Contact-Based Fringe Projection Profilometry for High-Resolution 3-D Surface Measurement of Reflective and Transparent Objects

2026-06-16 · Source: Computer Vision and Pattern Recognition · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Expert, quick

Summary

A new contact-based 3-D surface measurement method utilizes a Digital Fringe Projection (DFP) system to overcome limitations of existing vision-based tactile sensors like GelSight. While GelSight infers depth from surface gradients, leading to accumulated errors and calibration difficulties over larger areas, especially with reflective or transparent objects, the proposed DFP-based technique performs direct triangulation. This method reconstructs 3-D shapes on a coated silicone contact surface, delivering dense per-pixel surface geometry and full-field measurement. By integrating high-accuracy digital fringe projection, the system simplifies calibration for larger sensing areas and significantly enhances depth precision for complex surfaces. Experimental comparisons with a GelSight Mini sensor, sphere-fitting accuracy evaluations, and uncertainty analyses confirm improved accuracy and stability, enabling reliable reconstruction of objects with diverse optical properties.

Key takeaway

For Robotics Engineers designing advanced tactile sensors, you should consider contact-based Digital Fringe Projection systems. This approach offers superior depth accuracy and simplified calibration compared to photometric stereo methods, especially when dealing with highly reflective or transparent objects. Integrating DFP can enhance your robotic manipulation capabilities and improve the reliability of 3-D surface measurements.

Key insights

A DFP-based contact sensor directly measures 3-D surface geometry, improving accuracy and calibration for reflective/transparent objects over gradient-based methods.

Principles

• Triangulation provides direct 3-D depth measurement.
• DFP simplifies calibration for larger sensing areas.
• Coated silicone enables fringe projection contact sensing.

Method

The method performs triangulation-based 3-D reconstruction on a coated silicone contact surface using a Digital Fringe Projection system to capture dense per-pixel surface geometry.

In practice

• High-resolution 3-D measurement of reflective objects.
• Enhanced robotic fingertip manipulation.
• Improved contact sensing for transparent materials.

Topics

• Digital Fringe Projection
• 3D Surface Measurement
• Tactile Sensing
• Robotic Manipulation
• Reflective Objects
• Transparent Objects
• GelSight

Best for: Research Scientist, AI Scientist, Computer Vision Engineer, Robotics Engineer

Related on AIssential

• Comparing Commercial Depth Sensor Accuracy for Medical Applications — The Zivid 2M+ 60 depth sensor demonstrated superior accuracy across diverse medical specimens compared to three other commercial sensors.
• UMI-3D: Extending Universal Manipulation Interface from Vision-Limited to 3D Spatial Perception — UMI-3D enhances robot manipulation data collection via LiDAR-centric SLAM and multimodal sensor fusion.
• Broadband Hyperspectral 3D Imaging using Dispersed Structured Light — A single-spectrograph system enables broadband hyperspectral 3D imaging by extending dispersed structured light across visible-SWIR.
• Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation — Modeling depth ambiguity with multiple hypotheses per pixel prevents flying points and improves boundary reconstruction in depth estimation.
• TactStyle: 3D modeling you can feel — Haptic feedback in 3D modeling enhances intuition and precision by allowing users to feel virtual objects.
• Efficient Sensor Fusion for Gesture Recognition on Resource-Constrained Devices — Sensor fusion of low-resolution ToF and IR enables efficient, private gesture recognition on resource-constrained devices.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Computer Vision and Pattern Recognition.