CN106970581B - A kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group - Google Patents
A kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group Download PDFInfo
- Publication number
- CN106970581B CN106970581B CN201710299446.2A CN201710299446A CN106970581B CN 106970581 B CN106970581 B CN 106970581B CN 201710299446 A CN201710299446 A CN 201710299446A CN 106970581 B CN106970581 B CN 106970581B
- Authority
- CN
- China
- Prior art keywords
- pantograph
- train
- unmanned plane
- monitoring unit
- detection device
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/048—Monitoring; Safety
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/08—Indexing scheme for image data processing or generation, in general involving all processing steps from image acquisition to 3D model generation
Abstract
The invention discloses a kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group, this method carries out comprehensive detection to pantograph by introducing unmanned plane pantograph detection device, fully utilize the mobility of unmanned aerial vehicle platform, active fast searching train pantograph to be checked is simultaneously tracked, and ensure that controllability and accuracy to train pantograph to be checked detection；Using multigroup unmanned plane can working space different zones simultaneously work the characteristics of, worked by multi-set parallel to improve the efficiency of work, make up the deficiency of single group unmanned plane detectability, realized simultaneously by different angle scanning of the unmanned aerial vehicle group to pantograph to pantograph three-dimensional reconstruction, realize the full visual angle detection in real time to train pantograph state and " visual angle blind zone " of pantograph monitoring system and the check frequency of bow failure are avoided from technical scheme, the detection efficiency of abnormal problem can be effectively improved, this can significantly improve the operation safety of train.
Description
Technical field
The invention belongs to railway track detection field, more particularly to a kind of train based on the three-dimensional full visual angle of unmanned aerial vehicle group by
Pantograph real-time intelligent monitoring method and system.
Background technology
Pantograph-OCS system is the key components in electrified railway power supply system, by Traction networks electrical energy transportation to electric power machine
Car.Due to severe working environment, pantograph --- complicated mechanical, electric reciprocal effect effect between contact net be present, its
Fault rate is higher always, has a strong impact on the safe operation of electric railway.Railway relevant departments need timing to pantograph, power network
Strict detection is carried out to reduce the generation of electric locomotive accident.According to statistics, railway accident caused by tractive power supply system failure
28.8%, 40.4%, the 29.6% of total number of accident then was accounted for respectively, in 2008 in 2009 in 2010.Pantograph-OCS system
Quality has turned into speed-raising, has improved an important factor for operation reliability.
At present, newly make and bow net real-time dynamic monitoring system has been installed on EMUs, on the EMUs vehicle runed
Also this system is installed additional successively.The system is installed on car body top, and real time image collection work is carried out to pantograph working condition, and
By illuminating device for supplying feed the light source of data acquisition, level and the pitching to camera body are realized by head
Regulation, to realize to the real-time monitoring of pantograph, the video data aided in and analysis are provided to handle pantograph and catenary fault with car machinist
Image, to take measures or repair in time to ensure traffic safety.
Pantograph most common failure has the abrasion of slide plate bar, bow net arcing, slide plate eccentric wear, scrapes bow, porcelain vase failure, pantograph part
Damage etc..Online bow net dynamic detection system is because fixed installation site and camera visual angle are limited, only from a direction
Visual angle pantograph is monitored, can not accomplish to the above-mentioned most common failure of pantograph carry out complete detection, it is complete to pantograph
Orientation detection lacks effective means.
The content of the invention
The invention provides a kind of train pantograph real-time intelligent monitoring method based on the three-dimensional full visual angle of unmanned aerial vehicle group and
System, it is intended that overcome in the prior art, because fixed installation site and camera visual angle are limited, existing bow net
The problem of real-time dynamic monitoring system can not carry out complete detection to most common failure.
