Automatic Evaluation of Functional Movement Screening Based on Attention Mechanism and Score Distribution Prediction

Abstract

Functional movement screening (FMS) is a crucial testing method that evaluates fundamental movement patterns in the human body and identifies functional limitations. However, due to the inherent complexity of human movements, the automated assessment of FMS poses significant challenges. Prior methodologies have struggled to effectively capture and model critical human features in video data. To address this challenge, this paper introduces an automatic assessment approach for FMS by leveraging deep learning techniques. The proposed method harnesses an I3D network to extract spatiotemporal video features across various scales and levels. Additionally, an attention mechanism (AM) module is incorporated to enable the network to focus more on human movement characteristics, enhancing its sensitivity to diverse location features. Furthermore, the multilayer perceptron (MLP) module is employed to effectively discern intricate patterns and features within the input data, facilitating its classification into multiple categories. Experimental evaluations conducted on publicly available datasets demonstrate that the proposed approach achieves state-of-the-art performance levels. Notably, in comparison to existing state-of-the-art (SOTA) methods, this approach exhibits a marked improvement in accuracy. These results corroborate the efficacy of the I3D-AM-MLP framework, indicating its significance in extracting advanced human movement feature expressions and automating the assessment of functional movement screening.

Automatic Evaluation Method for Functional Movement Screening Based on a Dual-Stream Network and Feature Fusion

“…Table 1 presents recent advancements in FMS and related work, with the work [9], which focused on the combination of attention mechanisms and FMS, being most closely related to our paper. However, our work shifts the focus to the integration of dual-stream networks and feature fusion with FMS.…”

“…The dataset includes exercises such as squat, hurdling, split squat, shoulder mobility, straight leg raise, trunk stability push-up, and rotary stability. We split the dataset based on [9]. The experiment ran on a server utilizing cloud computing power, with AutoDL.…”

Automatic Evaluation Method for Functional Movement Screening Based on Multi-Scale Lightweight 3D Convolution and an Encoder–Decoder

“…However, their efficacy is contingent upon the availability of a vast amount of training data, which can be prohibitively time-consuming to acquire. Additionally, many traditional deep learning methods rely on feature extraction by models like I3D [7][8][9][10]. I3D employs three-dimensional convolutional kernels, which implies that each kernel provides both spatial and temporal information.…”