Image semantic segmentation method based on local and global feature enhancement modules

Abstract

The invention discloses an image semantic segmentation method based on local and global feature enhancement modules. The image semantic segmentation method comprises the following steps: selecting andmanufacturing a training set image and a verification set image required by a semantic segmentation task, and corresponding label pictures; performing data enhancement on the training set image; standardizing sample images in the training set image and the verification set image respectively; encoding the corresponding label image, designing a convolutional neural network, taking the processed data as input data of the model, outputting a multi-channel feature map, optimizing parameters of the convolutional neural network, inputting a real scene image into the convolutional neural network with optimized parameters for semantic segmentation, and outputting an image with marked pixels. Important technical support is provided for subsequent operation in research such as scene analysis and reinforcement learning, and the method can be applied to the fields of virtual reality, automatic driving and man-machine interaction.

Description

technical field [0001] The invention relates to a convolutional neural network and image semantic segmentation technology, in particular to an image semantic segmentation method based on enhanced features of the convolutional neural network. Background technique [0002] Image semantic segmentation is one of the important research topics in computer vision, and its research results have an important impact on other vision tasks. Semantic segmentation technology has been widely used in artificial analysis, virtual reality, automatic driving and other fields. However, in some complex scenes, due to the large variety of segmentation targets and the diversity of scales, the segmentation accuracy of small-scale targets is relatively low. Pixel classification between objects is error-prone. [0003] With the steady development of deep learning and machine learning, the use of convolutional neural networks to learn target features has been greatly sought after by researchers. Ther...

AI Technical Summary

Problems solved by technology

Semantic segmentation technology has been widely used in artificial analysis, virtual reality, automatic driving and other fields. However, in some complex scenes, due to the large variety of segmentation targets and the diversity of scales, the segmentation accuracy of small-scale targets is relatively low. Error-prone classification of pixels between objects

Images