RESUMEN

The precise recognition of entire classroom meta-actions is a crucial challenge for the tailored adaptive interpretation of student behavior, given the intricacy of these actions. This paper proposes a Dynamic Position Embedding-based Model for Student Classroom Complete Meta-Action Recognition (DPE-SAR) based on the Video Swin Transformer. The model utilizes a dynamic positional embedding technique to perform conditional positional encoding. Additionally, it incorporates a deep convolutional network to improve the parsing ability of the spatial structure of meta-actions. The full attention mechanism of ViT3D is used to extract the potential spatial features of actions and capture the global spatial-temporal information of meta-actions. The proposed model exhibits exceptional performance compared to baseline models in action recognition as observed in evaluations on public datasets and smart classroom meta-action recognition datasets. The experimental results confirm the superiority of the model in meta-action recognition.

RESUMEN

To address the problem of phase unwrapping for interferograms, a deep learning (DL) phase-unwrapping method based on adaptive noise evaluation is proposed to retrieve the unwrapped phase from the wrapped phase. First, this method uses a UNet3+ as the skeleton and combines with a residual neural network to build a network model suitable for unwrapping wrapped fringe patterns. Second, an adaptive noise level evaluation system for interferograms is designed to estimate the noise level of the interferograms by integrating phase quality maps and phase residues of the interferograms. Then, multiple training datasets with different noise levels are used to train the DL network to achieve the trained networks suitable for unwrapping interferograms with different noise levels. Finally, the interferograms are unwrapped by the trained networks with the same noise levels as the interferograms to be unwrapped. The results with simulated and experimental interferograms demonstrate that the proposed networks can obtain the popular unwrapped phase from the wrapped phase with different noise levels and show good robustness in the experiments of phase unwrapping for different types of fringe patterns.

Asunto(s)

RESUMEN

A robust phase unwrapping algorithm based on a rank information filter is proposed to retrieve the unambiguous unwrapped phase from noisy wrapped phase images. First, a recursive phase unwrapping program, based on a rank information filter, is proposed to transform the problem of phase unwrapping for wrapped phase into the problem of the state estimation for state variables under the framework of a rank information filter, where a local phase gradient estimator based on the amended matrix pencil model (AMPM) is used to obtain phase gradient information required by the recursive phase unwrapping program. Second, an efficient path-following strategy based on heap-sort is used to guide the phase unwrapping path, which ensures that the recursive phase unwrapping program based on a rank information filter unwraps wrapped phase images along the path from high-quality pixels to low-quality pixels. Finally, the results obtained from synthetic data and experimental measured data demonstrate the effectiveness of the proposed method and show this method can obtain robust solutions from noisy wrapped phase images.