CN109978862A - A kind of air pollution estimation method based on satellite image - Google Patents
A kind of air pollution estimation method based on satellite image Download PDFInfo
- Publication number
- CN109978862A CN109978862A CN201910238150.9A CN201910238150A CN109978862A CN 109978862 A CN109978862 A CN 109978862A CN 201910238150 A CN201910238150 A CN 201910238150A CN 109978862 A CN109978862 A CN 109978862A
- Authority
- CN
- China
- Prior art keywords
- image
- detection
- point
- carried out
- key point
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10041—Panchromatic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30192—Weather; Meteorology
Abstract
The air pollution estimation method based on satellite image that the present invention provides a kind of, comprising: the thermal infrared grayscale image of 10-TIRS wave band obtains the thermal infrared grayscale image for meeting preset standard in the Landsat-8 satellite that will acquire after being pre-processed；Operation is carried out out to image, the image Jing Guo threshold filtering is carried out critical point detection by threshold filtering, calculates detection key point duplicate removal of the Duplication to acquisition, the detection key point and detection range dispersed；The image of detection key point and detection range to dispersion carries out threshold filtering, and removal pixel value is lower than the detection key point of threshold value, remaining detection key point and detection range are restored in original image.The present invention estimates the subregional air pollution in Jing-jin-ji region northeast using the image of the subregional satellite thermal infrared detection in northeast of single width Jing-jin-ji region.And by assisting the prediction of the weather visibility of some areas of Jing-jin-ji region, the method increase calculating speed, reducing costs using estimated data as the auxiliary data of weather visibility.
Description
Technical field
The invention belongs to air pollution estimation technique field more particularly to a kind of air pollution estimation sides based on satellite image
Method.
Background technique
In the prior art, the method for the prediction of weather visibility generally reads satellite data medium cloud amount product and and corresponds to
Criterion be compared, determine that the biggish range of possibility occur in cloud or haze；Using cloud optical thickness information in satellite data and
Corresponding criterion is compared, and further extracts the region of haze distribution；Using satellite data medium cloud phase information and corresponding sentence
According to being compared, the region of haze distribution is further extracted；It is compared using cloud top pressure data and corresponding criterion, further
Extract the region of haze distribution.The present invention also designs the method for determining the criterion.The present invention is especially with POLDER satellite data
Illustrate the process implemented for P3L2TRGB.This method under the premise of not needing other auxiliary datas, can fast and stable it is real
The detection of existing POLDER satellite data haze, calculation amount are small and applied widely.
Inventor has found in the course of the study: it is big that existing technology needs to obtain data volume, obtain a large amount of data into
The cost of row processing is larger, while to will cause calculating speed slow for biggish data volume, and consumption computing resource is big.
Remote sensing technology has the ability for efficiently collecting earth's surface information, remotely-sensed data introduction used in the present invention: 2013 2
The moon 11, NASA (NASA) succeeds in sending up Landsat-8 satellite.Two sensings are carried on Landsat-8 satellite
Device is the land OLI imager (Operational Land Imager) and TIRS thermal infrared sensor (Thermal respectively
Infrared Sensor)。
Landsat-8 spatial resolution and in terms of almost the same, satellite is maintained with Landsat1-7
One shares 11 wave bands, and the spatial resolution of wave band 1-7,9-11 are 30 meters, and wave band 8 is the panchromatic wave-band of 15 meters of resolution ratio, is defended
A Global coverage may be implemented within star every 16 days.
The land OLI imager has 9 wave bands, and imaging wide cut is 185x185km.With the ETM sensor phase on Landsat-7
Than the land OLI imager has done following adjustment: the wavelength band of 1.Band5 is adjusted to 0.845-0.885 μm, eliminates 0.825
The influence of water vapor absorption at μm；2.Band8 panchromatic wave-band range is relatively narrow, so as to more preferably distinguish vegetation and nonvegetated area domain；
3. increasing two wave bands newly.Band1 blue wave band (0.433-0.453 μm) is mainly used in littoral zone observation, Band9 short-wave infrared
(1.360-1.390 μm) of wave band are applied to cloud detection.The TIRS thermal infrared sensor carried on LandSat-8 is mainly used for collecting
The heat losses in two hot-zones of earth area, target are to understand observed area water consumption.
The present invention will use the satellite image data of 10-TIRS wave band collected by TIRS thermal infrared sensor to discharge
Estimation.
The purposes of 10-TIRS wave band (30 meters) is to carry out Surface Temperature Retrieval, fire detection, soil moisture evaluation, night
Imaging, used wave band/μm: 10.60-11.19.10-TIRS wave band is quick to the plant emissions point and high temperature discharge object of high temperature
Sense, in the satellite mapping of 10-TIRS wave band, the higher object of temperature is presented as that pixel value is higher in figure.The present invention is directed to 10-
This characteristic of TIRS wave band carries out the range of discharge detection estimation discharge to the corresponding region of satellite acquisition image.
Summary of the invention
The purpose of the present invention is the images of the satellite thermal infrared of the partial region using single width Jing-jin-ji region detection to Jing-jin-ji region
The subregional air pollution in northeast is estimated.And by using estimated data as the auxiliary data of weather visibility, auxiliary
The prediction of the weather visibility of northeast some areas of Jing-jin-ji region provides a kind of air pollution estimation side based on satellite image
Method, this method can be improved calculating speed, reduce cost.
In order to achieve the above objectives, the present invention implements by the following technical programs:
The present invention provides a kind of air pollution estimation method based on satellite image, comprising:
Step 1: after the thermal infrared grayscale image of 10-TIRS wave band is pre-processed in the Landsat-8 satellite that will acquire
To the thermal infrared grayscale image for meeting preset standard；
Step 2: operation is carried out out to the image for the thermal infrared grayscale image for meeting preset standard, it will be after opening operation
Image carries out threshold filtering, obtains the high temperature extraordinary image vegetarian refreshments that pixel value is higher than threshold value；
Step 3: the image Jing Guo threshold filtering is carried out critical point detection, detection key point and detection range are obtained.
Step 4: detection key point duplicate removal of the calculating Duplication to acquisition, the detection key point dispersed and detection model
It encloses；The image of detection key point and detection range to dispersion carries out threshold filtering, and detection of the removal pixel value lower than threshold value is closed
Key point restores remaining detection key point and detection range in original image.
Pretreated step includes: in the step 1
For the thermal infrared grayscale image image of the 10-TIRS wave band in the Landsat-8 satellite of acquisition with tilt angle
Profile correction is carried out, and gridding cutting is carried out to the image after profile correction based on pre-set dimension, obtains meeting preset standard
Thermal infrared grayscale image.
The step of opening operation in the step 2 include:
Corroded by image of the preset smoothing factor to the thermal infrared grayscale image for meeting preset standard, and to corrosion
Image later carries out expansion process.
In the step 2, the step of image after operating carries out threshold filtering is opened, comprising:
The split obtained result figure that operates draws grey level histogram, takes threshold value as segmentation threshold grey level histogram, small
0 is taken in threshold value, greater than the holding initial value of threshold value.
Further, include: by the method that the image by filtering carries out critical point detection
Image by filtering is subjected to critical point detection by SURF algorithm or SIFT algorithm.
In the step 3, include: by the step of SURF algorithm progress critical point detection
All characteristic points will be generated, will be used by pretreated image as input building Hessian matrix (Hessian)
In the extraction of feature；
Scaling is carried out to the image of input and constructs different scale spaces；
Positioning feature point is carried out to the different scale spatial image of building and obtains characteristic point；
Principal direction distribution is carried out to characteristic point, obtains the location information, principal direction information and range information of characteristic point；
The location information of characteristic point, principal direction information and range information are combined and generate feature point description；
The position in original image is corresponded to characteristic point based on feature point description to match, and obtains being labeled with testing result
Result figure is exported, crucial test point and detection range are exported.
In the step 3, include: by the step of SIFT algorithm progress critical point detection
Scaling will be carried out by pretreated image construct scale space；
Extremum extracting is carried out to the scale space of building, there is scale invariability and rotation by the identification of gaussian derivative function
The characteristic point of invariance；
The characteristic point of different scale is positioned, the gradient direction of the part based on image, for the characteristic point point of identification
With principal direction；
Descriptor is generated for the characteristic point on the figure on selected scale, descriptor includes principal direction and the spy of characteristic point
Levy the position location of point.
The beneficial effects of the present invention are:
The present invention is handled using the satellite image of the 10-TIRS wave band of Landsat-8 satellite, due to the number of data set
It measures less and is easy to get, while the process that have passed through the estimation that pretreated image carries out plant emissions only needs 60s or so,
Preferably 50s greatly reduces the time of processing data, and the factory that can quickly and efficiently obtain the current locale object time is dirty
Contaminate the estimation of discharge.The calculating speed of technical solution provided by the invention is fast: calculating the 10- of a complete Landsat-8
The time that the image of TIRS needs is few, it is only necessary to the time less than one minute, and be obtained with without training as a result, opposite
The process and a large amount of data with mark for needing largely to train than deep neural network, save data calculation processing when
Between；Calculate at low cost: required data from the satellite image data downloaded on the website EarthExploer；Calculate consumption
Few, hardware requirement is low: any one CPU with notebook can be carried out the processing of image data.
Detailed description of the invention
Fig. 1 show the thermal infrared grayscale image schematic diagram of 10-TIRS wave band in the Landsat-8 satellite of acquisition.
Fig. 2 obtains the thermal infrared grayscale image schematic diagram for meeting preset standard after showing pretreatment.
Fig. 3 show out operation chart.
Fig. 4 show the result schematic diagram obtained by opening operation.
Fig. 5 show the result schematic diagram obtained by binaryzation.
Fig. 6, which is shown, carries out critical point detection result schematic diagram by SURF algorithm.
Fig. 7 show the result schematic diagram judged by duplicate removal and pixel value.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
Embodiment one
As shown in figs. 1-7, the air pollution estimation method based on satellite image that the embodiment of the invention provides a kind of, packet
It includes:
Step 1: after the thermal infrared grayscale image of 10-TIRS wave band is pre-processed in the Landsat-8 satellite that will acquire
To the thermal infrared grayscale image for meeting preset standard.
Since the thermal infrared grayscale image of the 10-TIRS wave band of downloading acquisition generally all has certain inclined angle, generally
It is 15 °, while pixel is larger, has certain difficulty in processing, so needs to carry out pretreatment operation to image: where pre-
The step of processing includes: as shown in Figure 1, for the 10-TIRS wave band with tilt angle in the Landsat-8 satellite obtained
Thermal infrared grayscale image image carries out profile correction, and carries out gridding cutting to the image after profile correction based on pre-set dimension,
As shown in Fig. 2, carrying out the cutting of 10*10 to obtained correcting image, the thermal infrared grayscale image for meeting preset standard, the figure are obtained
For the thermal infrared grayscale image of the Jing-jin-ji region the Northeast of 10-TIRS wave band in the Landsat-8 satellite after profile is corrected.
Step 2: carrying out out operation to the image for the thermal infrared grayscale image for meeting preset standard, the image after operating will be opened
Threshold filtering is carried out, the high temperature extraordinary image vegetarian refreshments that pixel value is higher than threshold value is obtained.
The step of opening operation includes: the image by preset smoothing factor to the thermal infrared grayscale image for meeting preset standard
Corroded, and expansion process is carried out to the image after corrosion.As shown in figure 3, first A is corroded with smoothing factor B, then
The result after corrosion is expanded with BProcessing result is as illustrated in figures 4-5.
The step of image after opening operation carries out threshold filtering, comprising: it is straight that the result figure that split operation obtains draws gray scale
Fang Tu takes threshold value as segmentation threshold grey level histogram, takes 0 less than threshold value, greater than holding initial value (the present embodiment of threshold value
In, threshold value is set as 220, threshold value is set according to the case where histogram of image, and value range is in 84 to 240) filtering
High temperature extraordinary image vegetarian refreshments of the pixel value higher than threshold value in thermodynamic chart out.
Step 3: the image Jing Guo threshold filtering is carried out critical point detection, detection key point and detection range (one are obtained
As obtain is intensive Duplication big detection key point and detection range).Method includes: that will pass through by the image of filtering
SURF algorithm or SIFT algorithm carry out critical point detection, generate the discharge test point on satellite image.
As shown in fig. 6, the step of carrying out critical point detection by SURF algorithm includes: using filtered image as input
It constructs Hessian matrix (Hessian), generates all characteristic points, the extraction for feature；
Scaling is carried out to the image of input and constructs different scale spaces；
Positioning feature point is carried out to the different scale spatial image of building and obtains characteristic point；
Principal direction distribution is carried out to characteristic point, obtains the location information, principal direction information and range information of characteristic point；
The location information of characteristic point, principal direction information and range information are combined and generate feature point description；
The position in original image is corresponded to characteristic point based on feature point description to match, and obtains being labeled with testing result
Result figure is exported, crucial test point and detection range are exported.
