CN109040689A - Pattern information processing system for the tracking of helicopter line walking process infrared heat point - Google Patents
Pattern information processing system for the tracking of helicopter line walking process infrared heat point Download PDFInfo
- Publication number
- CN109040689A CN109040689A CN201810970749.7A CN201810970749A CN109040689A CN 109040689 A CN109040689 A CN 109040689A CN 201810970749 A CN201810970749 A CN 201810970749A CN 109040689 A CN109040689 A CN 109040689A
- Authority
- CN
- China
- Prior art keywords
- data
- video
- processing system
- gondola
- module
- 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
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/30—Transforming light or analogous information into electric information
- H04N5/33—Transforming infrared radiation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The present invention relates to electric inspection process technical fields, the more particularly, to pattern information processing system of helicopter line walking process infrared heat point tracking, including video data acquiring module, Data Analysis Services module, gondola is controlled in conjunction with the real time information of the synchronism output after Data Analysis Services resume module, video display module.Present system uses infrared, visible light video source image processing system, is tracked to various features, and carries out effective analytical integration to these information.It handles and shows by twin-channel video acquisition, transmission, analysis, respectively analyze data with individual buffer data, under the early stage condition for not influencing display and storage, high temperature tracking is carried out to electric power heat-producing device, and it can be to the GPS of real-time high-precision, helicopter attitude data carry out frame synchronization preservation, ensure that infrared synchronous with visible data, more steadily carry out follow-up of hot issues.
Description
Technical field
The present invention relates to electric inspection process technical fields, the more particularly, to figure of helicopter line walking process infrared heat point tracking
As information processing system.
Background technique
In recent years, as China surpasses the high speed development of (spy) ultra-high-tension power transmission line construction, high voltage, high-power, long range
Transmission line of electricity the more is built the more more, and the geographical environment passed through becomes increasingly complex, and helicopter line walking exists as a kind of efficient inspection technology
Domestic multiple power grid operation units are applied.Domestic helicopter power-operation business has gradually been stepped into fast-developing, steady
The track promoted is walked, the normalization and scale of the tour of transmission line of electricity helicopter are realized.
Traditional helicopter routing inspection operation carries the equipment such as infrared, visible light mainly using helicopter/unmanned plane as platform
The operation patrolled overhead transmission line and detected, and when use helicopter/unmanned plane progress line data-logging, common one
Kind inspection means are to carry photoelectric nacelle to carry out visible light/infrared imaging.When using gondola method inspection, usually a people uses phase
Machine and steady picture instrument carry out visual inspection, and in addition one man operation inspection photoelectric nacelle carries out infrared inspection.This inspection operation needs two
People operates respectively carries out inspection, and then the later period carries out data processing, and defective data cannot be handled timely, intelligent level
It is not able to satisfy the requirement of electric power line inspection operation in terms of deficiency, real-time property and accuracy increasingly.
Summary of the invention
Present invention combination the shortcomings of the prior art, it is open a kind of for going straight up in order to guarantee the tracking of infrared heat point
The pattern information processing system of machine line walking process infrared heat point tracking, it is ensured that the real-time and accuracy for tracking data reach straight
The purpose of machine follow-up of hot issues is risen, helicopter routing inspection efficiency is improved.
The present invention realizes the technical solution that above-mentioned purpose uses for the figure tracked for helicopter line walking process infrared heat point
Pattern information processing system as information processing system, for the tracking of helicopter line walking process infrared heat point, which is characterized in that institute
The system of stating includes: video data acquiring module, carries out video data acquiring using binary channels；Data Analysis Services module；In conjunction with
The real time information of synchronism output controls gondola after Data Analysis Services resume module；Video display module is used for
Timing control is carried out to output video data, the output for completing video is shown.
Further, the analog video signal that the video data acquiring module is exported by decoding camera shooting head, with avi
Format output digital video signal；The effective digital vision signal extracted is buffered using FIFO；Acquire GPS information and acquisition
The flight attitude of compass.
