Zhu Jiangping, Yang Fan, Hu Jialing, Zhou Pei
Opt Express. 2023 Jul 17;31(15):25318-25338. doi: 10.1364/OE.496208.
Accurate and complete 3D measurement of complex high dynamic range (HDR) surfaces has been challenging for structured light projection technique. The behavior of spraying a layer of diffuse reflection material, which will inevitably incur additional thickness. Existing methods based on additional facilities will increase the cost of hardware system. The algorithms-based methods are cost-effective and nondestructive, but they generally require redundant patterns for image fusion and model training, which fail to be suitable for practicing automated 3D measurement for complex HDR surfaces. In this paper, a HDR surface 3D reconstruction method based on sharing demodulation phase unwrapping mechanism and multi-indicators guided phase fusion strategy is proposed. The division of the exposure interval is optimized via the image entropy to generate an optimal exposure sequence. The combination of temporal-spatial binary (TSB) encoding fringe patterns with time-integration strategy and the variable exposure mode of digital mirror device (DMD)-based projector with a minimum projection exposure time of 233μs enables the proposed approach to broadly adapt complex HDR surfaces. We propose an efficient phase analysis solution called sharing mechanism that wrapped phase sequences from captured different intensity fringe images are unwrapped through sharing the same group of misaligned Gray code (MGC) decoding result. Finally, a phase sequences fusion model guided by multi-indicators, including exposure quality, phase gradient smoothness and pixel effectiveness, is established to obtain an optimum phase map for final 3D reconstruction. Comparative experiments indicate that the proposed method can completely restore the 3D topography of HDR surfaces with the images reduction of at least 65% and the measurement integrity is maintained at over 98% while preserving the measurement accuracy and excluding the outliers.
对于结构光投影技术而言，对复杂的高动态范围（HDR）表面进行精确且完整的三维测量一直具有挑战性。喷涂一层漫反射材料的做法会不可避免地增加额外厚度。现有的基于额外设备的方法会增加硬件系统成本。基于算法的方法具有成本效益且无损，但通常需要冗余图案进行图像融合和模型训练，这不适用于对复杂HDR表面进行自动化三维测量。本文提出了一种基于共享解调相位展开机制和多指标引导相位融合策略的HDR表面三维重建方法。通过图像熵优化曝光间隔的划分，以生成最优曝光序列。时空二进制（TSB）编码条纹图案与时间积分策略相结合，以及基于数字微镜器件（DMD）的投影仪的可变曝光模式（最小投影曝光时间为233μs），使该方法能够广泛适用于复杂的HDR表面。我们提出了一种高效的相位分析解决方案，称为共享机制，即通过共享同一组错位格雷码（MGC）解码结果，对从捕获的不同强度条纹图像中得到的包裹相位序列进行展开。最后，建立了一个由曝光质量、相位梯度平滑度和像素有效性等多指标引导的相位序列融合模型，以获得用于最终三维重建所需的最优相位图。对比实验表明，该方法能够以至少65%的图像减少率完全恢复HDR表面的三维形貌，在保持测量精度并排除异常值的同时，测量完整性保持在98%以上。
