CN113591708B - Meteorological disaster monitoring method based on satellite-borne hyperspectral image - Google Patents
Meteorological disaster monitoring method based on satellite-borne hyperspectral image Download PDFInfo
- Publication number
- CN113591708B CN113591708B CN202110872682.5A CN202110872682A CN113591708B CN 113591708 B CN113591708 B CN 113591708B CN 202110872682 A CN202110872682 A CN 202110872682A CN 113591708 B CN113591708 B CN 113591708B
- Authority
- CN
- China
- Prior art keywords
- image
- hyperspectral
- representing
- hyperspectral image
- satellite
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000012544 monitoring process Methods 0.000 title claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 27
- 230000003287 optical effect Effects 0.000 claims abstract description 10
- 230000002068 genetic effect Effects 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 6
- 238000005457 optimization Methods 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009833 condensation Methods 0.000 description 1
- 230000005494 condensation Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a meteorological disaster monitoring method based on a satellite-borne hyperspectral image. Firstly, performing saliency detection on images of each wave band of a hyperspectral image by using a saliency detection algorithm pulse cosine transform to obtain a saliency result image of each wave band of the hyperspectral image, then performing motion detection on the saliency view of the hyperspectral image by using a Lucas-Kanade optical flow detection method to obtain motion detection results of the atmosphere of each wave band, and finally performing weighted optimization on the atmosphere motion detection results of all wave bands by using a genetic algorithm to obtain the motion state of an atmosphere cloud layer so as to achieve the aim of monitoring meteorological disasters.
Description
Technical Field
The invention relates to the field of meteorological disaster monitoring, in particular to a meteorological disaster monitoring method based on a satellite-borne hyperspectral image.
Background
In recent years, with the rapid development of technology, aviation traffic has greatly developed, and convection clouds are generated by rising condensation of water vapor carried by atmospheric convection motion, and are important signs of occurrence of convective weather. The convective weather is likely to form disasters, and particularly the strong convective weather such as short-time strong precipitation, thunderstorm, hail, downburst storm, tornado and the like has the characteristics of strong burst and locality, short life history, heavy disasters and the like. For example, gravitational waves and atmospheric turbulence created by ram convection excitation can propagate hundreds of kilometers in both vertical and horizontal directions, and aircraft traversing these areas can create severe bumps and even threaten flight safety. However, the predictive consistency of the convective cloud is a difficulty in the development of science and technology,
therefore, it is needed to provide a method for detecting the convective cloud to increase the accuracy of meteorological monitoring.
Disclosure of Invention
In order to solve the above-mentioned problems. The invention provides a meteorological disaster monitoring method based on a satellite-borne hyperspectral image, which is used for effectively monitoring a convection cloud and achieving the purpose of:
the invention provides a meteorological disaster monitoring method based on a satellite-borne hyperspectral image, which comprises the following specific steps of:
step 1: collecting information of atmospheric convection cloud hyperspectral images by using a satellite-borne hyperspectral imager, wherein the size of each image is N x ×N y ×N λ Wherein x represents the width of the hyperspectral image space dimension, y represents the height of the hyperspectral image space dimension, and λ represents the number of the spectral dimensions;
step 2: performing significance detection on the data of each wave band of the hyperspectral image by using an improved PCT algorithm to obtain a significance result graph of each wave band of the hyperspectral image;
step 3: removing hyperspectral images with weak salience by using threshold selection to obtain useful hyperspectral salience images;
step 4: performing motion detection on the hyperspectral saliency view by using a Lucas-Kanade optical flow detection method to obtain a motion detection result of the atmosphere in each wave band;
step 5: and carrying out weighted average on detection results of all the wave bands to obtain an evaluation value of the atmospheric movement state, and optimizing the weight of each wave band by using a genetic algorithm.
As a further improvement of the invention, in the step 2, the improved PCT algorithm can be expressed as follows
C=cos(Y) (2)
Cr=cos -1 (S) (4)
A=abs(cr) (5)
P=G(A) (6)
Wherein X represents a hyperspectral image space dimension image,representing the mean value of the pixels of the hyperspectral image space dimension image, Y representing the image of the hyperspectral image space dimension image X after DC removal, cos (-) representing the discrete cosine transform, C representing the coefficient of the discrete cosine transform of the signal Y, C (i, j) representing the pixel value of the image C in the ith row and the jth column, S representing the image after the sign of C is taken, S (i, j) representing the pixel value of the image S in the ith row and the jth column, T 1 Representing symbol taking threshold, cos -1 (. Cndot.) represents inverse discrete cosine transform, cr represents coefficients obtained by taking inverse discrete cosine transform on symbol S, and A represents absolute value of CrFor values abs (-) represents the absolute function, P represents the low frequency image of a and G (-) represents the low pass filter.
As a further improvement of the present invention, in the step 3, the threshold selection is expressed as
Gr=grad(P) (7)
Wherein Gr represents a gradient image of a hyperspectral image space dimension significance image, grad (·) represents a gradient solving function, T2 represents a judging threshold, sum (·) represents a data accumulating solving function, abs (·) represents a data absolute value solving function, su represents a hyperspectral image significance flag bit, su=0 represents that the image significance content is insufficient, and then the hyperspectral image of this dimension is rejected.
As a further improvement of the invention, the method for evaluating the atmospheric motion state in the step 5 can be expressed as
R i =LK(Gr i ) (9)
Re=w 1 R 1 +w 2 R 2 +...+w λ R λ (10)
Where i=1, 2,..lambda, LK (·) represents the Lucas-Kanade optical flow detection algorithm function, gr i Gradient image representing hyperspectral image spatial dimension saliency image of ith spectral dimension, R i Representation Gr i Optical flow detection result, w i R represents i Re represents an evaluation value of the atmospheric motion state.
The meteorological disaster monitoring method based on the satellite-borne hyperspectral image has the beneficial effects that:
1. the invention provides an L-KWSD algorithm for effectively predicting the flow cloud.
2. The invention uses the multidimensional hyperspectral image as a data source, and increases the predictive robustness.
3. The method has low algorithm complexity and simple realization.
Drawings
FIG. 1 is a diagram of a system training model architecture;
FIG. 2 is a system test model architecture diagram;
Detailed Description
The invention provides a meteorological disaster monitoring method based on a satellite-borne hyperspectral image, which is used for effectively monitoring a convection cloud, wherein the method is shown in fig. 1 and 2, which are respectively a system training model structure diagram and a system testing model structure diagram.
Firstly, acquiring hyperspectral image information of atmospheric convection cloud by using a satellite-borne hyperspectral imager, wherein the size of each image is N x ×N y ×N λ Wherein x represents the width of the hyperspectral image space dimension, y represents the height of the hyperspectral image space dimension, and λ represents the number of the spectral dimensions;
then, performing significance detection on the data of each wave band of the hyperspectral image by using an improved PCT algorithm to obtain a significance result graph of each wave band of the hyperspectral image;
the modified PCT algorithm can be expressed as
C=cos(Y) (2)
Cr=cos -1 (S) (4)
A=abs(cr) (5)
P=G(A) (6)
Wherein X represents a hyperspectral image space dimension image,representing the mean value of the pixels of the hyperspectral image space dimension image, Y representing the image of the hyperspectral image space dimension image X after DC removal, cos (-) representing the discrete cosine transform, and C representing the letterThe coefficient of discrete cosine transform of the number Y, C (i, j) represents the pixel value of the image C in the ith row and the jth column, S represents the image after the symbol is given to C, S (i, j) represents the pixel value of the image S in the ith row and the jth column, T 1 Representing symbol taking threshold, cos -1 (. Cndot.) represents inverse discrete cosine transform, cr represents coefficients obtained by taking inverse discrete cosine transform on symbol S, A represents absolute value of Cr, abs (-) represents absolute value taking function, P represents low-frequency image of A, and G (-) represents low-pass filter.
Then, removing hyperspectral images with weak salience by using threshold selection to obtain useful hyperspectral salience images;
threshold selection is expressed as
Gr=grad(P) (7)
Wherein Gr represents a gradient image of a hyperspectral image space dimension significance image, grad (·) represents a gradient solving function, T2 represents a judging threshold, sum (·) represents a data accumulating solving function, abs (·) represents a data absolute value solving function, su represents a hyperspectral image significance flag bit, su=0 represents that the image significance content is insufficient, and then the hyperspectral image of this dimension is rejected.
Finally, motion detection is carried out on the hyperspectral saliency view by using a Lucas-Kanade optical flow detection method, and a motion detection result of the atmosphere in each wave band is obtained; and carrying out weighted average on detection results of all the wave bands to obtain an evaluation value of the atmospheric movement state, and optimizing the weight of each wave band by using a genetic algorithm.
The method for evaluating the atmospheric movement state can be expressed as
R i =LK(Gr i ) (9)
Re=w 1 R 1 +w 2 R 2 +...+w λ R λ (10)
Where i=1, 2,..lambda, LK (·) represents the Lucas-Kanade optical flow detection algorithm function, gr i Gradient image representing hyperspectral image spatial dimension saliency image of ith spectral dimension, R i Representation Gr i Optical flow detection result, w i R represents i Re represents an evaluation value of the atmospheric motion state.
The above description is only of the preferred embodiment of the present invention, and is not intended to limit the present invention in any other way, but is intended to cover any modifications or equivalent variations according to the technical spirit of the present invention, which fall within the scope of the present invention as defined by the appended claims.
Claims (3)
1. The weather disaster monitoring method based on the satellite-borne hyperspectral image comprises the following specific steps,
step 1: collecting information of atmospheric convection cloud hyperspectral images by using a satellite-borne hyperspectral imager, wherein the size of each image is N x ×N y ×N λ Wherein x represents the width of the hyperspectral image space dimension, y represents the height of the hyperspectral image space dimension, and λ represents the number of the spectral dimensions;
step 2: performing significance detection on the data of each wave band of the hyperspectral image by using an improved PCT algorithm to obtain a significance result graph of each wave band of the hyperspectral image;
in said step 2, the modified PCT algorithm is expressed as
C=cos(Y) (2)
Cr=cos -1 (S) (4)
A=abs(Cr) (5)
P=G(A) (6)
Wherein X represents a hyperspectral image space dimension image,representing the mean value of the pixels of the hyperspectral image space dimension image, Y representing the image of the hyperspectral image space dimension image X after DC removal, cos (-) representing the discrete cosine transform, C representing the coefficient of the discrete cosine transform of the signal Y, C (i, j) representing the pixel value of the image C in the ith row and the jth column, S representing the image after the sign of C is taken, S (i, j) representing the pixel value of the image S in the ith row and the jth column, T 1 Representing symbol taking threshold, cos -1 (. Cndot.) represents inverse discrete cosine transform, cr represents coefficients obtained by taking inverse discrete cosine transform for symbol S, A represents absolute value of Cr, abs (-) represents absolute value taking function, P represents low-frequency image of A, and G (-) represents low-pass filter;
step 3: removing hyperspectral images with weak salience by using threshold selection to obtain useful hyperspectral salience images;
step 4: performing motion detection on the hyperspectral saliency view by using a Lucas-Kanade optical flow detection method to obtain a motion detection result of the atmosphere in each wave band;
step 5: and carrying out weighted average on detection results of all the wave bands to obtain an evaluation value of the atmospheric movement state, and optimizing the weight of each wave band by using a genetic algorithm.
2. The method for monitoring meteorological disasters based on satellite-borne hyperspectral images according to claim 1, wherein the method comprises the following steps:
in the step 3, the threshold selection is expressed as
Gr=grad(P) (7)
Wherein Gr represents a gradient image of a hyperspectral image space dimension significance image, grad (·) represents a gradient solving function, T2 represents a judging threshold, sum (·) represents a data accumulating solving function, abs (·) represents a data absolute value solving function, su represents a hyperspectral image significance flag bit, su=0 represents that the image significance content is insufficient, and then the hyperspectral image of this dimension is rejected.
