Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
This paper introduces RACE-FPP, a novel AI-assisted characterization pipeline for Fringe Projection Profilometry (FPP) that integrates deep learning-based corner detection directly into the standard camera characterization workflow and extends projector characterization to white square centers. By explicitly analyzing the propagation of localization errors throughout the entire FPP characterization chain, rather than treating corner detection in isolation, the method significantly improves robustness under challenging imaging conditions. The proposed framework achieves substantial reductions in camera reprojection error (from 1.237 to 0.259 pixels) and projector reprojection error (approximately 50%), leading to enhanced geometric accuracy in 3D reconstructions.
Deep learning corner detection, when integrated into a full FPP characterization pipeline, drastically cuts camera reprojection error by over 80% and improves projector accuracy, unlocking more reliable 3D measurements even with blurry images.
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.