Garbage classification model modeling method and device, and garbage classification method and device

Abstract

The invention relates to a garbage classification model modeling method and device, and a garbage classification method and device, which are used for solving the problem of poor performance of a classification model caused by data category imbalance in a garbage classification task. A model is alternately trained through an unbalanced data set and a balanced data set, so that the model learns the characteristics of the majority samples in the unbalanced data set and also learns the characteristics of the minority samples, and the problem of poor performance of a classification model caused by data category imbalance in a garbage classification task is solved. According to the garbage classification method, on the basis of overcoming data category imbalance, results obtained by a classifier are processed through a perceptron network, and then information fusion is performed on the two results to obtain a more robust classification result.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a garbage classification model modeling method, a garbage classification method and a device. Background technique [0002] Garbage classification is one of the main tasks of cleaning robots. At present, the commonly used method is to learn garbage data sets through neural networks, so that cleaning robots can acquire the ability to "distinguish" types of garbage. In engineering projects, most of the garbage classification datasets collected from actual application scenarios have serious category imbalance problems. Class imbalance refers to the situation in which the number of training samples for different classes in a classification task varies greatly. For example, in the garbage classification data set collected in the railway station square, the number of samples of cigarette butts and cigarette box garbage far exceeds the number of samples of street tree litter, a...

AI Technical Summary

Problems solved by technology

[0003] The object of the present invention is to provide a garbage classification model modeling method, a garbage classification method and a device, which are used to solve the problem of poor performance of the classification model caused by unbalanced data categories in the garbage classification task

Images