CN108932742B - Large-scale infrared terrain scene real-time rendering method based on remote sensing image classification - Google Patents
Large-scale infrared terrain scene real-time rendering method based on remote sensing image classification Download PDFInfo
- Publication number
- CN108932742B CN108932742B CN201810750719.5A CN201810750719A CN108932742B CN 108932742 B CN108932742 B CN 108932742B CN 201810750719 A CN201810750719 A CN 201810750719A CN 108932742 B CN108932742 B CN 108932742B
- Authority
- CN
- China
- Prior art keywords
- terrain
- data
- infrared
- remote sensing
- rendering
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/001—Texturing; Colouring; Generation of texture or colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
- Image Generation (AREA)
Abstract
The invention discloses a large-scale infrared terrain scene real-time rendering method based on remote sensing image classification, and belongs to the technical field of infrared physics and virtual reality. Firstly, establishing a terrain classification model; establishing a simplified terrain radiation model, calculating terrain surface temperature values of different terrains, converting the calculated terrain surface temperature values of different terrains into color data according to a fragment shader, and adding infrared noise to realize infrared texture rendering; and finally, rendering the infrared characteristics of the large-scale terrain in real time based on the cfMMOC model. The rendering process is based on the cfMMOC model and the shader program, the rendering efficiency is high, and real-time rendering of the infrared characteristics of the global terrain can be realized under the condition of lower resource consumption. The frame rate in the whole rendering process can be stabilized to be more than 55 frames, and the real-time rendering condition is met.
Description
Technical Field
The invention belongs to the technical field of infrared physics and virtual reality, relates to a large-scale infrared terrain scene real-time rendering method based on remote sensing image classification, and particularly relates to a large-scale infrared terrain scene real-time rendering method for classifying different features of a large-scale terrain surface based on a visible light terrain remote sensing image.
Background
The infrared imaging simulation comprises background imaging simulation and target imaging simulation, wherein the target imaging simulation refers to an object of interest in a simulation area, such as a vehicle, a building and the like, the background is a scene except for a target, and any target cannot be isolated from the background and exists alone, wherein a large-range terrain is a very typical background. The terrain infrared characteristic is a very important component for the whole infrared terrain scene. Especially for applications concerning terrain infrared characteristics such as infrared target recognition and infrared stealth, accurate and real-time rendering of an infrared terrain scene is particularly important, and generally, the real-time rendering requirement is met, and the rendering result is required to be stabilized at 30 frames or more. The realization of the real-time rendering of large-scale infrared terrain scenes relates to subjects such as heat transfer science, infrared physics, mode recognition, computer graphic images and the like, and is a typical multidisciplinary cross problem.
Disclosure of Invention
Aiming at the problem that the large-scale infrared terrain scene cannot be rendered in real time in the prior art, the invention provides the large-scale infrared terrain scene real-time rendering method based on remote sensing image classification, emphasizes the realization of the infrared characteristic rendering function in the large-scale terrain rendering, and improves the rendering stability on the premise of ensuring the simulation reliability. The method comprises the steps of firstly, establishing a terrain classification model, and classifying surface features of images of different terrains in a visible light large-scale terrain remote sensing image; simplifying a ground surface radiation model, respectively calculating the terrain surface temperature values of different terrains by the simplified ground surface radiation model, converting the calculated terrain surface temperature values of different terrains into color data according to a fragment shader (shader), and superposing infrared noise on the color data to realize infrared texture rendering; and finally, rendering the infrared characteristics of the large-scale terrain in real time based on an out-of-core terrain unified rendering framework cfMMOC (A constrained frame of multi-resolution management and encapsulation for out-of-core terrain rendering) model.
The invention provides a large-scale infrared terrain scene real-time rendering method based on remote sensing image classification, which specifically comprises the following steps:
establishing a terrain classification model, and classifying visible light large-scale terrain remote sensing images;
step 101, obtaining a large-scale terrain remote sensing image under a visible light wave band;
and 102, selecting a surface material characteristic vector in the large-scale terrain remote sensing image.