3. The method for monitoring meteorological disasters based on satellite-borne hyperspectral images according to claim 1, wherein the method comprises the following steps:
the method for evaluating the atmospheric movement state in the step 5 can be expressed as
R i =LK(Gr i ) (9)
Re=w 1 R 1 +w 2 R 2 +…+w λ R λ (10)
Where i=1, 2,..lambda, LK (·) represents the Lucas-Kanade optical flow detection algorithm function, gr i Gradient image representing hyperspectral image spatial dimension saliency image of ith spectral dimension, R i Representation Gr i Optical flow detection result, w i R represents i Re represents an evaluation value of the atmospheric motion state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110872682.5A CN113591708B (en) | 2021-07-30 | 2021-07-30 | Meteorological disaster monitoring method based on satellite-borne hyperspectral image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110872682.5A CN113591708B (en) | 2021-07-30 | 2021-07-30 | Meteorological disaster monitoring method based on satellite-borne hyperspectral image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113591708A CN113591708A (en) | 2021-11-02 |
CN113591708B true CN113591708B (en) | 2023-06-23 |
Family
ID=78252825
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110872682.5A Active CN113591708B (en) | 2021-07-30 | 2021-07-30 | Meteorological disaster monitoring method based on satellite-borne hyperspectral image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113591708B (en) |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008040945A1 (en) * | 2006-10-06 | 2008-04-10 | Imperial Innovations Limited | A method of identifying a measure of feature saliency in a sequence of images |
CN103020992A (en) * | 2012-11-12 | 2013-04-03 | 华中科技大学 | Video image significance detection method based on dynamic color association |
CN103413127A (en) * | 2013-09-10 | 2013-11-27 | 上海海事大学 | Marine target significance detection method based on spectrum singular value decomposition |
CN106296632A (en) * | 2015-05-25 | 2017-01-04 | 中国海洋大学 | A kind of well-marked target detection method analyzed based on amplitude spectrum |
CN106529549A (en) * | 2016-10-31 | 2017-03-22 | 郑州轻工业学院 | Visual saliency detection method based on adaptive features and discrete cosine transform |
CN108470154A (en) * | 2018-02-27 | 2018-08-31 | 燕山大学 | A kind of large-scale crowd salient region detection method |
CN109767454A (en) * | 2018-12-18 | 2019-05-17 | 西北工业大学 | Based on Space Time-frequency conspicuousness unmanned plane video moving object detection method |
CN109784183A (en) * | 2018-12-17 | 2019-05-21 | 西北工业大学 | Saliency object detection method based on concatenated convolutional network and light stream |
CN110287944A (en) * | 2019-07-04 | 2019-09-27 | 吉林大学 | The crop pests monitoring method of multi-spectrum remote sensing image based on deep learning |
CN110458192A (en) * | 2019-07-05 | 2019-11-15 | 中国地质大学(武汉) | The Classification of hyperspectral remote sensing image method and system of view-based access control model conspicuousness |
CN112183633A (en) * | 2020-09-29 | 2021-01-05 | 西安理工大学 | Hyperspectral image salient target detection method based on improved FT algorithm |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9208573B2 (en) * | 2013-10-29 | 2015-12-08 | Google Inc. | Systems and methods for determining motion saliency |
-
2021
- 2021-07-30 CN CN202110872682.5A patent/CN113591708B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2008040945A1 (en) * | 2006-10-06 | 2008-04-10 | Imperial Innovations Limited | A method of identifying a measure of feature saliency in a sequence of images |
CN103020992A (en) * | 2012-11-12 | 2013-04-03 | 华中科技大学 | Video image significance detection method based on dynamic color association |
CN103413127A (en) * | 2013-09-10 | 2013-11-27 | 上海海事大学 | Marine target significance detection method based on spectrum singular value decomposition |
CN106296632A (en) * | 2015-05-25 | 2017-01-04 | 中国海洋大学 | A kind of well-marked target detection method analyzed based on amplitude spectrum |
CN106529549A (en) * | 2016-10-31 | 2017-03-22 | 郑州轻工业学院 | Visual saliency detection method based on adaptive features and discrete cosine transform |
CN108470154A (en) * | 2018-02-27 | 2018-08-31 | 燕山大学 | A kind of large-scale crowd salient region detection method |
CN109784183A (en) * | 2018-12-17 | 2019-05-21 | 西北工业大学 | Saliency object detection method based on concatenated convolutional network and light stream |
CN109767454A (en) * | 2018-12-18 | 2019-05-17 | 西北工业大学 | Based on Space Time-frequency conspicuousness unmanned plane video moving object detection method |
