gSLICr-master
所属分类:图形图像处理
开发工具:Python
文件大小:544KB
下载次数:12
上传日期:2017-12-11 15:30:27
上 传 者:
ns5417
说明: 主要是用于图像的分割,具体的算法不详,但是当前景和背景的区分度稍微高时,分割效果是相当不错的,但是如果区分度不是很高,效果就稍微差一点;
(the image segmentaion for image matting which is suitable for images which has a high contrast between foreground and background;)
文件列表:
CMakeLists.txt (1373, 2017-05-20)
LICENCE (3812, 2017-05-20)
NVTimer.h (14027, 2017-05-20)
ORUtils (0, 2017-05-20)
ORUtils\CMakeLists.txt (1340, 2017-05-20)
ORUtils\CUDADefines.h (928, 2017-05-20)
ORUtils\Cholesky.h (1420, 2017-05-20)
ORUtils\Dummy.cpp (116, 2017-05-20)
ORUtils\Image.h (1686, 2017-05-20)
ORUtils\LexicalCast.h (802, 2017-05-20)
ORUtils\MathUtils.h (1014, 2017-05-20)
ORUtils\Matrix.h (21315, 2017-05-20)
ORUtils\MemoryBlock.h (6474, 2017-05-20)
ORUtils\MemoryBlockPersister.h (7454, 2017-05-20)
ORUtils\MetalContext.h (1261, 2017-05-20)
ORUtils\MetalContext.mm (1528, 2017-05-20)
ORUtils\PlatformIndependence.h (889, 2017-05-20)
ORUtils\Vector.h (33329, 2017-05-20)
demo.cpp (3344, 2017-05-20)
gSLICr_Lib (0, 2017-05-20)
gSLICr_Lib\engines (0, 2017-05-20)
gSLICr_Lib\engines\gSLICr_core_engine.cpp (1385, 2017-05-20)
gSLICr_Lib\engines\gSLICr_core_engine.h (720, 2017-05-20)
gSLICr_Lib\engines\gSLICr_seg_engine.cpp (998, 2017-05-20)
gSLICr_Lib\engines\gSLICr_seg_engine.h (1160, 2017-05-20)
gSLICr_Lib\engines\gSLICr_seg_engine_GPU.cu (12882, 2017-05-20)
gSLICr_Lib\engines\gSLICr_seg_engine_GPU.h (718, 2017-05-20)
gSLICr_Lib\engines\gSLICr_seg_engine_shared.h (6828, 2017-05-20)
gSLICr_Lib\gSLICr.h (114, 2017-05-20)
gSLICr_Lib\gSLICr_defines.h (2256, 2017-05-20)
gSLICr_Lib\objects (0, 2017-05-20)
gSLICr_Lib\objects\gSLICr_settings.h (378, 2017-05-20)
gSLICr_Lib\objects\gSLICr_spixel_info.h (325, 2017-05-20)
sample.bmp (1228854, 2017-05-20)
# gSLICr: SLIC superpixels at over 250Hz
![sample](sample.bmp)
This is the software bundle "gSLICr", a library for real-time superpixel segmentation written in C++ and CUDA. The current version is maintained by:
[Carl Yuheng Ren](http://www.carlyuheng.com/) :
[Victor Adrian Prisacariu](http://www.robots.ox.ac.uk/~victor/) :
Ian D Reid :
For more information about gSLICr please visit the project website .
Other related projects can be found in the Oxford Active Vision Library .
# 1. Updates from gSLIC
- Works for any size / number of super pixels
- With GTX Titan X, 3.4ms@***0x480, 12ms@1280x960, 20ms@1920x1080 image
- Multi-platform supported
- Win8 Visual Studio
- Ubuntu 14.04
- Mac OSX 10.10
# 2. Building the System
### 2.1 Requirements
Several 3rd party libraries are needed for compiling gSLICr. The given version numbers are checked and working, but different versions might be fine as well. Some of the libraries are optional, and skipping them will reduce functionality.
- cmake (e.g. version 2.8.10.2 or 3.2.3)
REQUIRED for Windows and Linux, unless you write your own build system
available at http://www.cmake.org/
- CUDA (e.g. version 6.0 or 7.0)
REQUIRED for all GPU accelerated code
available at https://developer.nvidia.com/cuda-downloads
- OpenCV (e.g. version 3.0)
REQUIRED if you want to run the demo, where it is used for reading camera input and displaying UI
available at http://opencv.org/downloads.html
### 2.2 Build Process
To compile the system, use the standard cmake approach:
```
$ mkdir build
$ cd build
$ cmake /path/to/gSLICr
$ make
```
To run demo:
- plug in a webcam
- use the standard cmake approach:
```
mkdir build
cd build
cmake ../
make
./demo
```
- press `s` to save current segmentation result to current folder.
# 3. What to cite
If you use this code for your research, please kindly cite:
```
@article{gSLICr_2015,
author = {{Ren}, C.~Y and {Prisacariu}, V.~A. and {Reid}, I.~D},
title = "{gSLICr: SLIC superpixels at over 250Hz}",
journal = {ArXiv e-prints},
eprint = {1509.04232},
year = 2015,
month = sep
}
```
[arxiv linke](http://arxiv.org/abs/1509.04232)
近期下载者:
相关文件:
收藏者: