Architectural drawing component classification method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses an architectural drawing component classification method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of an architectural drawing in an inputted training data set, and obtaining a target architectural drawing; carrying out down-sampling on the target architectural drawing througha full convolution segmentation network to obtain a first feature map, and carrying out up-sampling on the first feature map to obtain a second feature map; performing category judgment on each pixelpoint in the second feature map by adopting a threshold segmentation method, and outputting a classification result of each component in the architectural drawing; repeating the steps to train a firstclassifier for classifying single components and a second classifier for uniformly classifying all the components; and determining a finally used target classifier according to the test effects of the first classifier and the second classifier on the test data set, and classifying the components in the to-be-classified architectural drawing by using the target classifier. The architectural drawing component classification method and device, the electronic equipment and the storage medium provided by the embodiment of the invention are beneficial to improving the effect of building drawing component classification.

Description

technical field [0001] The present application relates to the technical field of image recognition, and in particular to a method, device, electronic equipment and storage medium for classifying architectural drawing components. Background technique [0002] The development of deep learning has made significant progress in applications in many fields such as speech recognition, natural language processing, image and video analysis. The existing deep learning models use neural networks, such as: Fully Convolutional Networks (Fully Convolutional Networks) for Semantic Segmentation (FCN) is a widely used network model in the field of image recognition. The fully convolutional network can classify images at the pixel level in the recognition of architectural drawings, thereby realizing the classification (recognition) of components in the drawings. The advantage of the fully connected network is that it can accept input images of any size, but when the fully convolutional networ...

AI Technical Summary

Problems solved by technology

The fully convolutional network can classify images at the pixel level in the recognition of architectural drawings, thereby realizing the classification (recognition) of components in the drawings. The advantage of the fully connected network is that it can accept input images of any size, but when the fully convolutional network When the upsampling factor of the feature map is too large, the upsampling result will be blurred and smooth, resulting in poor classification of components in architectural drawings

Images