Tutorials
The ZED SDK GitHub repository provides a set of useful tutorials to help you get familiar with the ZED SDK API in the different available code languages.
If you need assistance with building the examples, you can refer to the API Language section of the documentation for detailed instructions on how to set up your development environment.
| TUTORIAL | Description | Link |
|---|---|---|
| 1 - Hello ZED | Opens a ZED camera with basic initialization parameters, reads back its serial number, and closes it. The simplest possible starting point for the ZED SDK API. (C, C++, Python, C#) | GitHub |
| 2 - Image Capture | Grabs images in a loop and retrieves the left image along with its timestamp and resolution, until 50 frames have been captured. (C, C++, Python, C#) | GitHub |
| 3 - Depth Sensing | Enables depth sensing, retrieves the depth map and colored point cloud for 50 frames, and measures the distance to the point at the center of the image. (C, C++, Python, C#) | GitHub |
| 4 - Positional Tracking | Enables positional tracking and retrieves the camera’s real-time position and orientation (pose) in the world reference frame over 1000 frames, including fused IMU data when available. (C, C++, Python, C#) | GitHub |
| 5 - Spatial Mapping | Enables positional tracking and spatial mapping to reconstruct a 3D mesh of the environment over 500 frames, filters it, and exports it as an OBJ file. (C, C++, Python, C#) | GitHub |
| 6 - Object Detection | Enables the AI-based Object Detection module to detect, classify and localize objects in 3D space, with a runtime-adjustable confidence threshold. Requires a camera with an integrated IMU. (C, C++, Python, C#) | GitHub |
| 7 - Sensor Data | Retrieves IMU, barometer and magnetometer data from the camera’s onboard sensors for 800 samples, synchronized or not with image frames. (C, C++, Python, C#) | GitHub |
| 8 - Body Tracking | Enables the Body Tracking module to detect and track 3D human body skeletons, with a confidence threshold tuned for indoor or outdoor use. Requires a camera with an integrated IMU. (C, C++, Python, C#) | GitHub |
| 9 - Global Localization | Uses the Fusion API to ingest simulated GNSS coordinates and fuse them with the camera’s visual-inertial odometry, computing a global position (latitude, longitude, altitude). (C++, Python) | GitHub |
| 10 - Split Process | Decouples image and depth acquisition with read() and grab(), so images can be retrieved at full frame rate while depth is only computed every few frames, and reports the resulting FPS. (C++) | GitHub |
| 11 - Health Status | Enables the camera’s image validity check and reads the detailed health status (image quality, lighting, depth and motion-sensor reliability) to detect corrupted frames in real time. (C++) | GitHub |
| 12 - Retrieve Tensor | Uses Camera::retrieveTensor() to get a resized, normalized image tensor (NCHW) straight from the ZED camera, ready to feed into a deep learning inference pipeline. (C++) | GitHub |