pending CN107463931A (en) | 2017-07-06 | 2017-07-06 | A kind of real-time pointer instrument reading method and device based on ARM platforms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107463931A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108827530A (en) * | 2018-03-13 | 2018-11-16 | 安徽瑞鑫自动化仪表有限公司 | A kind of pressure gauge remote data automation acquisition system |
| CN108827101A (en) * | 2018-08-17 | 2018-11-16 | 上海盛染智能科技有限公司 | Part circumference runout error automatic detection device and method |
| CN109977725A (en) * | 2017-12-27 | 2019-07-05 | 中移物联网有限公司 | A kind of water meter reading method and system |
| CN110059529A (en) * | 2017-12-13 | 2019-07-26 | 台达电子工业股份有限公司 | The recognition methods and its image capturing equipment of the direction of the pointer of analog measurement device |
| CN110929716A (en) * | 2019-11-29 | 2020-03-27 | 航天科技控股集团股份有限公司 | Pointer capture-based instrument panel center determination method and system |
| CN112001379A (en) * | 2020-05-19 | 2020-11-27 | 西安工程大学 | Correction algorithm of automobile instrument fixed viewpoint reading instrument based on machine vision |
| CN112051003A (en) * | 2020-09-10 | 2020-12-08 | 中国科学院自动化研究所 | Automatic product detection device, detection method and reading method for hydraulic meter |
| CN112257676A (en) * | 2020-11-19 | 2021-01-22 | 南京天创电子技术有限公司 | Pointer instrument reading method and system and inspection robot |
| CN112668578A (en) * | 2020-12-31 | 2021-04-16 | 中广核研究院有限公司 | Pointer instrument reading method and device, computer equipment and storage medium |
| CN113792727A (en) * | 2021-07-30 | 2021-12-14 | 华能大理风力发电有限公司 | Reading estimation method, device and system based on pointer instrument video image |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110052094A1 (en) * | 2009-08-28 | 2011-03-03 | Chunyu Gao | Skew Correction for Scanned Japanese/English Document Images |
| WO2013011013A2 (en) * | 2011-07-19 | 2013-01-24 | Wincor Nixdorf International Gmbh | Method and device for ocr-detection of valuable documents by means of a matrix camera |
| CN105389572A (en) * | 2015-12-10 | 2016-03-09 | 威海北洋电气集团股份有限公司 | All-in-one machine for human face and identity card recognition and light supplementing method capable of automatically adjusting brightness |
| CN106295658A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic recognition system |
| CN106599897A (en) * | 2016-12-09 | 2017-04-26 | 广州供电局有限公司 | Machine vision-based pointer type meter reading recognition method and device |
| CN106855421A (en) * | 2017-01-17 | 2017-06-16 | 中国第汽车股份有限公司 | A kind of automobile instrument automatization test system and method for testing based on machine vision |
-
2017
- 2017-07-06 CN CN201710545000.3A patent/CN107463931A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110052094A1 (en) * | 2009-08-28 | 2011-03-03 | Chunyu Gao | Skew Correction for Scanned Japanese/English Document Images |
| WO2013011013A2 (en) * | 2011-07-19 | 2013-01-24 | Wincor Nixdorf International Gmbh | Method and device for ocr-detection of valuable documents by means of a matrix camera |
| CN105389572A (en) * | 2015-12-10 | 2016-03-09 | 威海北洋电气集团股份有限公司 | All-in-one machine for human face and identity card recognition and light supplementing method capable of automatically adjusting brightness |
| CN106295658A (en) * | 2016-08-13 | 2017-01-04 | 国网福建省电力有限公司 | A kind of transformer station readings of pointer type meters automatic recognition system |
| CN106599897A (en) * | 2016-12-09 | 2017-04-26 | 广州供电局有限公司 | Machine vision-based pointer type meter reading recognition method and device |
| CN106855421A (en) * | 2017-01-17 | 2017-06-16 | 中国第汽车股份有限公司 | A kind of automobile instrument automatization test system and method for testing based on machine vision |
Non-Patent Citations (3)
| Title |
|---|
| 徐超 等: "基于距离变换的新型骨架提取方法", 《仪器仪表学报》 * |
| 朱柏林 等: "基于ORB和改进Hough变换的指针仪表智能识读方法", 《仪表技术与传感器》 * |
| 金京犬 等: "基于嵌入式ARM的指针式仪表读数的识别研究", 《南京师范大学学报(工程技术版)》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110059529A (en) * | 2017-12-13 | 2019-07-26 | 台达电子工业股份有限公司 | The recognition methods and its image capturing equipment of the direction of the pointer of analog measurement device |
| CN109977725A (en) * | 2017-12-27 | 2019-07-05 | 中移物联网有限公司 | A kind of water meter reading method and system |
| CN109977725B (en) * | 2017-12-27 | 2023-10-31 | 中移物联网有限公司 | Water meter reading method and system |
| CN108827530A (en) * | 2018-03-13 | 2018-11-16 | 安徽瑞鑫自动化仪表有限公司 | A kind of pressure gauge remote data automation acquisition system |
| CN108827101A (en) * | 2018-08-17 | 2018-11-16 | 上海盛染智能科技有限公司 | Part circumference runout error automatic detection device and method |
| CN110929716B (en) * | 2019-11-29 | 2022-07-15 | 航天科技控股集团股份有限公司 | Pointer capture-based instrument panel center determination method and system |
