Stereo Vision

An affordable and easy to implement 3D sensing solution.


How stereo vision works

The distance extraction in stereo vision is based on triangulation between two sensors whose baseline (B) and focal plane (f) is known.  The disparity – a key parameter all triangulation methods - is calculated by processing the images of both sensors (rectification and matching algorithm) and extracting the correspondences.

​​​​​​The maximum detectable depth range is proportional to the baseline (B) and the sensor resolution. The final depth resolution is mainly limited by matching and calibration errors.
> More about our dot projector Belago

> More about our flood illuminator EGA2000

Seres 4.1 - front facing mobile active stereo vision reference design

Seres is our active stereo vision reference design for front facing 3D sensing in smart phones and tablets. It uses our latest Belago dot projector, PMSILPlus flood illuminator, Mira130 image sensors and SW (both depth map and face authentication), enabling fast time-to-market for OEMs. The turn-key reference design is optimized for the Qualcomm SD platforms (845, 855, 670). It delivers excellent depth map quality at a small form factor and a low BOM.

Hermes - active stereo vision & structured light evaluation kit

Hermes is a USB 3D camera evaluation kit. Our 3D sensing solution both for active stereo vision and structured light can be evaluated with it. The 3D camera uses our latest Belago 1.1 dot projector featuring a focus free, high contrast, and randomized 5k dot pattern, our PMSIL+ flood illuminator as well as two Mira130 high QE image sensors. In simple software with a user interface running on any Windows 10 PC, the image streams and depth map can be visualized and exported for R&D.