Image semantic segmentation method based on convolutional neural network

Abstract

The invention discloses an image semantic segmentation method based on a convolutional neural network. The method comprises the following steps that ResNet101 is selected as a skeleton network to carry out feature extraction, a JFP model is provided to combine the last three layers output by the ResNet101, feature extraction of the ResNet101 is perfected, and the problem of image information lossis solved; then the output of the JFP is accessed to an ASPP model to further extract the spatial scale information of the image, and the part is used as a coding structure to better extract the imageinformation; and finally, the output image of the neural network is restored to the original size by using a simple decoding structure to finish semantic segmentation of the image. Meanwhile, an attention model is designed, a loss function of the model is combined with a loss function of the semantic segmentation network, the network is assisted in training, and the effect of training the model is improved. The method remarkably improves the image semantic segmentation effect in a complex scene, can be suitable for various scenes, and has the semantic segmentation processing capability for images of more than 20 types of objects.

Description

technical field [0001] The invention belongs to the technical fields of digital image processing, pattern recognition and machine learning, and relates to an image semantic segmentation method, in particular to an image semantic segmentation method based on a convolutional neural network. Background technique [0002] Image-based semantic segmentation is to segment images at the pixel level. It is necessary to classify each pixel of the image semantically. Pixels of the same category are marked with the same category label, which is reflected in the segmentation results that objects of the same category are marked with the same color. And different colors are different types of objects. [0003] The application of convolutional neural network (CNN) has led to the rapid development of image semantic segmentation. Various semantic segmentation network structures based on convolutional neural network have been proposed. The proposal of fully convolutional network (FCN) has made...

AI Technical Summary

Problems solved by technology

[0005] At present, most of the network models for semantic segmentation use deep convolutional neural network (DCNN) as the skeleton network. On this basis, a specific neural network model for image semantic segmentation is designed. The problem of loss. At the same time, current methods, such as dilated convolutions, pyramid models, and global pooling, cannot handle complex semantic information.

Images