A semantic image segmentation method in a convolutional neural network

Abstract

The invention discloses a novel deep convolutional neural network architecture for image semantic segmentation. The architecture comprises a backbone network and a context fusion network. The featureinformation of each convolutional layer in the convolutional network is fully utilized, and the shallow context information and the deep context information are combined, so that a better image semantic segmentation effect is obtained. compared with the deep convolution features, Shallow convolution features can retain good image bottom layer detail information. The deep features can extract high-level semantic information, convolutional features of the deep features and the high-level semantic information are combined, local context features and global context features in the image can be considered at the same time, the final segmentation accuracy is determined, and therefore the network architecture can conduct refining extraction on the features of the shallow layer and the deep layerin the network. Experimental results show that compared with a traditional deep convolutional network model, the method has the advantage that the segmentation precision and efficiency are obviously improved.

Description

technical field [0001] The invention belongs to the field of semantic image segmentation, and in particular relates to the realization of semantic image segmentation by adopting a deep learning method. Background technique [0002] With the continuous deepening of computer vision research, researchers have gradually turned their attention to more accurate analysis and understanding of images. The problem of semantic image segmentation is proposed to meet this requirement. The fundamental purpose of semantic image segmentation is to determine the semantic category of each pixel in the image by training the content of the image. The following are some achievements in the field of image semantic segmentation in recent years. [0003] Fully Convolutional Networks (FCN, Fully Convolutional Networks) can be said to be the pioneering work of deep learning in image semantic segmentation tasks. It was proposed by the research team of the University of California, Berkeley, and prom...

AI Technical Summary

Problems solved by technology

[0005] In view of the defects and deficiencies of the above-mentioned prior art, the purpose of the present invention is to propose a new convolutional neural network architecture, which uses image context information aggregation to solve the problem of image semantic segmentation

Images