Title :
A low-power structured light sensor for outdoor scene reconstruction and dominant material identification
Author :
Mertz, Christoph ; Koppal, Sanjeev J. ; Sia, Solomon ; Narasimhan, Srinivasa
Abstract :
We introduce a compact structured light device that utilizes a commercially available MEMS mirror-enabled hand-held laser projector. Without complex re-engineering, we show how to exploit the projector´s high-speed MEMS mirror motion and laser light-sources to suppress ambient illumination, enabling low-cost and low-power reconstruction of outdoor scenes in sunlight. We discuss how the line-striping acts as a kind of “light-probe”, creating distinctive patterns of light scattered by different types of materials. We investigate visual features that can be computed from these patterns and can reliably identify the dominant material characteristic of a scene, i.e. where most of the objects consist of either diffuse (wood), translucent (wax), reflective (metal) or transparent (glass) materials.
Keywords :
image reconstruction; laser mirrors; light scattering; light sources; lighting; micromechanical devices; optical projectors; sensors; sunlight; MEMS mirror motion; MEMS mirror-enabled hand-held laser projector; ambient illumination suppression; compact structured light device; diffuse material; dominant material identification; laser light-sources; light scatter distinctive pattern; light-probe; line-striping; low-power structured light sensor; outdoor scene reconstruction; reflective material; sunlight; translucent material; transparent material; visual features; Glass; Image reconstruction; Lighting; Mirrors; Robot sensing systems; Visualization;
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2012 IEEE Computer Society Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4673-1611-8
Electronic_ISBN :
2160-7508
DOI :
10.1109/CVPRW.2012.6239194