Green Action -- Intelligent waste sorting system based on convolutional Neural Network

摘要

In view of Chinese people's inability to correctly judge and place garbage categories，an intelligent garbage classification system based on convolutional neural network was designed. Based on the detection of objects to be recognized under the Open MV framework，the model trained by convolutional neural network algorithm has a very high accuracy，and has good advantages in garbage classification and recognition. This paper presents a design of intelligent garbage sorting system. The system is composed of Raspberry PI control board，camera module，near infrared sensor module，steering gear module，power module and frame structure. Based on the Internet of Things technology and artificial intelligence technology，the system uses the image processing capability of Open MV to establish a garbage classification model and realize the recognition and classification of garbage. The near infrared sensor module is used to detect the capacity. If the garbage storage reaches the set full load limit，the full load alarm will be carried out，and the full load information will be displayed on the administrator screen.