用关键点+循环网络实现实时抗视角干扰的手臂手势识别
Fast Real-Time Pipeline for Robust Arm Gesture Recognition
- 基于OpenPose关键点与归一化处理，结合坐标和角度特征
- 在自建交通手势数据集上实现多视角、多速度下的高精度识别
- 通过人工旋转训练数据提升对相机角度变化的鲁棒性
本文提出一种基于OpenPose关键点估计、关键点归一化与循环神经网络分类器的实时动态手臂手势识别流程。引入1×1归一化方案及坐标与角度两种特征表示方法。同时，通过使用人工旋转的训练数据，提出一种有效提升对相机视角变化鲁棒性的方法。在自建交通指挥手势数据集上的实验表明，该方法在不同观测角度和运动速度下均保持高准确率。此外，还提出了计算手臂动作速度的可选方案。
原文摘要 · Abstract (English)
This paper presents a real-time pipeline for dynamic arm gesture recognition based on OpenPose keypoint estimation, keypoint normalization, and a recurrent neural network classifier. The 1 x 1 normalization scheme and two feature representations (coordinate- and angle-based) are presented for the pipeline. In addition, an efficient method to improve robustness against camera angle variations is also introduced by using artificially rotated training data. Experiments on a custom traffic-control gesture dataset demonstrate high accuracy across varying viewing angles and speeds. Finally, an approach to calculate the speed of the arm signal (if necessary) is also presented.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。