A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Vehicle operation detection device and vehicle operation detection method
The invention provides a vehicle operation detection device capable of improving the detection accuracy of the posture of a user. An operation detection device (200) is provided with: a storage unit (210) that stores a learning completion model in which machine learning is performed using training data in which a pre-captured image and a tiptoe of a user are associated; an entry determination unit (220) that determines, on the basis of the tiptoe position of the user in an image obtained by inputting a newly captured image into the learned model, whether or not the tiptoe of the user has entered an identification region (A3) set in an image capture region (A2) of the camera (80); and a posture determination unit (230) that calculates a displacement vector of the tiptoe of the user on the basis of a plurality of images captured at intervals after it is determined that the tiptoe of the user has entered the recognition region (A3), and determines whether or not the posture has been performed on the basis of whether or not the orientation of the displacement vector of the tiptoe of the user is a direction corresponding to the posture.
本发明提供一种能够提高用户的姿势的检测精度的车用操作检测装置。操作检测装置(200)具备：存储使用将预先拍摄的图像与用户的脚尖相关联的训练数据进行了机器学习的学习完毕模型的存储部(210)；基于通过将新拍摄的图像向学习完毕模型输入而得到的该图像中的用户的脚尖位置，判定用户的脚尖是否进入了设定在照相机(80)的拍摄区域(A2)内的识别区域(A3)内的进入判定部(220)；基于在判定为用户的脚尖进入了识别区域(A3)内之后隔开时间而拍摄的多个图像，来计算用户的脚尖的位移向量，并根据用户的脚尖的位移向量的朝向是否是与姿势对应的方向来判定是否实施了姿势的姿势判定部(230)。
Vehicle operation detection device and vehicle operation detection method
The invention provides a vehicle operation detection device capable of improving the detection accuracy of the posture of a user. An operation detection device (200) is provided with: a storage unit (210) that stores a learning completion model in which machine learning is performed using training data in which a pre-captured image and a tiptoe of a user are associated; an entry determination unit (220) that determines, on the basis of the tiptoe position of the user in an image obtained by inputting a newly captured image into the learned model, whether or not the tiptoe of the user has entered an identification region (A3) set in an image capture region (A2) of the camera (80); and a posture determination unit (230) that calculates a displacement vector of the tiptoe of the user on the basis of a plurality of images captured at intervals after it is determined that the tiptoe of the user has entered the recognition region (A3), and determines whether or not the posture has been performed on the basis of whether or not the orientation of the displacement vector of the tiptoe of the user is a direction corresponding to the posture.
本发明提供一种能够提高用户的姿势的检测精度的车用操作检测装置。操作检测装置(200)具备：存储使用将预先拍摄的图像与用户的脚尖相关联的训练数据进行了机器学习的学习完毕模型的存储部(210)；基于通过将新拍摄的图像向学习完毕模型输入而得到的该图像中的用户的脚尖位置，判定用户的脚尖是否进入了设定在照相机(80)的拍摄区域(A2)内的识别区域(A3)内的进入判定部(220)；基于在判定为用户的脚尖进入了识别区域(A3)内之后隔开时间而拍摄的多个图像，来计算用户的脚尖的位移向量，并根据用户的脚尖的位移向量的朝向是否是与姿势对应的方向来判定是否实施了姿势的姿势判定部(230)。
Vehicle operation detection device and vehicle operation detection method
车用操作检测装置以及车用操作检测方法
TAMURA TAKUYA (author)
2022-12-27
Patent
Electronic Resource
Chinese
VEHICLE OPERATION DETECTION DEVICE AND VEHICLE OPERATION DETECTION METHOD
| European Patent Office | 2022
VEHICLE OPERATION DETECTION DEVICE AND VEHICLE OPERATION DETECTION METHOD
| European Patent Office | 2022
Vehicle operation detection device and vehicle operation detection method
| European Patent Office | 2024
VEHICLE OPERATION DETECTION DEVICE AND VEHICLE OPERATION DETECTION METHOD
| European Patent Office | 2021
VEHICLE OPERATION DETECTION DEVICE AND VEHICLE OPERATION DETECTION METHOD
| European Patent Office | 2021