And extracting surface material characteristic vectors according to surface characteristics of different terrains in the large-scale terrain remote sensing image, wherein the surface characteristics comprise color characteristics and texture characteristics, hue, saturation and lightness in the color characteristics are selected as the color characteristic vectors, and energy, entropy, moment of inertia and standard deviation in the texture characteristics are selected as the texture characteristic vectors. The surface material feature vector comprises a color feature vector and a texture feature vector.
And 103, generating corresponding training pictures and label data according to the surface material characteristic vectors in the remote sensing images, and selecting test pictures for testing. The label data refers to terrain types including five types of bare land, grassland, forest, withered forest and water body.
And 104, selecting a support vector machine as a terrain type judgment basis, classifying the earth surface material characteristic vectors of the training pictures, and training the terrain classification model by using the test pictures as training data to establish a terrain classification model. And applying the terrain classification model to the remote sensing image to obtain terrain classification results of all the 15 levels of remote sensing images.
Step two, simplifying the earth surface radiation balance equation to obtain a simplified earth surface radiation model;
simplifying the earth surface radiation model, wherein the process is as follows:
a: in solar radiation, the influence of reflection on the radiation balance is neglected; b: in inward radiation, the temperature distribution law is simplified: assuming that the temperature 0.5m below the surface is constant and varies uniformly from the surface to the bottom; C. and setting an empirical value for the parameter with indirect influence of the surface energy balance equation or stable numerical value per se.
Step three: and performing infrared rendering on the large-scale terrain based on the cfMMOC model.
The invention has the advantages that:
(1) based on the visible light terrain remote sensing image and the general environmental data of the meteorological station, the data are easy to obtain.
(2) And under the condition of ensuring the calculation accuracy, the surface temperature of bare land, grassland, withered forest, green forest and water body is calculated in real time according to the environmental data.
(3) The rendering process is based on the cfMMOC model and the shader program, the rendering efficiency is high, and real-time rendering of global terrain infrared characteristics can be achieved under the condition of low resource consumption.
Drawings
FIG. 1 is a flow chart of the present invention for building a terrain classification model;
FIG. 2 is a method for real-time generation of infrared texture in accordance with the present invention;
FIG. 3 is a schematic structural comparison of a simplified front and back earth surface model according to the present invention;
FIG. 4 is a cfMMOC large-scale terrain rendering framediagram;
fig. 5 is a graph of large-scale terrain infrared rendering results.
Detailed Description
The following describes in detail a specific embodiment of the present invention with reference to the drawings.
The invention provides a real-time rendering method of large-scale infrared terrain scenes, which is used for classifying different features of large-scale terrain surfaces based on visible light large-scale terrain remote sensing images, aiming at the problem that the large-scale infrared terrain scenes cannot be rendered in real time in the prior art, and the method comprises the steps of classifying different features of different terrain surfaces based on the visible light large-scale terrain remote sensing images, and establishing a terrain classification model; establishing a ground surface radiation model according to the different terrains, respectively calculating the terrain surface temperature values of the different terrains by a ground surface energy balance equation, and performing infrared rendering on the calculated terrain surface temperature values of the different terrains according to a fragment shader (shader); and finally, performing real-time rendering on the large-scale infrared terrain scene based on an out-of-core terrain unified rendering framework cfMMOC (A constrained frame of multi-resolution management and encapsulation for out-of-core terrain rendering) model. The method specifically comprises the following steps:
the method comprises the following steps: classifying all terrain surfaces based on a large-scale terrain remote sensing image of visible light, establishing a terrain classification model and providing support for infrared characteristic calculation; as shown in fig. 1, the specific steps are as follows:
step 101, acquiring a large-scale terrain remote sensing image under a visible light wave band, and dividing the large-scale terrain remote sensing image into 15-level LOD (levels of detail) data sets of 0-14 in total according to the resolution fineness;
and 102, respectively selecting the surface features of the images of different terrains in the large-scale terrain remote sensing image as the characteristic vectors of the earth surface materials.
