CN106101618A - Field apparatus video frequency monitoring method based on image recognition - Google Patents

Field apparatus video frequency monitoring method based on image recognition Download PDF

Info

Publication number
CN106101618A
CN106101618A CN201610427877.8A CN201610427877A CN106101618A CN 106101618 A CN106101618 A CN 106101618A CN 201610427877 A CN201610427877 A CN 201610427877A CN 106101618 A CN106101618 A CN 106101618A
Authority
CN
China
Prior art keywords
monitoring
real
equipment
video
monitored
Prior art date
Application number
CN201610427877.8A
Other languages
Chinese (zh)
Inventor
张正林
董红军
粟闯
许家伟
农国武
Original Assignee
中国铝业股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 中国铝业股份有限公司 filed Critical 中国铝业股份有限公司
Priority to CN201610427877.8A priority Critical patent/CN106101618A/en
Publication of CN106101618A publication Critical patent/CN106101618A/en

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
    • G06K9/00771Recognising scenes under surveillance, e.g. with Markovian modelling of scene activity
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N7/00Television systems
    • H04N7/18Closed circuit television systems, i.e. systems in which the signal is not broadcast
    • H04N7/181Closed circuit television systems, i.e. systems in which the signal is not broadcast for receiving images from a plurality of remote sources

Abstract

The present invention provides a kind of field apparatus video frequency monitoring method based on image recognition: A, each monitoring camera duty to monitored object carries out video monitoring, and by video information transmission to control centre;B, control centre are preset with the feature samples of the monitored object that is stored with and the property data base of parameter, the backup database storing the result of the video information that each monitoring camera sends and control centre;Control centre carries out picture catching according to the interval setting and obtains each image information, obtain each real-time characteristic data after feature extraction identification is carried out to each image information and contrast with feature samples, if there is real-time characteristic data and the unmatched situation of feature samples, then the transmission of corresponding monitored object information, real-time characteristic data and mismatch case is carried out alarm indication to display centre.This monitoring method overcomes the defect that prior art monitoring is single, unified management is difficult, have monitoring comprehensively, manage feature easily.

Description

Field apparatus video frequency monitoring method based on image recognition

Technical field

The present invention relates to on-site supervision field, be specifically related to a kind of field apparatus video monitoring side based on image recognition Method.

Background technology

Video monitoring is widely used in the monitoring system in industry-by-industry, and video monitoring system is the production side of bringing Just, as under some more rugged environment, video can substitute for manpower to carry out monitoring control;Video will not produce what people occurred The physiological defects such as visual fatigue;Camera can carry out multi-angle Synchronous observation etc.;Video monitoring is to ensure that having of production safety Power is supplemented.

Digital image processing techniques are a kind of advanced meanses that production information gathers, achieved with significant progress, such as car plate Identification, Face datection, Meter recognition, financial document recognition etc. are the hot topics of current research and application, but by video monitoring Monitor at plant site with image automatic identification connected applications, promote that production of intelligent admin instance is few.

Workshop monitors referent wide variety, and required collection information ownership is not clear, video monitoring and management connection Dynamic property is not strong, production automation monitoring level to be improved, and needs to utilize new method to realize monitoring and management integration.

Content of the invention

It is desirable to provide a kind of field apparatus video frequency monitoring method based on image recognition, this monitoring method overcomes existing Have the defect that technology monitoring is single, unified management is difficult, have monitoring comprehensively, manage feature easily.

Technical scheme is as follows: a kind of field apparatus video frequency monitoring method based on image recognition, including following Step:

A, each monitoring camera carry out video monitoring to monitored object equipment, the duty of monitoring device, each prison Control camera by video information transmission to control centre;

B, control centre are preset with property data base, backup database, and described property data base is stored with monitored object Feature samples and parameter, the video information that the described each monitoring camera of Backup Data library storage is sent and the place of control centre Reason result;Control centre carries out picture catching to the real-time video information from each monitoring camera, the interval according to setting Obtain each image information, after feature extraction identification is carried out to each image information, obtain each real-time characteristic data, by each in real time Characteristic contrasts with feature samples, if there is real-time characteristic data and the unmatched situation of feature samples, then by right Monitored object information, real-time characteristic data and the mismatch case transmission answered carry out alarm indication to display centre;

Preferably, described monitored object equipment include device signal lamp, equipment indicating lamp, digital instrument, pointer meters, Perspective container, facility switching, equipment profile.

Preferably, the described instrument digital in step B, pointer meters, facility switching, equipment profile image information Feature extraction identification process include: utilize grayscale mathematical morphology image information is carried out positioning with region divide, utilize corruption Erosion computing carries out denoising, utilizes dilation operation to carry out edge enhancement afterwards.

Preferably, described erosion operation and dilation operation particularly as follows: utilize grayscale mathematical morphology computing, if f (x, y) For input picture, (x, y) is structural element to b, defines respectively with erosion operation and dilation operation to input picture for the structural element b For:

( f ⊗ b ) ( s , t ) = m i n { f ( s + x , t + y ) + b ( x , y ) | ( s + x , t + y ) ∈ D f , x ∈ D b }

( f ⊗ b ) ( s , t ) = max { f ( s - x , t - y ) + b ( x , y ) | ( s - x , t - y ) ∈ D f , x ∈ D b }

Df, DbIt is the definition territory of f and b respectively;(s t) represents x, y direction pixel coordinate value;Min for taking minimum value function, Max is for taking max function;

Carrying out opening operation with b to f, it is defined as:

The effect of opening operation is to remove little grain noise, disconnects adhesion between object, the border of smooth larger object, But and inconspicuous its area of change.

Preferably, in described step B, the feature samples of characteristic library storage monitored object is just including device signal lamp Color under normal state, the color under equipment indicating lamp normal condition, the digital instrument reading of normal range (NR), the finger of pointer meters Equipment profile under pin reading, the liquid level readings of perspective container, normal condition.

Preferably, the real-time characteristic data described in step B include that the color of real-time device signal lamp image, equipment refer to Show that the color of lamp image, the reading value of digital instrument, the total indicator reading of pointer meters, the liquid level readings of perspective container, equipment are opened Close is turned on and off state, equipment profile.

Preferably, the unmatched situation in described step B refers to:

For the characteristic of device signal lamp or equipment indicating lamp, its corresponding color characteristic and corresponding normal condition Under color inconsistent;

For the characteristic of digital instrument or pointer meters or the liquid level of perspective container, the reading of its digital instrument or refer to The liquid level readings of the total indicator reading of pin instrument or perspective container exceeds normal range (NR);

For the characteristic of facility switching, the open and close state of facility switching is corresponding with under facility switching normal condition Open and close state is inconsistent;

For the characteristic of equipment profile, its equipment profile exceeds the equipment profile model under normal condition Enclose.

Field apparatus of the present invention monitoring method carries out real time image collection to monitored object, is unified by control centre Image procossing, is contrasted by identifying, obtains different classes of monitored object feature and corresponding state or numerical value, basis further Sample information of all categories carries out abnormal judgement respectively, and then carries out showing according to judged result and report to the police;The monitoring setting is right As species is many so that monitor more fully, in covering workshop it may happen that the equipment of exception and region;Further, normal shape is preset Judgement parameter under state so that the judgement of abnormality is simpler directly, accelerates deterministic process, improves the real-time of system, Guarantee to report to the police the abnormal conditions occurring in time.

Brief description

The field apparatus video frequency monitoring method flow chart based on image recognition that Fig. 1 provides for the present invention.

Detailed description of the invention

Illustrate the present invention with embodiment below in conjunction with the accompanying drawings.

Embodiment 1

As it is shown in figure 1, the field apparatus video frequency monitoring method based on image recognition that the present embodiment provides comprises the following steps:

A, each monitoring camera carry out video monitoring to monitored object equipment, the duty of monitoring device, each prison Control camera by video information transmission to control centre;

B, control centre are preset with property data base, backup database, and described property data base is stored with monitored object Feature samples and parameter, the video information that the described each monitoring camera of Backup Data library storage is sent and the place of control centre Reason result;Control centre carries out picture catching to the real-time video information from each monitoring camera, the interval according to setting Obtain each image information, after feature extraction identification is carried out to each image information, obtain each real-time characteristic data, by each in real time Characteristic contrasts with feature samples, if there is real-time characteristic data and the unmatched situation of feature samples, then by right Monitored object information, real-time characteristic data and the mismatch case transmission answered carry out alarm indication to display centre;

Described monitored object equipment includes device signal lamp, equipment indicating lamp, facility switching, digital instrument, pointer instrument Table, equipment profile;

