System and method for realizing subway scene classification based on deep learning

Abstract

The present invention relates to a system and method for realizing subway scene classification based on deep learning. The system comprises an image preprocessing module configured to perform preprocessing of subway scene images; a convolutional neural network extraction image feature module configured to perform deep feature learning and extract the image features through adoption of the built convolutional neural network; and a full connection network scene classification module configured to input the optimal features learned from the convolutional neural network to the full connection network for classification so as to obtain the tag class of samples. Through adoption of the structure, the system and method for realizing subway scene classification based on deep learning extract subway scene image features based on a convolutional neural network and take a single-layer full connection network as a classifier, are able to realize correct classification of different subway scene images with no need for analysis of scene semantics, and are high in robustness; and moreover, the method for realizing subway scene classification based on deep learning has an important value for the subsequent subway operation state monitoring work, and has a wide application range.

Description

technical field [0001] The present invention relates to the technical field of pattern recognition, in particular to the technical field of convolutional neural network deep learning, and specifically refers to a system and method for classifying subway scenes based on deep learning. Background technique [0002] The working environment in the subway operation channel is relatively complex, and the scene is changeable. In order to ensure that the subway is in a good and stable working state in different scenes, it is usually necessary to use different detection methods for different scenes. At this time, it is possible to accurately distinguish the various Different scenarios are particularly important. However, the scene classification in the prior art generally uses low-level features such as color, texture, and shape or image semantic features for representation and classification, but feature extraction and calculation analysis are often not robust. Contents of the inv...

AI Technical Summary

Problems solved by technology

However, the scene classification in the existing technology generally uses the underlying features such as color, texture, shape or image semantic features for representation and classification, but the feature extraction and calculation analysis are often not robust.

Images