The types of the landforms are set to be five landforms of bare land, grassland, forest, withered forest and water body, so that the five landforms are identified and classified by adopting a supervised learning method in the follow-up process. The surface characteristics comprise color characteristics and texture characteristics, the color characteristics comprise hue, saturation and lightness, 10 dimensions are selected as color characteristic vectors, the texture characteristics comprise energy, entropy, moment of inertia and standard deviation, 8 dimensions are selected as texture characteristic vectors, and accordingly 38-dimensional earth surface material characteristic vectors comprising 30-dimensional color characteristic vectors and 8-dimensional texture characteristic vectors are formed.
And 103, selecting the remote sensing image with the finest level (14 levels) in the remote sensing image data set as training data in supervised learning, and setting label data. The label data refers to terrain types including five types of bare land, grassland, forest, withered forest and water body.
And 104, randomly extracting a certain amount of remote sensing images as a test data set for testing the training effect, performing classification learning by adopting a Support Vector Machine (Support Vector Machine) method in a Machine learning integration method, wherein a kernel function selects a Gaussian kernel (RBF), the Gaussian kernel coefficient in the super-parameter is selected to be 0.43, and the penalty coefficient is selected to be 1.0. And performing iterative training on the test data set to obtain a terrain classification result. And when the terrain classification result meets the classification requirement (the Kappa coefficient is more than 0.8), completing the model training process to obtain a terrain classification model. And applying the terrain classification model to the remote sensing image to obtain terrain classification results of all the remote sensing images of 15 levels.
Step two, simplifying the earth surface radiation balance equation to obtain a simplified earth surface radiation model;
the earth surface radiation model is established according to an earth surface radiation balance equationThe method is divided into six parts: inwardly radiating Q Mg Sensible heat flux Q H Latent heat flux Q LE Solar radiation Q sun Atmospheric radiation Q sky And outwardly radiating Q G There are the following table energy balance equations:
wherein k is λ The material is the heat conductivity coefficient of the earth surface, S is the surface area, n is the normal direction of the earth surface, and T is the temperature.
In order to improve the operation efficiency, the invention simplifies the surface radiation model, as shown in fig. 3, the process is as follows:
a: in solar radiation, the influence of reflection on the radiation balance is neglected; b: in inward irradiation, the temperature distribution law is simplified: assuming that the temperature 0.5m below the surface is constant and varies uniformly from the surface down; C. appropriate empirical values are set for parameters which are not directly influenced by the surface energy balance equation or have stable numerical values per se, as shown in the following table 1, and the simplified parts of A and B are marked by a dashed box in FIG. 3; the simplified earth surface radiation model receives local time, environment temperature, wind speed and relative humidity as input data and outputs earth surface temperature values corresponding to five types of terrain. Through measurement, the single calculation of the terrain surface temperature value takes about 1.5 milliseconds, and good guarantee is provided for the real-time rendering performance of the invention.
TABLE 1 empirical values of parameters
Step three: real-time rendering is performed on the infrared characteristics of the large-scale terrain based on the cfMMOC large-scale terrain rendering model and the infrared texture real-time generation based on the shader, as shown in FIG. 5;
the method comprises the following specific steps:
301, obtaining elevation data of a 15-level LOD remote sensing image, converting the elevation data into three-dimensional grid Mesh data describing a terrain, performing structured division according to the requirements of a cfMMOC model, and storing remote sensing images and three-dimensional grid Mesh data of different levels according to a quadtree structure.
Step 302, realizing real-time dynamic rendering of the infrared texture based on a shader;
as shown in fig. 2, firstly, a shader control script is written based on Cg language, and the terrain classification result obtained in the first step is input into a fragment shader material input interface; and then local environment data is acquired from a meteorological station and input into an earth surface radiation model, a terrain surface temperature value in the remote sensing image is calculated, and the terrain surface temperature value is input into a numerical value input interface of a fragment shader.
The local environmental data includes local time, ambient temperature, wind speed and relative humidity.
Inputting the corresponding relation between gray level and temperature or the corresponding relation between infrared pseudo color and temperature into a fragment shader in an image form, writing corresponding codes to realize the conversion from temperature to color data/gray level data, and superposing infrared noise on a conversion result to finally realize the real-time dynamic rendering from a terrain surface temperature value to an infrared texture.
