CN104267940A - Quick map tile generation method based on CPU+GPU - Google Patents
Quick map tile generation method based on CPU+GPU Download PDFInfo
- Publication number
- CN104267940A CN104267940A CN201410474686.8A CN201410474686A CN104267940A CN 104267940 A CN104267940 A CN 104267940A CN 201410474686 A CN201410474686 A CN 201410474686A CN 104267940 A CN104267940 A CN 104267940A
- Authority
- CN
- China
- Prior art keywords
- gpu
- cpu
- data
- data block
- map
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Processing Or Creating Images (AREA)
Abstract
The invention is suitable for the field of network geographic information systems and discloses a quick map tile generation method based on CPU+GPU. The quick map tile generation method based on CPU+GPU includes that step 1, obtaining the hardware processing performance information of a running computer which is provided with a GPU and at least two CPU corns, and testing the computing abilities of the CPU and GPU; step 2, obtaining map data and tile configuration information, and distributing slicing task load according to the computing abilities of the CPU and GPU; step 3, carrying out block division treatment on the map data, loading the data blocks into the CPU memory and GPU storage in sequence according to the distributed slicing task load, and enabling the CPU and GPU to slice the data blocks to generate pictures; step 4, ending after all the data blocks are processed. The quick map tile generation method based on CPU+GPU is featured with fast slicing speed, simple hardware condition, low cost, easiness in configuration and the like, and the quick map tile generation method based on CPU+GPU supports extra-large map data.
Description
Technical field
The invention belongs to network geographic information system field, particularly relate to the rapid generation that a kind of map based on CPU+GPU is cut into slices.
Background technology
Current, map section is very important function in network geographic information system (WebGIS), map section is cached to after in file system and can realizes fast access map in client.But when the situation such as increase of the amendment of spot diagram data, pattern conversion, engineer's scale adjustment, tile classification, need again to cut into slices to map datum.Simultaneously because map tile is pyramid structure, the quantity of map tile presents the growth of geometric series along with the growth of tile classification, and calculated amount is also just sharply surged.So the map that the speed of map section directly has influence on WebGIS uses.
At present, usually adopt two kinds of methods to carry out slicing treatment, one adopts serial algorithm to cut into slices, and the method realizes simple, but speed is very slow, cannot process the data of more than GB level in real time; Another adopts swarm algorithm to cut into slices, the method speed, but hardware cost is higher, it is complicated to dispose.
Summary of the invention
The object of the embodiment of the present invention is the rapid generation providing a kind of map based on CPU+GPU to cut into slices, to solve the problem that prior art hardware cost is high, dispose complexity.
The embodiment of the present invention is achieved in that and said method comprising the steps of the rapid generation that a kind of map based on CPU+GPU is cut into slices:
Step 1, obtain the hardware handles performance information of moving calculation machine, described allocation of computer has the core cpu of GPU and at least two, tests the computing power of described CPU and GPU;
Step 2, obtains map datum and tile configuration information, distributes section task amount according to the computing power of described CPU and GPU;
Step 3, carries out piecemeal process to described map datum, and data block be loaded into successively in the internal memory of described CPU and the storer of described GPU according to the section task amount of described distribution, described CPU and described GPU carries out slicing treatment generating pictures to described data block;
Step 4, when all described data block process complete, terminates.
The beneficial effect of the rapid generation that a kind of map based on CPU+GPU that the embodiment of the present invention provides is cut into slices comprises:
1, based on the rapid generation that the map of CPU+GPU is cut into slices, have that chip rate is fast, hardware condition is simple, cost is low, configuration is easy and support the features such as especially big map datum;
2, piecemeal process is carried out to map datum, the size of data block is large as far as possible, until be no more than the maximum free memory of CPU and GPU, and distribute section task amount according to the computing power of CPU and GPU, the number of times of process can be reduced as far as possible when reasonable distribution process when meeting CPU and GPU, raise the efficiency; When distributing section task amount according to the computing power of CPU and GPU, in core cpu, additional free goes out a core cpu and does not participate in section and calculate, and ensures the normal operation of operating system and section procedure logical control system;
3, CPU and GPU adopts diverse ways to carry out slicing treatment, and multiple core cpu walks abreast and completes the slicing processing of each level of zoom successively, carries out distinct methods process, improve processing speed further in GPU slicing processing to dissimilar data.
