Stereo Vision - Banner

Stereo Vision

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.

 

stereo vision

Stereo Vision Reference Design

Stereo Vision Reference Design

The stereovision reference design demonstrates active stereo technology using latest illuminators, image sensors and SW (both depthmap and faceID) and enables fast time-to-market for OEMs. The turn-key reference design is optimized for the Qualcomm SD platforms (845, 855, 670) for front facing 3D and delivers excellent depth map quality at a small form factor and a low BOM.

Stereo Vision Reference Design