Systems, methods, and apparatus for real-time contactless elevator service operation of an elevator include training a neural network (TNN) model. The TNN model is trained with the enhancement dataset as a synthetic training dataset using a training processor to later perform elevator identifier identification. An enhancement dataset is generated from a synthetic text image that is enhanced to a predetermined number of variants in appearance of the training elevator identifier set with different geometric and visual parameters. A camera captures a user image. A text image portion from the user image is extracted using a TNN model, and an elevator identifier in the extracted text image portion is detected using the extracted text image portion and the TNN model. The detected elevator identifier is displayed for user confirmation or user cancellation, and upon user confirmation, a control command is generated based on the detected elevator identifier associated with the elevator service.
用于电梯的实时无接触电梯服务操作的系统、方法和装置包括训练神经网络(TNN)模型。TNN模型以增强数据集作为合成训练数据集来使用训练处理器进行训练,以稍后执行电梯标识符识别。从合成文本图像生成增强数据集,合成文本图像以不同的几何参数和视觉参数增强至训练电梯标识符集合的在外观上的预定数量的变体。相机捕获用户图像。来自用户图像的文本图像部分使用TNN模型来提取,并且使用所提取的文本图像部分和TNN模型检测所提取的文本图像部分中的电梯标识符。所检测到的电梯标识符被显示以供用户确认或用户取消,并且在用户确认时,基于所检测到的与电梯服务关联的电梯标识符来生成控制命令。
Enhanced dataset-based contactless elevator service for elevators
电梯的基于增强数据集的无接触电梯服务
2023-05-23
Patent
Electronic Resource
Chinese
IPC: | B66B Aufzüge , ELEVATORS |