Accompanying drawing explanation
In order to be illustrated more clearly in the technical scheme in the embodiment of the present invention, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of the rapid generation that the map based on CPU+GPU provided by the invention is cut into slices;
Fig. 2 is the process flow diagram of the rapid generation that the map based on CPU+GPU that the embodiment of the present invention provides is cut into slices;
Fig. 3 is the process flow diagram of the method for the CPU generating pictures that the embodiment of the present invention provides;
Fig. 4 is the process flow diagram of the method for the GPU generating pictures that the embodiment of the present invention provides.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
In order to technical solutions according to the invention are described, be described below by specific embodiment.
Be illustrated in figure 1 the process flow diagram of the rapid generation that the map based on CPU+GPU provided by the invention is cut into slices, said method comprising the steps of:
In step 1, obtain the hardware handles performance information of moving calculation machine, this allocation of computer has the core cpu of GPU and at least two, tests the computing power of this CPU and GPU.
In step 2, obtain map datum and tile configuration information, distribute section task amount according to the computing power of CPU and GPU.
In step 3, carry out piecemeal process to map datum, data block is loaded in the internal memory of CPU and the storer of GPU by section task amount according to distributing successively, CPU and GPU carries out slicing treatment generating pictures to data block.
In step 4, when all data block process complete, terminate.
The embodiment of the present invention, utilize multi-core CPU and GPU to carry out hybrid parallel acceleration on computers simultaneously, effectively raise the map publishing efficiency of WebGIS, have that chip rate is fast, hardware condition is simple, cost is low, configuration is easy, support the features such as especially big map datum.
Embodiment one
Be illustrated in figure 2 the process flow diagram of the embodiment of the rapid generation that the map based on CPU+GPU provided by the invention is cut into slices, as shown in Figure 2, in the embodiment of the rapid generation of map section provided by the invention, comprise:
The hardware handles performance information of moving calculation machine obtained in step 1 comprises the dominant frequency of CPU, core amounts and available memory space size, the dominant frequency of GPU, core amounts and available video memory size.By performing the parallel algorithm comprising a large amount of thread, the computation capability of test CPU and GPU and floating point arithmetic ability.
In step 2, the map data information of acquisition comprises: the information such as body of a map or chart and map layer; The tile configuration information obtained comprises: the information such as classification, engineer's scale, tile size and map projection's mode.
When distributing section task amount according to the computing power of CPU and GPU, need additional free to go out a core cpu in the core cpu of above-mentioned at least two and do not participate in section calculating, ensure the normal operation of operating system and section procedure logical control system, other core cpus and GPU are according to computation capability and floating point arithmetic capability distribution section task amount.
In step 3, map datum is carried out in the process of piecemeal process, first according to the map map datum is divided into different process layer by the different levels of data display, the data block of size such as then map datum to be spatially divided on the basis of process layer, the size of data block is large as far as possible, until be no more than the maximum free memory of CPU and GPU, reduce the number of times of process when meeting CPU and GPU and can processing as far as possible, raise the efficiency.
Before data block being loaded into the internal memory of CPU and the storer of GPU, map datum is also classified and conversion process.
Carry out classification process to map datum to comprise: calculating data be divided into: vector data, raster data and auxiliary data three class, wherein vector data is divided into point-like data, wire data and planar data; Auxiliary data is divided into annotation data and pattern data.
The process of carrying out conversion process to map datum is vector data is converted to the data layout that OpenGL can support.
Process data block being loaded into the internal memory of CPU and the storer of GPU comprises: after reading internal memory by needing the data block being loaded into GPU from external memory storage, by the video memory needing the data block being loaded into GPU to be copied to GPU, emptying internal memory, being copied to internal memory by needing the data block being loaded into CPU.
For sorted map datum, CPU and GPU carries out slicing treatment in different ways, concrete, is the process flow diagram of the embodiment of the method for CPU and GPU generating pictures as shown in Figure 3 and Figure 4, and as shown in Figure 3, the embodiment of CPU slicing processing comprises:
Step 301, generates the scope of section according to the parameter of section.