And 303, reading the infrared texture data acquired in the step 302 based on the cfMMOC model to realize the real-time rendering of the three-dimensional infrared scene of the large-scale terrain remote sensing image.
The rendering of the cfMMOC model is divided into a front process and a back process. As shown in fig. 4, a renderer in a front process sends viewpoint information in an original window to a renderer in a back process, the renderer in the back process implements pixel calculation in a small window, a pixel calculation result represents visibility information, the visibility information is sent to a terrain block management unit of the front process, the terrain block management unit of the front process feeds a terrain block state back to the terrain block management unit of the back process, the terrain block management unit of the back process judges a loading state of a terrain resource in the front process, and sends data loading/unloading request information to the terrain block loader of the front process by combining terrain block state data. After the pre-process acquires the topographic data loading/unloading request information, the topographic grid data is updated in the original window, and the real-time three-dimensional infrared scene rendering is performed by combining the infrared texture data generated in the step 302 in real time. In the process, the terrain block data are loaded through terrain block loaders in front and back processes respectively.
The rendering result realized based on the steps is shown in fig. 5, a-D in fig. 5 are infrared scene effect graphs under different levels in a front process, and E-H in fig. 5 are scheduling schematic diagrams of terrains at different levels in a rear process. The frame rate in the whole rendering process can be stabilized to be more than 55 frames, and the real-time rendering condition is met.
Claims (1)
1. A large-scale infrared terrain scene real-time rendering method based on remote sensing image classification specifically comprises the following steps:
establishing a terrain classification model, and carrying out terrain classification on a visible light large-scale terrain remote sensing image;
step two, establishing a simplified topographic radiation model;
selecting five terrains, establishing equilibrium equations of solar radiation, atmospheric radiation, earth surface outward radiation, latent heat flux, sensible heat flux and earth surface downward radiation according to an energy equilibrium equation, and establishing an earth surface radiation model; simplifying the earth surface radiation model, and the process is as follows:
a: neglecting the effect of surface reflections on ambient radiation;
b: assuming that the temperature 0.5m below the surface is constant and varies uniformly from the surface to the bottom;
C. setting an empirical value for parameters which are not directly influenced by the earth surface energy balance equation or have stable numerical values;
step three: generating infrared textures of a shader in real time based on the cfMMOC large-scale terrain rendering model, and rendering infrared characteristics of large-scale terrain in real time;
the method is characterized in that:
the specific process of the step one is as follows:
step 101, acquiring a large-scale terrain remote sensing image under a visible light wave band, and dividing the large-scale terrain remote sensing image into data sets of 15 levels of LOD (level of detail) of 0-14 according to the resolution fineness;
102, selecting a surface material characteristic vector in the large-scale terrain remote sensing image;
the surface material characteristic vector comprises a color characteristic vector and a texture characteristic vector;
the color feature vector comprises 10 dimensions of hue, saturation and lightness;
the texture feature vector comprises 8 dimensions of energy, entropy, moment of inertia and standard deviation;
103, selecting a 14-level remote sensing image in a remote sensing image data set as training data in supervised learning, generating corresponding training pictures and label data, and selecting test pictures for testing;
the label data refers to terrain types including five types of bare land, grassland, forest, withered forest and water body;
104, classifying and learning the training pictures by adopting a support vector machine method in a machine learning integration method, wherein a kernel function adopts a Gaussian kernel, the Gaussian kernel coefficient in the hyperparameter is selected to be 0.43, and a penalty coefficient is selected to be 1.0;
performing iterative training on the test data set to obtain a terrain classification result;
when the Kappa coefficient of the terrain classification result is larger than 0.8, completing a model training process to obtain a terrain classification model;
applying the terrain classification model to the remote sensing images to obtain terrain classification results of all the remote sensing images with 15 levels;
the third specific process is as follows:
301, acquiring elevation data of a 15-level LOD remote sensing image, converting the elevation data into three-dimensional grid Mesh data describing a terrain, performing structured division according to the requirements of a cfMMOC model, and storing remote sensing images and three-dimensional grid Mesh data of different levels according to a quadtree structure;
step 302, realizing real-time dynamic rendering of the infrared texture based on a shader;
inputting the terrain classification result obtained in the first step into a fragment shader material input interface; selecting local time, environment temperature, wind speed and relative humidity from meteorological station data as input data of a simplified earth surface radiation model, calculating a terrain surface temperature value in a remote sensing image, and inputting the terrain surface temperature value into a numerical value input interface of a fragment shader;
the fragment shader converts the terrain surface temperature value into color data or gray data according to the corresponding relation between gray and temperature or infrared pseudo color, and infrared noise is superposed on the color data or gray data to realize real-time dynamic rendering from the terrain surface temperature value to infrared texture;
step 303, reading the infrared texture data obtained in the step 302 based on the cfMMOC model to realize real-time rendering of the three-dimensional infrared scene of the large-scale terrain remote sensing image;
the rendering of the cfMMOC model is divided into a front process and a rear process;
the renderer in the front process sends the viewpoint information in the original window to the renderer in the back process;
a renderer in the later process realizes pixel calculation in a small window, the pixel calculation result embodies visibility information, and the visibility information is sent to a terrain block management unit of the former process;
the terrain block management unit of the front process feeds the terrain block state back to the terrain block management unit of the back process;
the terrain block management unit of the back process judges the loading state of the terrain resource in the front process and sends data loading/unloading request information to a terrain block loader of the front process by combining terrain block state data;
after acquiring the topographic data loading/unloading request information, the front process updates topographic grid data in the original window, and performs real-time three-dimensional infrared scene rendering by combining the infrared texture data generated in step 302 in real time;
in the process, the terrain block data are loaded through terrain block loaders in front and back processes respectively.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810750719.5A CN108932742B (en) | 2018-07-10 | 2018-07-10 | Large-scale infrared terrain scene real-time rendering method based on remote sensing image classification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810750719.5A CN108932742B (en) | 2018-07-10 | 2018-07-10 | Large-scale infrared terrain scene real-time rendering method based on remote sensing image classification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108932742A CN108932742A (en) | 2018-12-04 |
| CN108932742B true CN108932742B (en) | 2022-09-09 |
Family
ID=64446928
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810750719.5A Active CN108932742B (en) | 2018-07-10 | 2018-07-10 | Large-scale infrared terrain scene real-time rendering method based on remote sensing image classification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108932742B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| BR112021009659A2 (en) * | 2018-12-10 | 2021-08-17 | The Climate Corporation | mapping of field anomalies using digital images and machine learning models. |
| CN110648395A (en) * | 2019-02-02 | 2020-01-03 | 完美世界(北京)软件科技发展有限公司 | Terrain rendering method and device |
| CN109920056B (en) * | 2019-03-18 | 2023-08-01 | 阿波罗智联(北京)科技有限公司 | Building rendering method, device, equipment and medium |
| CN110889888B (en) * | 2019-10-29 | 2020-10-09 | 桂林理工大学 | Three-dimensional model visualization method integrating texture simplification and fractal compression |
| CN112288841B (en) * | 2020-12-18 | 2021-04-02 | 完美世界(北京)软件科技发展有限公司 | Method and device for creating rendering frame graph |
| CN112233217B (en) * | 2020-12-18 | 2021-04-02 | 完美世界(北京)软件科技发展有限公司 | Rendering method and device of virtual scene |
