Edge perception image semantic segmentation method based on adaptive feature fusion

Abstract

The invention provides an edge perception image semantic segmentation method based on adaptive feature fusion. The edge perception image semantic segmentation method is a new semantic segmentation method based on a residual network. A double-branch network structure model comprises an edge branch and a semantic branch, the edge branch is led out from a shallow layer part of the semantic branch, and the semantic branch adopts a coding and decoding structure. In the edge branch, the added multi-scale cross fusion operation obtains image multi-scale features by superposing hole convolution with different hole rates; and meanwhile, the robustness of the multi-scale features can be further improved through cross fusion among the branches. In the semantic branch, the deep features and the shallow features are fused based on a spatial attention mechanism; a large amount of noise contained in the superficial layer feature can be filtered while rich spatial information contained in the superficial layer feature is obtained; finally, the semantic branch features and the edge branch features are fused, and the segmentation effect is further optimized.

Description

technical field [0001] The invention relates to the technical field of semantic segmentation, in particular to an edge-aware image semantic segmentation method based on adaptive feature fusion. Background technique [0002] Semantic segmentation refers to the automatic recognition and segmentation of image content at the pixel level. It has been widely used in land use planning, earthquake monitoring, vegetation classification, environmental pollution monitoring and other fields. For example, through the analysis of atmospheric remote sensing images, the distribution status of atmospheric pollutants can be clarified, so as to monitor air pollution. How to accurately segment images has always been a hot and difficult research topic at home and abroad. [0003] In recent years, with the rapid development of the field of deep learning, breakthroughs have been made in the research of semantic segmentation. The semantic segmentation model based on convolutional neural network ha...

AI Technical Summary

Problems solved by technology

Although these advanced models can achieve good segmentation results, there are still two main problems: (1) The edge features of the image are not fully extracted, resulting in poor segmentation performance of the model in the edge area

(2) The shallow feature map is not filtered before the fusion of the shallow and deep feature maps, and a large amount of noise information is introduced

Images