This parameter comprises: level of zoom, image capturing range, projection and slice size etc.
Step 302, carries out slicing treatment to each level of zoom successively.
Multiple core cpu has walked abreast the slicing processing of a level of zoom, and when completing a level of zoom, each core cpu can distribute the section of impartial quantity as far as possible.
Step 303, terminates this CPU slicing processing when all level of zoom slicing treatment complete.
As shown in Figure 4, the embodiment of GPU slicing processing comprises:
Step 311, generates the scope of section according to the parameter of section.
This parameter comprises: level of zoom, image capturing range, projection and slice size etc.
Step 312, judges to be loaded into the type of the data block of the storer of GPU, this data block be incremental data or labeled data time, perform step 313, when this data block is raster data, perform step 314.
Step 313, adopts OpenGL to carry out color applying drawing section, performs step 315.
Step 314, adopt the method for image procossing to complete slicing treatment, perform step 315, this image processing process comprises resampling and over-sampling.
Step 315, is copied to internal memory by asynchronous for the data after slicing treatment, terminates GPU slicing processing when all data blocks in the storer of GPU complete slicing treatment.
After CPU and GPU all completes slicing processing, the data in internal memory are converted to picture format data, by picture to comprise the data of the png form of transparent layer, slice of data is stored in file system according to the mode of Z, X, Y.
Embodiment two
For validity and the feasibility of checking the present embodiment method, in following hardware environment, for different slicing parameters and map, perform the computer program write according to the present embodiment method, simultaneously carry out contrast test with the section program that provides in QGIS2.2, obtain following the result.
Main hardware environment:
| Type of hardware | Model | Feature |
| CPU | AMD?A10-5800K | 4 cores, dominant frequency 3.8GHz |
| Internal memory | Jin Shidun DDR3-1600Hz8G | Two, 16GB space altogether |
| GPU | Nvidia?GT630 | 96 cores, 2GB space |
| Hard disk | West Digital lT | 7200rpm |
Main software environment:
| Software type | Model and version |
| Operating system | Windows?server2008r2x64 |
| Integrated Development Environment | Visual?studio2008 |
| Development language | C++ |
| GPU development environment | CUDA5.0 |
| CPU parallel development environment | OpenMP |
| Generalized information system | QGIS2.2.0 |
| Graphic package interface | OpenGL4.3 |
| Other third parties increase income storehouse | GDAL1.9、QT4.7.1 |
Data cases:
| Data type | Size | Remarks |
| CHINESE REGION *** high definition image | 8GB | 47872 (wide) * 46080 (height) * 3 (wave band number) |
| China's 1: 400 ten thousand polar plot | 200MB | ArcGIS Shapefile form |
Carry out chip rate comparing result:
By analyzing known to the above results, this dicing method can obtain extraordinary acceleration effect, and it is more obvious that progression more adds effect.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. based on the rapid generation that the map of CPU+GPU is cut into slices, it is characterized in that, described method comprises:
Step 1, obtain the hardware handles performance information of moving calculation machine, described allocation of computer has the core cpu of GPU and at least two, tests the computing power of described CPU and GPU;
Step 2, obtains map datum and tile configuration information, distributes section task amount according to the computing power of described CPU and GPU;
Step 3, carries out piecemeal process to described map datum, and data block be loaded into successively in the internal memory of described CPU and the storer of described GPU according to the section task amount of described distribution, described CPU and described GPU carries out slicing treatment generating pictures to described data block;
Step 4, when all described data block process complete, terminates.
2. the method for claim 1, it is characterized in that, the hardware handles performance information of described moving calculation machine obtained in described step 1 comprises the dominant frequency of CPU, core amounts and available memory space size, the dominant frequency of GPU, core amounts and available video memory size;
Perform the parallel algorithm comprising a large amount of thread, the computation capability of test CPU and GPU and floating point arithmetic ability.
3. the method for claim 1, is characterized in that, the described map data information obtained in described step 2 comprises: body of a map or chart and map layer;
The tile configuration information obtained comprises: classification, engineer's scale, tile size and map projection's mode.
4. the method for claim 1, it is characterized in that, when distributing section task amount according to the computing power of CPU and GPU in described step 2, in the core cpu of described at least two, the free time goes out a core cpu and does not participate in section and calculate, and other core cpus in the core cpu of described at least two and GPU are according to computation capability and floating point arithmetic capability distribution section task amount.
5. the method for claim 1, it is characterized in that, carry out described piecemeal process to described map datum in described step 3 to comprise: according to the different levels that described map datum shows, described map datum is divided into different process layer, described map datum is spatially divided into equal-sized data block by the basis of described process layer, and the size of described data block is the maximal value of the maximum free memory being no more than CPU and GPU.
6. the method for claim 1, is characterized in that, before described data block being loaded into the internal memory of described CPU and the storer of GPU in described step 3, also classifies and conversion process to described map datum;
Carry out described classification process to described map datum to comprise:
Calculating data are divided into vector data, raster data and auxiliary data; Described vector data is divided into point-like data, wire data and planar data; Described auxiliary data is divided into annotation data and pattern data;
The process of described map datum being carried out to conversion process is the data layout described vector data being converted to OpenGL support.
7. the method for claim 1, is characterized in that, the process in described step 3, described data block being loaded into the internal memory of described CPU and the storer of described GPU comprises:
After reading described internal memory by needing the data block being loaded into described GPU from external memory storage, by the described video memory needing the data block being loaded into GPU to be copied to described GPU, emptying described internal memory, being copied to described internal memory by needing the data block being loaded into CPU.
8. the method for claim 1, is characterized in that, described in described step 3, CPU comprises the process that described data block carries out slicing treatment generating pictures:
Step 301, generates the scope of section according to the parameter of section;
This parameter comprises: level of zoom, image capturing range, projection and slice size;
Step 302, carries out slicing treatment to each level of zoom successively;
Described core cpu has walked abreast the slicing processing of a described level of zoom;
Step 303, terminates described CPU slicing processing when all level of zoom slicing treatment complete.
9. method as claimed in claim 6, it is characterized in that, described in described step 3, GPU comprises the process that described data block carries out slicing treatment generating pictures:
Step 311, generates the scope of section according to the parameter of section;
This parameter comprises: level of zoom, image capturing range, projection and slice size;
Step 312, judges to be loaded into the type of the described data block of the storer of described GPU, described data block be described incremental data or labeled data time, perform step 313, when described data block is described raster data, perform step 314.
Step 313, adopts OpenGL to carry out color applying drawing section, performs step 315;
Step 314, adopts the method for image procossing to complete slicing treatment, performs step 315;
Described image processing process comprises resampling and over-sampling;
Step 315, is copied to described internal memory by asynchronous for the data after slicing treatment, terminates described GPU slicing processing when all data blocks in the storer of described GPU complete slicing treatment.
10. the method for claim 1, it is characterized in that, after described CPU and GPU all completes slicing processing, data in described internal memory are converted to picture format data, by picture to comprise the data of the png form of transparent layer, slice of data according to Z, the mode of X, Y is stored in file system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410474686.8A CN104267940A (en) | 2014-09-17 | 2014-09-17 | Quick map tile generation method based on CPU+GPU |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410474686.8A CN104267940A (en) | 2014-09-17 | 2014-09-17 | Quick map tile generation method based on CPU+GPU |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104267940A true CN104267940A (en) | 2015-01-07 |
Family
ID=52159464
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410474686.8A Pending CN104267940A (en) | 2014-09-17 | 2014-09-17 | Quick map tile generation method based on CPU+GPU |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104267940A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109670001A (en) * | 2018-11-14 | 2019-04-23 | 南京大学 | Polygonal gird GPU parallel calculating method based on CUDA |
| CN109684426A (en) * | 2018-12-04 | 2019-04-26 | 北京世纪高通科技有限公司 | A kind of map dicing method and device |
| CN109783157A (en) * | 2018-12-29 | 2019-05-21 | 深圳云天励飞技术有限公司 | A kind of method and relevant apparatus of algorithm routine load |
| CN110135569A (en) * | 2019-04-11 | 2019-08-16 | 中国人民解放军国防科技大学 | Heterogeneous platform neuron positioning three-level flow parallel method, system and medium |
| CN110427345A (en) * | 2019-07-25 | 2019-11-08 | 武汉星源云意科技有限公司 | A kind of fast cache method of network level map datum |
| CN111489281A (en) * | 2020-04-09 | 2020-08-04 | 常州奥创医疗科技有限公司 | Detection method based on GPU and CPU cooperative operation |
| WO2020086027A3 (en) * | 2018-10-23 | 2020-10-29 | Maptriks Bilisim Teknolojileri Sanayi Ve Ticaret A.S | Fast visualization and analysis engine increasing processing speed of queries made on geographical and numerical data |
| CN112905277A (en) * | 2021-01-25 | 2021-06-04 | 四川长虹电器股份有限公司 | Intelligent display terminal large image loading method |
| CN114461406A (en) * | 2022-04-13 | 2022-05-10 | 麒麟软件有限公司 | DMA OpenGL optimization method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080117220A1 (en) * | 2006-09-25 | 2008-05-22 | Neurala Llc | Graphic Processor Based Accelerator System and Method |
| CN101526934A (en) * | 2009-04-21 | 2009-09-09 | 浪潮电子信息产业股份有限公司 | Construction method of GPU and CPU combined processor |
| CN101706741A (en) * | 2009-12-11 | 2010-05-12 | 中国人民解放军国防科学技术大学 | Method for partitioning dynamic tasks of CPU and GPU based on load balance |
| CN101887595A (en) * | 2009-05-14 | 2010-11-17 | 武汉如临其境科技创意有限公司 | Three-dimensional digital earth-space data organizing and rendering method based on quad-tree index |
| CN102929718A (en) * | 2012-09-17 | 2013-02-13 | 江苏九章计算机科技有限公司 | Distributed GPU (graphics processing unit) computer system based on task scheduling |
| CN103617626A (en) * | 2013-12-16 | 2014-03-05 | 武汉狮图空间信息技术有限公司 | Central processing unit (CPU) and ground power unit (GPU)-based remote-sensing image multi-scale heterogeneous parallel segmentation method |
| CN103713949A (en) * | 2012-10-09 | 2014-04-09 | 鸿富锦精密工业（深圳）有限公司 | System and method for dynamic task allocation |
-
2014
- 2014-09-17 CN CN201410474686.8A patent/CN104267940A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080117220A1 (en) * | 2006-09-25 | 2008-05-22 | Neurala Llc | Graphic Processor Based Accelerator System and Method |
| US20140192073A1 (en) * | 2006-09-25 | 2014-07-10 | Neurala Inc. | Graphic processor based accelerator system and method |
| CN101526934A (en) * | 2009-04-21 | 2009-09-09 | 浪潮电子信息产业股份有限公司 | Construction method of GPU and CPU combined processor |
| CN101887595A (en) * | 2009-05-14 | 2010-11-17 | 武汉如临其境科技创意有限公司 | Three-dimensional digital earth-space data organizing and rendering method based on quad-tree index |
| CN101706741A (en) * | 2009-12-11 | 2010-05-12 | 中国人民解放军国防科学技术大学 | Method for partitioning dynamic tasks of CPU and GPU based on load balance |
| CN102929718A (en) * | 2012-09-17 | 2013-02-13 | 江苏九章计算机科技有限公司 | Distributed GPU (graphics processing unit) computer system based on task scheduling |
| CN103713949A (en) * | 2012-10-09 | 2014-04-09 | 鸿富锦精密工业（深圳）有限公司 | System and method for dynamic task allocation |