| CN113297344B (en) * | 2021-06-16 | 2021-11-30 | 重庆富沛和科技有限公司 | Three-dimensional remote sensing image-based ground linear matching method and device and ground object target position positioning method |
| CN114842286B (en) * | 2022-03-24 | 2024-02-23 | 西北工业大学 | Large-scale remote sensing data set generation method based on real topography |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102867331A (en) * | 2012-08-31 | 2013-01-09 | 电子科技大学 | Graphics processing unit (GPU)-orientated large-scale terrain fast drawing method |
| CN103186906A (en) * | 2011-12-28 | 2013-07-03 | 中国科学院沈阳自动化研究所 | Real-time infrared dynamic scene simulation method for multiple objects in sea and sky background |
| CN103761762A (en) * | 2013-12-11 | 2014-04-30 | 南京乐飞航空技术有限公司 | Infrared imaging simulation method based on OpenGL shader |
| CA2834575A1 (en) * | 2012-11-30 | 2014-05-30 | Thales | Method of rendering a terrain stored in a massive database |
-
2018
- 2018-07-10 CN CN201810750719.5A patent/CN108932742B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103186906A (en) * | 2011-12-28 | 2013-07-03 | 中国科学院沈阳自动化研究所 | Real-time infrared dynamic scene simulation method for multiple objects in sea and sky background |
| CN102867331A (en) * | 2012-08-31 | 2013-01-09 | 电子科技大学 | Graphics processing unit (GPU)-orientated large-scale terrain fast drawing method |
| CA2834575A1 (en) * | 2012-11-30 | 2014-05-30 | Thales | Method of rendering a terrain stored in a massive database |
| CN103761762A (en) * | 2013-12-11 | 2014-04-30 | 南京乐飞航空技术有限公司 | Infrared imaging simulation method based on OpenGL shader |
Non-Patent Citations (3)
| Title |
|---|
| 《Real-time and multi-resolution rendering of the infrared characteristics for large-scale terrains》;Li, N 等;《INFRARED PHYSICS & TECHNOLOGY 》;20180920;全文 * |
| 《地面背景红外辐射特性建模与仿真研究》;吕震华 等;《中国电子科学研究院学报》;20170831;第12卷(第4期);正文第1-2节 * |
| 《基于核外渲染的大规模红外场景实时仿真系统研究》;张俭;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20141115(第11期);正文第三、四章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108932742A (en) | 2018-12-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108932742B (en) | Large-scale infrared terrain scene real-time rendering method based on remote sensing image classification | |
| US10979640B2 (en) | Estimating HDR lighting conditions from a single LDR digital image | |
| CN110910486B (en) | Indoor scene illumination estimation model, method and device, storage medium and rendering method | |
| US10957026B1 (en) | Learning from estimated high-dynamic range all weather lighting parameters | |
| Schmohl et al. | Submanifold sparse convolutional networks for semantic segmentation of large-scale ALS point clouds | |
| US20070036467A1 (en) | System and method for creating a high resolution material image | |
| US20060017740A1 (en) | Diurnal variation of geo-specific terrain temperatures in real-time infrared sensor simulation | |
| US20060018565A1 (en) | System and method for infrared sensor simulation | |
| Wang et al. | Neural light field estimation for street scenes with differentiable virtual object insertion | |
| CN111223191A (en) | Large-scale scene infrared imaging real-time simulation method for airborne enhanced synthetic vision system | |
| WO2006012552A2 (en) | A supervised neural network for encoding continuous curves | |
| CN107301633B (en) | Simulation method for remote sensing imaging under cloud and fog interference | |
| CN116385619B (en) | Object model rendering method, device, computer equipment and storage medium | |
| US20060018566A1 (en) | System and method for adding spatial frequency into an image | |
| CN113869262A (en) | Prediction method and device of land information of target area based on Unet model | |
| CN112991537B (en) | City scene reconstruction method and device, computer equipment and storage medium | |
| CN112017159A (en) | Ground target reality simulation method in remote sensing scene | |
| CN109300079A (en) | The real-time light and color homogenization preview technology of remote sensing image based on GPU | |
| CN118096978B (en) | 3D artistic content rapid generation method based on arbitrary stylization | |
| CN117332840B (en) | Training method of nerve radiation field, method and device for acquiring target scene image | |
| Ye et al. | Gaussian in the Dark: Real‐Time View Synthesis From Inconsistent Dark Images Using Gaussian Splatting | |
| CN118172507B (en) | Digital twinning-based three-dimensional reconstruction method and system for fusion of transformer substation scenes | |
| KR20200064377A (en) | Method and apparatus for relative radiometric normalization of image | |
| Han | Joint up-sampling high dynamic range images with a guidance image | |
| Zverev et al. | Development of Infrared Scene Model in a Wide Wavelength Range |
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 |