中值滤波代码matlab-SMSOM:堆叠式多层自组织图

  • X5_328634
    了解作者
  • 8.6MB
    文件大小
  • zip
    文件格式
  • 0
    收藏次数
  • VIP专享
    资源类型
  • 0
    下载次数
  • 2022-06-13 01:06
    上传日期
中值过滤代码matlab SMSOM-BM SMSOM-BM代表堆叠式多层自组织地图背景模型,这是我们在论文中提出的一种背景建模方法[1] 。 该存储库是我们原始工作流程(源代码,可执行文件,工具等,在下面说明)的克隆, [1]的实验以此为基础。 请参阅有关SMSOM-BM的更多信息。 您可以继续此README文件以查找如何使用它。 如果您对SMSOM-BM有任何疑问,意见或错误报告,请联系或提出要求。 该存储库的文件树为: . ├── Debug │   ├── cudart32_50_35.dll │   ├── cudart64_50_35.dll │   ├── smsom.exe │   ├── smsom.ilk │   └── smsom.pdb ├── README.md ├── smsom │   ├── smsom.cu │   ├── smsom.vcxproj │   ├── smsom.vcxproj.user │   └── vc100.pdb ├── smsom.sdf ├── smsom.sln ├── smsom.suo ├── src │   ├──
SMSOM-master.zip
  • SMSOM-master
  • smsom.suo
    12.5KB
  • Debug
  • smsom.ilk
    726.1KB
  • cudart32_50_35.dll
    461.4KB
  • cudart64_50_35.dll
    633.9KB
  • smsom.exe
    2.7MB
  • smsom.pdb
    2.2MB
  • src
  • smsom.cu
    82.2KB
  • CMakeLists.txt
    308B
  • smsom.sln
    882B
  • smsom
  • smsom.cu
    82.2KB
  • smsom.vcxproj.user
    143B
  • vc100.pdb
    588KB
  • smsom.vcxproj
    5.6KB
  • smsom.sdf
    17MB
  • tools
  • median_filter.m
    336B
  • README.md
    4.8KB
内容介绍
------------------------------------------------------------ # SMSOM-BM SMSOM-BM stands for Stacked Multi-layer Self-Organizing Map Background Model, which is a background modeling method presented in our paper **[1]**. This repository is a clone of our original work flow (source code, executable, tools, etc., explained below), and the experiments of **[1]** are based on it. Please see [project homepage][project homepage] for more information about SMSOM-BM. You can continue this README file to find how to use it. If you have any questions, comments, or bug reports regarding to SMSOM-BM, please contact zhaozj89@gmail.com, or pull a request. The file tree of this repository is: <pre> . ├── Debug │   ├── cudart32_50_35.dll │   ├── cudart64_50_35.dll │   ├── smsom.exe │   ├── smsom.ilk │   └── smsom.pdb ├── README.md ├── smsom │   ├── smsom.cu │   ├── smsom.vcxproj │   ├── smsom.vcxproj.user │   └── vc100.pdb ├── smsom.sdf ├── smsom.sln ├── smsom.suo ├── src │   ├── CMakeLists.txt │   └── smsom.cu └── tools └── median_filter.m </pre> ------------------------------------------------------------ # How to use ### For Windows users: If you have a working environment of OpenCV 2.4.5, CUDA 5.0, Visual Studio 2010, Windows 7 (64 bit), then you can use this repository directly. The executable is **.\Debug\smsom.exe**; therefore, you should first use **cmd** in Windows to navigate to the directory **Debug**. Please ENSURE smsom can find OpenCV library, and you have CUDA compatible GPU installed in your computer. Then you have two options: * If you have foreground free traning images, then execute: `smsom train <start_frame_number> <end_frame_number> <input_file_name> <output_file_name>` where `<start_frame_number>` and `<end_frame_number>` stand for the index range of the training images; `<input_file_name>` is the format of the input image's name, and the last parameter `<output_file_name>` is optional, if you omit it, then the output images are just shown in your screen, but not stored in your computer. For example, if I put the input images in: **E:\Data\input\**, the image files' name format is: **in000001.jpg** (any number), and I use 1-100 images to train the model, then I can execute: `smsom train 1 100 E:\\Data\\input\\in%06d.jpg E:\\Data\\results\\bin%06d.jpg` where I put the result images in **E:\Data\results**. or `smsom train 1 100 E:\\Data\\input\\in%06d.jpg` where I do not store the output images. * If you do not have foreground free training images, you can execute: `smsom nottrain <input_file_name> <output_file_name>` where the meanings of `<input_file_name>` and `<output_file_name>` (optional) are the same as the previous case. In this situation, we set the threshold tau=0.06 (see **[1]** for more details). ### For Linux users: You have to build yourself. Please ENSURE you have installed OpenCV and CUDA. See **[2]** for how to use CUDA on Linux platform. Then you can navigate to **./src/**, and execute the following commands in order: `cmake .` `make` The usage of the generated executable `smsom` is the same as the commands shown previously in Windows. (You may use `./smsom <parameters>` instead of `smsom <parameters>`) ------------------------------------------------------------ # Demos Some demo scripts are shown as follows (assuming you have decompressed dataset **[3]** in **E:\Data\**): * fountain01: ``smsom train 1 399 E:\\Data\\dynamicBackground\\fountain01\\input\\in%06d.jpg`` * highway: ``smsom nottrain E:\\Data\\baseline\\highway\\input\\in%06d.jpg`` * traffic: ``smsom train 129 200 E:\\Data\\cameraJitter\\traffic\\input\\in%06d.jpg`` * ladeSide: ``smsom train 1 999 E:\\Data\\thermal\\lakeSide\\input\\in%06d.jpg`` ------------------------------------------------------------ # Post-processing and quantitative evaluation You should use the Matlab script **.\tools\median_filter.m** to do a 5X5 median filtering to get the same results presented in this paper. Quatitative evaluation (Precision, Recall, F-measure) is done by the [Matlab tool][Matlab tool] of **[3]**. ------------------------------------------------------------ # References [1] Zhenjie Zhao, Xuebo Zhang, and Yongchun Fang. Stacked Multilayer Self-Organizing Map for Background Modeling. In: *IEEE Transactions on Image Processing*, vol. 24, no. 9, pp. 2841-2850, Sep 2015. [2] http://docs.nvidia.com/cuda/cuda-getting-started-guide-for-linux/#axzz3DimlP7Yp [3] http://www.changedetection.net/ [project homepage]: http://zhaozj89.github.io/SMSOM/ [Matlab tool]: http://wordpress-jodoin.dmi.usherb.ca/static/code/MatlabCode2012.zip ------------------------------------------------------------ All rights reserved.
评论
    相关推荐
    • Bug_Bounty_Dorks:该Bug_Bounty_Dorks存储库包含流行的Bug Bounty Dorks,它们从不同
      Bug_Bounty_Dorks:该Bug_Bounty_Dorks存储库包含流行的Bug Bounty Dorks,它们从不同的位置获取并在一个位置进行编译
    • Minecraft-Bugfixes
      我会不时将一些带有错误修正的Minecraft反编译类放到该存储库中,以将其链接到Minecraft Bug Tracker( )。 它只会包含单个(或什至只是部分)类,并且不打算盗版任何东西,而只是用来帮助解释错误和可能的修复。
    • ecshop bug
      ecshop 中出现的bug处理,js-jq冲突问题,在有冲突页面加载bug.js即可
    • rtape:迁移到 NotABug
      rtape 是一个包,用于以比标准 RData 格式更舒适的方式存储大量数据。 以 RData 格式存储大量数据会导致问题,因为必须将整个文件加载到内存中才能访问和操作此类文件中的对象; rtape 是这个问题的简单解决方案。...
    • gazelle-bugreport-2-dep:该存储库使用gazelle-bugreport-2-fork; 因此,该gaze
      gazelle-bugreport-2-dep:该存储库使用gazelle-bugreport-2-fork; 因此,该gazelle-bugreport-2-dep的用户将拥有gazelle-bugreport-2-fork作为传递依赖项
    • BugTracking的数据库
      刚上传的BugTracking的数据库,下载下来直接就可以用,里面有所有的存储过程代码
    • autoclonetype2_bug
      对于那些希望基于火箭芯片甚至芯片场开发RTL的人来说,这是一个模板存储库,它们能够编辑凿子环境中的所有源,而无需将其发布到本地常春藤。 您可以在build.sc添加自己的子模块。 有关更多信息,请在添加您自己的...
    • Bug Spray.zip
      语言:English 一键单击以创建详细文档以附加到Bug票证。 厌倦了与具有相同问题的开发人员来回返回?您使用的是哪个浏览器版本?哪种操作系统?... Bug喷雾跟踪的数据永远不会发送或存储除非您的设备除外。
    • BugFree2.1.1
      BugFree2.1.1发布!-开源中国社区.ZIP
    • bugfree bugfree 2.2
      bugfree 2.2拥有更加全面的管理Bug的功能