|
| 双流移位时空图卷积：热成像动作识别 |
| Two-stream Shift Graph Convolutional Network: Thermal Infrared Action Recognition |
| 投稿时间：2024-01-03 修订日期：2024-03-04 |
| DOI： |
| 中文关键词: 动作识别 热红外 时空图卷积网络 双流结构 |
| 英文关键词: Action recognition Thermal infrared Spatial-temporal graph convolutional networks Two-stream structure |
| 基金项目:国家自然科学基金项目(No.61973109) |
|
| 摘要点击次数: 84 |
| 全文下载次数: 0 |
| 中文摘要: |
| 本文针对目前主要依赖可见光研究动作识别的趋势，充分利用热红外图像对光线变化不敏感的优势，提出了一种利用人体骨骼识别热红外视频中动作的轻量级算法，本研究贡献有：该算法使用YOLOv7-tiny进行目标检测，Alphapose进行姿势估计和动态骨架建模，最后利用时空图卷积神经网络提取时空特征；算法避免将整个视频视为一个整体，提取个人在不同时间间隔的动作以提高鲁棒性；为提高动作识别的准确性引入了双流移位图卷积网络（2s-ShiftGCN）.2s-ShiftGCN的实验中，在InfAR-skeleton数据集上的Top-1准确率为88.06%，Top-5准确率为98.28%.在过滤kinetics-skeleton数据集上的Top-1准确率为55.26%，Top-5准确率为83.98%. |
| 英文摘要: |
| This study addresses the prevailing trend of relying predominantly on visible light for action recognition. Leveraging the advantage of infrared imagery's insensitivity to changes in lighting conditions, a lightweight algorithm for action recognition in thermal infrared videos is proposed. The contributions of this research include the utilization of YOLOv7-tiny for target detection, Alphapose for pose estimation and dynamic skeleton modeling, and GCN for the extraction of spatiotemporal features. By refraining from treating the entire video as a single entity and extracting individual actions at different time intervals, the algorithm significantly enhances robustness. To improve the accuracy of action recognition, a bistream shifted graph convolutional network (2s-ShiftGCN) is introduced. Experimental results of 2s-ShiftGCN show a Top-1 accuracy of 88.06% and a Top-5 accuracy of 98.28% on the InfAR-skeleton dataset. On the filtered kinetics-skeleton dataset, the Top-1 accuracy is 55.26%, and the Top-5 accuracy is 83.98%. |
|
View Fulltext
查看/发表评论 下载PDF阅读器 |
| 关闭 |