A kind of train pantograph real-time intelligent monitoring method based on the three-dimensional full visual angle of unmanned aerial vehicle group, comprises the following steps：
Step 1：Railroad track is equidistantly divided, each track section is provided with monitoring unit, and each monitoring is single
Member is configured with 3 groups of unmanned plane pantograph detection devices, and is communicated with remote master center；
The unmanned plane pantograph detection device includes flight instruments and the Kinect being loaded on flight instruments sensings
Device array, speed tester for vehicle train and unmanned plane wireless communication module；
Step 2：When monitoring unit receives detection instruction, and train to be checked enters monitoring unit place track section,
3 groups of unmanned plane pantograph detection devices of monitoring unit configuration are taken off, and synchronized tracking train to be checked；
During 3 groups of unmanned plane pantograph detection device synchronized trackings train to be checked, geo-stationary is kept with train to be checked, and point
Not Wei Yu train pantograph top position point to be checked and both sides location point；
Using 3 groups of unmanned planes can working space different zones (3 groups of unmanned plane pantograph detection devices respectively by
Above pantograph, front and back work, the i.e. working space of unmanned plane) while the characteristics of work, pantograph device is carried out complete
Visual angle is scanned, and carries out three-dimensional reconstruction using the pantograph image in the respective stop position point direction obtained, realizes pantograph
Full visual angle detection.
Step 3：Utilize the airborne Kinect sensor array scanning pantograph figure of each unmanned plane pantograph detection device
Picture, and it is sent to affiliated monitoring unit；
Step 4：Monitoring unit carries out three-dimensional reconstruction to the pantograph image of reception, and the pantograph image after reconstruct is carried out
Three-dimensional feature is extracted, and using the feature recognition pantograph state of extraction, pantograph state is sent to far through monitoring unit in real time
Journey Master Control Center, complete the real-time detection of pantograph；
Three-dimensional reconstruction is carried out to pantograph image, three-dimensional feature extraction is carried out to the pantograph image after reconstruct, using carrying
The process of the feature recognition pantograph state taken is realized using existing algorithm；
Further, in 3 groups of unmanned plane pantograph detection device synchronized trackings train to be checked, above pantograph
Unmanned plane pantograph detection device is measured by airborne train speed's measuring instrument to train speed, and passes through radio communication
Module and other two groups of unmanned plane pantograph detection devices carry out short haul connection, 3 groups of unmanned plane pantograph detection devices according to
Train running speed and direction, follow method to keep formation flight using navigator, carry out Collaborative Control and pose adjustment.
The Collaborative Control and pose tune that 3 groups of unmanned plane pantograph detection devices follow method to carry out unmanned aerial vehicle group using navigating
Whole, Kinect sensor carries out three-dimensional all-directional Scanning Detction to pantograph, and the image information collected is wireless over long distances
Communication is sent to affiliated monitoring unit.Unmanned plane pantograph detection device 1 directly over pantograph is used as " pilotage people ", leads to
Cross the velocity information of locomotive velocity measuring measurement device train, in addition two groups of real-time survey calculations of unmanned plane pantograph detection device nobody
Machine and " pilotage people " distance and direction.Three groups of unmanned plane pantograph detection devices carry out short-distance wireless communication by bluetooth module
Position, velocity information and the train speed information of each group unmanned plane pantograph detection device are obtained, constantly adjusts itself flight
Speed and flight attitude, keep the relative position with train vehicle body.
Further, the line of centres of 3 groups of unmanned plane pantograph detection devices of geo-stationary is kept with train to be checked,
It is in isosceles triangle on the vertical plane of train；
The Kinect sensor array being loaded on flight instruments is made up of 3 Kinect sensors, by three
Kinect sensor is respectively placed in the midpoint on the upper bottom edge and two stringcourses of an isosceles trapezoid device, and isosceles trapezoid is wherein
Two interior angles are respectively 120 °, 60 °, and plane where isosceles trapezoid device is the vertical plane of train.
Further, when pantograph breaks down, monitoring unit sends pre-warning signal, and remote master center is according to early warning
Signal is scheduled to the train in corresponding section.
A kind of train pantograph real-time intelligent monitoring system based on the three-dimensional full visual angle of unmanned aerial vehicle group, including：
Monitoring unit, for being communicated with remote master center, unmanned plane pantograph detection device is controlled；
The monitoring unit is and each prison by equidistantly being divided, being arranged in track section to railroad track
Unit three groups of unmanned plane pantograph detection devices of management and control are controlled, including image capture module, picture recognition module and monitoring are wirelessly
Communication module, wherein, the vision signal that image capture module gathers to Kinect sensor is handled, picture recognition module pair
Signal after image capture module processing carries out three-dimensional reconstruction, feature extraction and pantograph state recognition successively；
The unmanned plane pantograph detection device includes flight instruments and the Kinect being loaded on flight instruments sensings
Device array, speed tester for vehicle train and unmanned plane wireless communication module；
Remote master center, for receiving the message of monitoring unit transmission, control instruction is sent to monitoring unit, and to row
Car is scheduled.
