In the field of environmental protection, the effective classification of domestic waste has gradually become the focus of social development. The process of waste classification is the key to domestic waste treatment. In this paper, the methods of urban ecological environment construction and waste classification are studied by using computer analysis technology and data fusion technology. This paper adopts the deep learning classification model based on mobilenet V2. The model classifies common garbage according to the following categories: recyclables, kitchen waste, hazardous waste and other wastes. This paper uses the model trained on Imagenet large-scale visual recognition challenge data set for migration learning. The baseline mobilenet V2 model is optimised, and the final test accuracy is 82. The method proposed in this paper has a certain reference value for the research of waste classification and urban ecological environment construction.
展开▼
