CN106682668A - Power transmission line geological disaster monitoring method using unmanned aerial vehicle to mark images - Google Patents
Power transmission line geological disaster monitoring method using unmanned aerial vehicle to mark images Download PDFInfo
- Publication number
- CN106682668A CN106682668A CN201611031508.3A CN201611031508A CN106682668A CN 106682668 A CN106682668 A CN 106682668A CN 201611031508 A CN201611031508 A CN 201611031508A CN 106682668 A CN106682668 A CN 106682668A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- electricity
- unmanned plane
- power transmission
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Probability & Statistics with Applications (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a power transmission line geological disaster monitoring method using an unmanned aerial vehicle to mark images. The method includes the following steps that: the unmanned aerial vehicle is utilized to acquire reference power transmission line images and mark the images; k-medoids cluster analysis is performed on the reference power transmission line images, so that a training set is obtained; the unmanned aerial vehicle is utilized to acquire target power transmission line images and mark the images; classification detection is performed according to the training set; and a geological disaster site is obtained according to the detection result of the classification detection. Unmanned aerial vehicle power transmission line inspection can effectively and quickly cover areas around a power transmission line, achieve ground feature high resolution, complete image marking, and provide a better data source for geological hazard detection so as to improve the accuracy of geological disaster detection; and real-time image marking can be completed in an unmanned aerial vehicle image acquisition process so as to assist analysis after disaster detection. With the above steps of the method of the invention adopted, power transmission line geological disaster monitoring can be competed fast.
Description
Technical field
The present invention relates to the invention belongs to unmanned aerial vehicle remote sensing data processing field, more particularly to one kind is marked using unmanned plane
The transmission line of electricity Geological Hazards Monitoring method of image.
Background technology
Transmission line of electricity as the important component part in power construction, in recent years country increase to the newly-built of transmission line of electricity and
Overhaul.Due to being affected by natural conditions and artificial construction wrong is limited, transmission line of electricity can often be subject to the prestige of geological disaster
The side of body.The generation of geological disaster will cause to damage to transmission line of electricity, have a strong impact on daily life, cause great economy property
Loss, to country and government great pressure is caused.It can be seen that, accurately carrying out transmission line of electricity Geological Hazards Monitoring can aid in correlation
Power department carries out in time maintenance and the disaster prevention of transmission line of electricity, and takes Disaster Relief Measures in time, it is ensured that transmission line of electricity is normal
Operation and the quality of transmission line construction, promote power industry sustainable health development.Transmission line of electricity geological disaster can be efficient
The premise of monitoring be each department to having occurred, it is all types of and various in the case of geological disaster carry out detailed analysis and grind
Study carefully, and can quickly find transmission line of electricity geological disaster, it is therefore desirable to which data volume is abundant, sample type is comprehensive and diversified
Transmission line of electricity periphery geological disaster correlation visible images sample and quick data acquisition modes.
And there are unreasonable shooting angle, rare numbers, divide in current transmission line of electricity periphery geological disaster visible images
The not enough defect of resolution, while at present geological disaster visible images sample is only original image, not comprising any markup information,
The information such as time, region, route, the geology and geomorphology of such as image collection, it is impossible to as the training of geological disaster detection algorithm
Data source and test data source, process work that more cannot be to transmission line of electricity geological disaster after monitoring provides guidance.For regarding
For feeling algorithm, traditional detection algorithm is firstly the need of hand-designed feature, such as color, texture, position, form etc..Because
Hand-designed feature needs substantial amounts of experience, needs to be applied to field and data are well understood by, in addition it is also necessary to what is designed
Feature carries out substantial amounts of debugging efforts, and a suitable grader has been also needed on this basis.While design feature, and select
One grader, the effect for merging both and being optimal, is practically impossible to completing for task.
The content of the invention
The present invention provides a kind of transmission line of electricity Geological Hazards Monitoring method of use unmanned plane tag images, existing to solve
The technical problem of monitoring effect difference in technology.
The present invention provides a kind of transmission line of electricity Geological Hazards Monitoring method of use unmanned plane tag images, methods described bag
Include：
Using unmanned plane collection is with reference to transmission line of electricity image and marks；
K-medoids cluster analyses are carried out to the reference transmission line of electricity image, training set is obtained；
Target transmission line of electricity image is gathered using unmanned plane and mark；
Classification and Detection is carried out according to the training set；
The scene of geological disaster is obtained according to the testing result of the classification and Detection.
