CN109005391A - A kind of camera moving method of detection failure - Google Patents
A kind of camera moving method of detection failure Download PDFInfo
- Publication number
- CN109005391A CN109005391A CN201811073327.6A CN201811073327A CN109005391A CN 109005391 A CN109005391 A CN 109005391A CN 201811073327 A CN201811073327 A CN 201811073327A CN 109005391 A CN109005391 A CN 109005391A
- Authority
- CN
- China
- Prior art keywords
- camera
- holder
- fault point
- detection failure
- easy fault
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N17/00—Diagnosis, testing or measuring for television systems or their details
- H04N17/002—Diagnosis, testing or measuring for television systems or their details for television cameras
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Studio Devices (AREA)
Abstract
The present invention relates to detection failure field, in particular to the camera moving method of a kind of detection failure.A kind of camera moving method of detection failure includes holder, camera and the end PC, and the camera frame is set on holder, and the camera is connect with the end PC, and the method includes establishing three-dimensional coordinate system；The coordinate of easy fault point is arranged, and presetting bit, the cruise route that multiple presetting bits are formed by connecting are learnt according to the coordinate of easy fault point, it cruises between point of invocation, holder is run repeatedly on the cruise line road of setting, and in the process of running, detection failure is carried out to easy fault point, and result is recorded.The problem of not only solving using the low efficiency for monitoring mechanical breakdown is manually garrisoned by machinery, a kind of camera moving method of detection failure of the invention, the problem of not only solving and utilize the problem of manually garrisoning by machinery the low efficiency for monitoring mechanical breakdown, and employee cannot be assisted to find out fault point in time.
Description
Technical field
The present invention relates to detection failure field, in particular to the camera moving method of a kind of detection failure.
Background technique
Since the 21th century, " people-oriented ", " energy conservation and environmental protection " idea be rooted in the hearts of the people, factory automation is proposed
New requirement.With computer technology, wireless technology, field bus technique, industrial Ethernet technology, IT technology, robot skill
The continuous development and innovation of the science and technology such as art, sensor technology and safe practice, factory automation experienced single machine certainly
Positive factory integrated automation is (also known as totally automatic after several important stages such as dynamicization, job-shop automation, full factory's centralized control
Change) development, i.e., combine process control, Supervised Control, product design, quality-monitoring, factory management etc. together, with existing
It is real for control theory, the theory of large scale system, artificial intelligence, 4C (Computer, Commu-Iieation, CRT, Contro1) technology
Existing optimal control, grading control, decentralised control, test automation, building automation, information processing and business decision are automatic
Change, to further increase working efficiency, guarantees quality and safety, energy saving and raw material.
As the degree of factory automation is deepened, garrisons compared to worker and monitored by machinery, pass through camera head monitor machine
The operation of tool equipment can undoubtedly reduce headcount, and improve working efficiency；Fixing camera monitors limited viewing angle, so through
Often need multi-angle of view that multiple cameras are set, there are great wastes, and multiple camera shooting overhead pass data volumes are big, and mutually generate
It influences, monitors employee's task amount weight；And present camera is used only for obtaining image, can do nothing to help employee and finds out failure in time
Point.
Summary of the invention
It is an object of the invention to: a kind of camera moving method of detection failure is provided, not only solves and utilizes people
Work garrisons by machinery the problem of low efficiency for monitoring mechanical breakdown, and multiple cameras need to be installed by also solving multi-angle of view monitoring
Problem, and the problem of employee cannot be assisted to find out fault point in time.
The technical solution adopted by the invention is as follows:
A kind of camera moving method of detection failure includes holder, camera and the end PC, and the camera frame is set to cloud
On platform, the camera is connect with the end PC, and described method includes following steps:
S1: using holder initial makeup location as origin, the three-dimensional coordinate system established using horizontal plane as benchmark plane；
S2: easy fault point coordinate is calculated according to three-dimensional coordinate system, and cloud is arranged according to the distributing position of easy fault point
The vertical range and horizontal movement range of platform；
S3: the acquisition of the presetting bit of holder is carried out according to easy fault point coordinate；
S4: by the residence time typing holder of presetting bit and each default position；
S5: the cruise route that multiple presetting bits are formed by connecting cruises between point of invocation, and holder is anti-on the cruise line road of setting
Multiple operation；
S6: judge to detect in holder operation easy fault point whether break down therefore, and record.