Further, it is additionally provided with LED light supplement lamp in the unmanned plane pantograph detection device.
LED light supplement lamp is used for the light filling operation of Kinect sensor under dark or night conditions.
Further, the Kinect sensor array being loaded on flight instruments is made up of 3 Kinect sensors,
The midpoint three Kinect sensors being respectively placed on the upper bottom edge and two stringcourses of an isosceles trapezoid device, isosceles trapezoid
Two of which interior angle be respectively 120 °, 60 °, plane where isosceles trapezoid device is the vertical plane of train.
By rearranging for 3 sensors, the vertical angle of view scope of each Kinect sensor is 60 °, by waiting
Each Kinect sensor vertical angle of view border overlay is realized in arrangement on waist ladder-shaped apparatus, is arranging Kinect sensor array
Car vertical direction realizes full visual angle non-blind area detection.
Beneficial effect
The invention provides a kind of train pantograph real-time intelligent monitoring method based on the three-dimensional full visual angle of unmanned aerial vehicle group and
System, this method carry out comprehensive detection to pantograph by introducing unmanned plane pantograph detection device, utilize unmanned aerial vehicle group
Carry Kinect sensor to scan pantograph different angle, and carry out pantograph three-dimensional reconstruction, realize to train pantograph shape
The full visual angle of state is detected in real time, is avoided from technical scheme " the monitoring blind area " of bow failure；Dexterously using multiple
Kinect sensor arrangement realizes Kinect in the full visual angle detection of vertical direction.Compared to traditional camera, the invention
Property carry out image acquisition, Kinect sensor fused images depth information from Kinect sensor, it is possible to achieve it is immediately dynamic
The functions such as state seizure, image identification, it is cheap in three-dimensional reconstruction correlation acquisition equipment.The system using it is multigroup nobody
Machine can working space different zones simultaneously work the characteristics of, worked by multi-set parallel to improve the efficiency of work, more
The deficiency of single group unmanned plane detectability is mended, while is realized by different angle scanning of the unmanned aerial vehicle group to pantograph to pantograph
Three-dimensional reconstruction, " visual angle blind zone " for the full visual angle of train pantograph state being detected and being reduced in real time pantograph monitoring is realized,
The detection efficiency of abnormal problem can be effectively improved, hence it is evident that improve the operation safety of train.
Brief description of the drawings
Fig. 1 is the flow chart of detection method of the present invention；
Fig. 2 is the structural representation of detecting system of the present invention；
Fig. 3 is unmanned aerial vehicle group position and attitude schematic diagram, wherein, (a) is top view, and (b) is side view.
Embodiment
Below in conjunction with drawings and examples, the present invention is described further.
As shown in figure 1, a kind of train pantograph real-time intelligent monitoring method based on the three-dimensional full visual angle of unmanned aerial vehicle group, including
Following steps：
Step 1：Railroad track is equidistantly divided, each track section is provided with monitoring unit, and each monitoring is single
Member is configured with 3 groups of unmanned plane pantograph detection devices, and is communicated with remote master center；
The unmanned plane pantograph detection device includes flight instruments and the Kinect being loaded on flight instruments sensings
Device array, speed tester for vehicle train and wireless communication module；
Wireless communication module communicates for unmanned plane pantograph detection device with the data of monitoring unit, while is used for nobody
Short haul connection between a group of planes, realize the Collaborative Control of unmanned aerial vehicle group.Locomotive velocity measuring device is to allow unmanned plane pantograph to detect
Device can measure the real time running speed of current running train, and UAV position and orientation is adjusted.