In the step 3, include: by the step of SIFT algorithm progress critical point detection
Scaling will be carried out by pretreated image carry out building scale space；
Extremum extracting is carried out to the scale space of building, there is scale invariability and rotation by the identification of gaussian derivative function
The characteristic point of invariance；
The characteristic point of different scale is positioned, the gradient direction of the part based on image, for the characteristic point point of identification
With principal direction；
Descriptor is generated for the characteristic point on the figure on selected scale, descriptor includes principal direction and the spy of characteristic point
Levy the position location of point.
Step 4: detection key point duplicate removal of the calculating Duplication to acquisition, the detection key point dispersed and detection model
It encloses；The image of detection key point and detection range to dispersion carries out threshold filtering, and (in the present embodiment, threshold value is set as herein
120), removal temperature is lower than the detection key point of threshold value, and (the point error detection in mountain range and gully is plant emissions point by removal
Error detection key point) remaining detection key point and detection range are restored in original image.
As shown in fig. 7, obtaining the pixel position that be labeled with may for plant emissions point and discharge range to step 3
Mark obtains non-overlapping detection zone to having the detection zone being largely overlapped to choose the maximum detection zone of coverage area；
Threshold decision is carried out to the pixel of detection zone, it is object detection area that pixel value, which is higher than given threshold, is lower than
Threshold value is non-targeted detection zone；Finally obtained target area is plotted in the original image of input.
Experimental verification: table 1 is detection elapsed time comparison:
Table 1
The beneficial effect of the embodiment of the present invention one is:
The present invention is handled using the satellite image of the 10-TIRS wave band of Landsat-8 satellite, due to the number of data set
It measures less and is easy to get, while the process that have passed through the estimation that pretreated image carries out plant emissions only needs 60s or so,
Preferably 50s greatly reduces the time of processing data, and the factory that can quickly and efficiently obtain the current locale object time is dirty
Contaminate the estimation of discharge.The calculating speed of technical solution provided by the invention is fast: calculating the 10- of a complete Landsat-8
Time needed for the image of TIRS is few, it is only necessary to be obtained with less than 1 minute, and without training as a result, the depth that compares
Neural network needs the process of training, saves the time of data calculation processing；It is at low cost: required data come from
The satellite image data downloaded on the website EarthExploer；It is few to calculate consumption, hardware requirement is low: any one has notebook
CPU can be carried out the processing of image data.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
It should be noted that for the various method embodiments described above, for simple description, therefore, it is stated as a series of
Combination of actions, but those skilled in the art should understand that, the present invention is not limited by the sequence of acts described because
According to the present invention, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art should also know
It knows, the embodiments described in the specification are all preferred embodiments, and related actions and modules is not necessarily of the invention
It is necessary.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (7)
1. a kind of air pollution estimation method based on satellite image characterized by comprising
Step 1: the thermal infrared grayscale image of 10-TIRS wave band is accorded with after being pre-processed in the Landsat-8 satellite that will acquire
Close the thermal infrared grayscale image of preset standard；
Step 2: operation is carried out out to the image for the thermal infrared grayscale image for meeting preset standard, by the image after opening operation
Threshold filtering is carried out, the high temperature extraordinary image vegetarian refreshments that pixel value is higher than threshold value is obtained；
Step 3: the image Jing Guo threshold filtering is carried out critical point detection, detection key point and detection range are obtained.
Step 4: calculating detection key point duplicate removal of the Duplication to acquisition, the detection key point and detection range dispersed；It is right
The detection key point of dispersion and the image of detection range carry out threshold filtering, and removal is lower than the detection key point of threshold value, will be remaining
Detection key point and detection range restored in original image.
2. the method as described in claim 1, which is characterized in that pretreated step includes: in the step 1
It is carried out for the thermal infrared grayscale image image of the 10-TIRS wave band in the Landsat-8 satellite of acquisition with tilt angle
Profile correction, and gridding cutting is carried out to the image after profile correction based on pre-set dimension, obtain the heat for meeting preset standard
Infrared grayscale image.
3. method according to claim 1 or 2, which is characterized in that the step of opening operation in the step 2 include:
Corroded by image of the preset smoothing factor to the thermal infrared grayscale image for meeting preset standard, and to corrosion after
Image carry out expansion process.
4. the method as described in one of claim 1-3, which is characterized in that in the step 2, the image after opening operation is carried out
The step of threshold filtering, comprising:
The split obtained result figure that operates draws grey level histogram, takes threshold value as segmentation threshold grey level histogram, is less than threshold
Value takes 0, greater than the holding initial value of threshold value.
5. the method as described in one of claim 1-4, which is characterized in that in the step 3, by by filtering image into
The method of row critical point detection includes:
Image by filtering is subjected to critical point detection by SURF algorithm or SIFT algorithm.
6. method as claimed in claim 5, which is characterized in that in the step 3, carry out key point inspection by SURF algorithm
The step of survey includes:
All characteristic points will be generated, for spy by pretreated image as input building Hessian matrix (Hessian)
The extraction of sign；
Scaling is carried out to the image of input and constructs different scale spaces；
Positioning feature point is carried out to the different scale spatial image of building and obtains characteristic point；
Principal direction distribution is carried out to characteristic point, obtains the location information, principal direction information and range information of characteristic point；
The location information of characteristic point, principal direction information and range information are combined and generate feature point description；
The position in original image is corresponded to characteristic point based on feature point description to match, and obtains the output for being labeled with testing result
Result figure exports crucial test point and detection range.
7. method as claimed in claim 5, which is characterized in that in the step 3, carry out key point inspection by SIFT algorithm
The step of survey includes:
Scaling will be carried out by pretreated image construct scale space；
Extremum extracting is carried out to the scale space of building, there is scale invariability and invariable rotary by the identification of gaussian derivative function
The characteristic point of property；
The characteristic point of different scale is positioned, the gradient direction of the part based on image, distributes master for the characteristic point of identification
Direction；
Descriptor is generated for the characteristic point on the figure on selected scale, descriptor includes the principal direction and characteristic point of characteristic point
Position location.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910238150.9A CN109978862B (en) | 2019-03-27 | 2019-03-27 | Air pollution estimation method based on satellite image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910238150.9A CN109978862B (en) | 2019-03-27 | 2019-03-27 | Air pollution estimation method based on satellite image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109978862A true CN109978862A (en) | 2019-07-05 |
| CN109978862B CN109978862B (en) | 2021-04-27 |
Family
ID=67080961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910238150.9A Active CN109978862B (en) | 2019-03-27 | 2019-03-27 | Air pollution estimation method based on satellite image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109978862B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889327A (en) * | 2019-10-16 | 2020-03-17 | 南京航空航天大学 | Intelligent detection method for sewage draining exit around water area based on thermal infrared image |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645410A (en) * | 2012-04-28 | 2012-08-22 | 中国神华能源股份有限公司 | Detection method, device and data processing device of coal gangue pollution scope |
| CN102944880A (en) * | 2012-11-13 | 2013-02-27 | 中国科学院城市环境研究所 | Urban industrial thermal pollution source investigation method based on remote sensing |
| US20140016667A1 (en) * | 2012-07-13 | 2014-01-16 | Blue Water Satellite, Inc. | Method for monitoring water temperature |
| KR101378774B1 (en) * | 2013-11-07 | 2014-03-27 | 중앙항업(주) | Method for time-series monitoring of surface temperature using tir (thermal infrared) images |
| CN106023203A (en) * | 2016-05-19 | 2016-10-12 | 中国科学院遥感与数字地球研究所 | Fire point detection method based on Landsat-8 landsat data |
| CN106558072A (en) * | 2016-11-22 | 2017-04-05 | 重庆信科设计有限公司 | A kind of method based on SIFT feature registration on remote sensing images is improved |
-
2019
- 2019-03-27 CN CN201910238150.9A patent/CN109978862B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102645410A (en) * | 2012-04-28 | 2012-08-22 | 中国神华能源股份有限公司 | Detection method, device and data processing device of coal gangue pollution scope |
| US20140016667A1 (en) * | 2012-07-13 | 2014-01-16 | Blue Water Satellite, Inc. | Method for monitoring water temperature |
| CN102944880A (en) * | 2012-11-13 | 2013-02-27 | 中国科学院城市环境研究所 | Urban industrial thermal pollution source investigation method based on remote sensing |
| KR101378774B1 (en) * | 2013-11-07 | 2014-03-27 | 중앙항업(주) | Method for time-series monitoring of surface temperature using tir (thermal infrared) images |
| CN106023203A (en) * | 2016-05-19 | 2016-10-12 | 中国科学院遥感与数字地球研究所 | Fire point detection method based on Landsat-8 landsat data |
| CN106558072A (en) * | 2016-11-22 | 2017-04-05 | 重庆信科设计有限公司 | A kind of method based on SIFT feature registration on remote sensing images is improved |
Non-Patent Citations (5)
| Title |
|---|
| HAIPING XIA ET AL.: "A simple method based on the thermal anomaly index to detect industrial heat sources", 《INT J APPL EARTH OBS GEOINFORMATION》 * |
| MARCIN IWANOWSKI: "Detection of heat-emission sources using satellite imagery and morphological image processing", 《RESEARCHGATE》 * |
| SHENG MIAO ET AL.: "Small Fire Smoke Region Location and recogniton in Satellite Image", 《CISP-BMEI 2016》 * |
| 朱长军 等: "地面背景下基于SURF的红外目标识别方法", 《红外技术》 * |
| 马兰: "热红外遥感图像典型目标识别技术研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889327A (en) * | 2019-10-16 | 2020-03-17 | 南京航空航天大学 | Intelligent detection method for sewage draining exit around water area based on thermal infrared image |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109978862B (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Feng et al. | Using land use change trajectories to quantify the effects of urbanization on urban heat island | |
| Fu et al. | Consistent land surface temperature data generation from irregularly spaced Landsat imagery | |
| Zeng et al. | Reconstructing MODIS LST based on multitemporal classification and robust regression | |
| KR20110100970A (en) | System and method for detecting volumetric soil water content | |
| CN107610164A (en) | A kind of No. four Image registration methods of high score based on multiple features mixing | |
| CN107145848B (en) | A kind of wind erosion of soil monitoring method and system based on remotely-sensed data | |
| CN105139396B (en) | Full-automatic remote sensing image cloud and fog detection method | |
| Azmi et al. | A modified and enhanced normalized built-up index using multispectral and thermal bands | |
| Ran et al. | RGAN: Rethinking generative adversarial networks for cloud removal | |
| Guilloteau et al. | Beyond the pixel: Using patterns and multiscale spatial information to improve the retrieval of precipitation from spaceborne passive microwave imagers | |
| CN109978862A (en) | A kind of air pollution estimation method based on satellite image | |
| Liu et al. | Extraction of oil spill information using decision tree based minimum noise fraction transform | |
| CN104616253A (en) | Light cloud removing method of optical remote sensing image utilizing independent component analysis technology | |
| Zheng et al. | A thin cloud removal method from remote sensing image for water body identification | |
| Parmar et al. | Land use land cover change detection and its impact on land surface temperature of malana watershed kullu, Himachal Pradesh, India | |
| Handoko et al. | Gradient Boosting Tree for Land Use Change Detection Using Landsat 7 and 8 Imageries: A Case Study of Bogor Area as Water Buffer Zone of Jakarta | |
| Rokni | Investigating the impact of Pan Sharpening on the accuracy of land cover mapping in Landsat OLI imagery | |
| Kim et al. | Development of cloud and shadow detection algorithm for periodic composite of Sentinel-2A/B satellite images | |
| Fraser | East Antarctic landfast sea-ice distribution and variability | |
| Xu et al. | Thermal anomaly detection based on saliency computation for district heating system | |
| Peddinti et al. | Effect of aggregation and disaggregation of land surface temperature imagery on evapotranspiration estimation | |
| Zhang et al. | Remote sensing and GIS based geothermal exploration in southwest Tengchong, China | |
| Bouchahma et al. | Optical-flow-based approach for the detection of shoreline changes using remote sensing data | |
| Yin et al. | Estimating subpixel turbulent heat flux over leads from MODIS thermal infrared imagery with deep learning | |
| Listyawati et al. | Analysis of Urban Heat Island Phenomenon as A Global Warming Control Based on Remote Sensing in Jember Urban, Indonesia |
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 |