3D Sensing

Flood NIR: near-infrared image, acquired with assist of a PMSILPlus flood illuminator. This images are used for 2D image analysis that will be fused with the 3D image data.

Dot NIR: near-infrared image, acquired with assist of a dot projector. The dot pattern is enhancing contrast in the image to provide a very good depth map in all lighting conditions with low contrast objects in the scene.

Depth Map: ams face recognition use depth map information of the user’s face. A facial depth map is a set of thousands of coordinates mapped in three-dimensional space describing the contours of the surface of the user’s head relative to a single point of view in front of the user. This depth map may be compared with a reference depth map of the user’s face to authenticate the user. 

Reconstructed 3D image is handed over to the application software for further use case specific processing (e.g. face recognition).

Stereo matching algorithms might fail to find correspondences in surface with uniform color, low texture and no features. Passive stereo vision systems rely on the ambient light to capture images and perform poorly under low light conditions. For optimal performance, active stereo vision includes an additional pattern light projector to enhance feature extraction and low light performance. The illumination increase the light intensity and a number of features in the scene to overcome typical system limitations.