| 冯文宇,张宇豪,张 堃,费敏锐,徐 胜.复杂环境下课堂多人状态检测算法研究[J].电子测量与仪器学报,2021,35(6):53-62 |
| 复杂环境下课堂多人状态检测算法研究 |
| Research on multi-person detection algorithm inclassroom in complex environment |
| |
| DOI： |
| 中文关键词: 多人异常检测 姿态识别 口罩识别 YOLO 模型 OpenPose 模型 |
| 英文关键词:multi-people anomaly detection gesture recognition mask recognition YOLO model OpenPose |
| 基金项目:国家自然基金重点项目（61633016）、江苏省高校自然基金（18KJB510038）、江苏省333工程可研项目（BRA2018218）、国家级大学生创新创业训练计划资助项目（202010304065Z）资助 |
|
|
| Author | Institution |
| Feng Wenyu | 1. School of Electrical Engineering, Nantong University,2. School of Zhangjian,
Nantong University |
| Zhang Yuhao | 1. School of Electrical Engineering, Nantong University,2. School of Zhangjian,
Nantong University |
| Zhang Kun | 1. School of Electrical Engineering, Nantong University |
| Fei Minrui | 3. Shanghai Key Laboratory of Power Station Automation Technology,
School of Mechatronic Engineering and Automation, Shanghai University |
| Xu Sheng | 4. School of Electronics and Information,Nantong Vocational University，5. The East China Science and Technology Research Institute of Changshu Co. , Ltd |
|
| 摘要点击次数: 391 |
| 全文下载次数: 4 |
| 中文摘要: |
| 新冠肺炎疫情背景下课堂多人佩戴口罩及姿态识别问题,提出了基于 YOLO 和 OpenPose 模型的课堂多人状态检测算
法。 提出的 Efficient-YOLO 模型,通过采用 CBAM 注意力模块、SPNET-NEW 模块,解决了多人遮挡和无规则化目标的口罩佩戴
检测精度问题。 此外,提出了一种轻量化的 Class-OpenPose 模型检测学生上课姿态,该算法在 OpenPose 模型基础上,使用
ShuffleNetV2-NEW 对传统模型在底层特征提取方面进行改进,实现了复杂环境下关键姿态点的实时准确检测。 实验表明,在课
堂多人异常状态检测任务中,Class-OpenPose 模型平均准确率高于传统模型,为 79. 0%,检测速度达到 13. 5 F/ s;Efficient-YOLO
口罩识别模型达到 83. 1%的平均准确率,检测时间仅需 31. 54 ms,为课堂学生状态检测提供了不错的算法思路。 |
| 英文摘要: |
| Aiming at the problem of multi-person wearing masks in the classroom and gesture recognition in COVID-19, this paper
presents a multi-person state detection algorithm, based on the YOLO and OpenPose models. The Efficient-YOLO model proposed in this
paper uses the classical CBAM attention and SPNET-NEW modules to deal with the problems of multi-person occlusion and irregular
targets. In addition, this paper presents a lightweight Class-OpenPose model to detect the students’ posture. Based on the OpenPose
model, our proposed algorithm uses ShuffleNetV2-NEW to improve the traditional model in terms of low-level feature extraction, and
extracts correct key posture points in complex environments and in real-time. Experiments show that in the multi-person abnormal event
detection task, the average accuracy of the Class-OpenPose model is 79. 0% that is higher than that of the traditional model, and the
detection speed reaches 13. 5 F/ s; the Efficient-YOLO mask recognition model achieves an average accuracy of 83. 1%, and the
detection time is only 31. 54 ms, which provides a good algorithm idea for classroom student status detection. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
