| 面向扶梯不安全行为的改进型深度学习检测算法 |
| |
| 引用本文： | 李伟达,叶靓玲,郑力新,朱建清,曾远跃,林俊杰.面向扶梯不安全行为的改进型深度学习检测算法[J].华侨大学学报(自然科学版),2022,43(1):119-126. |
| |
| 作者姓名： | 李伟达 叶靓玲 郑力新 朱建清 曾远跃 林俊杰 |
| |
| 作者单位： | 1. 华侨大学 工学院, 福建 泉州 362021;2. 华侨大学 工业智能化与系统福建省高校工程研究中心, 福建 泉州 362021;3. 福建省特种设备检验研究院 泉州分院, 福建 泉州 362021 |
| |
| 基金项目： | 国家自然科学基金面上资助项目（61976098）；;福建省科技计划项目（2020Y0039）； |
| |
| 摘 要： | 以YOLOv5s网络模型为基础,引入注意力机制CBAM模块,基于Ghost卷积模块重构网络模型的卷积操作,提出一种面向扶梯不安全行为的改进型深度学习检测算法.然后,在自主收集的扶梯不安全行为数据集上对其进行训练评估.结果表明,所提算法在检测精度有所提高的同时,大幅减少了检测所需的参数量和计算量.
|
| 关 键 词： | 扶梯 不安全行为 目标检测 YOLOv5s CBAM模块 Ghost卷积模块 |
Improved Deep Learning Detection Algorithm for Unsafe Escalator Behavior |
| |
| LI Weida,YE Liangling,ZHENG Lixin,ZHU Jianqing,ZHENG Yuanyue,LIN Junjie.Improved Deep Learning Detection Algorithm for Unsafe Escalator Behavior[J].Journal of Huaqiao University(Natural Science),2022,43(1):119-126. |
| |
| Authors: | LI Weida YE Liangling ZHENG Lixin ZHU Jianqing ZHENG Yuanyue LIN Junjie |
| |
| Institution: | 1. College of Engineering, Huaqiao University, Quanzhou 362021, China; 2. Industrial Intelligence and System Fujian University Engineering Research Center, Huaqiao University, Quanzhou 362021, China; 3. Quanzhou Branch of Special Equipment Inspection Research Institute, Quanzhou 362021, China |
| |
| Abstract: | An improved deep learning detection algorithm for unsafe escalator behavior was proposed. The algorithm is based on the YOLOv5s network model, introduces the attention mechanism CBAM module, and reconstructs the convolution operation of the network model based on the Ghost convolution module. It is trained and evaluated on the self-collected escalator unsafe behavior data set. The results show that the proposed algorithm has improved the detection accuracy while greatly reducing the amount of parameters and calculation required for detection. |
| |
| Keywords: | escalator unsafe behavior object detection YOLOv5s CBAM module Ghost convolution module |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《华侨大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《华侨大学学报(自然科学版)》下载免费的PDF全文 |
|
