The invention discloses an elevator door pre-sensing type anti-pinch system and method based on three-dimensional point cloud deep learning, and the method comprises the following steps: S1, collecting the space in the closing distance of a car door and a landing door through a three-dimensional scanning device, obtaining a point cloud picture through three-dimensional scanning, and obtaining a simplified point cloud of a foreign matter through the point cloud picture; and S2, on the basis of the simplified point cloud, foreign matter point cloud data are obtained through a pre-trained convolutional neural network model, and the foreign matter state is judged. By adopting the three-dimensional point cloud deep learning method, various foreign matters in the process of closing the elevator door can be accurately recognized, the closing time of the elevator door is shortened, and the operation efficiency of the elevator is improved.
本申请公开了基于三维点云深度学习的电梯门预感式防夹系统及方法,方法包括如下步骤:S1.使用三维扫描装置采集轿门和厅门关闭路程中的空间,通过三维扫描,得到点云图,通过点云图,得到异物的精简点云;S2.基于精简点云,通过预先训练好的卷积神经网络模型,得到异物点云数据,判断异物状态。采用三维点云深度学习的方法可以对电梯门关闭途中的各种异物进行精准识别,缩减电梯门关闭时间,提高电梯运行效率。
Elevator door pre-sensing type anti-pinch system and method based on three-dimensional point cloud deep learning
基于三维点云深度学习的电梯门预感式防夹系统及方法
2023-09-22
Patent
Electronic Resource
Chinese
European Patent Office | 2023
|