VISIONWORKS README.txt for Windows NVIDIA® VisionWorks™ Toolkit is a CUDA accelerated software development package for Computer Vision (CV). The toolkit is designed to provide a production-quality, standard interface that implements and extends the OpenVX standard, enabling high performance computer vision applications on NVIDIA Tegra devices. With the VisionWorks™ library of Computer Vision primitives, and its framework optimized for NVIDIA platforms, you can develop mobile and embedded applications for Robotics, Drones, Autonomous Driving, Augmented Reality (AR), Intelligent Video Analytics, and other Computer Vision markets. Where applicable, VisionWorks™ technologies take advantage of underlying hardware acceleration, such as NVIDIA® CUDA® technology, enabling significant speedup and thereby reducing engineering efforts in designing real-time vision applications. -------------------------------------------------------------------------------- NOTE: The installation instructions in this README supersede the instructions in the VisionWorks HTML documentation. These details are planned to be updated in the HTML documentation for the next release. PLATFORMS The following table shows the supported hardware, system software and the corresponding versions of OpenCV and CUDA. For desktop platforms a GPU of supported generation is required. You can check your GPU support status on official NVIDIA web page: -------------------------------------------------------------------------------- (1) Windows 8 x64, with Kepler(TM) (compute capability 3.x) and Maxwell(TM) (compute capability 5.x) GPU generations, Microsoft Visual Studio 2013 (Any edition, except Express) OS : Windows 8 x64 OpenCV : public OpenCV 2.4.12 CUDA : NVIDIA(R) CUDA(R) 7.0 * GPU must support Compute Capability 3.0 or higher. See for a complete list of compatible products. ** Microsoft Visual Studio 2013 Community or Professional required (Express edition is not supported). INSTALLATION INSTRUCTIONS -------------------------------------------------------------------------------- NOTE: This README file ONLY describes the installation instructions for Windows platform. Other platforms' installation instructions are available in corresponding README files. Install VisionWorks with the following steps: (1) CUDA Installation (2) OpenCV Installation (3) VisionWorks Installation The following sections contain detailed instructions for the installation of these packages. These instructions use the following variables: o specifies the package release version (e.g. 7.0). o specifies CUDA toolkit installation directory (e.g. C:\program Files\NVIDIA GPU Computing Toolkit\CUDA\v7.0) o specifies the OpenCV installation directory (e.g. C:\opencv) o specifies the package release version (e.g. 2412). o specifies the VisionWorks version (e.g. 1.0). o specifies the VisionWorks installation directory (e.g. C:\Program Files\NVIDIA VisionWorks) o specifies user defined folder for building VisionWorks samples (e.g. user specific "My Documents" folder) (1) CUDA Installation The NVIDIA invented CUDA(TM) technology provides a parallel computing platform and programming model that enables dramatic increases in computing performance by harnessing the power of the graphics processing unit (GPU). Download and install the CUDA Windows package from: (2) OpenCV installation Download the latest OpenCV 2.4.x from Run the executable file and specify the folder in which to install OpenCV (``). (3) VisionWorks Installation NVIDIA provides VisionWorks as an installation package named VisionWorks--win64.exe. Run the application and install VisionWorks to the desired folder following the installation instructions. Once the installation completes successfully, you can locate the libraries, headers, samples, and documentation (and some extra files) in the directories listed in the table below: | Component name | Installed Location | |-----------------------|------------------------------------------------------| | Documentation | `\share\visionworks\docs` | | Header files | `\include` | | Shared libraries | `\bin` | | Source code for demos | `\share\visionworks\sources`| The next steps describe the build procedure for VisionWorks samples. Note that the Express edition of Microsoft Visual Studio 2013 is not supported. Copy samples from \share\visionworks\sources to a directory with write access . Open Visual Studio's Developer Command Prompt - VS2013 x64 Native Tools Command Prompt. A default installation of Visual Studio 2013 will have a shortcut to this tool in the following folder: C:\Program Files (x86)\Microsoft Visual Studio 12.0\Common7\Tools\Shortcuts Go to the : > cd Edit the config.nmake file to insert correct paths for all prerequisite installation directory information. The should be in the following format: MajorMinorMinor (e.g. 2.4.11 becomes 2411). Note that config.nmake includes some of the paths assuming default paths are used in the installation process: # Dependency locations CUDA_DIR = OPENCV_DIR = \build OpenCV_VERSION = VISIONWORKS_DIR = # Debug build? dbg = 0 Build samples > nmake Once the build has completed, a number of executable files with the names starting with `nvx_sample` or `nvx_demo` will be located in the bin directory: \bin\x64\WinNT\release The OpenCV and VisionWorks library files required by the samples and demos will also be copied to this location. UNINSTALL INSTRUCTIONS -------------------------------------------------------------------------------- This section describes the uninstallation steps for VisionWorks and CUDA. (1) Uninstall VisionWorks (2) Uninstall CUDA (1) To uninstall VisionWorks VisionWorks library can be uninstalled via normal system way of software uninstallation. One should open Control Panel -> Uninstall a program, select NVIDIA VisionWorks and click on the Uninstall/Change widget. (2) To uninstall CUDA For the instructions on uninstalling CUDA please refer to the official documentation (NVIDIA CUDA Getting Started Guide for Windows).