In described step B, the feature samples of characteristic library storage monitored object includes under device signal lamp normal condition Color, the color under equipment indicating lamp normal condition, the digital instrument reading of normal range (NR), pointer meters total indicator reading, Equipment profile model under corresponding open and close state under the perspective liquid level readings of container, facility switching normal condition, normal condition Enclose;

Real-time characteristic data described in step B include the color of real-time device signal lamp image, equipment indicating lamp figure The color of picture, the reading value of digital instrument, the total indicator reading of pointer meters, the perspective liquid level readings of container, the opening of facility switching, Closed state, equipment profile;

The described instrument digital in step B, pointer meters, facility switching, the feature of equipment profile image information Extract identification process to include: utilize grayscale mathematical morphology to carry out positioning to image information and divide with region, utilize erosion operation Carry out denoising, utilize dilation operation to carry out edge enhancement afterwards.

Preferably, described erosion operation and dilation operation particularly as follows: utilize grayscale mathematical morphology computing, if f (x, y) For input picture, (x, y) is structural element to b, defines respectively with erosion operation and dilation operation to input picture for the structural element b For:

( f ⊗ b ) ( s , t ) = m i n { f ( s + x , t + y ) + b ( x , y ) | ( s + x , t + y ) ∈ D f , x ∈ D b }

( f ⊗ b ) ( s , t ) = max { f ( s - x , t - y ) + b ( x , y ) | ( s - x , t - y ) ∈ D f , x ∈ D b }

Df, DbIt is the definition territory of f and b respectively;(s t) represents x, y direction pixel coordinate value;Min for taking minimum value function, Max is for taking max function;

Carrying out opening operation with b to f, it is defined as:

Claims (7)

1. the field apparatus video frequency monitoring method based on image recognition, it is characterised in that comprise the following steps:
A, each monitoring camera carry out video monitoring to monitored object equipment, the duty of monitoring device, and each monitoring is taken the photograph As head by video information transmission to control centre;
B, control centre are preset with property data base, backup database, and described property data base is stored with the spy of monitored object Levy sample and parameter, the process knot of the video information that the described each monitoring camera of Backup Data library storage is sent and control centre Really;Control centre, to the real-time video information from each monitoring camera, carries out picture catching according to the interval setting and obtains Each image information, obtains each real-time characteristic data after carrying out feature extraction identification to each image information, by each real-time characteristic Data contrast with feature samples, if there is real-time characteristic data and the unmatched situation of feature samples, then by corresponding Monitored object information, real-time characteristic data and mismatch case transmission carry out alarm indication to display centre.
2. the field apparatus video frequency monitoring method based on image recognition as claimed in claim 1, it is characterised in that:
Described monitored object equipment includes device signal lamp, equipment indicating lamp, digital instrument, pointer meters, perspective container, sets Standby switch, equipment profile.
3. the field apparatus video frequency monitoring method based on image recognition as claimed in claim 2, it is characterised in that:
The described instrument digital in step B, pointer meters, facility switching, the feature extraction of equipment profile image information Identification process includes: utilizes grayscale mathematical morphology to carry out positioning to image information and divides with region, utilizes erosion operation to carry out Denoising, utilizes dilation operation to carry out edge enhancement afterwards.
4. as claimed in claim 3 based on the field apparatus video frequency monitoring method of image recognition, it is characterised in that:
Described erosion operation and dilation operation particularly as follows: utilize grayscale mathematical morphology computing, if f (x, y) is input picture, B (x, y) is structural element, is respectively defined as with erosion operation and dilation operation to input picture for the structural element b:
( f ⊗ b ) ( s , t ) = min { f ( s + x , t + y ) + b ( x , y ) | ( s + x , t + y ) ∈ D f , x ∈ D b }
( f ⊕ b ) ( s , t ) = max { f ( s - x , t - y ) + b ( x , y ) | ( s - x , t - y ) ∈ D f , x ∈ D b }
Df, DbIt is the definition territory of f and b respectively;(s t) represents x, y direction pixel coordinate value;Min is for taking minimum value function, and max is Take max function;
Carrying out opening operation with b to f, it is defined as:
5. the field apparatus video frequency monitoring method based on image recognition as claimed in claim 2, it is characterised in that:
In described step B, the feature samples of characteristic library storage monitored object includes the face under device signal lamp normal condition Color under look, equipment indicating lamp normal condition, the digital instrument reading of normal range (NR), the total indicator reading of pointer meters, perspective Equipment profile under corresponding open and close state under the liquid level readings of container, facility switching normal condition, normal condition.
6. the field apparatus video frequency monitoring method based on image recognition as claimed in claim 5, it is characterised in that:
Real-time characteristic data described in step B include the color of real-time device signal lamp image, equipment indicating lamp image Color, the reading value of digital instrument, the total indicator reading of pointer meters, the liquid level readings of perspective container, the open and close shape of facility switching State, equipment profile.
7. the field apparatus video frequency monitoring method based on image recognition as claimed in claim 6, it is characterised in that:
Unmatched situation in described step B refers to:
For the characteristic of device signal lamp or equipment indicating lamp, its corresponding color and the color under corresponding normal condition Inconsistent;
For the characteristic of digital instrument or the liquid level of pointer meters or perspective container, the reading of its digital instrument or pointer instrument The liquid level readings of the total indicator reading of table or perspective container exceeds normal range (NR);
For the characteristic of facility switching, the open and close state of facility switching and corresponding open and close under facility switching normal condition State is inconsistent;
For the characteristic of equipment profile, its equipment profile exceeds the equipment profile under normal condition.
CN201610427877.8A 2016-06-16 2016-06-16 Field apparatus video frequency monitoring method based on image recognition CN106101618A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610427877.8A CN106101618A (en) 2016-06-16 2016-06-16 Field apparatus video frequency monitoring method based on image recognition