Further, the data that the Data Analysis Services module acquires the video data acquiring module are separately opened slow
Punching carries out Mean-Shift track algorithm for buffering frame data, and exports to real time synchronization.
Further, the data to the acquisition of video data acquiring module are separately opened buffering and are included the following steps:
1) visible light, infrared video flow data are buffered；
2) discovery detection target carries out gondola control to detection target；
3) visible light tracking is carried out in the video stream data of buffering.
Further, the method controlled gondola is the infrared highest temperature by analysis detection target, is obtained
The picture position of the highest temperature, fine tuning gondola makes the infrared highest temperature to image center, and the center is fed back to gondola,
To adjust the posture of the gondola until will test target is adjusted to central point, helicopter hovering.
Working principle: the pattern information processing system for the tracking of helicopter line walking process infrared heat point of the invention is adopted
With the image processing system in infrared visible light video source, various features are tracked, and these information are effectively divided
Analysis integration.It handles and shows by twin-channel video acquisition, transmission, analysis, carried out respectively with individual buffer data to data
It is analyzed, under the early stage condition for not influencing display and storage, high temperature tracking is carried out to electric power heat-producing device, and can be to real-time
High-precision GPS, helicopter attitude data carry out frame synchronization preservation, ensure that it is infrared synchronous with visible data, more surely
Surely follow-up of hot issues is carried out.
The method of the present invention is used have the beneficial effect that existing for the tracking of helicopter line walking process infrared heat point
(1) infrared video, the visible light video that can play synchronous recording simultaneously using binary channels, realize the real-time of data
And accuracy, use is infrared, visible light video source image processing system, is tracked to various features, can increase tracking
Stability, the problems such as solving Target type information in single visible image capturing head, temperature information missing.
(2) synchronizing information is written in the data and the every frame of video acquired using high-precision GPS, aircraft compass attitude parameter,
To realize the frame synchronization of acquisition information in real time.
(3) it realizes and the synchronous of data is saved during helicopter tracking, improve effective control of helicopter tracking
Property, reduce the time delay of control.
(4) achieve the purpose that helicopter follow-up of hot issues, more prepare to position and track target, realize visible light and infrared video
Manifold effective use of information, realize it is twin-channel accurately track, improve helicopter routing inspection efficiency.
Detailed description of the invention
Fig. 1 is the program flow diagram of Mean-Shift algorithm of the present invention.
Fig. 2 is the iterative process figure of Mean-Shift algorithm of the present invention.
Specific embodiment
Below in conjunction with the accompanying drawings and embodiment the invention will be further described.
The present invention is used for the pattern information processing system of helicopter line walking process infrared heat point tracking, and the system comprises views
Frequency data acquisition module；Data Analysis Services module；And combine the reality of the synchronism output after Data Analysis Services resume module
When information gondola is controlled.
(1) video acquisition module
The main collecting work for completing two-pass video data, since the video data obtained after A/D is sampled can not
It is directly handled, obtained data need to complete the extraction of valid data according to flag bit, and complete turning for video format
It changes.The flight attitude including high-precision GPS information, compass is acquired by data, is specifically included: 1) the simulation view of camera output
The digital video signal of output avi format after frequency signal is decoded；2) video acquisition module is had using what FIFO buffering was extracted
Imitate vision signal, the extraction to vision signal；3) by acquisition GPS information, the flight attitude of acquisition compass, orientation skill is used
Art, such as use 10m Long baselines, can reach 0.05 ° it is high-precision fixed to.Pass through the flight attitude data of high-precision GPS, compass
Acquisition, and to being inputted in real time, data basis is provided for the accurate tracking of helicopter.
(2) analysis and processing module
Buffering is separately opened to collected data to analyze, and realizes the real-time tracking function of high-temperature targets.Pass through buffered frame
Data carry out Mean-Shift track algorithm.Guaranteeing that video show and store simultaneously, it is seen that light identifies target,
Target's center's position control heart point in the picture, to realize the control centre of target position tracking, locking gondola.Open up buffering
Area analyze in another thread and output in real time is as a result, and and synchronizing result information and being saved in video frame number to buffer area
According to specific steps are as follows: buffering visible light, infrared video flow data；It was found that high-temperature targets, carry out gondola control to target；Slow
Visible light tracking is carried out in the video stream data of punching.
Mean-Shift target tracking algorism is a kind of method of printenv estimation, using color histogram probability distribution come
Target is described, core ideas is to add by the distance between target's center's point to each pixel to each pixel
Power corrects estimated location by calculating mean shift amount repeatedly, eventually finds target position, which can be good at inhibiting side
The problems such as edge noise, chaff interferent and partial occlusion bring influences.Meanwhile Mean-Shift method is a kind of semi-automatic mesh
Track algorithm is marked, program most starts to need by manually irising out target by search window, and the color calculated in the window is straight
Side's figure distribution, during tracking, calculates the histogram distribution in current frame window, judges local maximum by similarity measurement
Value increases search window by maximum direction along density and moves, until being moved to the actual position of target.Mean-Shift method
Algorithm calculation amount is small, is modeled using kernel function histogram model, blocks to edge, target rotates, deformation and background motion are insensitive, tool
There are good real-time and robustness.
The program circuit of Mean-Shift algorithm determines target window as shown in Figure 1, obtain target's center's position coordinates first
Then size carries out Mean-Shift algorithm iteration and obtains target position estimation, judges this Pasteur distance and threshold value relationship, such as
Fruit is less than threshold value RL and then thinks to find correct target position, in next frame image, the target that will be finally obtained in previous frame
Starting point of the position as candidate family in present frame, restarts Mean-Shift iteration；If Pasteur's distance is greater than setting threshold
Value RL and be less than RH think target position inaccuracy, but still may by successive iterations correct target, next frame still with
The point is algorithm starting point；Think that algorithm loses target if threshold value is greater than RH, needs to redefine target position.
The iterative process of Mean-Shift algorithm is as shown in Fig. 2, first with given position (x, y) for starting point, to gray value
Subregion calculates candidate region grey level histogram Px and Py according to kernel function, calculates normalization coefficient Ch, obtains normalization histogram
Figure distribution PCx and PCy, then calculates each pixel weight w i, is weighted and averaged to obtain new candidate to pixel position in window
Point calculates the grey level histogram distribution of the point, calculates it with the Pasteur of goal histogram distance and compared with given threshold, is less than
Then iteration terminates threshold value, using the point as target position；If being not less than threshold value, and the number of iterations is less than setting value, then with the point
The initial position of new an iteration is sat in position.
(3) gondola control module
Gondola rotation control is completed, to realize the high-temperature targets tracking of gondola.By analyzing the infrared highest temperature, obtain most
The picture position of high temperature, fine tuning gondola makes the infrared highest temperature to image center, and the center is fed back to gondola, with
The posture for adjusting the gondola, until target position is adjusted to central point, helicopter hovers.
Method particularly includes: control gondola rotates horizontally and vertical rotary, finally controls gondola, is digital in the present embodiment
Dynamic IR thermal imaging system locks shaft tower, entire shaft tower is placed in the visual field of digital Dynamic IR thermal imaging system.Pass through analysis
The infrared highest temperature, obtains the picture position of the highest temperature, and fine tuning gondola makes the infrared highest temperature to image center, and by the center
Position feedback is to gondola, to adjust the posture of the gondola.In this way, will test target is adjusted to central point, paid close attention in detail, directly
The machine of liter hovers.
(4) video display module
The output for carrying out video is shown, carries out timing control to output video data, the output for completing video is shown.
1) video data carries out real-time display in cabinet.
Video display module realizes that video data exports display function on VGA display, and digital picture is shown in VGA
Display needs to complete the conversion of the timing building and digital signal to analog signal of VGA on device.Video is exported to differentiate according to original view
Rate exports display, the standard VGA display pattern of 320 × 240@30Hz similar in infrared selection resolution sizes.
2) GPS that acquires in real time, flight attitude information carry out frame synchronization write-in, and save information.
The frame synchronization of GPS, posture information and video data are written and read.The 30Hz of infrared display module, it is seen that light is
20MHz.Using the image processing system in infrared visible light video source, various features are tracked, and can increase the stabilization of tracking
Property, the problems such as solving Target type information in single visible image capturing head, temperature information missing.Binary channels is infrared, visible light
Video source is capable of providing the data information of the richer multiplicity of more single video source, carries out effective analytical integration to these information,
It can be realized the significantly more efficient real-time tracking to equipment heating target.Pass through twin-channel video acquisition, transmission, analysis
It handles and shows.Respectively analyze data with individual buffer data, in the early stage condition for not influencing display with storage
Under, high temperature tracking is carried out to electric power heat-producing device, and frame synchronization can be carried out to the GPS of real-time high-precision, helicopter attitude data
It saves, ensure that infrared synchronous with visible data, more stable carry out follow-up of hot issues, tracking accuracy≤20% field angle
(RMS)。
The above embodiments are merely illustrative of the technical solutions of the present invention, rather than is limited；Although referring to aforementioned reality
Applying example, invention is explained in detail, for those of ordinary skill in the art, still can be to aforementioned implementation
Technical solution documented by example is modified or equivalent replacement of some of the technical features；And these are modified or replace
It changes, the spirit and scope for claimed technical solution of the invention that it does not separate the essence of the corresponding technical solution.
Claims (5)
1. the pattern information processing system for the tracking of helicopter line walking process infrared heat point, which is characterized in that the system packet
It includes:
Video data acquiring module carries out video data acquiring using binary channels；
Data Analysis Services module；
Gondola is controlled in conjunction with the real time information of the synchronism output after Data Analysis Services resume module；
Video display module, for carrying out timing control to output video data, the output for completing video is shown.
2. pattern information processing system as described in claim 1, which is characterized in that the video data acquiring module passes through decoding
The analog video signal of camera output, with avi format output digital video signal；The significant figure extracted is buffered using FIFO
Word vision signal；It acquires GPS information and acquires the flight attitude of compass.
3. pattern information processing system as described in claim 1, which is characterized in that the Data Analysis Services module is to the view
The data of frequency data collecting module collected separately open buffering, for buffering frame data, carry out Mean-Shift track algorithm, and to reality
When synchronizing information export.
4. pattern information processing system as claimed in claim 3, which is characterized in that it is described to video data acquiring module acquisition
Data are separately opened buffering and are included the following steps:
1) visible light, infrared video flow data are buffered；
2) discovery detection target carries out gondola control to detection target；
3) visible light tracking is carried out in the video stream data of buffering.
5. pattern information processing system as described in claim 1, which is characterized in that the method controlled gondola is logical
The infrared highest temperature for crossing analysis detection target, obtains the picture position of the highest temperature, and fine tuning gondola makes the infrared highest temperature into image
Heart point, and the center is fed back into gondola, to adjust the posture of the gondola until will test target is adjusted to central point,
Helicopter hovering.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810970749.7A CN109040689A (en) | 2018-08-24 | 2018-08-24 | Pattern information processing system for the tracking of helicopter line walking process infrared heat point |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810970749.7A CN109040689A (en) | 2018-08-24 | 2018-08-24 | Pattern information processing system for the tracking of helicopter line walking process infrared heat point |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109040689A true CN109040689A (en) | 2018-12-18 |
Family
ID=64627357
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810970749.7A Pending CN109040689A (en) | 2018-08-24 | 2018-08-24 | Pattern information processing system for the tracking of helicopter line walking process infrared heat point |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040689A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115338282A (en) * | 2022-10-17 | 2022-11-15 | 南通长石科技有限公司 | Magnesium alloy forging product stamping forming system and stamping forming method |
| CN115562332A (en) * | 2022-09-01 | 2023-01-03 | 北京普利永华科技发展有限公司 | Efficient processing method and system for airborne recorded data of unmanned aerial vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005067285A (en) * | 2003-08-20 | 2005-03-17 | Fujitsu Ltd | Infrared image device and marine search method using the same |
| CN103941745A (en) * | 2014-03-07 | 2014-07-23 | 国家电网公司 | Movable substation and working method for unmanned aerial vehicle electric transmission line inspection |
| CN105245855A (en) * | 2015-10-29 | 2016-01-13 | 天津航天中为数据系统科技有限公司 | Terminal and method for intelligent inspection of helicopter |
| CN107871324A (en) * | 2017-11-02 | 2018-04-03 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | One kind is based on twin-channel method for tracking target and device |
-
2018
- 2018-08-24 CN CN201810970749.7A patent/CN109040689A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005067285A (en) * | 2003-08-20 | 2005-03-17 | Fujitsu Ltd | Infrared image device and marine search method using the same |
| CN103941745A (en) * | 2014-03-07 | 2014-07-23 | 国家电网公司 | Movable substation and working method for unmanned aerial vehicle electric transmission line inspection |
| CN105245855A (en) * | 2015-10-29 | 2016-01-13 | 天津航天中为数据系统科技有限公司 | Terminal and method for intelligent inspection of helicopter |
| CN107871324A (en) * | 2017-11-02 | 2018-04-03 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | One kind is based on twin-channel method for tracking target and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115562332A (en) * | 2022-09-01 | 2023-01-03 | 北京普利永华科技发展有限公司 | Efficient processing method and system for airborne recorded data of unmanned aerial vehicle |
| CN115562332B (en) * | 2022-09-01 | 2023-05-16 | 北京普利永华科技发展有限公司 | Efficient processing method and system for airborne record data of unmanned aerial vehicle |
| CN115338282A (en) * | 2022-10-17 | 2022-11-15 | 南通长石科技有限公司 | Magnesium alloy forging product stamping forming system and stamping forming method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2018214195A1 (en) | Remote sensing imaging bridge detection method based on convolutional neural network | |
| CN105373135B (en) | A kind of method and system of aircraft docking guidance and plane type recognition based on machine vision | |
| CN109949375A (en) | A kind of mobile robot method for tracking target based on depth map area-of-interest | |
| CN109448025B (en) | Automatic tracking and track modeling method for short-path speed skating athletes in video | |
| CA3100569A1 (en) | Ship identity recognition method base on fusion of ais data and video data | |
| CN103997624B (en) | Overlapping domains dual camera Target Tracking System and method | |
| CN111199556B (en) | Indoor pedestrian detection and tracking method based on camera | |
| WO2014190651A1 (en) | Photovoltaic power predication method based on ground-based nephogram | |
| CN108229587A (en) | A kind of autonomous scan method of transmission tower based on aircraft floating state | |
| CN112084871B (en) | High-resolution remote sensing target boundary extraction method based on weak supervised learning | |
| CN105913028A (en) | Face tracking method and face tracking device based on face++ platform | |
| CN104821010A (en) | Binocular-vision-based real-time extraction method and system for three-dimensional hand information | |
| CN111123962A (en) | Rotor unmanned aerial vehicle repositioning photographing method for power tower inspection | |
| CN109040689A (en) | Pattern information processing system for the tracking of helicopter line walking process infrared heat point | |
| CN109144109A (en) | A kind of dynamic hotspot during helicopter line walking tracks locking means | |
| CN110503092A (en) | The improvement SSD monitor video object detection method adapted to based on field | |
| CN111723747A (en) | Lightweight high-efficiency target detection method applied to embedded platform | |
| CN115240089A (en) | Vehicle detection method of aerial remote sensing image | |
| CN107067423A (en) | A kind of micro- method for becoming monitoring of the historical relic body for being applied to open environmental effect | |
| Wang et al. | Citrus recognition based on YOLOv4 neural network | |
| CN114202819B (en) | Substation inspection method, system and computer based on robot | |
| CN117036404A (en) | Monocular thermal imaging simultaneous positioning and mapping method and system | |
| Jacobs et al. | Cloud motion as a calibration cue | |
| CN113837044B (en) | Organ positioning method based on ambient brightness and related equipment | |
| CN106508051B (en) | A kind of FPGA implementation method of air-ground image trace |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |