CN110532872A - A kind of landslide hierarchy system and method based on convolution supporting vector neural network - Google Patents
A kind of landslide hierarchy system and method based on convolution supporting vector neural network Download PDFInfo
- Publication number
- CN110532872A CN110532872A CN201910672223.5A CN201910672223A CN110532872A CN 110532872 A CN110532872 A CN 110532872A CN 201910672223 A CN201910672223 A CN 201910672223A CN 110532872 A CN110532872 A CN 110532872A
- Authority
- CN
- China
- Prior art keywords
- image
- landslide
- supporting vector
- classification
- neural network
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 title abstract description 8
- 230000004069 differentiation Effects 0.000 claims abstract description 19
- 238000012545 processing Methods 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims description 15
- 239000011248 coating agent Substances 0.000 claims description 13
- 238000000576 coating method Methods 0.000 claims description 13
- 210000005036 nerve Anatomy 0.000 claims description 12
- 238000013145 classification model Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 210000004218 nerve net Anatomy 0.000 claims description 4
- 230000008859 change Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000000720 eyelash Anatomy 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
Classifications
-
- 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
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of landslide hierarchy system and method based on convolution supporting vector neural network, belong to subgrade engineering field.A kind of landslide hierarchy system based on convolution supporting vector neural network, including the image storage module for storing acquired image, for obtaining the image collection module of image data, the image processing module of Classification of Landslides differentiation is carried out to image, described image processing module includes the image classification unit for identifying image with the presence or absence of the image discriminating unit on landslide and for carrying out landslide classification to image.By collecting image, and image is analyzed to judge landslide classification, saves manpower, it is high-efficient, without security risk.
Description
Technical field
The present invention relates to subgrade engineering fields, relate generally to a kind of landslide classification based on convolution supporting vector neural network
System and method.
Background technique
Past highway because grade it is low, it is linear it is poor, roadbed is not wide, excavate not depth, influence of the slope stability to safety is not
Significantly, people's Slope Stability does not cause enough attention still, with the development of the development of the national economy, communication
Make rapid progress, grade is higher and higher, and inevitable builds the feelings of high-grade highway to high embankment under MODEL OVER COMPLEX TOPOGRAPHY
Condition is increasing, and both at home and abroad there are many example of major landslip, landslide not only influences traffic safety, or even buries, interrupts
Traffic forces and abandons built use, causes immeasurable economic loss, the Study of Landslides origin cause of formation and prevention and treatment, has compeled in eyebrow
Eyelash.
In the prior art, common landslide classification needs manually to in-site measurement landslide soil amount, i.e. landslide classification;It is existing
The resources such as the usual labor intensive of method, equipment and time and the security risk of engineering staff can be brought, therefore this kind of existed with manpower
The method role that work location carries out landslide classification is limited.
Summary of the invention
The object of the present invention is to provide a kind of landslide stage divisions based on convolution supporting vector neural network, pass through collection
Image, and image is analyzed to judge landslide classification, manpower is saved, it is high-efficient, without security risk.
The above-mentioned technical purpose of the present invention is achieved through the following technical solutions, and one kind being based on convolution supporting vector nerve net
The landslide hierarchy system of network, including the image storage module for storing acquired image, for obtaining the image of image data
Module is obtained, the image processing module of Classification of Landslides differentiation is carried out to image, described image processing module includes for identifying figure
As the image discriminating unit with the presence or absence of landslide and the image classification unit for carrying out landslide classification to image.
As a preference of the present invention, described image judgement unit simultaneously differentiates image with described image taxon
And classification.As a preference of the present invention, a kind of landslide stage division based on convolution supporting vector neural network, including following step
It is rapid:
Step S1, collect image, and according to image be made whether exist landslide classification differentiation, if it exists landslide classification, then into
Pedestrian's work mark, until step S2;
Step S2, the image differentiated in step S1 is normalized, the image data after normalized is inputted
Convolution supporting vector nerve network system carries out disaggregated model training;
Step S3, whether identification and classification model accuracy meets the requirements, and requires if not meeting differentiation, convolution supporting vector nerve net
Network system adjust automatically optimizes convolution supporting vector neural network node weight, and return step S1, requires if meeting differentiation, institute
Training the disaggregated model come is optimal classification model;
Step S4, image to be detected is obtained, the differentiation of landslide classification is carried out using optimal classification model, according to convolution supporting vector
The probit value for the landslide grade that nerve network system provides selects the classification of maximum of probability, obtains classification achievement.
In the technical scheme, collected point image to be detected landslide classification is carried out with optimal classification model to differentiate,
Mainly image to be detected is put into convolution supporting vector nerve network system and calculate the classification of image to be detected landslide
The probability of type, and landslide hierarchical type of the maximum landslide hierarchical type of select probability as the image to be detected.It is specific main
If being sampled by the target area in image to be detected, it is put into the input layer of neural network, is supported vector layer
Obtain the probability of each label, the i.e. real value in section [0,1].
As a preference of the present invention, convolution supporting vector nerve network system is carrying out disaggregated model instruction according to step S2
When practicing, and carry out the differentiation of image grading.
As a preference of the present invention, landslide probit value includes large landslide probit value, major landslip probability according to step S4
Value, medium-sized landslide probit value, small-sized landslide probit value, the large landslide probit value, the major landslip probit value, it is described in
Type landslide probit value, the sum of described small-sized landslide probit value are 1.
In the technical scheme, Landslides are divided into large landslide, major landslip, medium-sized landslide, small-sized landslide, and totally 4 kinds
The landslide grade labelling of type, i.e. 4 data, this 4 data and be equal to 1, then, by obtained each image to be detected
The probability of label is averaged, and the probability of the label of image to be detected is obtained, and the maximum label of select probability is to be detected as this
The label of the landslide hierarchical type of image.
As a preference of the present invention, the normalized includes the meter for carrying out comentropy mean value to all image pixels
The characteristic value between -1 to 1 is obtained after calculation.
As a preference of the present invention, convolution supporting vector neural network structure includes input layer, and convolutional layer, active coating, under
Sample level normalizes layer and supporting vector layer.
As a preference of the present invention, input layer is the transverse and longitudinal coordinate and color of image of image.
Compared with prior art, the present invention has the following advantages:
1, using manually image is differentiated and classified with computer mutually matched mode, study precision is improved.
2, directly image is differentiated and is classified, save manpower, it is high-efficient, without security risk.
Detailed description of the invention
Fig. 1 is present system flow chart.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings.
This specific embodiment is only explanation of the invention, is not limitation of the present invention, those skilled in the art
Member can according to need the modification that not creative contribution is made to the present embodiment after reading this specification, but as long as at this
All by the protection of Patent Law in the scope of the claims of invention.
A kind of landslide hierarchy system based on convolution supporting vector neural network according to figure 1, including for storing
The image storage module of acquired image carries out Classification of Landslides to image and sentences for obtaining the image collection module of image data
Other image processing module, described image processing module include for identify image with the presence or absence of landslide image discriminating unit with
And the image classification unit for carrying out landslide classification to image.Described image judgement unit and described image taxon are simultaneously
Image is differentiated and is classified.
A kind of landslide stage division based on convolution supporting vector neural network, comprising the following steps:
Step S1, collect image, and according to image be made whether exist landslide classification differentiation, if it exists landslide classification, then into
Pedestrian's work mark, until step S2;
Step S2, the image differentiated in step S1 is normalized, the image data after normalized is inputted
Convolution supporting vector nerve network system carries out disaggregated model training;
Step S3, whether identification and classification model accuracy meets the requirements, and requires if not meeting differentiation, convolution supporting vector nerve net
Network system adjust automatically optimizes convolution supporting vector neural network node weight, and return step S1, requires if meeting differentiation, institute
Training the disaggregated model come is optimal classification model;
Step S4, image to be detected is obtained, the differentiation of landslide classification is carried out using optimal classification model, according to convolution supporting vector
The probit value for the landslide grade that nerve network system provides selects the classification of maximum of probability, obtains classification achievement.
In the technical scheme, collected point image to be detected landslide classification is carried out with optimal classification model to differentiate,
Mainly image to be detected is put into convolution supporting vector nerve network system and calculate the classification of image to be detected landslide
The probability of type, and landslide hierarchical type of the maximum landslide hierarchical type of select probability as the image to be detected.It is specific main
If being sampled by the target area in image to be detected, it is put into the input layer of neural network, is supported vector layer
Obtain the probability of each label, the i.e. real value in section [0,1].
Normalized obtains the feature between -1 to 1 after referring to the calculating for carrying out comentropy mean value to all image pixels
Value.
According to step S2, convolution supporting vector nerve network system carries out image point when carrying out disaggregated model training
The differentiation of grade.The image pattern differentiated input convolution supporting vector nerve network system is carried out to the training of disaggregated model, it is main
If learning to convolutional neural networks system is brought into the image pattern manually marked;Repeat " training -> adjustment network
The process of structure -> retraining " is until differentiating correct.
According to step S3, the subjective setting value required as user is differentiated, if differentiating, accuracy is greater than user's subjectivity and sets
Definite value then meets differentiation and requires to differentiate that accuracy is less than subjective setting value, then do not meet differentiation and require.
According to step S4, the probit value that comes down includes large landslide probit value, major landslip probit value, medium-sized landslide probability
Value, small-sized landslide probit value, the large landslide probit value, the major landslip probit value, the medium-sized landslide probit value, institute
Stating the sum of small-sized landslide probit value is 1.
In the technical scheme, Landslides are divided into large landslide, major landslip, medium-sized landslide, small-sized landslide, and totally 4 kinds
The landslide grade labelling of type, i.e. 4 data, this 4 data and be equal to 1, then, by obtained each image to be detected
The probability of label is averaged, and the probability of the label of image to be detected is obtained, and the maximum label of select probability is to be detected as this
The label of the landslide hierarchical type of image.
Normalized includes that the calculating of comentropy mean value is carried out to all image datas, by all figures manually marked
Sample point after all being normalized divided by comentropy mean value as the space length of data.
Convolution supporting vector neural network structure includes input layer, convolutional layer, active coating, down-sampling layer, normalization layer and
Supporting vector layer.
Input layer is the transverse and longitudinal coordinate and color of image of image.
Convolutional layer:
1) size of core must be odd number, and no more than the width or height of this layer input;
2) transverse and longitudinal coordinate is not changed when intermediate representation passes through convolutional layer.
Active coating:
1) active coating does not change the transverse and longitudinal coordinate and color of image of convolutional layer expression;
2) activation primitive used in active coating includes but is not limited to following type function:
F (x)=l/(1+e-x)
F (x)=a*tanh (b*x), a, b are any non-zero real
f(x)= max(0,x)
f(x)= min(a,max(0,x))
f(x)= log(l+ex)
f(x)= |x|
f(x)= x2
f(x)= √X
f(x)= ax+b
3) active coating is followed after convolutional layer.
Down-sampling layer:
1) down-sampling layer does not change the color of image of intermediate representation;
2) down-sampling layer is the size of core to the drawdown ratio of image: i.e. core is that the down-sampling layer of m x n will cause intermediate representation
It is reduced into one layer (1/m) x (1/n), theoretically m and n can be random natural number.For example, 15x15x32 under 3x3 by adopting
After sample, become 5x5x32;After the down-sampling that 15x15x32 passes through 5x5, become 3x3x32;But 15x15x32 not can be carried out 2x2
Down-sampling because 15 cannot be divided exactly by 2;Be not to say that, input size must be 2 power, i.e., 16,32,64 etc., input ruler
As long as very little guarantee to be sampled by all down-sampling layers.
Normalize layer:
1) normalization layer does not change any size of intermediate representation;
2) normalization layer is necessary in the present invention, and addition normalization layer improves precision in this regular meeting and increases calculation amount.
- as combination be: convolutional layer -> active coating -> down-sampling layer -> normalization layer.
Following situations is special:
1) layer is smaller to precision improvement when but increasing many operands for addition normalization, cancels normalization layer, i.e., using following
Combination: convolutional layer -> active coating -> down-sampling layer;
2) normalization layer shift to an earlier date, effect is essentially identical, that is, use following combination: convolutional layer -> active coating -> normalization layer -> under adopt
Sample layer.
3) cancel down-sampling layer: convolutional layer -> active coating;Or convolutional layer -> active coating -> normalization layer;Down-sampling essence
Be in order to
Increase robustness, while being reduced the effect of the operand of succeeding layer;Several layers of down-samplings are usually had in one network, but
Not all " convolutional layer -> active coating " below will be with down-sampling.
Claims (8)
1. a kind of landslide hierarchy system based on convolution supporting vector neural network, which is characterized in that including being adopted for storing
The image storage module for collecting image carries out Classification of Landslides differentiation to image for obtaining the image collection module of image data
Image processing module, described image processing module include the image discriminating unit and use for identifying image with the presence or absence of landslide
In the image classification unit for carrying out landslide classification to image.
2. a kind of landslide hierarchy system based on convolution supporting vector neural network according to claim 1, feature exist
In described image judgement unit is differentiated and classified to image simultaneously with described image taxon.
3. a kind of landslide stage division based on convolution supporting vector neural network, which comprises the steps of:
Step S1, collect image, and according to image be made whether exist landslide classification differentiation, if it exists landslide classification, then into
Pedestrian's work mark, until step S2;
Step S2, the image differentiated in step S1 is normalized, the image data after normalized is inputted
Convolution supporting vector nerve network system carries out disaggregated model training;
Step S3, whether identification and classification model accuracy meets the requirements, and requires if not meeting differentiation, convolution supporting vector nerve net
Network system adjust automatically optimizes convolution supporting vector neural network node weight, and return step S1, requires if meeting differentiation, institute
Training the disaggregated model come is optimal classification model;
Step S4, image to be detected is obtained, the differentiation of landslide classification is carried out using optimal classification model, according to convolution supporting vector
The probit value for the landslide grade that nerve network system provides selects the classification of maximum of probability, obtains classification achievement.
4. a kind of landslide stage division based on convolution supporting vector neural network according to claim 3, feature exist
According to step S2, convolution supporting vector nerve network system carries out image grading when carrying out disaggregated model training
Differentiate.
5. a kind of landslide stage division based on convolution supporting vector neural network according to claim 3, feature exist
According to step S4, the probit value that comes down includes large landslide probit value, major landslip probit value, and medium-sized landslide probit value is small-sized
Come down probit value, the large landslide probit value, the major landslip probit value, and the medium-sized landslide probit value is described small-sized
The sum of the probit value that comes down is 1.
6. a kind of landslide stage division based on convolution supporting vector neural network according to claim 3, feature exist
In the normalized obtains the feature between -1 to 1 after referring to the calculating for carrying out comentropy mean value to the image pixel of image
Value.
7. a kind of landslide stage division based on convolution supporting vector neural network according to claim 3, feature exist
In, convolution supporting vector neural network structure include input layer, convolutional layer, active coating, down-sampling layer, normalization layer and support to
Measure layer.
8. a kind of landslide stage division based on convolution supporting vector neural network according to claim 7, feature exist
In input layer is the transverse and longitudinal coordinate and color of image of image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910672223.5A CN110532872A (en) | 2019-07-24 | 2019-07-24 | A kind of landslide hierarchy system and method based on convolution supporting vector neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910672223.5A CN110532872A (en) | 2019-07-24 | 2019-07-24 | A kind of landslide hierarchy system and method based on convolution supporting vector neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110532872A true CN110532872A (en) | 2019-12-03 |
Family
ID=68661291
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910672223.5A Pending CN110532872A (en) | 2019-07-24 | 2019-07-24 | A kind of landslide hierarchy system and method based on convolution supporting vector neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110532872A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898419A (en) * | 2020-06-17 | 2020-11-06 | 西安交通大学 | Partition landslide detection system and method based on cascade deep convolutional neural network |
CN112508861A (en) * | 2020-11-19 | 2021-03-16 | 安徽理工大学 | Coal mining subsidence early warning system based on image processing |
CN112529084A (en) * | 2020-12-16 | 2021-03-19 | 电子科技大学 | Similar landslide recommendation method based on landslide section image classification model |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103971342A (en) * | 2014-05-21 | 2014-08-06 | 厦门美图之家科技有限公司 | Image noisy point detection method based on convolution neural network |
CN107463991A (en) * | 2017-06-28 | 2017-12-12 | 西南石油大学 | A kind of Regional Landslide method for evaluating hazard based on slopes unit and machine learning |
WO2018121035A1 (en) * | 2016-12-29 | 2018-07-05 | 山东科技大学 | Customized method for determining coal mining face floor water inrush risk level |
CN109886329A (en) * | 2019-02-18 | 2019-06-14 | 中国铁建重工集团有限公司 | Rock crusher level detection method, detection system and heading equipment |
-
2019
- 2019-07-24 CN CN201910672223.5A patent/CN110532872A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103971342A (en) * | 2014-05-21 | 2014-08-06 | 厦门美图之家科技有限公司 | Image noisy point detection method based on convolution neural network |
WO2018121035A1 (en) * | 2016-12-29 | 2018-07-05 | 山东科技大学 | Customized method for determining coal mining face floor water inrush risk level |
CN107463991A (en) * | 2017-06-28 | 2017-12-12 | 西南石油大学 | A kind of Regional Landslide method for evaluating hazard based on slopes unit and machine learning |
CN109886329A (en) * | 2019-02-18 | 2019-06-14 | 中国铁建重工集团有限公司 | Rock crusher level detection method, detection system and heading equipment |
Non-Patent Citations (2)
Title |
---|
李兴等: "基于模糊神经网络的高速公路边坡危险性评价与防护策略", 《公路工程》 * |
许冲等: "逻辑回归模型在玉树地震滑坡危险性评价中的应用与检验", 《工程地质学报》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111898419A (en) * | 2020-06-17 | 2020-11-06 | 西安交通大学 | Partition landslide detection system and method based on cascade deep convolutional neural network |
CN111898419B (en) * | 2020-06-17 | 2022-10-25 | 西安交通大学 | Partitioned landslide detection system and method based on cascaded deep convolutional neural network |
CN112508861A (en) * | 2020-11-19 | 2021-03-16 | 安徽理工大学 | Coal mining subsidence early warning system based on image processing |
CN112529084A (en) * | 2020-12-16 | 2021-03-19 | 电子科技大学 | Similar landslide recommendation method based on landslide section image classification model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109800736B (en) | Road extraction method based on remote sensing image and deep learning | |
Odgers et al. | Disaggregating and harmonising soil map units through resampled classification trees | |
CN110532872A (en) | A kind of landslide hierarchy system and method based on convolution supporting vector neural network | |
Bock et al. | Spatial indicators for nature conservation from European to local scale | |
Metternicht | Change detection assessment using fuzzy sets and remotely sensed data: an application of topographic map revision | |
Domazetović et al. | Development of automated multicriteria GIS analysis of gully erosion susceptibility | |
Kwinta et al. | The description of parcel geometry and its application in terms of land consolidation planning | |
Liu et al. | Road selection based on Voronoi diagrams and “strokes” in map generalization | |
CN108346144A (en) | Bridge Crack based on computer vision monitoring and recognition methods automatically | |
Chen et al. | Fractal dimensions derived from spatial allometric scaling of urban form | |
CN107316064A (en) | A kind of asphalt pavement crack classifying identification method based on convolutional neural networks | |
CN108052980A (en) | Air quality grade detection method based on image | |
CN104537597A (en) | A technical method of diagnosing rationality of city spatial patterns | |
CN104282026A (en) | Distribution uniformity assessment method based on watershed algorithm and minimum spanning tree | |
CN102214290B (en) | License plate positioning method and license plate positioning template training method | |
CN109472075A (en) | A kind of base station performance analysis method and system | |
CN110765419A (en) | Important water functional area water quality risk assessment method based on multi-source data coupling | |
CN111125285A (en) | Animal geographic zoning method based on species spatial distribution relation | |
CN116310853A (en) | Multi-source data-based extraction method for edge regions of medium and small cities | |
CN109146563A (en) | A kind of Urban House land evaluation methods based on transfer learning | |
CN105243503A (en) | Coastal zone ecological safety assessment method based on space variables and logistic regression | |
CN111626103A (en) | Urbanization gradient measurement method based on night light remote sensing image | |
Wan et al. | The knowledge rules of debris flow event: A case study for investigation Chen Yu Lan River, Taiwan | |
CN107967454A (en) | Take the two-way convolutional neural networks Classification in Remote Sensing Image method of spatial neighborhood relation into account | |
CN104331708B (en) | A kind of zebra crossing automatic detection analysis method and system |
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: 20191203 |