A kind of camera moving method of detection failure of the invention drives camera mobile by holder, reaches camera
The function that multi-angle flexibly detects reduces camera quantity, avoids multiple camera shooting overhead pass data volumes big, and mutually generates shadow
It rings, increases monitoring employee's task amount；Easy fault point is positioned by establishing three-dimensional coordinate system, makes the default position of holder
It is more convenient and accurate with motion profile setting；The residence time of each default position is set by holder, can not only reduce camera pair
The detection time of non-easy fault point, improves the efficiency of supervision, can also increase the residence time of easy fault point, facilitate behind employee
Transfer screen stream analyzing failure cause；And in being run repeatedly on the cruise line road of setting by camera, to easy fault point
Detection failure is carried out, and result is recorded.
Further, the method whether to break down easy fault point detected in holder operation for the judgement, including following
Step:
S6.1: fault signature database is established；
S6.2: establishing convolutional neural networks, learns to fault signature database；
S6.3: continuous two field pictures in the video flowing of camera are obtained；
S6.4: image recognition is carried out by the two field pictures that convolutional neural networks obtain S6.2.
By the fault signature typing fault signature database of easy fault point, the fault signature of easy fault point includes oil leak, seeps
Water, spark, stuck, component it is super away from etc., input terminal of the fault signature database as convolutional neural networks, for convolutional neural networks
Study, when camera is moved to easy fault point and stops by the preset residence time, the end PC is obtained in the video flowing of camera
Continuous two field pictures carry out fault signature identification to two field pictures by convolutional neural networks.
Further, the judgement detects the method whether to break down easy fault point in holder operation, including obtains
The two field pictures being spaced in the video flowing of camera apply to the component moved, two field pictures are compared, if two frames
The technical characteristic similarity of picture is greater than preset threshold, is judged as failure.
Further, the recording method of the S6 includes adjustment optical zoom multiple, when being judged as mechanical breakdown, the end PC hair
It send adjustment optical zoom multiple to instruct to camera, and then improves the optical zoom multiple of camera, which is carried out special
It writes, facilitates when transferring screen stream analyzing failure cause behind employee, clearly image is provided.
Further, the residence time of the prefabricated position includes a duty cycle of easy fault point, with each fault point
Residence time of the duty cycle as prefabricated position, the case where can accurately recording easy one duty cycle of fault point.
Further, the S3 obtains the view of camera the following steps are included: to each easy fault point progress multi-angle camera shooting
Picture in frequency stream, filters out optimal visual angle, records coordinate and is set as the presetting bit of holder, facilitates and transfer screen behind employee
When flowing analyzing failure cause, good visual angle is provided.
In conclusion by adopting the above-described technical solution, the beneficial effects of the present invention are:
1. a kind of camera moving method of detection failure of the invention drives camera mobile by holder, reach camera shooting
The function that head multi-angle flexibly detects, reduces camera quantity, avoids multiple camera shooting overhead pass data volumes big, and mutually generates
It influences, increases monitoring employee's task amount.
2. a kind of camera moving method of detection failure of the invention is by establishing three-dimensional coordinate system for easy failure
Point is positioned, and keeps the default position of holder and motion profile setting more convenient and accurate.
3. the residence time of each default position is arranged by holder for a kind of camera moving method of detection failure of the invention,
Camera can not only be reduced to the detection time of non-easy fault point, the efficiency of supervision is improved, stopping for easy fault point can also be increased
The time is stayed, facilitates and transfers screen stream analyzing failure cause behind employee.
4. a kind of camera moving method of detection failure of the invention is anti-on the cruise line road of setting by camera
In multiple operation, detection failure is carried out to easy fault point, and record to result.
Specific embodiment
All features disclosed in this specification or disclosed all methods or in the process the step of, in addition to mutually exclusive
Feature and/or step other than, can combine in any way.
Embodiment one:
A kind of camera moving method of detection failure includes holder, camera and the end PC, and the camera frame is set to cloud
On platform, the camera connect that described method includes following steps with the end PC:
S1: using holder initial makeup location as origin, the three-dimensional coordinate system established using horizontal plane as benchmark plane；
S2: easy fault point coordinate is calculated according to three-dimensional coordinate system, and cloud is arranged according to the distributing position of easy fault point
The vertical range and horizontal movement range of platform；
S3: the acquisition of the presetting bit of holder is carried out according to easy fault point coordinate；
S4: by the residence time typing holder of presetting bit and each default position；
S5: the cruise route that multiple presetting bits are formed by connecting cruises between point of invocation, and holder is anti-on the cruise line road of setting
Multiple operation；
S6: judge to detect in holder operation easy fault point whether break down therefore, and record.
A kind of camera moving method of detection failure of the invention drives camera mobile by holder, reaches camera
The function that multi-angle flexibly detects reduces camera quantity, avoids multiple camera shooting overhead pass data volumes big, and mutually generates shadow
It rings, increases monitoring employee's task amount；Easy fault point is positioned by establishing three-dimensional coordinate system, makes the default position of holder
It is more convenient and accurate with motion profile setting；The residence time of each default position is set by holder, can not only reduce camera pair
The detection time of non-easy fault point, improves the efficiency of supervision, can also increase the residence time of easy fault point, facilitate behind employee
Transfer screen stream analyzing failure cause；And in being run repeatedly on the cruise line road of setting by camera, to easy fault point
Detection failure is carried out, and result is recorded.
The course of work of the invention are as follows: established using holder initial makeup location as origin, using horizontal plane as benchmark plane
Three-dimensional coordinate system；The coordinate of easy fault point is calculated according to three-dimensional coordinate system, and establishes set, by X, the Y in set,
The maximum value of Z is sought, and according to the vertical range and horizontal movement range of the maximum value setting holder asked above, is reduced
The motion range of holder can reduce the time cycle of operation of holder；According to the coordinate for calculating easy fault point, calculates easy fault point and sit
Mark and the straight slope of origin institute, the position of the prefabricated position of holder is sought according to the coordinate of slope and easy fault point；By prefabricated position
With the residence time typing holder of each default position；The cruise route that multiple presetting bits are formed by connecting cruises between point of invocation, and holder exists
The cruise line road of setting is run repeatedly, and in the process of running, carries out detection failure to easy fault point, and carry out to result
Record.
Embodiment two: the present embodiment on the basis of the above embodiments, further, visit in holder operation by the judgement
Survey the method whether easy fault point breaks down, comprising the following steps:
S6.1: fault signature database is established；
S6.2: establishing convolutional neural networks, learns to fault signature database；
S6.3: continuous two field pictures in the video flowing of camera are obtained；
S6.4: image recognition is carried out by the two field pictures that convolutional neural networks obtain S6.2.
By the fault signature typing fault signature database of easy fault point, the fault signature of easy fault point includes oil leak, seeps
Water, spark, stuck, component it is super away from etc., input terminal of the fault signature database as convolutional neural networks, for convolutional neural networks
Study, when camera is moved to easy fault point and stops by the preset residence time, the end PC is obtained in the video flowing of camera
Continuous two field pictures carry out fault signature identification to two field pictures by convolutional neural networks.