CN110287944A (en) * | 2019-07-04 | 2019-09-27 | 吉林大学 | The crop pests monitoring method of multi-spectrum remote sensing image based on deep learning |
CN110458192A (en) * | 2019-07-05 | 2019-11-15 | 中国地质大学(武汉) | The Classification of hyperspectral remote sensing image method and system of view-based access control model conspicuousness |
CN112183633A (en) * | 2020-09-29 | 2021-01-05 | 西安理工大学 | Hyperspectral image salient target detection method based on improved FT algorithm |
Non-Patent Citations (11)
Title |
---|
Antonakos E 等.Feature-based lucas–kanade and active appearance models.《IEEE Transactions on Image Processing》.2015,第24卷(第09期),2617-2632. * |
Hedayati M 等.Combination of mean shift of colour signature and optical flow for tracking during foreground and background occlusion.《Image and Video Technology: 7th Pacific-Rim Symposium, PSIVT 2015》.2016,87-98. * |
Laachfoubi N 等.Cloud motion estimation in satellite image sequences by tracking skeleton critical points using Lucas-Kanade method.《2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV)》.2016,178-183. * |
Yu Ying 等.Bottom–up attention: pulsed PCA transform and pulsed cosine transform.《Cognitive neurodynamics》.2011,第05卷321-332. * |
季一锦 等.基于电梯视频的乘客暴力行为检测.《工业控制计算机》.2018,第31卷(第06期),1-3. * |
寇墨林 等.无人机影像目标检测技术研究进展.《测控技术》.2020,第39卷(第08期),47-61. * |
彭忻怡 等.基于视觉显著性波段选择的高光谱分类.《云南民族大学学报(自然科学版)》.2021,第30卷(第03期),251-257. * |
王建超.基于深度网络的高光谱图像显著性目标检测方法研究.《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》.2021,(第06期),C028-87. * |
王烨蕾.基于显著性分析的多特征目标检测算法研究.《中国优秀硕士学位论文全文数据库 (信息科技辑)》.2018,(第12期),I138-1278. * |
赵宗然.快速无损高光谱图像压缩算法的研究.《中国优秀硕士学位论文全文数据库 (信息科技辑)》.2016,(第02期),I138-1376. * |
黄锋 等.光流法和显著性相结合的动态背景下运动目标检测方法.《成都工业学院学报》.2020,第23卷(第01期),13-18. * |
Also Published As
Publication number | Publication date |
---|---|
CN113591708A (en) | 2021-11-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110728658A (en) | High-resolution remote sensing image weak target detection method based on deep learning | |
CN111104906A (en) | Transmission tower bird nest fault detection method based on YOLO | |
CN112464920B (en) | FY-3D infrared hyperspectral cloud detection method based on extreme random tree | |
CN113469278B (en) | Strong weather target identification method based on deep convolutional neural network | |
US9159132B1 (en) | Process and system for identifying damage | |
CN109145962B (en) | Atmospheric parameter inversion observation method based on digital image | |
CN111639530B (en) | Method and system for detecting and identifying power transmission tower and insulator of power transmission line | |
CN111259770B (en) | Unmanned plane platform and deep learning-based cable force rapid test method under complex background | |
Alam et al. | Automatic assessment and prediction of the resilience of utility poles using unmanned aerial vehicles and computer vision techniques | |
CN111666903A (en) | Method for identifying thunderstorm cloud cluster in satellite cloud picture | |
CN111428862A (en) | Polar imbalance space-time joint convection birth short-term forecasting method | |
Ruzanski et al. | Scale filtering for improved nowcasting performance in a high-resolution X-band radar network | |
Kwak et al. | A new approach for rapid urban flood mapping using ALOS-2/PALSAR-2 in 2015 Kinu River Flood, Japan | |
Vaibhav et al. | Real-time fog visibility range estimation for autonomous driving applications | |
Guo et al. | Correction of sea surface wind speed based on SAR rainfall grade classification using convolutional neural network | |
Shukla et al. | Satellite-based nowcasting of extreme rainfall events over Western Himalayan region | |
CN113591708B (en) | Meteorological disaster monitoring method based on satellite-borne hyperspectral image | |
CN103605988A (en) | Foundation cloud atlas classification method based on spatial pyramid random mapping | |
US20240044783A1 (en) | Generating high-resolution concentration maps for atmospheric gases using geography-informed machine learning | |
Malothu et al. | Tropical cyclone detection in South Pacific and Atlantic coastal area using optical flow estimation and RESNET deep learning model | |
Thwal et al. | Land cover classification and change detection analysis of multispectral satellite images using machine learning | |
Kondapalli et al. | Real-time rain severity detection for autonomous driving applications | |
Tamura et al. | Extraction of ocean wave parameters from video images | |
CN110769390A (en) | Compressed sensing method based on intelligent vertical net | |
Said et al. | Desertification Detection in Makkah Region based on Aerial Images Classification. |
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 |