Shen Jing, Chen Ling, He Xiaotong, Zuo Chuanlin, Li Xiangjun, Dong Lin
College of Engineering and Design, Hunan Normal University, Changsha 410081, China.
Institute of General and Applied Linguistics and Phonetics (ILPGA), Sorbonne Nouvelle University-Paris 3, 75012 Paris, France.
Biomimetics (Basel). 2025 Jul 1;10(7):431. doi: 10.3390/biomimetics10070431.
This paper presents a human-in-the-loop interactive framework for skeleton-based posture recognition, designed to support model training and artistic education. A total of 4870 labeled images are used for training and validation, and 500 images are reserved for testing across five core posture categories: standing, sitting, jumping, crouching, and lying. From each image, comprehensive skeletal features are extracted, including joint coordinates, angles, limb lengths, and symmetry metrics. Multiple classification algorithms-traditional (KNN, SVM, Random Forest) and deep learning-based (LSTM, Transformer)-are compared to identify effective combinations of features and models. Experimental results show that deep learning models achieve superior accuracy on complex postures, while traditional models remain competitive with low-dimensional features. Beyond classification, the system integrates posture recognition with a visual recommendation module. Recognized poses are used to retrieve matched examples from a reference library, allowing instructors to browse and select posture suggestions for learners. This semi-automated feedback loop enhances teaching interactivity and efficiency. Among all evaluated methods, the Transformer model achieved the best accuracy of 92.7% on the dataset, demonstrating the effectiveness of our closed-loop framework in supporting pose classification and model training. The proposed framework contributes both algorithmic insights and a novel application design for posture-driven educational support systems.
本文提出了一种基于骨架的姿态识别的人在回路交互式框架，旨在支持模型训练和艺术教育。总共4870张带标签的图像用于训练和验证，500张图像留作测试，涵盖五个核心姿态类别：站立、坐着、跳跃、蹲伏和躺卧。从每张图像中提取综合骨骼特征，包括关节坐标、角度、肢体长度和对称度量。比较了多种分类算法——传统算法（KNN、SVM、随机森林）和基于深度学习的算法（LSTM、Transformer），以确定特征和模型的有效组合。实验结果表明，深度学习模型在复杂姿态上具有更高的准确率，而传统模型在低维特征上仍具有竞争力。除了分类，该系统还将姿态识别与视觉推荐模块集成在一起。识别出的姿态用于从参考库中检索匹配的示例，使教师能够浏览并为学习者选择姿态建议。这种半自动反馈回路提高了教学交互性和效率。在所有评估方法中，Transformer模型在数据集上达到了92.7%的最佳准确率，证明了我们的闭环框架在支持姿态分类和模型训练方面的有效性。所提出的框架为姿态驱动的教育支持系统提供了算法见解和新颖的应用设计。