| CN110929716A (en) * | 2019-11-29 | 2020-03-27 | 航天科技控股集团股份有限公司 | Pointer capture-based instrument panel center determination method and system |
| CN112001379A (en) * | 2020-05-19 | 2020-11-27 | 西安工程大学 | Correction algorithm of automobile instrument fixed viewpoint reading instrument based on machine vision |
| CN112051003A (en) * | 2020-09-10 | 2020-12-08 | 中国科学院自动化研究所 | Automatic product detection device, detection method and reading method for hydraulic meter |
| CN112051003B (en) * | 2020-09-10 | 2021-09-14 | 中国科学院自动化研究所 | Automatic product detection device, detection method and reading method for hydraulic meter |
| CN112257676B (en) * | 2020-11-19 | 2023-10-24 | 南京天创电子技术有限公司 | Pointer type instrument reading method and system and inspection robot |
| CN112257676A (en) * | 2020-11-19 | 2021-01-22 | 南京天创电子技术有限公司 | Pointer instrument reading method and system and inspection robot |
| CN112668578A (en) * | 2020-12-31 | 2021-04-16 | 中广核研究院有限公司 | Pointer instrument reading method and device, computer equipment and storage medium |
| CN112668578B (en) * | 2020-12-31 | 2023-11-07 | 中广核研究院有限公司 | Pointer type instrument reading method, pointer type instrument reading device, computer equipment and storage medium |
| CN113792727A (en) * | 2021-07-30 | 2021-12-14 | 华能大理风力发电有限公司 | Reading estimation method, device and system based on pointer instrument video image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107463931A (en) | A kind of real-time pointer instrument reading method and device based on ARM platforms | |
| CN102176228B (en) | Machine vision method for identifying dial plate information of multi-pointer instrument | |
| CN104102912A (en) | Sub-item metering energy consumption data collection device based on video image identification and method thereof | |
| CN110378865A (en) | A kind of greasy weather visibility intelligence hierarchical identification method and system under complex background | |
| CN112837290A (en) | Crack image automatic identification method based on seed filling algorithm | |
| CN106682665B (en) | Seven-segment type digital display instrument number identification method based on computer vision | |
| CN106599890B (en) | digital instrument recognition algorithm for substation inspection robot | |
| CN105093167B (en) | Outdoor electrical energy meter fault automatic gauging terminal | |
| CN115019158B (en) | Image recognition-based marine pollution area recognition method and system | |
| CN108334815A (en) | Method for inspecting, on off state recognition methods and the system of second power equipment | |
| CN105182274A (en) | Automatic outdoor electric energy meter fault detection method | |
| CN107264570B (en) | Steel rail light band distribution detecting device and method | |
| CN112365475A (en) | Power transmission line icing monitoring method and system based on image processing mode | |
| Jin et al. | A Smart Water Metering System Based on Image Recognition and Narrowband Internet of Things. | |
| CN110287967B (en) | Image-based digit and mechanical watch digit identification method | |
| CN111339927A (en) | Intelligent work state identification system for personnel in electric power business hall | |
| CN112906602B (en) | Automatic identification device and identification method for electric quantity meter of power distribution cabinet based on image processing | |
| CN114627461A (en) | Method and system for high-precision identification of water gauge data based on artificial intelligence | |
| CN114417981A (en) | Intelligent river length patrol system | |
| CN114418970A (en) | Haze distribution and aerosol optical thickness detection method and device based on satellite remote sensing | |
| CN116385735B (en) | Water level measurement method based on image recognition | |
| CN110135274B (en) | Face recognition-based people flow statistics method | |
| CN111767826A (en) | Timing fixed-point scene abnormity detection method | |
| CN110719445A (en) | Remote meter reading system and method based on image recognition | |
| CN116225070A (en) | Environment monitoring method and system based on unmanned aerial vehicle automatic patrol |
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 | ||
| CB02 | Change of applicant information |
Address after: 100031 West Chang'an Avenue, Xicheng District, Xicheng District, Beijing Applicant after: State Grid Corporation of China Applicant after: Electric Power Research Institute, State Grid Fujian Electric Power Co., Ltd. Applicant after: NARI Group Co. Ltd. Address before: 100031 West Chang'an Avenue, Xicheng District, Xicheng District, Beijing Applicant before: State Grid Corporation of China Applicant before: Electric Power Research Institute, State Grid Fujian Electric Power Co., Ltd. Applicant before: Nanjing Nari Co., Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171212 |
|
| RJ01 | Rejection of invention patent application after publication |