Human-vehicle interaction method and device based on human eye sight and storage medium

The invention discloses a human-vehicle interaction method and device based on human eye sight and a storage medium, and the method and device are applied to a vehicle, and the method specifically comprise the steps: obtaining a face image of a driver of the vehicle; processing the face image by using a neural network algorithm to obtain a current sight line direction and eye actions of the driver; and according to the current sight line direction and the eye movement, executing an operation on in-vehicle equipment in the vehicle. In this way, a driver does not need to operate corresponding equipment in the automobile with hands, and therefore the adverse effect on safe driving of the automobile due to the fact that the driver executes the control action needing to release the steering wheel is avoided. 本申请公开了一种基于人眼视线的人车交互方法、装置和存储介质，该方法和装置应用于车辆，具体为获取车辆的驾驶员的人脸图像；利用神经网络算法对人脸图像进行处理，得到驾驶员的当前视线方向和眼部动作；根据当前视线方向与眼部动对车辆内的车内设备执行操作。这样一来，就无需驾驶员用手去对相应车内设备进行操作，从而避免驾驶员执行需要放开方向盘的操控动作而对汽车的安全行驶造成的不利影响。