Step 2：When monitoring unit receives detection instruction, and train to be checked enters monitoring unit place track section,
3 groups of unmanned plane pantograph detection devices of monitoring unit configuration are taken off, and synchronized tracking train to be checked；
During 3 groups of unmanned plane pantograph detection device synchronized trackings train to be checked, geo-stationary is kept with train to be checked, and point
Not Wei Yu train pantograph top position point to be checked and both sides location point；As shown in figure 3, two location point positions of train both sides
In on the same longitudinal cross-section of pantograph that This train is bound for XXX.For the ease of distinguishing, by directly over train pantograph
Unmanned plane pantograph detection device is named as unmanned plane pantograph device 1, and the unmanned plane pantograph of train direction to the car is detected
Device is named as unmanned plane pantograph detection device 2, will be named positioned at the unmanned plane pantograph detection device that This train is bound for XXX
For unmanned plane pantograph detection device 3；
The Kinect sensor array being loaded on flight instruments is made up of 3 Kinect sensors, by three
Kinect sensor is respectively placed in the midpoint on the upper bottom edge and two stringcourses of an isosceles trapezoid device, and isosceles trapezoid is wherein
Two interior angles are respectively 120 °, 60 °, and plane where isosceles trapezoid device is the vertical plane of train.
By taking DSA250 type pantographs as an example, pantograph desin speed 250km/h, chopper bar position spread length about 2600mm, most
Big rising bow height (including insulator) 3000mm, bow length 1950mm.Kinect v2 sensors effective detection distance is 0.5-
4.5m, in order to ensure that train is safe for operation with unmanned plane, while improve accuracy of detection, R values 1.8-2.2m, H value distance by
Pantograph upper surface 0.5-1m.Kinect v2 sensor levels detection range is 70 °, and vertical detection range is 60 °.
In the horizontal direction, θ=2tan-1(1/2)=52.1 °, horizontal detection range is met.
In vertical direction, θ=2tan-1(1.5/2)=73.7 °, beyond vertical direction detection range.
Because pantograph structure is more complicated, each structure can block mutually, be difficult to obtain using single Kinect sensor
Pantograph vertical direction information.
The vertical angle of view scope of each Kinect sensor is 60 °, by 3 sensors rearrange realize it is each
Kinect sensor visual angle border overlay, Kinect sensor is set to realize full visual angle non-blind area detection in vertical direction.
In 3 groups of unmanned plane pantograph detection device synchronized trackings train to be checked, unmanned plane above pantograph by
Pantograph detection means is measured by vehicle-mounted train speed's measuring instrument to train speed, and by wireless communication module and separately
Outer two groups of unmanned plane pantograph detection devices carry out short haul connection, and 3 groups of unmanned plane pantograph detection devices are according to train driving
Speed and direction, follow method to keep formation flight using navigator, carry out Collaborative Control and pose adjustment.
The Collaborative Control and pose tune that 3 groups of unmanned plane pantograph detection devices follow method to carry out unmanned aerial vehicle group using navigating
Whole, Kinect sensor carries out three-dimensional all-directional Scanning Detction to pantograph, and the image information collected is wireless over long distances
Communication is sent to affiliated monitoring unit.Unmanned plane pantograph detection device 1 directly over pantograph is used as " pilotage people ", leads to
Cross the velocity information of locomotive velocity measuring measurement device train, in addition two groups of real-time survey calculations of unmanned plane pantograph detection device nobody
Machine and " pilotage people " distance and direction.Three groups of unmanned plane pantograph detection devices carry out short-distance wireless communication by bluetooth module
Position, velocity information and the train speed information of each group unmanned plane pantograph detection device are obtained, constantly adjusts itself flight
Speed and flight attitude, keep the relative position with train vehicle body.
Step 3：Pantograph image is scanned using the vehicle-mounted Kinect sensor of each unmanned plane pantograph detection device, and
It is sent to affiliated monitoring unit；
Step 4：Monitoring unit carries out three-dimensional reconstruction to the pantograph image of reception, and the pantograph image after reconstruct is carried out
Three-dimensional feature is extracted, and pantograph state is identified using the feature of extraction, pantograph state is passed through monitoring unit in real time
Remote master center is delivered to, completes the real-time detection of pantograph.
When pantograph breaks down, monitoring unit sends pre-warning signal, and remote master center is according to pre-warning signal to right
The train in section is answered to be scheduled.
