Intelligent desk lamp with child health learning supervision function

Abstract

The invention discloses an intelligent desk lamp with a child health learning supervision function, which is mainly based on image recognition and combined with a deep learning algorithm which is popular at present and has an obvious application effect, and an open-source Tensorflow framework is combined with a DeepLab technology to realize monitoring of child autonomous learning. Meanwhile, opensource hardware Raspberry Pi is used for internal control, a table lamp is used as a carrier, and the designed system module comprises an image processing module, a communication module, a front-end control module, a cloud data module and a mobile terminal display module. The image processing module is responsible for image collection, model training and image recognition. The communication moduleis responsible for Bluetooth communication and WIFI communication. The front-section control module is responsible for interactive control and induction automatic control. The cloud data module is responsible for data storage, data query and data communication. And the mobile terminal display module is responsible for data configuration and binding registration of the mobile terminal. The methodis combined with the built-in voice module to monitor the learning state of the child and help the child to learn autonomously.

Description

technical field [0001] The invention belongs to the field of information technology, belongs to the application of computer vision and artificial intelligence in intelligent hardware, relates to an image automatic recognition method based on deep learning, and specifically relates to a combination of a raspberry pie as hardware interactive control and a convolution network Image classification model is a new smart desk lamp with children's health learning supervision function supported by software technology. Background technique [0002] The emergence of the Convolution Neural Networks (CNN) model drives the upsurge of artificial intelligence development. The CNN structure establishes a layered model structure similar to the human brain, and extracts the features from the bottom layer to the top layer of the input data step by step, so that it can be easily It is good to automatically establish the mapping relationship from low-level signals to high-level semantics. With t...

AI Technical Summary

Problems solved by technology

However, the user's sitting posture does not always reflect the difference in height and angle, and the height characteristics of users at different growth stages are prone to obvious changes. The role of posture correction

Images