Implementation of an FPGA-Based 3D Shape Measurement System Using High-Level Synthesis

Abstract

Three-dimensional(3D) shape measurement using point clouds has recently gained significant attention. Phase measuring profilometry (PMP) is widely preferred for its robustness against external lighting changes and high-precision results. However, PMP suffers from long computation times due to complex calculations and its high memory usage. It also faces a 2π ambiguity issue, as the measured phase is limited to the 2π range. This is typically resolved using dual-wavelength methods. However, these methods require separate measurements of phase changes at two wavelengths, increasing the data processing volume and computation times. Our study addresses these challenges by implementing a 3D shape measurement system on a System-on-Chip (SoC)-type Field-Programmable Gate Array (FPGA). We developed a PMP algorithm with dual-wavelength methods, accelerating it through high-level synthesis (HLS) on the FPGA. This hardware implementation significantly reduces computation time while maintaining measurement accuracy. The experimental results demonstrate that our system operates correctly on the SoC-type FPGA, achieving computation speeds approximately 11.55 times higher than those of conventional software implementations. Our approach offers a practical solution for real-time 3D shape measurement, potentially benefiting applications in fields such as quality control, robotics, and computer vision.