Trichromatic mask particle image velocimetry is a recently developed volumetric technique using a single color camera, with strong potential for applications in confined spaces. However, it faces two key challenges: limited demosaicing accuracy of Bayer-encoded particle images and depth-wise particle elongation caused by insufficient parallax, both of which reduce the spatial resolution of reconstructed volumes. This paper presents a deep learning-based framework that integrates a U-Net++ demosaicing network with an Artificial Intelligence Particle Reconstruction algorithm to improve image fidelity and reconstruction accuracy. The performance of multiple demosaicing methods is quantitatively compared on particle images, with a particular focus on the influence of image noise. The effects of viewing angle parameters on three-dimensional (3D) particle reconstruction quality are further evaluated. The proposed method is validated using numerical simulations of Gaussian vortex rings and experimental measurements of 3D wake flow behind a cylinder, demonstrating the accuracy and applicability of the proposed approach.

Surface treatment processes such as mass finishing play a crucial role in enhancing the quality of machined parts across industries. However, accurate measurement of the velocity field of granular media in mass finishing presents significant challenges. Existing measurement methods suffer from issues such as complex and expensive equipment, limited to single-point measurements, interference with the flow field, and lack of universality in different scenarios. This study addresses these issues by proposing a single-camera-based method with deep learning to measure the three-dimensional velocity field of granular flow. We constructed a complete measurement system and analyzed the accuracy and performance of the proposed method by comparing the measurement results with those of the traditional DIC algorithm. The results show that the proposed method is very accurate in measuring spatial displacement, with an average error of less than 0.07 mm and a calculation speed that is 1291.67% of the traditional DIC algorithm under the same conditions. Additionally, experiments in a bowl-type vibratory finishing machine demonstrate the feasibility of the proposed method in capturing the three-dimensional flow of granular media. This research not only proposed a novel method for three-dimensional reconstruction and velocity field measurement using a single-color camera, but also demonstrated a way to combine deep learning with traditional optical techniques. It is of great significance to introduce deep learning to improve traditional optical techniques and apply them to practical engineering measurements.