The colour imagery shot and infrared camera for the Kinect device that 3 groups of unmanned plane pantograph detection devices pass through carrying point
Respective independent RGB image and depth image are not obtained.Due to the influence that Kinect device reason itself or measuring environment etc. are brought,
The depth image that Kinect video camera obtains would generally produce certain noise, and these noises can have to calculating below compared with
Big adverse effect, therefore carry out bilateral filtering denoising firstly the need of to original depth image.By the depth map of pretreatment
As having two-dimensional signal, the value of pixel is depth information, expression pantograph surface to the straight line between Kinect sensor away from
From.Then depth image is alignd by certain Coordinate Conversion with RGB image, eliminates and produced because two camera positions are different
Raw picture centre is inconsistent, calculates X, the Y-coordinate of measurement space point, finally that three dimensional point cloud (X, Y, Z, R, G, B) is logical
Cross PCL (Dian Yunku) displays.
The pixel of coloured image is expressed as (uR,vR,zR)T, uR,vR,zRThe abscissa of coloured image, ordinate are represented respectively
With the depth value under camera coordinates system；Similarly, the pixel of depth image is (uL,vL,zL)T, uL,vL,zLDepth is represented respectively
Depth value under the abscissa of image, ordinate and camera coordinates system, then depth map registration transformation matrix W' be：
Pantograph is scanned from different perspectives by three groups of unmanned plane pantograph detection devices, each group pantograph image
Between include certain common portion.In order to carry out three-dimensional reconstruction using depth image, it is necessary to analyze image, solve each
Transformation parameter between image.Using ICP algorithm (iterative closest point algorithm), on the basis of the common portion of pantograph, not
The multiple series of images cascade matching that same angle, illumination obtain calculates corresponding translation vector and rotation into unified coordinate system
Matrix, while eliminate redundancy.
By image denoising, coordinate transform, resurfacing, Three-dimensional Display process, three with texture information are ultimately generated
Dimension module.
As shown in Fig. 2 a kind of train pantograph real-time intelligent monitoring system based on the three-dimensional full visual angle of unmanned aerial vehicle group, bag
Include：
Monitoring unit, for being communicated with remote master center, unmanned plane pantograph detection device is controlled；
The monitoring unit is and each prison by equidistantly being divided, being arranged in track section to railroad track
Unit three groups of unmanned plane pantograph detection devices of management and control are controlled, including image capture module, picture recognition module and monitoring are wirelessly
Communication module, wherein, the vision signal that image capture module gathers to Kinect sensor is handled, picture recognition module pair
Signal after image capture module processing carries out three-dimensional reconstruction, feature extraction and pantograph state recognition successively；
The unmanned plane pantograph detection device includes flight instruments and the Kinect being loaded on flight instruments sensings
Device array, speed tester for vehicle train and unmanned plane wireless communication module；
LED light supplement lamp is additionally provided with the unmanned plane pantograph detection device, LED light supplement lamp is used for dark or night
Between under the conditions of Kinect sensor light filling operation.
Remote master center, for receiving the message of monitoring unit transmission, control instruction is sent to monitoring unit, and to row
Car is scheduled；
Remote master center includes warning module and memory module, wherein, memory module storage whole piece Along Railway is whole
In train license number/train position of inspection train and the firm information of pantograph of each monitoring unit of reception；Warning module, transported according to train
Row regulation rule provides train in section the alarm of appropriate level, is sent to the train operation control system in inspection failure train
Parking checking instruction etc..
It is responsible for storing the whole train license number/train position in inspection train of whole piece Along Railway in remote master center；It is real
When receive the bow failure information that the transmission of each monitoring unit comes, carry out Data Analysis Services, storage, display, printing；And according to
The information content takes timely and effectively measure, and according to train operation regulation rule, parking inspection is sent to train operation control system
Look into instruction etc..
The above embodiments are merely illustrative of the technical scheme of the present invention and are not intended to be limiting thereof, although with reference to above-described embodiment pair
The present invention is described in detail, those of ordinary skills in the art should understand that：Still can be to the specific of the present invention
Embodiment is modified or equivalent substitution, and without departing from any modification of spirit and scope of the invention or equivalent substitution,
It all should cover among scope of the presently claimed invention.
Claims (5)
- A kind of 1. train pantograph real-time intelligent monitoring method based on the three-dimensional full visual angle of unmanned aerial vehicle group, it is characterised in that including Following steps：Step 1：Railroad track is equidistantly divided, each track section is provided with monitoring unit, and each monitoring unit is matched somebody with somebody 3 groups of unmanned plane pantograph detection devices are equipped with, and are communicated with remote master center；The unmanned plane pantograph detection device includes flight instruments and the Kinect sensor battle array being loaded on flight instruments Row, speed tester for vehicle train and unmanned plane wireless communication module；Step 2：When monitoring unit receives detection instruction, and train to be checked enters monitoring unit place track section, the prison 3 groups of unmanned plane pantograph detection devices of control unit configuration are taken off, and synchronized tracking train to be checked；During 3 groups of unmanned plane pantograph detection device synchronized trackings train to be checked, geo-stationary, and position respectively are kept with train to be checked Location point in train pantograph top position point to be checked and both sides；Step 3：Using the airborne Kinect sensor array scanning pantograph image of each unmanned plane pantograph detection device, and It is sent to affiliated monitoring unit；Step 4：Monitoring unit carries out three-dimensional reconstruction to the pantograph image of reception, the pantograph image after reconstruct is carried out three-dimensional Feature extraction, using the feature recognition pantograph state of extraction, pantograph state is sent to long-range master through monitoring unit in real time Control center, complete the real-time detection of pantograph；The line of centres of 3 groups of unmanned plane pantograph detection devices of geo-stationary is kept with train to be checked, in the vertical flat of train It is in isosceles triangle on face；The Kinect sensor array being loaded on flight instruments is made up of 3 Kinect sensors, by three Kinect Sensor is respectively placed in the midpoint on the upper bottom edge and two stringcourses of an isosceles trapezoid device, in the two of which of isosceles trapezoid Angle is respectively 120 °, 60 °, and plane where isosceles trapezoid device is the vertical plane of train.
- 2. according to the method for claim 1, it is characterised in that treated in 3 groups of unmanned plane pantograph detection device synchronized trackings When examining train, the unmanned plane pantograph detection device above pantograph is by vehicle-mounted train speed's measuring instrument to train car Speed measures, and carries out short haul connection by wireless communication module and other two groups of unmanned plane pantograph detection devices, 3 groups Unmanned plane pantograph detection device follows method to keep formation flight, assisted according to train running speed and direction using navigator With control and pose adjustment.
- 3. according to the method for claim 2, it is characterised in that when pantograph breaks down, monitoring unit sends early warning Signal, remote master center are scheduled according to pre-warning signal to the train in corresponding section.
- A kind of 4. train pantograph real-time intelligent monitoring system based on the three-dimensional full visual angle of unmanned aerial vehicle group, it is characterised in that including：Monitoring unit, for being communicated with remote master center, unmanned plane pantograph detection device is controlled；The monitoring unit is by equidistantly being divided, being arranged in track section to railroad track, and each monitoring is single First three groups of unmanned plane pantograph detection devices of management and control, including image capture module, picture recognition module and monitoring wireless telecommunications Module, wherein, image capture module is handled the picture signal of Kinect sensor array acquisition, picture recognition module pair Signal after image capture module processing carries out three-dimensional reconstruction, feature extraction and pantograph state recognition successively；The unmanned plane pantograph detection device includes flight instruments and the Kinect sensor battle array being loaded on flight instruments Row, speed tester for vehicle train and unmanned plane wireless communication module；Remote master center, for receiving the message of monitoring unit transmission, control instruction is sent to monitoring unit, and train is entered Row scheduling；The Kinect sensor array being loaded on flight instruments is made up of 3 Kinect sensors, by three Kinect Sensor is respectively placed in the midpoint on the upper bottom edge and two stringcourses of an isosceles trapezoid device, in the two of which of isosceles trapezoid Angle is respectively 120 °, 60 °, and plane where isosceles trapezoid device is the vertical plane of train.
- 5. system according to claim 4, it is characterised in that be additionally provided with the unmanned plane pantograph detection device LED light supplement lamp.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710299446.2A CN106970581B (en) | 2017-04-30 | 2017-04-30 | A kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710299446.2A CN106970581B (en) | 2017-04-30 | 2017-04-30 | A kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106970581A CN106970581A (en) | 2017-07-21 |
| CN106970581B true CN106970581B (en) | 2018-03-30 |
Family
ID=59331604
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710299446.2A Active CN106970581B (en) | 2017-04-30 | 2017-04-30 | A kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106970581B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992061B (en) * | 2018-01-23 | 2019-09-27 | 中南大学 | A kind of wisdom laboratory machine people means of delivery and system |
| CN108829755B (en) * | 2018-05-25 | 2021-04-13 | 国网山东省电力公司青岛供电公司 | Transformer fault case matching search method based on iteration closest point |
| CN109556521B (en) * | 2018-11-24 | 2020-09-11 | 华北理工大学 | Railway steel rail displacement detection method based on unmanned aerial vehicle |
| CN110047133A (en) * | 2019-04-16 | 2019-07-23 | 重庆大学 | A kind of train boundary extraction method towards point cloud data |
| CN110695992A (en) * | 2019-09-27 | 2020-01-17 | 中国铁路昆明局集团有限公司昆明机务段 | Intelligent robot for overhauling roof of electric locomotive |
| CN110717937A (en) * | 2019-09-29 | 2020-01-21 | 深圳市图郅创新科技有限公司 | Image correction method and system, electronic device and storable medium |
| CN112325781B (en) * | 2020-10-16 | 2022-05-17 | 易思维（杭州）科技有限公司 | Rail transit contact line abrasion detection device and method |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004352108A (en) * | 2003-05-29 | 2004-12-16 | Aichi Corp | Exoergic detecting device for track equipment |
| CN105518702B (en) * | 2014-11-12 | 2018-06-26 | 深圳市大疆创新科技有限公司 | A kind of detection method, detection device and robot to target object |
| CN105681735A (en) * | 2014-11-18 | 2016-06-15 | 成都捷康特科技有限公司 | Thermal infrared imager and laser radar based thermal infrared bow net operation monitoring system |
| CN105208347B (en) * | 2015-10-08 | 2018-08-14 | 成都时代星光科技有限公司 | The aerial unmanned plane of railway line is patrolled and real time image collection transmitting, monitoring device automatically |
| CN105514872A (en) * | 2016-02-15 | 2016-04-20 | 西南交通大学 | High-efficiency unmanned aerial vehicle group power inspection system |
-
2017
- 2017-04-30 CN CN201710299446.2A patent/CN106970581B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106970581A (en) | 2017-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106970581B (en) | A kind of train pantograph real-time intelligent monitoring method and system based on the three-dimensional full visual angle of unmanned aerial vehicle group | |
| CN106192634B (en) | A kind of railroad track elastic bar fastener condition automatic detection device and method | |
| CN102129564B (en) | Contact network failure detection and diagnosis method based on unmanned aerial vehicle | |
| CN102507600B (en) | Automatic abrasion detection device for pantograph pan of high-speed locomotive | |
| CN209070035U (en) | A kind of rail traffic electricity car overhead contact line comprehensive detection device | |
| CN2884370Y (en) | Comprehensive testing device for safety of loading by train | |
| CN207335877U (en) | A kind of vehicle-mounted bow net condition monitoring system | |
| CN206034212U (en) | Railway rails elastic tensioning clamp state automatic checkout device | |
| CN204674616U (en) | A kind of dynamic detector for train wheel pair size | |
| CN103723161A (en) | Real-time automatic detection equipment for train loading safety | |
| CN110824497A (en) | Intelligent detection device and detection method for contact network | |
| CN207850304U (en) | A kind of electrification railway contact net detecting system | |
| CN109238756A (en) | Lorry operation troubles motion image detection equipment and detection method | |
| CN206954227U (en) | Track plates detect car and system | |
| CN114264491B (en) | Rail vehicle wheel set parameter detection system | |
| CN205890910U (en) | Limit detecting device is invaded with track foreign matter that infrared light combines to visible light | |
| CN213750759U (en) | Railway tunnel intelligent patrol vehicle based on SLAM technology | |
| CN205373648U (en) | Contact net geometric parameters dynamic verification device based on triangulation | |
| CN111812101A (en) | Pantograph slide plate defect detection device and method | |
| JP5952759B2 (en) | Overhead wire position measuring apparatus and method | |
| CN205754595U (en) | A kind of tunnel high definition holographic imaging apparatus | |
| CN112508893A (en) | Machine vision-based method and system for detecting tiny foreign matters between two railway tracks | |
| CN209706773U (en) | Steel-aluminum conductor rail wear detecting system | |
| CN217932084U (en) | Comprehensive train detection system | |
| CN116331069A (en) | Portable bow net detection track inspection vehicle detection system with power |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |