AI improves 3D scanner accuracy by fixing pattern corner detection
RACE-FPP: A Robust AI-assisted Characterisation Enhancement for Fringe Projection Profilometry
Computer Vision and Pattern Recognition
Summary
3D scanning with fringe projection needs to precisely identify pattern corners on a checkerboard, which is hard when images are blurry or taken at odd angles. The authors created a new method that uses AI to better find these corners and checks how small errors affect the whole 3D measurement process. Their approach reduces errors in locating camera and projector points, leading to more accurate 3D models, especially in tough situations. This makes 3D scanning more reliable for industrial uses.
What this means in practice
- •For industrial metrology teams: Improve 3D shape measurements by reducing errors from pattern detection in harsh imaging conditions during quality control.
- •For machine vision engineers: Enhance system calibration accuracy for camera-projector setups by integrating deep learning corner detection into calibration workflows.
Authors
Osman Ali, Xiangjun Kong, Tibebe Yalew, Waiel Elmadih, Samanta Piano
Abstract
Fringe Projection Profilometry (FPP) requires precise system characterisation to achieve reliable three-dimensional (3D) reconstructions; however, characterisation accuracy strongly depends on robust checkerboard feature localisation, which can deteriorate under challenging imaging conditions such as lens blur and characterisation target orientations. Existing deep learning-based corner detectors are typically assessed using detection metrics and camera reprojection error alone, without considering their wider impact on projector characterisation, camera-projector stereo characterisation consistency, or overall measurement accuracy. In this work, we introduce a complete FPP characterisation pipeline that incorporates deep learning-based corner detection into the standard camera characterisation workflow. We also characterise the projector by sampling phase values at the centres of the white squares in the characterisation target. Rather than treating corner detection as an isolated task, the proposed framework explicitly analyses how localisation errors propagate throughout the entire FPP characterisation chain. Performance is evaluated using detection metrics (e.g., precision and recall), camera and projector reprojection errors, and the camera and projector stereo characterisation. Across a mixed dataset of clean and degraded images, the camera reprojection error is reduced from 1.237 pixels to 0.259 pixels, while the projector reprojection error is reduced by roughly 50%. Dimensional evaluation of reconstructed artefacts shows improved geometric accuracy compared with those resulting from the conventional pipeline. Overall, the findings indicate increased robustness of system-level characterisation under challenging imaging conditions, thereby enabling more reliable industrial FPP measurements.