Embodiment three: on the basis of the above embodiments, the judgement detects easy failure in holder operation to the present embodiment
The method that whether breaks down of point, the two field pictures being spaced in the video flowing including obtaining camera apply to be moved
Component compares two field pictures, if the technical characteristic similarity of two frame pictures is greater than preset threshold, is judged as failure.Institute
The recording method for stating S6 includes adjustment optical zoom multiple, and when being judged as mechanical breakdown, the end PC sends adjustment optical zoom multiple
It instructs to camera, and then improves the optical zoom multiple of camera, feature is carried out to the fault point, facilitates and is transferred behind employee
When screen stream analyzing failure cause, clearly image is provided.The residence time of the prefabricated position includes a work of easy fault point
Make the period, using the duty cycle of each fault point as the residence time of prefabricated position, can accurately record the work of easy fault point one
The case where making the period.The S3 obtains the video flowing of camera the following steps are included: to each easy fault point progress multi-angle camera shooting
In picture, filter out optimal visual angle, record coordinate and be set as the presetting bit of holder, facilitate and transfer screen flow point behind employee
When analysing failure cause, good visual angle is provided.
The above, only the preferred embodiment of the present invention, but scope of protection of the present invention is not limited thereto, it is any
Those skilled in the art within the technical scope disclosed by the invention, can without the variation that creative work is expected or
Replacement, should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be limited with claims
Subject to fixed protection scope.
Claims (6)
1. a kind of camera moving method of detection failure, including holder, camera and the end PC, the camera frame is set to holder
On, the camera is connect with the end PC it is characterized by: described method includes following steps:
S1: using holder initial makeup location as origin, the three-dimensional coordinate system established using horizontal plane as benchmark plane；
S2: easy fault point coordinate is calculated according to three-dimensional coordinate system, and holder is arranged according to the distributing position of easy fault point
Vertical range and horizontal movement range；
S3: the acquisition of the presetting bit of holder is carried out according to easy fault point coordinate；
S4: by the residence time typing holder of presetting bit and each default position；
S5: the cruise route that multiple presetting bits are formed by connecting cruises between point of invocation, and holder is transported repeatedly on the cruise line road of setting
Row；
S6: judge to detect in holder operation easy fault point whether break down therefore, and record.
2. a kind of camera moving method of detection failure according to claim 1, it is characterised in that: the judgement is in cloud
The method whether easy fault point breaks down is detected in platform operation, comprising the following steps:
S6.1: fault signature database is established；
S6.2: establishing convolutional neural networks, learns to fault signature database；
S6.3: continuous two field pictures in the video flowing of camera are obtained；
S6.4: image recognition is carried out by the two field pictures that convolutional neural networks obtain S6.2.
3. a kind of camera moving method of detection failure according to claim 1 or 2, it is characterised in that: the judgement
The method whether to break down easy fault point is detected in holder operation, two frames being spaced in the video flowing including obtaining camera
Image compares two field pictures.
4. a kind of camera moving method of detection failure according to claim 1, it is characterised in that: the record of the S6
Method includes adjustment optical zoom multiple.
5. a kind of camera moving method of detection failure according to claim 1, it is characterised in that: the prefabricated position
Residence time includes a duty cycle of easy fault point.
6. a kind of camera moving method of detection failure according to claim 1, it is characterised in that: the S2 include with
Lower step: carrying out multi-angle camera shooting to each easy fault point, obtain the picture in the video flowing of camera, filter out optimal visual angle,
Record coordinate and the presetting bit for being set as holder.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811073327.6A CN109005391A (en) | 2018-09-14 | 2018-09-14 | A kind of camera moving method of detection failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811073327.6A CN109005391A (en) | 2018-09-14 | 2018-09-14 | A kind of camera moving method of detection failure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109005391A true CN109005391A (en) | 2018-12-14 |