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610427877.8A CN106101618A (en) 2016-06-16 2016-06-16 Field apparatus video frequency monitoring method based on image recognition

Publications (1)

Publication Number Publication Date
CN106101618A true CN106101618A (en) 2016-11-09

Family

ID=57236318

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610427877.8A CN106101618A (en) 2016-06-16 2016-06-16 Field apparatus video frequency monitoring method based on image recognition

Country Status (1)

Country Link
CN (1) CN106101618A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106529497A (en) * 2016-11-25 2017-03-22 浙江大华技术股份有限公司 Image acquisition device positioning method and device
CN106961595A (en) * 2017-03-21 2017-07-18 深圳市科漫达智能管理科技有限公司 A kind of video frequency monitoring method and video monitoring system based on augmented reality
CN107103330A (en) * 2017-03-31 2017-08-29 深圳市浩远智能科技有限公司 A kind of LED status recognition methods and device
CN107807573A (en) * 2017-11-01 2018-03-16 炜呈智能电力科技(杭州)有限公司 River course lock station center monitoring method and computer-readable storage medium
CN107807572A (en) * 2017-11-01 2018-03-16 炜呈智能电力科技(杭州)有限公司 River course lock station machine room monitoring system
CN107820061A (en) * 2017-11-24 2018-03-20 合肥博焱智能科技有限公司 Intelligent monitor system based on FPGA
CN108520567A (en) * 2018-03-26 2018-09-11 云南电网有限责任公司丽江供电局 A kind of auxiliary method for inspecting identified by capture apparatus operation image
CN108520568A (en) * 2018-04-03 2018-09-11 武汉木科技有限公司 A kind of equipment indicating lamp positioning identifying method and device
CN109120922A (en) * 2018-09-27 2019-01-01 太仓太乙信息工程有限公司 A kind of camera condition monitoring system and its method
CN110996060A (en) * 2019-12-10 2020-04-10 安徽银河物联通信技术有限公司 Industrial automation intelligent linkage system and method

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101236603A (en) * 2008-02-28 2008-08-06 上海交通大学 Vehicle intelligent back vision method
CN101419663A (en) * 2008-06-05 2009-04-29 华中科技大学 Indicating light status real time monitor and identification method for power equipment fault indicator
KR20090118582A (en) * 2008-05-14 2009-11-18 주식회사 토페스 Unexpcted accident monitoring system
CN102412627A (en) * 2011-11-29 2012-04-11 安徽继远电网技术有限责任公司 Image identification-based intelligent transformer substation state monitoring system
CN104199453A (en) * 2014-09-27 2014-12-10 江苏华宏实业集团有限公司 Intelligent robot used for inspecting electric power meter
CN104994334A (en) * 2015-06-09 2015-10-21 海南电网有限责任公司 Automatic substation monitoring method based on real-time video
CN105530456A (en) * 2014-09-28 2016-04-27 深圳中兴力维技术有限公司 Method, device and system for substation monitoring

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101236603A (en) * 2008-02-28 2008-08-06 上海交通大学 Vehicle intelligent back vision method
KR20090118582A (en) * 2008-05-14 2009-11-18 주식회사 토페스 Unexpcted accident monitoring system
CN101419663A (en) * 2008-06-05 2009-04-29 华中科技大学 Indicating light status real time monitor and identification method for power equipment fault indicator
CN102412627A (en) * 2011-11-29 2012-04-11 安徽继远电网技术有限责任公司 Image identification-based intelligent transformer substation state monitoring system
CN104199453A (en) * 2014-09-27 2014-12-10 江苏华宏实业集团有限公司 Intelligent robot used for inspecting electric power meter
CN105530456A (en) * 2014-09-28 2016-04-27 深圳中兴力维技术有限公司 Method, device and system for substation monitoring
CN104994334A (en) * 2015-06-09 2015-10-21 海南电网有限责任公司 Automatic substation monitoring method based on real-time video

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106529497A (en) * 2016-11-25 2017-03-22 浙江大华技术股份有限公司 Image acquisition device positioning method and device
CN106961595A (en) * 2017-03-21 2017-07-18 深圳市科漫达智能管理科技有限公司 A kind of video frequency monitoring method and video monitoring system based on augmented reality
CN107103330A (en) * 2017-03-31 2017-08-29 深圳市浩远智能科技有限公司 A kind of LED status recognition methods and device
CN107807573A (en) * 2017-11-01 2018-03-16 炜呈智能电力科技(杭州)有限公司 River course lock station center monitoring method and computer-readable storage medium
CN107807572A (en) * 2017-11-01 2018-03-16 炜呈智能电力科技(杭州)有限公司 River course lock station machine room monitoring system
CN107820061A (en) * 2017-11-24 2018-03-20 合肥博焱智能科技有限公司 Intelligent monitor system based on FPGA
CN108520567A (en) * 2018-03-26 2018-09-11 云南电网有限责任公司丽江供电局 A kind of auxiliary method for inspecting identified by capture apparatus operation image
CN108520568A (en) * 2018-04-03 2018-09-11 武汉木科技有限公司 A kind of equipment indicating lamp positioning identifying method and device
CN109120922A (en) * 2018-09-27 2019-01-01 太仓太乙信息工程有限公司 A kind of camera condition monitoring system and its method
CN110996060A (en) * 2019-12-10 2020-04-10 安徽银河物联通信技术有限公司 Industrial automation intelligent linkage system and method

Similar Documents

Publication Publication Date Title
Romano et al. Automated detection of pipe bursts and other events in water distribution systems
US9734001B2 (en) Efficient health management, diagnosis and prognosis of a machine
Kanarachos et al. Detecting anomalies in time series data via a deep learning algorithm combining wavelets, neural networks and Hilbert transform
US9471057B2 (en) Method and system for position control based on automated defect detection feedback
JP4436042B2 (en) Anomaly detection system and method for teaching the same
Peitsman et al. Application of black-box models to HVAC systems for fault detection
CN101793501B (en) Transmission line ice coating status detection method based on image
US8868985B2 (en) Supervised fault learning using rule-generated samples for machine condition monitoring
Mounce et al. Burst detection using hydraulic data from water distribution systems with artificial neural networks
CN103901835A (en) Apparatus and methods to monitor and control cyclic process units in a steady plant environment
Fontugne et al. Strip, bind, and search: a method for identifying abnormal energy consumption in buildings
CN105301810A (en) Screen defect detecting method and screen defect detecting device
CA2748165C (en) System, method and computer program for pattern based intelligent control, monitoring and automation
CN102750535B (en) Method and system for automatically extracting image foreground
EP1818746A1 (en) Method of condition monitoring
CN103234976A (en) Warp knitting machine cloth flaw on-line visual inspection method based on Gabor transformation
CN105608479B (en) In conjunction with the anomaly detection method and system of depth data
CN104992449A (en) Information identification and surface defect on-line detection method based on machine visual sense
Sturman Multiple approaches to analyzing count data in studies of individual differences: The propensity for type I errors, illustrated with the case of absenteeism prediction
CN100454006C (en) Machine vision based LCD spot flaw detection method and system
CN102881010A (en) Method for evaluating perception sharpness of fused image based on human visual characteristics
CN105004737A (en) Self-adaption improved gradient information-based fruit surface defect detection method
JP2009070071A (en) Learning process abnormality diagnostic device and operator's judgement estimation result collecting device
BRPI0414557B1 (en) method and apparatus for inspecting a continuous sheet
JPH1145919A (en) Manufacture of semiconductor substrate

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into 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: 20161109