This sample shows how to interface the ZED SDK and OpenCV to acquire and display ZED stereo images and depth map.

• First, download the latest version of the ZED SDK on stereolabs.com.
• Make sure you have OpenCV installed.
• For more information, check out this blog post and read the ZED API documentation.

• Windows 7 64bits or later, Ubuntu 16.04
• ZED SDK and its dependencies (CUDA, OpenCV 3.1)

Download the sample and follow these instructions:

• Create a "build" folder in the source folder
• Open cmake-gui and select the source and build folders
• Generate the Visual Studio Win64 solution
• Open the resulting solution and change configuration to Release
• Build solution

Open a terminal in the sample directory and execute the following command:

mkdir build
cd build
cmake ..
make

• Navigate to the build directory and launch the executable file

• Or open a terminal in the build directory and run the sample :

    ./ZED\ with\ OpenCV [path to SVO file]
  

You can optionally provide an SVO file path (recorded stereo video of the ZED)

This sample is the perfect place to get started coding with the ZED. It shows how to use the basic functions of the ZED SDK:

• Capture stereo video from the ZED or an SVO file.
• Capture depth map as a compatible 32bits float OpenCV matrix.
• Display stereo video in several viewing modes: raw, rectified, grayscale, anaglyph, overlay, difference and side-by-side.
• Display disparity and depth map.
• Adjust several depth parameters: depth sensing mode, max range, depth confidence.

To learn how to add camera tracking capabilities, see the dedicated tracking sample.

This table lists keyboard shortcuts that you can use in the sample application.

• For simplicity's sake, this sample uses GPU->CPU data transfer to retrieve and display the images with OpenCV.
• For optimal performance, we recommend using a direct device to device copy of the ZED SDK GPU buffer to OpenGL buffer, rather than using the CPU as an intermediate.