Family
ID=64591482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811073327.6A Pending CN109005391A (en) | 2018-09-14 | 2018-09-14 | A kind of camera moving method of detection failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109005391A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080607A (en) * | 2019-12-12 | 2020-04-28 | 哈尔滨市科佳通用机电股份有限公司 | Rolling bearing oil slinging fault detection method based on image recognition |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101205265B1 (en) * | 2012-08-10 | 2012-11-27 | 주식회사 명품 코리아 | Monitoring Camera System Having Fault Diagnosis Functionality |
| CN102866712A (en) * | 2012-09-07 | 2013-01-09 | 安科智慧城市技术（中国）有限公司 | Method and system for realizing automatic cruise of pan-tilts |
| CN107590834A (en) * | 2017-08-10 | 2018-01-16 | 北京博思廷科技有限公司 | A kind of road traffic accident video detecting method and system |
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN108366229A (en) * | 2018-02-11 | 2018-08-03 | 北京鲁能物业服务有限责任公司 | A kind of pointing device intelligence method for inspecting |
-
2018
- 2018-09-14 CN CN201811073327.6A patent/CN109005391A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101205265B1 (en) * | 2012-08-10 | 2012-11-27 | 주식회사 명품 코리아 | Monitoring Camera System Having Fault Diagnosis Functionality |
| CN102866712A (en) * | 2012-09-07 | 2013-01-09 | 安科智慧城市技术（中国）有限公司 | Method and system for realizing automatic cruise of pan-tilts |
| CN107590834A (en) * | 2017-08-10 | 2018-01-16 | 北京博思廷科技有限公司 | A kind of road traffic accident video detecting method and system |
| CN107680195A (en) * | 2017-11-13 | 2018-02-09 | 国网内蒙古东部电力有限公司 | A kind of transformer station intelligent robot inspection Computer Aided Analysis System and method |
| CN108366229A (en) * | 2018-02-11 | 2018-08-03 | 北京鲁能物业服务有限责任公司 | A kind of pointing device intelligence method for inspecting |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111080607A (en) * | 2019-12-12 | 2020-04-28 | 哈尔滨市科佳通用机电股份有限公司 | Rolling bearing oil slinging fault detection method based on image recognition |
| CN111080607B (en) * | 2019-12-12 | 2020-10-09 | 哈尔滨市科佳通用机电股份有限公司 | Rolling bearing oil slinging fault detection method based on image recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chauhan et al. | A comparative study of machine vision based methods for fault detection in an automated assembly machine | |
| CN112871703B (en) | Intelligent management coal preparation platform and method thereof | |
| US9377778B2 (en) | Integration of manufacturing control functions using a multi-functional vision system | |
| CN109941700A (en) | Coal handling system Intelligent unattended cruising inspection system | |
| CN115941529B (en) | Cable tunnel detection method and system based on robot | |
| CN110238556B (en) | Real-time detection method for welding track in welding process of welding robot | |
| CN112934518A (en) | Automatic spraying device and method based on point cloud | |
| CN110912976A (en) | Railway construction equipment remote monitoring system | |
| CN117671814B (en) | AIoT technology-based space visual night patrol method and system | |
| CN113592326A (en) | Remote intelligent monitoring system suitable for wisdom mill | |
| CN111932711A (en) | Intelligent inspection system and method for coal conveying belt of thermal power generating unit | |
| CN109005391A (en) | A kind of camera moving method of detection failure | |
| CN115527158A (en) | Method and device for detecting abnormal behaviors of personnel based on video monitoring | |
| CN106454278A (en) | Fault detection method and device of downhole control system | |
| CN117784668A (en) | Flour production line processing safety intelligent supervision system based on data analysis | |
| Wang | Cyber manufacturing: research and applications | |
| CN108062750A (en) | A kind of intelligence machine vision ore particles detecting system | |
| CN115937415A (en) | Continuous casting robot digital twin system based on 3D modeling technology | |
| KR101989461B1 (en) | Safety system and Method for Robot working environment using vision system | |
| Mondal et al. | Moving object detection for event-based vision using k-means clustering | |
| CN113570580B (en) | Power equipment component loosening identification system and method based on machine vision | |
| CN206370904U (en) | A kind of remote on-line monitoring robot system | |
| CN113487166A (en) | Chemical fiber floating filament quality detection method and system based on convolutional neural network | |
| CN116969148A (en) | Multi-dimensional linkage monitoring and processing method and system for faults of adhesive tape machine | |
| CN113743214B (en) | Intelligent cradle head camera |
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 |
Application publication date: 20181214 |
|
| RJ01 | Rejection of invention patent application after publication |