Examples in this folder are designed to complement existing SDK examples and demonstrate how Intel RealSense cameras can be used together with opencv
in domain of computer-vision.
- ImShow - Minimal OpenCV application for visualizing depth data
- GrabCuts - Simple background removal using the GrabCut algorithm
- Latency-Tool - Basic latency estimation using computer vision
- DNN - Intel RealSense camera used for real-time object-detection
This page is certainly not a comprehensive guide to getting started with OpenCV and CMake, but it can help get on the right track.
- Download and install
CMake
from cmake.org/download - Clone or download OpenCV sources from github.com/opencv/opencv into a local directory (
C:/git/opencv-master
) - Run
cmake-gui
, input source code and binaries locations:
- Click
Configure
When working behind a firewall, you might want to consider unchecking
WITH_FFMPEG
andWITH_IPP
to avoid additional downloads
- Uncheck
BUILD_SHARED_LIBS
:
- Click
Generate
- Click
Open Project
to open Visual Studio - Press
Ctrl+Shift+B
to build solution - Clone or download librealsense sources from github.com/IntelRealSense/librealsense into a local directory (
C:/git/librealsense
) - Run
cmake-gui
and fill source code and binaries locations and pressConfigure
- Make sure you check the
BUILD_CV_EXAMPLES
flag and clickConfigure
again:
- Specify CMake binaries folder for OpenCV as
OpenCV_DIR
(c:/git/opencv-master
)
- Click
Generate
andOpen Project
- Locate CV solution-folder under Examples
- Right-click on one of the examples to
Set as StartUp Project
- Press
F5
to compile and run the example
- Build
opencv
from source using the official guide - Run
export OpenCV_DIR=~/opencv/build
(~/opencv/build
is the folder containingOpenCVConfig.cmake
) - Follow the instructions to build
librealsense
from source - Add
-DBUILD_CV_EXAMPLES=true
to yourcmake
command