Title: Robust 3D reconstruction in noisy environments

Abstract:
Automated inspection in industrial manufacturing can minimize the total production cost of a part. Current inspection solutions often involve measuring a part manually, which interrupts the machining process. We present two non-contact real-time systems which integrate visual inspection in-line with CNC (computer numerical control) machines and ensures dimensional model generation of parts with high accuracy. We first present a camera-projector scanning system that uses photometric stereo and structured light scanning to reconstruct the shape of objects in the presence of specular chip-like noise and high object revolution. We obtain reconstruction accuracies down to 0.5 mm for objects with complex reflectance on a representative CNC lathe. For rotationally symmetric objects, we also propose a novel shape from silhouette system which uses principles from light transport theory to effectively image transmissive paths through a scattering medium. The system enables in-line and highly-accurate geometric reconstructions down to 50 μm on CNC lathe machines in the presence of scattering fluid and specular metallic shavings. Both systems are compact and cost-effective alternatives to the current use of CMMs (co-ordinate measuring machines) for manual inspection of machined parts.

Committee:

Ioannis Gkioulekas (advisor)

Matthew P. O’Toole (advisor)

Aswin C Sankaranarayanan

Alankar Kotwal

ZOOM Link: https://cmu.zoom.us/j/99649202152?pwd=Rk5ZSTVMdXYwUG1pMlY4ZUNSdGlMUT09

Meeting ID: 996 4920 2152

Passcode: 311605