| CN103617626A (en) * | 2013-12-16 | 2014-03-05 | 武汉狮图空间信息技术有限公司 | Central processing unit (CPU) and ground power unit (GPU)-based remote-sensing image multi-scale heterogeneous parallel segmentation method |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020086027A3 (en) * | 2018-10-23 | 2020-10-29 | Maptriks Bilisim Teknolojileri Sanayi Ve Ticaret A.S | Fast visualization and analysis engine increasing processing speed of queries made on geographical and numerical data |
| CN109670001A (en) * | 2018-11-14 | 2019-04-23 | 南京大学 | Polygonal gird GPU parallel calculating method based on CUDA |
| CN109684426A (en) * | 2018-12-04 | 2019-04-26 | 北京世纪高通科技有限公司 | A kind of map dicing method and device |
| CN109783157A (en) * | 2018-12-29 | 2019-05-21 | 深圳云天励飞技术有限公司 | A kind of method and relevant apparatus of algorithm routine load |
| WO2020134830A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳云天励飞技术有限公司 | Algorithm program loading method and related apparatus |
| CN110135569A (en) * | 2019-04-11 | 2019-08-16 | 中国人民解放军国防科技大学 | Heterogeneous platform neuron positioning three-level flow parallel method, system and medium |
| CN110135569B (en) * | 2019-04-11 | 2021-09-21 | 中国人民解放军国防科技大学 | Heterogeneous platform neuron positioning three-level flow parallel method, system and medium |
| CN110427345A (en) * | 2019-07-25 | 2019-11-08 | 武汉星源云意科技有限公司 | A kind of fast cache method of network level map datum |
| CN110427345B (en) * | 2019-07-25 | 2023-02-03 | 武汉星源云意科技有限公司 | Rapid caching method for network level map data |
| CN111489281A (en) * | 2020-04-09 | 2020-08-04 | 常州奥创医疗科技有限公司 | Detection method based on GPU and CPU cooperative operation |
| CN112905277A (en) * | 2021-01-25 | 2021-06-04 | 四川长虹电器股份有限公司 | Intelligent display terminal large image loading method |
| CN114461406A (en) * | 2022-04-13 | 2022-05-10 | 麒麟软件有限公司 | DMA OpenGL optimization method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104267940A (en) | Quick map tile generation method based on CPU+GPU | |
| US9177351B2 (en) | Multi-primitive graphics rendering pipeline | |
| US9928645B2 (en) | Raster-based mesh decimation | |
| US9153209B2 (en) | Method and system for generating a displacement map from a normal map | |
| CN102591709B (en) | Shapefile master-slave type parallel writing method based on OGR (open geospatial rule) | |
| CN102880509B (en) | Compute unified device architecture (CUDA) based grid digital elevation model (DEM) neighborhood analysis system and method | |
| CN106383828B (en) | A kind of drawing practice and electronic equipment | |
| CN113190515B (en) | Heterogeneous parallel computing-based urban mass point cloud coordinate transformation method | |
| CN103606192A (en) | Wind field visual display method based on three-dimensional virtual globe | |
| EP3161793B1 (en) | Adaptive partition mechanism with arbitrary tile shape for tile based rendering gpu architecture | |
| CN109242967B (en) | Three-dimensional terrain rendering method and device | |
| CN104570081A (en) | Pre-stack reverse time migration seismic data processing method and system by integral method | |
| US9626285B2 (en) | Storage resource allocation to dataflows based on data requirements and attributes | |
| CN113012269A (en) | Three-dimensional image data rendering method and equipment based on GPU | |
| TW201539376A (en) | System and method for cutting point clouds | |
| CN112749244A (en) | Method and device for realizing digital twin city space coordinate system based on illusion engine and storage medium | |
| CN115018992B (en) | Method and device for generating hair style model, electronic equipment and storage medium | |
| CN103871019A (en) | Optimizing triangle topology for path rendering | |
| CN106548500A (en) | A kind of two-dimension situation image processing method and device based on GPU | |
| US20180211434A1 (en) | Stereo rendering | |
| TW201447812A (en) | Stencil-then-cover path rendering with shared edges | |
| Stojanovic et al. | High performance processing and analysis of geospatial data using CUDA on GPU | |
| CN113094536B (en) | Power transmission tower lightweight display method and device based on power grid GIM | |
| US9135749B2 (en) | Method and apparatus for processing three-dimensional model data | |
| CN105574917A (en) | Normal map reconstruction processing system and method for 3D models |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150107 |
|
| WD01 | Invention patent application deemed withdrawn after publication |