CN111652056B - Pedestrian road network solar irradiation index detection method based on remote sensing image - Google Patents
Pedestrian road network solar irradiation index detection method based on remote sensing image Download PDFInfo
- Publication number
- CN111652056B CN111652056B CN202010332218.2A CN202010332218A CN111652056B CN 111652056 B CN111652056 B CN 111652056B CN 202010332218 A CN202010332218 A CN 202010332218A CN 111652056 B CN111652056 B CN 111652056B
- Authority
- CN
- China
- Prior art keywords
- road network
- remote sensing
- solar
- pedestrian road
- sensing 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 10
- 238000000034 method Methods 0.000 claims description 33
- 238000012417 linear regression Methods 0.000 claims description 28
- 239000011159 matrix material Substances 0.000 claims description 14
- 230000004927 fusion Effects 0.000 claims description 9
- ATNHDLDRLWWWCB-AENOIHSZSA-M chlorophyll a Chemical compound C1([C@@H](C(=O)OC)C(=O)C2=C3C)=C2N2C3=CC(C(CC)=C3C)=[N+]4C3=CC3=C(C=C)C(C)=C5N3[Mg-2]42[N+]2=C1[C@@H](CCC(=O)OC\C=C(/C)CCC[C@H](C)CCC[C@H](C)CCCC(C)C)[C@H](C)C2=C5 ATNHDLDRLWWWCB-AENOIHSZSA-M 0.000 claims description 6
- 229930002875 chlorophyll Natural products 0.000 claims description 5
- 235000019804 chlorophyll Nutrition 0.000 claims description 5
- 230000003287 optical effect Effects 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000003384 imaging method Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000252229 Carassius auratus Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002354 daily effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000012774 insulation material Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000002834 transmittance Methods 0.000 description 1
- 235000013311 vegetables Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J1/00—Photometry, e.g. photographic exposure meter
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Automation & Control Theory (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a pedestrian road network solar irradiation index detection method based on remote sensing images, which comprises the following steps: acquiring a remote sensing image of a region to which a pedestrian road network belongs, and processing to obtain a normalized differential vegetation index and texture characteristics; randomly selecting part of position points in a road network, collecting solar irradiance as an attribute for constructing training data, and obtaining attribute information by a model by using the rest position points as detection data; constructing a multiple regression model by using training data, and acquiring a solar irradiation index from the detection data; and matching the obtained solar irradiation index to a position point in the road network, and then obtaining road network basic data with attribute information. The invention aims to automatically detect solar irradiation indexes of road networks in different areas so as to acquire road network data with the attribute, provide a certain data base for personalized pedestrian navigation and solve the current situation that the prior art cannot provide path recommendation with specific requirements for users.
Description
Technical Field
The invention relates to the technical field of intelligent transportation, in particular to a pedestrian road network solar irradiation index detection method based on remote sensing images.
Background
The use of pedestrian navigation systems is becoming more and more common in everyday life today, becoming an indispensable daily requirement. However, most of the existing navigation systems perform path analysis based on the shortest path, and lack the measurement of road environment factors. The most important reason is the lack of basic data required by the navigation system to such information.
Under the strong irradiation of sunlight and hot environment, the solar radiation intensity of the external environment is extremely high, so that the ultraviolet index of the environment is increased, and the damage to the skin of a human body is increased. Meanwhile, as the surface temperature rises, the perceived temperature of the human body is also improved, and the travelling comfort of pedestrians is greatly influenced.
Therefore, the prior art still needs to be improved and developed, and the invention provides a simple method for detecting solar irradiance, which obtains road network irradiation indexes of different areas and improves the existing problems.
Disclosure of Invention
The invention aims to solve the technical problems that the method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image aims to solve the problems that a navigation system cannot analyze a path by considering the shade degree of a road in the prior art.
The technical scheme adopted for solving the technical problems is as follows:
a pedestrian road network solar irradiation index detection method based on remote sensing images comprises the following steps:
acquiring a remote sensing image of a region to which a pedestrian road network belongs, and processing to obtain a normalized differential vegetation index and texture characteristics;
randomly selecting partial position points of the road network, and collecting solar irradiance and corresponding position information;
acquiring normalized differential vegetation indexes and texture features corresponding to solar irradiance of each position point through the position information, and fusing and constructing a training data set; the residual data are used as a detection data set for attribute detection based on the position information fusion normalized differential vegetation index and texture characteristics;
constructing a multiple linear regression model suitable for irradiance detection based on the training dataset;
automatically identifying irradiance of the detection dataset by using a multiple linear regression model;
map matching is carried out based on the existing pedestrian road network, and the detected attribute information is endowed to position points in the pedestrian road network, so that road network basic data with the attribute information is obtained.
The method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image, wherein the method for obtaining the remote sensing image of the area to which the pedestrian road network belongs, and processing to obtain the normalized difference vegetation index and the texture feature comprises the following steps:
acquiring a remote sensing image and preprocessing the remote sensing image to obtain a preprocessed remote sensing image;
calculating a normalized differential vegetation index of the preprocessed remote sensing image by utilizing the optical characteristics of the vegetation chlorophyll;
and calculating texture features of the preprocessed remote sensing image by adopting the gray level co-occurrence matrix.
The pedestrian road network solar irradiation index detection method based on the remote sensing image, wherein the random selection of road network partial position points, the collection of solar irradiance and corresponding position information, comprises the following steps:
randomly selecting partial position points of the road network, and acquiring solar irradiance through a solar tester;
and acquiring position information corresponding to the solar irradiance acquisition point through a built-in sensor of the mobile phone.
The method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image, wherein the solar irradiance is acquired by a solar tester, comprises the following steps:
when the acquisition position point is determined, the solar irradiance of the point is acquired, meanwhile, the data of the nearby point is acquired, and the average value is obtained to obtain the final solar irradiance of the point.
According to the pedestrian road network solar irradiation index detection method based on the remote sensing image, normalized differential vegetation indexes and texture features corresponding to irradiance of each position point are obtained through position information, and a training data set is fused and constructed; the remaining data is used for attribute detection based on the position information fusion normalized differential vegetation index and texture feature as a detection data set, and comprises the following steps:
the data obtained by remote sensing image processing all have position information, and normalized differential vegetation indexes and texture features corresponding to the nearest points of solar irradiance positions are obtained through GPS data comparison, and a training data set is constructed after fusion; the rest position points which are not used for constructing the training set are only fused with the normalized difference vegetation fingers and the texture features to be used as a detection data set of the model;
wherein T represents the training data set,
represents the i-th normalized differential vegetation index, +.>
Representing the ith texture feature, y i Represents the ith solar irradiance and n represents the sample size of the training dataset.
The pedestrian road network solar irradiation index detection method based on the remote sensing image, wherein the multiple linear regression model is as follows:
irrad(x)＝θ 1 x 1 +θ 2 x 2 +θ 0 +R t
wherein irrad (x) represents solar irradiance, θ, obtained by a multiple linear regression model 1 Representing the correlation coefficient of normalized differential vegetation index and solar irradiance, θ 2 Representing the correlation coefficient of image texture and solar irradiance, R t Reference value, θ, expressed as solar irradiance for each period 0 Is a model parameter.
The pedestrian road network solar irradiation index detection method based on the remote sensing image comprises the following steps of:
wherein,,
j (θ) is lossA loss function, T represents a transpose;
the coefficient theta of the multiple linear regression model is as follows:
θ＝(X T X) -1 X T Y。
the method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image comprises the steps of carrying out map matching on the existing pedestrian road network based on map matching, and endowing detected attribute information to position points in the pedestrian road network to obtain road network basic data with the attribute information, wherein the method comprises the following steps:
based on the existing pedestrian road network OpenStreetMap, solar irradiance obtained by multiple linear regression model detection is endowed to matched position points in the pedestrian road network according to the position information, so that the basic data of the pedestrian road network has attribute information.
The method for detecting the solar irradiance index of the pedestrian road network based on the remote sensing image, wherein the solar irradiance obtained by detecting the multiple linear regression model is endowed to matched position points in the pedestrian road network according to the position information, comprises the following steps:
sequentially calculating the distance between the GPS point corresponding to the solar irradiance obtained by detection and each position point in the pedestrian road network;
and selecting the point pair combination with the shortest distance, and endowing the point solar irradiance with the matched position point in the pedestrian road network to obtain the road network basic data with the attribute information.
The pedestrian road network solar irradiation index detection method based on the remote sensing image, wherein the distance is as follows:
wherein l and m respectively represent longitude and latitude of the position point corresponding to the detected solar irradiance, l OSM And m OSM The longitude and latitude of the matched location point in the OpenStreetMap are represented, respectively.
The beneficial effects are that: the solar irradiation indexes of different regional road networks are automatically detected, and the pedestrian road network attribute with attribute information is obtained after matching, so that a certain data base is provided for personalized navigation. In the process of pedestrian travel path planning, the solar irradiation index is used as a measurement factor, so that travel paths with higher comfort can be recommended for pedestrian travel, and personalized requirements are met.
Drawings
FIG. 1 is a technical roadmap in accordance with the invention.
Fig. 2 is a flowchart of a pedestrian road network solar irradiation index detection method based on remote sensing images in the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more clear and clear, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
Referring to fig. 1-2, the present invention provides some embodiments of a method for detecting a solar irradiance index of a pedestrian road network based on a remote sensing image.
In the existing pedestrian navigation system, the route planning only analyzes the shortest route factor, lacks consideration of travel environment factors, and cannot recommend travel routes with high comfort for travel groups. Travel groups are willing to select a cool path for travel, however, the attribute information of the solar irradiation index is lacking in the current pedestrian road network data, so that a navigation system cannot take the attribute information as a measurement unit, and the navigation system can optimize and recommend comfortable navigation paths for the paths and only provide the shortest travel path. The shade degree of the road has a great relationship with the vegetation coverage condition. The vegetation index obtained from the satellite image can only reflect whether vegetation exists in the region, and can not directly reflect the vegetation coverage condition of the region. Therefore, the vegetation index needs to be analyzed together with the image texture to judge the real vegetation coverage.
As shown in fig. 1, the solar irradiance detection method provided by the invention mainly comprises four aspects. Firstly, acquiring data based on satellite images and a solar power tester, and simultaneously obtaining position information of each point; secondly, fusing the acquired data based on GPS data, and respectively constructing a training data set and a detection data set by using the fused data, wherein only the training data set is subjected to true value (irradiance) marking; thirdly, training to obtain an applicable regression model by using training set data based on a machine learning method, and detecting irradiance of a detection data set; and finally, matching the detected irradiation attribute into an OSM road network based on GPS data to obtain pedestrian road network data with attribute information. The detection method provided by the invention can automatically detect the solar irradiation indexes of different regional road networks, and the pedestrian road network data with attribute information is obtained after matching, so that a certain data basis is provided for personalized navigation. In the process of pedestrian travel path planning, the solar irradiation index is used as a measurement factor, so that travel paths with higher comfort can be recommended for pedestrian travel, and personalized requirements are met.
As shown in fig. 2, the pedestrian road network solar irradiation index detection method based on the remote sensing image comprises the following steps:
and S100, acquiring a remote sensing image of a region to which the pedestrian road network belongs, and processing to obtain a normalized differential vegetation index and texture characteristics.
Specifically, the remote sensing image refers to a digital image obtained by using various remote sensing platforms (satellite, airplane, unmanned aerial vehicle) to carry a multispectral and hyperspectral imager and adopting frame-type or scanning imaging. The acquisition channel comprises free downloading, paid ordering or shooting by using own equipment, and the like.
Specifically, the step S100 includes:
step S110, acquiring a remote sensing image and preprocessing the remote sensing image to obtain a preprocessed remote sensing image.
The preprocessing process of the remote sensing image comprises the following steps:
radiation pretreatment: the method is used for eliminating the influence of the sensor and the atmospheric interference in the imaging process on imaging, improving the image quality, and specifically comprises the processes of radiometric calibration, atmospheric correction and the like.
Geometric pretreatment: the method is characterized in that geometrical distortion, geographical position deviation and the like generated in the image imaging process are corrected through computer software, the images are inlaid, and the digital images with accurate geographical positions and no distortion or distortion meeting the requirements are formed, and specifically comprises the processes of internal orientation, relative orientation, absolute orientation, matching, splicing and the like.
And step S120, calculating a normalized differential vegetation index of the preprocessed remote sensing image by utilizing the optical characteristics of the vegetation chlorophyll.
After obtaining the preprocessed remote sensing image, the normalized vegetation index (NDVI) is calculated from the multispectral image layer using the image analysis function of arcmap—ndvi button. Specifically, normalized differential vegetation index (Normalized Difference Vegetation Index, NDVI) is calculated using the optical properties of the vegetation chlorophyll. The specific calculation principle is that vegetation chlorophyll forms strong reflection in a near infrared band and is strongly absorbed in a red band, and the calculation formula is as follows:
wherein ρ is NIR Is the reflectivity image value of near infrared band, ρ R Is the reflectance image value of the red band. In the simple calculation, the gray value calculation of the original image may be directly used instead of the reflectance image. The calculation method can be implemented in remote sensing (ENVI, ERDAS, PIE, etc.) or geographic information software (ArcMap, etc.).
The normalized differential vegetation index of the pixel point only reflects the chlorophyll concentration and does not directly reflect the vegetation type, such as grasslands, shrubs or arbors, that is, the NDVI value of each point cannot intuitively reflect the vegetation coverage condition of the position, such as grasslands or shrubs, and although the NDVI value is higher, the area is not covered by vegetation; and the vegetation cover is calculated only in the arbor area. Thus, it is further distinguished by texture features.
And step 130, calculating texture features of the preprocessed remote sensing image by using the gray level co-occurrence matrix.
Texture features are measured using a gray level co-occurrence matrix (Grey Level Cooccurrence Matrix, GLCM). The gray level co-occurrence matrix describes a rule that pixel gray levels repeatedly appear in spatial positions, and describes joint distribution of two pixel gray levels with a certain spatial position relationship. For any pixel, the gray level co-occurrence matrix texture feature calculation process is as follows:
(1) Setting a window with w being an odd number by taking the pixel as a center, and taking out a sub-image in the range for standby;
(2) Setting gray level symbiotic angles (such as 0 degree, 45 degree, 90 degree, 135 degree) and symbiotic intervals (such as 1,2,3 and the like);
(3) Setting a gray scale compression level N (e.g., 16, 32, 64, 128, etc.), stretching the image to a specified gray scale range;
(4) Initializing a gray level co-occurrence matrix P (matrix dimension N x N), counting gray level frequency on a sub-image according to a designated angle and an interval, recording the gray level frequency in the gray level co-occurrence matrix, and finally normalizing the co-occurrence matrix;
(5) Calculating a texture measurement index (P (i, j) by using the gray level co-occurrence matrix as an element of an ith row and a jth column in the gray level co-occurrence matrix P), wherein the index is calculated as follows:
contrast (Contrast) reflects the sharpness of the image and the depth of the texture grooves, the darker the texture grooves, the more pixels the greyscale difference is large, the larger the Contrast value.
The dissimilarity (dissimilarity) is similar to the contrast but increases linearly. The higher the local contrast, the higher the dissimilarity.
The energy (ASM) is a measure of the stability of the gray level variation of an image texture, with larger values representing a more regular variation of the texture.
The inverse difference moment (Inverse differentmoment, IDM) reflects the homogeneity of the image texture, measuring how much the image texture locally varies. The larger the value, the lack of variation between different regions of the image texture, and the locally very uniform.
Entropy (Entropy) reflects the uniformity of the gray level co-occurrence matrix value of the image, namely, when the image goldfish is random or the noise value is large, the Entropy is also large.
Step S200, randomly selecting partial position points of the road network, and collecting solar irradiance and corresponding position information.
Specifically, step S200 includes:
step S210, randomly selecting partial position points of the road network, and acquiring solar irradiance through a solar tester.
And S220, acquiring position information corresponding to the solar irradiance through a built-in sensor of the mobile phone.
The TES-1333 solar power tester is an accurate instrument specially used for measuring solar radiation power on site, can measure solar power in different directions and angles, solar transmittance of heat insulation materials, solar energy integral measurement and the like, and is suitable for solar panel construction and installation measurement, solar research, vegetable and flower greenhouse planting, indoor greenhouse design, glass, heat insulation paper and parasol production and hydrologic analysis. In the using process of the tester, the maximum value, the minimum value and the average value can be read according to the selection of the modes, and the read values of the maximum value, the minimum value and the average value are all the current read values. Wherein the average value is a moving average of the current value of the last 4 occurrences to smooth the unstable readings.
The solar irradiance is acquired by adopting the solar tester of the model, meanwhile, the data of the acquisition point and the nearby point are acquired, and the average value is obtained to obtain the solar irradiance. Since irradiance of an acquisition point cannot be directly reflected as a true value of the point in the data acquisition process, a plurality of points need to be acquired at the same time near the point, and a multi-point average value is used as the true value of the acquisition point. Besides the irradiance collection of the collection points and surrounding points, the GPS information of the collection points is recorded through the built-in sensor of the mobile phone.
In addition, weather reasons, time periods are different, and the collection of solar irradiance is greatly influenced by various time factors. Therefore, solar irradiance needs to be collected in open places for different weather and different time periods. Because the geographic factors and atmospheric conditions of the same regional area are basically similar, the solar irradiance in the same period is approximately the same, and the irradiance collected in an open environment is used as a reference value of the whole regional area. A reference value is added to the regression model to represent control of the time resolution.
Step S300, obtaining NDVI and texture features corresponding to solar irradiance of each position point through position information, and fusing and constructing a training data set; and the residual data are used as detection data sets for attribute detection based on the position information fusion NDVI and texture characteristics.
Specifically, because the data obtained by processing the remote sensing image all have position information, the NDVI and texture values corresponding to the nearest point of irradiance position are obtained through the comparison of GPS data, and a training data set is constructed after fusion; the rest position points which are not used for constructing the training set are only fused with the NDVI and the texture value to be used as detection data of the model. The training data are: the location information, the normalized differential vegetation index, the textural features, and the solar irradiance; the detection dataset comprises: the location information, the normalized differential vegetation index, and the textural features. Specifically, the training data set T and the detection data set D are respectively:
wherein,,
represents the i-th normalized differential vegetation index, +.>
Representing the ith texture feature, y i Represents the ith solar irradiance, n represents the sample size of the training dataset, and m represents the sample size of the detection dataset.
And step 400, constructing a multiple linear regression model suitable for irradiance detection based on the training data set.
After the training data set is obtained, regression analysis is carried out on the data of different solar irradiance by adopting a machine learning algorithm, and a multiple linear regression model suitable for irradiance detection is obtained.
A multiple linear regression model for predicting solar irradiance by establishing linear combinations between features,
the multiple linear regression model is:
irrad(x)＝θ 1 x 1 +θ 2 x 2 +θ 0 +R t
wherein irrad (x) represents solar irradiance, θ, obtained by a multiple linear regression model 1 Representing the correlation coefficient of normalized differential vegetation index and solar irradiance, θ 2 Representing the correlation coefficient of image texture and solar irradiance, R t Reference value, θ, expressed as solar irradiance for each period 0 Is a model parameter.
The mean square error is taken as a loss function of the multiple linear regression model, and model parameters theta are obtained by solving the loss function 0 、θ 1 θ 2 . The mean square error is the sum of squares of the residuals divided by the sample size n, and the sum of squares of the residuals is the parameter most commonly used in linear regression.
The loss function is:
wherein,,
t represents the transpose.
The coefficient theta of the multiple linear regression model can be obtained by the loss function J (theta):
θ＝(X T X) -1 X T Y
after the correlation coefficient of each feature in the model is determined, a multiple linear regression model among the feature NDVI, the image texture and the solar irradiance is obtained.
And S500, automatically identifying irradiance of the detection data set by using a multiple linear regression model.
Specifically, the detection data set is input as characteristic data of a regression model, and the numerical value of solar irradiance of the pedestrian road network corresponding to each data in the data set can be obtained. And (3) obtaining solar irradiation indexes of all position points of the pedestrian road network through a regression model, reserving position data of the position points, and using the position data for map matching in the next step to display attributes.
And step 600, map matching is performed based on the existing pedestrian road network, and the detected attribute information is endowed to position points in the pedestrian road network, so that road network basic data with the attribute information is obtained.
Specifically, based on the existing pedestrian road network OpenStreetMap, solar irradiance obtained by multiple linear regression model detection is endowed to matched position points in the pedestrian road network according to the position information, so that the basic data of the pedestrian road network has attribute information. In order to realize attribute addition of road network basic data, attribute matching is required to be carried out based on the position information. And taking the OpenStreetMap downloaded road network data as basic data, and adding the solar irradiation index with the position information into the road network to obtain the road network data with the attribute. To achieve this, attribute matching will be based on GPS data. The specific matching process comprises the following steps:
(1) And sequentially calculating the distance between the GPS point corresponding to the solar irradiance obtained by detection and each position point in the pedestrian road network.
The calculation formula of the distance is as follows:
wherein l and m respectively represent the longitude and latitude of the position point corresponding to the detected solar irradiance, l OSM And m OSM The longitude and latitude of the matched point in the OpenStreetMap are represented, respectively.
(2) And selecting the point pair combination with the shortest distance, and endowing the solar irradiance of the point to the matched position point in the pedestrian road network to obtain the road network basic data with the attribute information.
It is worth to say that the invention will extract normalized vegetation index (NDVI) based on the remote sensing image, image texture carry on the irradiation index detection of regional pedestrian road network. And collecting solar irradiance of the road network by using a solar power tester, and taking the solar irradiance as a true value. And constructing a linear regression model between the NDVI and the image texture and the solar irradiance through a machine learning algorithm. Data are acquired in the same way, and solar irradiance of the pedestrian road network of the area involved in the non-training data is detected by using the constructed model. The index obtained by detection is added into the data of the road network and used as attribute information of the road network basic data, namely, environmental factors can be considered in path planning, so that the service function of personalized navigation is realized.
In summary, the method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image provided by the invention comprises the following steps: acquiring a remote sensing image of a region to which a pedestrian road network belongs, and processing to obtain a normalized differential vegetation index and texture characteristics; randomly selecting partial position points of the road network, and collecting solar irradiance and corresponding position information; obtaining NDVI and texture values corresponding to solar irradiance of each position point through the position information, and fusing and constructing training data; the residual data is used for attribute detection based on the position fusion NDVI and the texture value as detection data; constructing a multiple linear regression model based on the training data set to obtain a regression model suitable for irradiance detection; and automatically detecting irradiance of the detection data by using the obtained regression model, carrying out map matching based on the existing pedestrian road network, and endowing the detected attribute information to position points in the road network to obtain road network basic data with the attribute information. The solar irradiation indexes of different regional road networks are automatically detected, and the pedestrian road network attribute with attribute information is obtained after matching, so that a certain data base is provided for personalized navigation. In the process of pedestrian travel path planning, the solar irradiation index is used as a measurement factor, so that travel paths with higher comfort can be recommended for pedestrian travel, and personalized requirements are met.
It is to be understood that the invention is not limited in its application to the examples described above, but is capable of modification and variation in light of the above teachings by those skilled in the art, and that all such modifications and variations are intended to be included within the scope of the appended claims.
Claims (8)
1. A pedestrian road network solar irradiation index detection method based on remote sensing images is characterized by comprising the following steps:
acquiring a remote sensing image of a region to which a pedestrian road network belongs, and processing to obtain a normalized differential vegetation index and texture characteristics;
randomly selecting partial position points of the road network, and collecting solar irradiance and corresponding position information;
acquiring normalized differential vegetation indexes and texture features corresponding to solar irradiance of each position point through the position information, and fusing and constructing a training data set; the residual data are used as a detection data set for attribute detection based on the position information fusion normalized differential vegetation index and texture characteristics;
constructing a multiple linear regression model suitable for irradiance detection based on the training dataset;
automatically identifying irradiance of the detection dataset by using a multiple linear regression model;
map matching is carried out based on the existing pedestrian road network, and the detected attribute information is endowed to position points in the pedestrian road network, so that road network basic data with the attribute information is obtained;
the multiple linear regression model is:
wherein,,
represents solar irradiance obtained by a multiple linear regression model,/->
Representing the correlation coefficient of the normalized differential vegetation index and solar irradiance,/->
Representing the correlation coefficient of the image texture and solar irradiance, ">
Reference value expressed as solar irradiance of each period, < +.>
For model parameters +.>
Representing normalized differential vegetation index,/->
Representing texture features;
coefficients of the multiple linear regression model
Obtained by the following loss function:
wherein,,
，/>
，/>
，/>
as a function of the loss,Trepresenting a transpose;
coefficients of the multiple linear regression model
The method comprises the following steps:
wherein,,
represent the firstnNormalized differential vegetation index->
Represent the firstnTexture feature->
Represent the firstnThe irradiance of the light of the individual sun,nrepresenting the sample size of the training dataset.
2. The method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image according to claim 1, wherein the steps of obtaining the remote sensing image of the area to which the pedestrian road network belongs, processing to obtain the normalized differential vegetation index and the texture feature comprise the following steps:
acquiring a remote sensing image and preprocessing the remote sensing image to obtain a preprocessed remote sensing image;
calculating a normalized differential vegetation index of the preprocessed remote sensing image by utilizing the optical characteristics of the vegetation chlorophyll;
and calculating texture features of the preprocessed remote sensing image by adopting the gray level co-occurrence matrix.
3. The method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image according to claim 1, wherein the step of randomly selecting the partial position points of the road network and collecting solar irradiance and corresponding position information comprises the following steps:
randomly selecting partial position points of the road network, and acquiring solar irradiance through a solar tester;
and acquiring position information corresponding to the solar irradiance acquisition point through a built-in sensor of the mobile phone.
4. The method for detecting the solar irradiance index of the pedestrian road network based on the remote sensing image according to claim 3, wherein the step of acquiring solar irradiance by a solar tester comprises the steps of:
when the acquisition position point is determined, the solar irradiance of the point is acquired, meanwhile, the data of the nearby point is acquired, and the average value is obtained to obtain the final solar irradiance of the point.
5. The method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image according to claim 1, wherein the normalized differential vegetation index and the texture feature corresponding to irradiance of each position point are obtained through position information, and are fused and a training data set is constructed; the remaining data is used for attribute detection based on the position information fusion normalized differential vegetation index and texture feature as a detection data set, and comprises the following steps:
the data obtained by remote sensing image processing all have position information, and normalized differential vegetation indexes and texture features corresponding to the nearest points of solar irradiance positions are obtained through GPS data comparison, and a training data set is constructed after fusion; the rest position points which are not used for constructing the training set are only fused with the normalized difference vegetation fingers and the texture features to be used as a detection data set of the model;
wherein T represents the training data set,
represent the firstiNormalized differential vegetation index->
Represent the firstiThe number of texture features is a function of the number of texture features,
represent the firstiAnd solar irradiance.
6. The method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image according to claim 1, wherein the map matching is performed based on the existing pedestrian road network, the detected attribute information is given to the position points in the pedestrian road network, and the road network basic data with the attribute information is obtained, and the method comprises the following steps:
based on the existing pedestrian road network OpenStreetMap, solar irradiance obtained by multiple linear regression model detection is endowed to matched position points in the pedestrian road network according to the position information, so that the basic data of the pedestrian road network has attribute information.
7. The method for detecting solar irradiance of pedestrian road network based on remote sensing image according to claim 6, wherein the step of assigning solar irradiance obtained by multiple linear regression model detection to the matched position point in the pedestrian road network according to the position information comprises the steps of:
sequentially calculating the distance between the GPS point corresponding to the solar irradiance obtained by detection and each position point in the pedestrian road network;
and selecting the point pair combination with the shortest distance, and endowing the solar irradiance of the point to the matched position point in the pedestrian road network to obtain the road network basic data with the attribute information.
8. The method for detecting the solar irradiation index of the pedestrian road network based on the remote sensing image according to claim 7, wherein the distance is as follows:
wherein,,
indicate distance (I)>
And->
Respectively representing longitude and latitude of the position point corresponding to the detected solar irradiance, +.>
And->
The longitude and latitude of the matched location point in the OpenStreetMap are represented, respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010332218.2A CN111652056B (en) | 2020-04-24 | 2020-04-24 | Pedestrian road network solar irradiation index detection method based on remote sensing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010332218.2A CN111652056B (en) | 2020-04-24 | 2020-04-24 | Pedestrian road network solar irradiation index detection method based on remote sensing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111652056A CN111652056A (en) | 2020-09-11 |
| CN111652056B true CN111652056B (en) | 2023-06-23 |
Family
ID=72349296
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010332218.2A Active CN111652056B (en) | 2020-04-24 | 2020-04-24 | Pedestrian road network solar irradiation index detection method based on remote sensing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111652056B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115060231B (en) * | 2022-06-10 | 2023-11-07 | 中国矿业大学 | Unmanned aerial vehicle image-based soil erosion trench depth measuring and calculating method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288954A (en) * | 2011-08-01 | 2011-12-21 | 高吉喜 | Remote sensing estimation method for vegetation coverage of grassland |
| CN102708307A (en) * | 2012-06-26 | 2012-10-03 | 上海大学 | Vegetation index construction method applied to city |
| CN110186820A (en) * | 2018-12-19 | 2019-08-30 | 河北中科遥感信息技术有限公司 | Multisource data fusion and environomental pollution source and pollutant distribution analysis method |
| CN110852381A (en) * | 2019-11-11 | 2020-02-28 | 四川航天神坤科技有限公司 | Forest fire burned area extraction method and system |
-
2020
- 2020-04-24 CN CN202010332218.2A patent/CN111652056B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102288954A (en) * | 2011-08-01 | 2011-12-21 | 高吉喜 | Remote sensing estimation method for vegetation coverage of grassland |
| CN102708307A (en) * | 2012-06-26 | 2012-10-03 | 上海大学 | Vegetation index construction method applied to city |
| CN110186820A (en) * | 2018-12-19 | 2019-08-30 | 河北中科遥感信息技术有限公司 | Multisource data fusion and environomental pollution source and pollutant distribution analysis method |
| CN110852381A (en) * | 2019-11-11 | 2020-02-28 | 四川航天神坤科技有限公司 | Forest fire burned area extraction method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111652056A (en) | 2020-09-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109581372B (en) | Ecological environment remote sensing monitoring method | |
| CN111368817B (en) | Method and system for quantitatively evaluating thermal effect based on earth surface type | |
| US20190258899A1 (en) | In-scene multi-angle surface-specific signature generation and exploitation | |
| CN110865040A (en) | Sky-ground integrated hyperspectral water quality monitoring and analyzing method | |
| Jawak et al. | Improved land cover mapping using high resolution multiangle 8-band WorldView-2 satellite remote sensing data | |
| CN111832518B (en) | Space-time fusion-based TSA remote sensing image land utilization method | |
| CN113284171B (en) | Vegetation height analysis method and system based on satellite remote sensing stereo imaging | |
| Luo et al. | Scale effect analysis of the relationships between urban heat island and impact factors: case study in Chongqing | |
| Otgonbayar et al. | Land suitability evaluation for agricultural cropland in Mongolia using the spatial MCDM method and AHP based GIS | |
| CN108896188A (en) | A kind of high rail remote sensing satellite infrared channel atmospheric correction method of Shared aperture | |
| Susaki et al. | Validation of MODIS albedo products of paddy fields in Japan | |
| CN114241024B (en) | Artificial neural network building texture mapping method and system based on sliding edge detection | |
| CN115457396B (en) | Surface target ground object detection method based on remote sensing image | |
| CN111652056B (en) | Pedestrian road network solar irradiation index detection method based on remote sensing image | |
| CN116519557B (en) | Aerosol optical thickness inversion method | |
| CN111582575A (en) | Method for identifying urban thermal environment formation development leading factors under multiple space-time scales | |
| Moreira et al. | Variation in spectral shape of urban materials | |
| CN115187481A (en) | Airborne push-broom hyperspectral image radiation disturbance correction method | |
| Zhang et al. | A back propagation neural network-based radiometric correction method (BPNNRCM) for UAV multispectral image | |
| CN110909821B (en) | Method for carrying out high-space-time resolution vegetation index data fusion based on crop reference curve | |
| CN110070513B (en) | Radiation correction method and system for remote sensing image | |
| CN115546658B (en) | Night cloud detection method combining quality improvement and CNN improvement of data set | |
| CN112364289B (en) | Method for extracting water body information through data fusion | |
| CN116612080A (en) | Variation detection method based on hyperspectral image spectrum curve | |
| CN105842755A (en) | Urban residential zone heat island effect measuring device and method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |