Control method of intelligent device and intelligent device

Abstract

The invention relates to the technical field of intelligent equipment, and provides an intelligent equipment control method and intelligent equipment, and the method comprises the steps: receiving a plurality of first images collected by an image collector in a set period, cutting out a second image from one first image according to a preset cutting-out rule when each first image is read, identifying the second image, and determining at least one gesture identification area and a corresponding gesture identification result; if the same control gesture exceeding the set number threshold exists in the same gesture recognition area, controlling the intelligent equipment to execute corresponding operation based on the control gesture. The first image is preprocessed according to the preset interception rule to reduce the hand detection difficulty, and the static gesture of the user is collected, so that the time spent on gesture recognition can be shortened, and the user experience can be improved.

Description

technical field [0001] The present application relates to the technical field of smart devices, and provides a method for controlling smart devices and smart devices. Background technique [0002] With the intelligent upgrade of product equipment, users use their hands to make different continuous actions (that is, dynamic gestures) to operate the screen to realize functions such as adjusting volume, changing channels, fast forwarding and rewinding, etc., making the operation of users controlling smart devices more and more Simple. [0003] However, when using the above method to control the smart device, the following problems will occur: the farther the user is from the camera, the smaller the proportion of the user's hand image in the collected image will be, which will greatly increase the difficulty of hand detection; , the camera will collect multiple consecutive images and input them into the neural network for recognition. Due to the large number of input images, th...

AI Technical Summary

Problems solved by technology

[0003] However, when using the above method to control the smart device, the following problems will occur: the farther the user is from the camera, the smaller the proportion of the user's hand image in the collected image will be, which will greatly increase the difficulty of hand detection; , the camera will collect multiple consecutive images and input them into the neural network for recognition. Due to the large number of input images, the recognition process of the neural network will take a long time and cannot meet the real-time response requirements. ;Finally, the user needs to make dynamic gestures to satisfy the response, and the user experience is poor

Images