The ZED is a passive stereovision based camera that reproduces the way human vision works. Using its two “eyes” and through triangulation, the ZED understand its surroundings and create a three-dimensional model of the scene it observes.
How does it work?
The ZED camera outputs a high resolution side-by-side color video on USB 3.0. The video contains two synchronized left and right video streams. This color video is used by the ZED software on the host machine to create a depth map of the scene. Developers have access to the color video and depth map simultaneously.
How does it compare to other depth sensors?
Up until now, 3D sensors have been limited up to perceiving depth at short range and indoors. The ZED Stereo Camera is the first sensor to introduce indoor and outdoor long range depth perception, enabling the development of new services and applications in many industries: robotics, AR/VR, video analytics, security, VFX, 3D printing and more.
Can I use the ZED for people counting and tracking?
The ZED can be used both indoors and outdoors at long range (up to 20m). The ZED Mini can also be used indoors and outdoors up to 15m. The configuration that offers the best depth accuracy is to place the camera at a working distance of 1 meter of the scene for the ZED (and 0.5m for the ZED Mini). To capture fast movements, use the camera high-speed modes (HD720 @ 60 FPS or VGA @ 100 FPS). Avoid using the camera in very low-light environments as the camera does not use IR but color images for depth perception.
What is the depth accuracy?
The ZED uses triangulation to estimate depth from the disparity image, with the following formula describing how depth resolution changes over the range of the camera:
Z is the distance and
alpha a constant.
Depth accuracy decreases quadratically over the z-distance, with a depth accuracy of 1% of the distance in the near range to 9% in the far range. Depth accuracy can also be affected by outliers’ measurements on homogenous and textureless surfaces such as white walls, green screens and specular areas. These surfaces usually generate temporal instability in depth measurements.