Preferably, the utilization unmanned plane collection is with reference to transmission line of electricity image and mark includes：
All shaft tower coordinates of transmission line of electricity to be flown are imported from power system；
Used UAS desired parameters are obtained, the parameter includes unmanned plane during flying speed, camera pixel chi
Very little and imaging resolution；
According to transmission line of electricity coordinate and UAS parametric programming flight track and shooting style；
Unmanned plane during flying is carried out according to the flight track, unmanned plane positioning and orientation system is obtained while taking pictures every time
POS information, attitude and load attitude；
All images to obtaining are marked.
Preferably, k-medoids cluster analyses are carried out to the reference transmission line of electricity image, before obtaining training set, institute
Stating method also includes：
Gray scale stretching is carried out to the reference transmission line of electricity image；
The reference transmission line of electricity image after to gray scale stretching builds H-S color histograms and gradient orientation histogram；
Corresponding probability distribution is obtained respectively according to the H-S color histograms and gradient orientation histogram.
Preferably, the reference transmission line of electricity image carries out k-medoids cluster analyses, and obtaining training set includes：
Choose initial classes cluster central point；
Determine the number of initial classes cluster central point；
JSD calculating is carried out with reference to transmission line of electricity image to described each, training set is obtained.
The technical scheme that embodiments of the invention are provided can include following beneficial effect：
The present invention provides a kind of transmission line of electricity Geological Hazards Monitoring method of use unmanned plane tag images, including：Utilize
Unmanned plane collection is with reference to transmission line of electricity image and marks；To carrying out k-medoids cluster analyses with reference to transmission line of electricity image, obtain
Training set；Target transmission line of electricity image is gathered using unmanned plane and mark；Classification and Detection is carried out according to training set；According to classification inspection
The testing result of survey obtains the scene of geological disaster.Unmanned plane polling transmission line can fast and effectively cover transmission line of electricity
Neighboring area, and reach thing resolution ratio higher and can be while completing image mark, there is provided detect more excellent to geological disaster
Data source, such that it is able to improve the accuracy of geological disaster detection.Meanwhile, figure can be in real time completed during unmanned plane image collection
The labeling task of picture, with the analysis work after aiding in disaster to detect.Quickly transmission of electricity can be completed by the above step present invention
Circuit Geological Hazards Monitoring works.
It should be appreciated that the general description of the above and detailed description hereinafter are only exemplary and explanatory, not
The present invention can be limited.
Description of the drawings
Fig. 1 is a kind of transmission line of electricity Geological Hazards Monitoring of the use unmanned plane tag images provided in the embodiment of the present invention
The method flow diagram of method；
Fig. 2 is the method flow diagram of the step of providing in embodiment of the present invention S100；
Fig. 3 is the method flow diagram of the step of providing in embodiment of the present invention S200.
Specific embodiment
Here exemplary embodiment will be illustrated in detail, its example is illustrated in the accompanying drawings.Explained below is related to
During accompanying drawing, unless otherwise indicated, the same numbers in different accompanying drawings represent same or analogous key element.Following exemplary embodiment
Described in embodiment do not represent and the consistent all embodiments of the present invention.Conversely, they be only with it is such as appended
The example of the consistent device of some aspects described in detail in claims, the present invention.
Each embodiment in this specification is described by the way of progressive, identical similar portion between each embodiment
Divide mutually referring to what each embodiment was stressed is the difference with other embodiments.
Traditional Geological Hazards Monitoring work based on earth observation data depends on image visualization interpretation and on the spot
Investigation, the time-consuming serious, somewhat expensive of this traditional mode, and many areas are difficult to on-site inspection, affect fast after disaster
Speed response.And unmanned plane image has the advantages that high-resolution, large scale compared with satellite image, it is also particularly suitable for obtaining banding area
Aerial images, and unmanned plane for take photo by plane photography provide it is easy to operate, it is easy to the remote sensing platform of transition.And electric transmission line channel is proper
Just become band area, is especially suitable for the application of unmanned plane.The present invention combines power industry while using unmanned aerial vehicle remote sensing images
Feature, the quick response being beneficial to after calamity is marked to image data.Simultaneously the present invention adopts color of image, edge histogram
The probability distribution of form come carry out data analysis and geological disaster detection.First nobody is planned according to grid locational information etc.
Machine flying method, and image collection and data markers are synchronously completed in flight course, then to unmanned aerial vehicle remote sensing images one by one
Enter column hisgram structure, probability distribution distance is calculated using JSD (Jensen-Shannon Divergence), using improved
K-medoids methods complete to train storehouse to build, and finally remotely-sensed data new every time is classified and is detected and complete with completing disaster
Into the analysis work of disaster.
Fig. 1 is refer to, a kind of transmission line of electricity of the use unmanned plane tag images provided in the embodiment of the present invention is provided
The method flow diagram of Geological Hazards Monitoring method, methods described includes：
Step S100：Using unmanned plane collection is with reference to transmission line of electricity image and marks.
Fig. 2 is refer to, the method flow diagram of the step of providing in embodiment of the present invention S100 is provided, including：
Step S101：All shaft tower coordinates of transmission line of electricity to be flown are imported from power system；
Step S102：Used UAS desired parameters are obtained, the parameter includes unmanned plane during flying speed, phase
Machine pixel dimension and imaging resolution；
Step S103：According to transmission line of electricity coordinate and UAS parametric programming flight track and shooting style；
Step S104：Unmanned plane during flying is carried out according to the flight track, unmanned plane positioning is obtained while taking pictures every time
Attitude determination system POS information, attitude and load attitude；
Step S105：All images to obtaining are marked.
Step S200：K-medoids cluster analyses are carried out to the reference transmission line of electricity image, training set is obtained.
K-medoids is that K-means is a kind of to be improved, and different place is the selection of central point, in K-means,
Central point is taken as the mean value of all data points in current cluster (class) for we, and in K-medoids algorithms, we will
Such a point is chosen from current cluster, it is minimum apart from sum to other all points (in current cluster),
As central point.Overcome K-means algorithms and produce the shortcoming that the size of class is more or less the same, it is very sensitive for dirty data.
Before step S200, methods described also includes：
Gray scale stretching is carried out to the reference transmission line of electricity image.
Because light reason can cause image local excessively bright or excessively dark, need that image is carried out stretching to be allowed to cover larger
Interval.Make bright region brighter, dark region is darker, the contrast of image is improved, so that image border is obvious.Gray scale
Stretching is that gray level image is carried out into segmenting change, and it is [a, b] that the grey scale change of even original image f (x, y) is interval, is schemed after conversion
As the tonal range of g (x, y) expands to interval [c, d], can be become using following linear and bring realization：
The reference transmission line of electricity image after to gray scale stretching builds H-S color histograms and gradient orientation histogram.
Relative to rgb space, HSV space can intuitively express the light and shade of color, tone, and bright-coloured degree very much,
The contrast between color is conveniently carried out, the reception and registration of emotion is also convenient for.Conversion formula is as follows：
V=max
32 bin are used to hue (tone) passage, saturatoin (saturation degree) passages are built using 30 bin
H-S histograms；The H-S histograms of all images are calculated in the manner described above, and are normalized in order to contrast.
Gradient orientation histogram builds
HOG (Histogram of Oriented Gradient) gradient orientation histogram describe sub- dimensional images feature to
Amount generation step：1. image normalization；2. image gradient is calculated using first differential；3. thrown based on the direction weight of gradient magnitude
Shadow；4.HOG characteristic vectors are normalized；5. the final characteristic vectors of HOG are drawn.The main purpose of normalized image is to improve detection
Robustness of the device to illumination, because a variety of occasions that the identification target of reality is likely to occur, detector must be to illumination
The less sensitive effect just having.Gradient orientation histogram bin numbers are 36.
Corresponding probability distribution is obtained respectively according to the H-S color histograms and gradient orientation histogram.
Probability distribution corresponding with H-S color histograms and gradient orientation histogram is to fall into be divided according to bin numbers
The stack result of the number of pixels in each region.
Fig. 3 is refer to, the method flow diagram of the step of providing in embodiment of the present invention S200 is provided, including：
Step S201：Choose initial classes cluster central point.
The simplest method for determining initial classes cluster central point is to randomly choose K point as initial class cluster central point,
But the method is poor in effect in some cases.Batch distance K point as far as possible is selected in the present invention.It is random first
Select at one o'clock as first initial classes cluster central point, then that farthest o'clock of the chosen distance point is initial as second
Class cluster central point, then reselection apart from the first two point minimum distance it is maximum o'clock as the 3rd initial classes cluster center
Point, by that analogy, until selecting K initial classes cluster central point.
Step S202：Determine the number of initial classes cluster central point.
Give a suitable class cluster index, such as mean radius or diameter, as long as we assume that the number of class cluster etc.
In or higher than real class cluster number when, the index rises can be very slow, once and attempt to obtain less than true number
During class cluster, the index can steeply rise.The weighted average that class cluster index is the average centroid distance of K class cluster is selected herein.
Step S203：JSD calculating is carried out with reference to transmission line of electricity image to described each, training set is obtained.
JSD (Jensen-Shannon Divergence) is the improvement of KL distances, and calculation is as follows：
Wherein,
KLD (P | Q)=∑ [P (i) × ln (P (i))/Q (i)]
D (P | R) refers to KLD, P and Q and refers to what is obtained according to the H-S color histograms and gradient orientation histogram respectively
The probability distribution of probability distribution and arbitrary reference transmission line of electricity image.
Step S300：Target transmission line of electricity image is gathered using unmanned plane and mark.
Step S400：Classification and Detection is carried out according to the training set.
The unmanned aerial vehicle remote sensing images new for one are converted to a H-S-G according to histogram building mode presented hereinbefore
The probability distribution of (tone-saturation degree-gradient), by the distribution with so the central point of cluster result carries out JSD calculating, according to
Arrive k distance calculates the probability of classification, is directly proportional to the inverse of distance, when maximum probability is more than given threshold, completes point
Class, otherwise increases new class.
Step S500：The scene of geological disaster is obtained according to the testing result of the classification and Detection.
The image of geological disaster detection is completed, human assistance is combined by the image segmentation based on region growing and is marked geology
Disaster region, is then finally joined away from zoning barycenter according to geometry using the corresponding unmanned plane of the image and load attitude etc.
Number, calculates empty three and resolves, and obtains the scene of the geological disaster.Believed with reference to transmission line of electricity according to geological disaster place, image
Breath, terrain data etc. aid in transmission line of electricity disaster process work.
Invention described above embodiment, does not constitute limiting the scope of the present invention.It is any in the present invention
Spirit and principle within modification, equivalent and the improvement made etc., should be included within the scope of the present invention.
It should be noted that herein, the relational terms of such as " first " and " second " or the like are used merely to one
Individual entity or operation make a distinction with another entity or operation, and not necessarily require or imply these entities or operate it
Between there is any this actual relation or order.And, term " including ", "comprising" or its any other variant are intended to
Cover including for nonexcludability, so that a series of process, method, article or equipment including key elements not only includes those
Key element, but also including other key elements being not expressly set out, or also include for this process, method, article or set
Standby intrinsic key element.In the absence of more restrictions, the key element for being limited by sentence "including a ...", it is not excluded that
Also there is other identical element in the process including the key element, method, article or equipment.
The above is only the specific embodiment of the present invention, is made skilled artisans appreciate that or realizing this
It is bright.Various modifications to these embodiments will be apparent to one skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, the present invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope for causing.
Claims (4)
1. a kind of transmission line of electricity Geological Hazards Monitoring method of use unmanned plane tag images, it is characterised in that methods described bag
Include：
Using unmanned plane collection is with reference to transmission line of electricity image and marks；
K-medoids cluster analyses are carried out to the reference transmission line of electricity image, training set is obtained；
Target transmission line of electricity image is gathered using unmanned plane and mark；
Classification and Detection is carried out according to the training set；
The scene of geological disaster is obtained according to the testing result of the classification and Detection.
2. the transmission line of electricity Geological Hazards Monitoring method of use unmanned plane tag images according to claim 1, its feature
It is that the utilization unmanned plane collection is with reference to transmission line of electricity image and mark includes：
All shaft tower coordinates of transmission line of electricity to be flown are imported from power system；
Obtain used UAS desired parameters, the parameter include unmanned plane during flying speed, camera pixel dimension and
Imaging resolution；
According to transmission line of electricity coordinate and UAS parametric programming flight track and shooting style；
Unmanned plane during flying is carried out according to the flight track, unmanned plane positioning and orientation system POS letter is obtained while taking pictures every time
Breath, attitude and load attitude；
All images to obtaining are marked.
3. the transmission line of electricity Geological Hazards Monitoring method of use unmanned plane tag images according to claim 1, its feature
It is that k-medoids cluster analyses are carried out to the reference transmission line of electricity image, before obtaining training set, methods described is also wrapped
Include：
Gray scale stretching is carried out to the reference transmission line of electricity image；
The reference transmission line of electricity image after to gray scale stretching builds H-S color histograms and gradient orientation histogram；
Corresponding probability distribution is obtained respectively according to the H-S color histograms and gradient orientation histogram.
4. the transmission line of electricity Geological Hazards Monitoring method of use unmanned plane tag images according to claim 3, its feature
It is that the reference transmission line of electricity image carries out k-medoids cluster analyses, obtaining training set includes：
Choose initial classes cluster central point；
Determine the number of initial classes cluster central point；
JSD calculating is carried out with reference to transmission line of electricity image to described each, training set is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611031508.3A CN106682668A (en) | 2016-11-18 | 2016-11-18 | Power transmission line geological disaster monitoring method using unmanned aerial vehicle to mark images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611031508.3A CN106682668A (en) | 2016-11-18 | 2016-11-18 | Power transmission line geological disaster monitoring method using unmanned aerial vehicle to mark images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106682668A true CN106682668A (en) | 2017-05-17 |
Family
ID=58866128
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611031508.3A Pending CN106682668A (en) | 2016-11-18 | 2016-11-18 | Power transmission line geological disaster monitoring method using unmanned aerial vehicle to mark images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106682668A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110457422A (en) * | 2019-08-20 | 2019-11-15 | 重庆壤科农业数据服务有限公司 | Collecting soil sample auto-distribution dot system and method |
| CN110969081A (en) * | 2019-10-24 | 2020-04-07 | 云南电网有限责任公司昆明供电局 | Power transmission line external force damage detection method based on KL divergence of multi-module division |
| US10703479B2 (en) | 2017-11-30 | 2020-07-07 | Industrial Technology Research Institute | Unmanned aerial vehicle, control systems for unmanned aerial vehicle and control method thereof |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819926A (en) * | 2012-08-24 | 2012-12-12 | 华南农业大学 | Fire monitoring and warning method on basis of unmanned aerial vehicle |
| CN103886189A (en) * | 2014-03-07 | 2014-06-25 | 国家电网公司 | Patrolling result data processing system and method used for unmanned aerial vehicle patrolling |
| CN104881865A (en) * | 2015-04-29 | 2015-09-02 | 北京林业大学 | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis |
| US9305214B1 (en) * | 2013-10-29 | 2016-04-05 | The United States Of America, As Represented By The Secretary Of The Navy | Systems and methods for real-time horizon detection in images |
-
2016
- 2016-11-18 CN CN201611031508.3A patent/CN106682668A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102819926A (en) * | 2012-08-24 | 2012-12-12 | 华南农业大学 | Fire monitoring and warning method on basis of unmanned aerial vehicle |
| US9305214B1 (en) * | 2013-10-29 | 2016-04-05 | The United States Of America, As Represented By The Secretary Of The Navy | Systems and methods for real-time horizon detection in images |
| CN103886189A (en) * | 2014-03-07 | 2014-06-25 | 国家电网公司 | Patrolling result data processing system and method used for unmanned aerial vehicle patrolling |
| CN104881865A (en) * | 2015-04-29 | 2015-09-02 | 北京林业大学 | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis |
Non-Patent Citations (6)
| Title |
|---|
| WEIRAN CAO等: "High voltage transmission line detection for uav based routing inspection", 《HIGH VOLTAGE TRANSMISSION LINE DETECTION FOR UAV BASED ROUTING INSPECTION》 * |
| 张宏军等: "《作战仿真数据工程》", 30 September 2014, 北京：国防工业出版社 * |
| 朱明: "《数据挖掘 第2版》", 30 November 2008, 合肥：中国科学技术大学出版社 * |
| 李伟等: "一种改进的快速K-近邻分类方法", 《现代计算机》 * |
| 梅自强等: "《纺织辞典》", 31 January 2007, 北京：中国纺织出版社 * |
| 牛雪锋等: "一种基于特征融合的部位外观模型", 《西安邮电大学学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10703479B2 (en) | 2017-11-30 | 2020-07-07 | Industrial Technology Research Institute | Unmanned aerial vehicle, control systems for unmanned aerial vehicle and control method thereof |
| CN110457422A (en) * | 2019-08-20 | 2019-11-15 | 重庆壤科农业数据服务有限公司 | Collecting soil sample auto-distribution dot system and method |
| CN110457422B (en) * | 2019-08-20 | 2023-06-06 | 重庆壤科农业数据服务有限公司 | Automatic soil sample collection and distribution system and method |
| CN110969081A (en) * | 2019-10-24 | 2020-04-07 | 云南电网有限责任公司昆明供电局 | Power transmission line external force damage detection method based on KL divergence of multi-module division |
| CN110969081B (en) * | 2019-10-24 | 2023-02-24 | 云南电网有限责任公司昆明供电局 | Power transmission line external force damage detection method based on KL divergence of multi-module division |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104778721B (en) | The distance measurement method of conspicuousness target in a kind of binocular image | |
| Xiao et al. | Change detection of built-up land: A framework of combining pixel-based detection and object-based recognition | |
| CN106250870B (en) | A kind of pedestrian's recognition methods again of joint part and global similarity measurement study | |
| Li et al. | Road network extraction via deep learning and line integral convolution | |
| Urbach et al. | Automatic detection of sub-km craters in high resolution planetary images | |
| CN104463856B (en) | The ground extracting method of the outdoor scene three dimensional point cloud based on normal vector ball | |
| CN104835175B (en) | Object detection method in a kind of nuclear environment of view-based access control model attention mechanism | |
| CN105023008A (en) | Visual saliency and multiple characteristics-based pedestrian re-recognition method | |
| CN104881865A (en) | Forest disease and pest monitoring and early warning method and system based on unmanned plane image analysis | |
| CN104463249B (en) | A kind of remote sensing images airfield detection method based on Weakly supervised learning framework | |
| CN105335973A (en) | Visual processing method for strip steel processing production line | |
| Yuan et al. | Learning to count buildings in diverse aerial scenes | |
| CN104517095A (en) | Head division method based on depth image | |
| CN108021890A (en) | A kind of high score remote sensing image harbour detection method based on PLSA and BOW | |
| CN112766184B (en) | Remote sensing target detection method based on multi-level feature selection convolutional neural network | |
| Wu et al. | An object-based image analysis for building seismic vulnerability assessment using high-resolution remote sensing imagery | |
| CN106504192A (en) | A kind of power transmission line corridor geological disaster exploration image treatment method and system | |
| CN107341781A (en) | Based on the SAR image correcting methods for improving the matching of phase equalization characteristic vector base map | |
| CN108710909A (en) | A kind of deformable invariable rotary vanning object counting method | |
| CN104504675A (en) | Active vision positioning method | |
| Uzar | Automatic building extraction with multi-sensor data using rule-based classification | |
| CN109308451A (en) | A kind of high score data information extraction system and method | |
| CN106295657A (en) | A kind of method extracting human height's feature during video data structure | |
| CN107704840A (en) | A kind of remote sensing images Approach for road detection based on deep learning | |
| CN106682668A (en) | Power transmission line geological disaster monitoring method using unmanned aerial vehicle to mark images |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210421 Address after: Yunda economic and Technological Development Zone in Yunnan province Kunming city 650217 West Road No. 105 Applicant after: YUNNAN POWER GRID CO., LTD. ELECTRIC POWER Research Institute Address before: Yunda economic and Technological Development Zone in Yunnan province Kunming city 650217 West Road No. 105 Applicant before: YUNNAN POWER GRID CO., LTD. ELECTRIC POWER Research Institute Applicant before: TIANJIN ZHONG WEI AEROSPACE DATA SYSTEM TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170517 |