Semantic Image Segmentation Method Using Convolutional Neural Networks

Abstract

The invention discloses a convolutional neural network semantic image segmentation method, which realizes semantic image segmentation by combining partial layered feature fusion in the network architecture and fully connected conditional random field processing. The specific steps include: constructing a network architecture model consisting of convolutional layers, pooling layers, upsampling layers, and loss functions, and the step size of each layer in the model, the size of the convolution kernel, and the number of output feature maps by Specification customization; fuse the shallow and deep information in the network architecture, and upsample the fused features to the resolution of the original image; use the fully connected conditional random field to optimize the post-processing of the feature image output by the upsampling segmentation. The application of the scheme of the present invention makes full use of the information of each layer through the feature fusion of different layers, and improves the final accuracy rate; combined with the fully connected CRF, the network output result is post-processed, and the connection between each pixel is processed. , making the result of image segmentation more accurate and smooth.

Description

technical field [0001] The invention belongs to the field of semantic image segmentation, and specifically refers to the implementation of semantic image segmentation by using a deep learning method. Background technique [0002] With the continuous breakthrough of deep learning, it has been widely used in various fields, such as computer vision, speech recognition, natural language processing, etc. The proposal of convolutional neural network (CNN) has made deep learning a hot word to some extent, and the proposal of fully convolutional neural network (FCN) has made a great breakthrough in semantic image segmentation. Semantic image segmentation can It is said to be the cornerstone technology of image understanding, and it plays a pivotal role in applications such as autonomous driving and drones. As we all know, an image is composed of many pixels, and semantic image segmentation, as the name implies, is to classify each pixel in the picture, that is, to realize the posit...

AI Technical Summary

Problems solved by technology

[0004] (1) To a certain extent, the information between the upper and lower layers is not well utilized, resulting in the loss of information;

[0005] (2) The connection between pixels is not considered

Images