Image Semantic Segmentation Method Based on Deep Fully Convolutional Network and Conditional Random Field

Abstract

The present invention provides an image semantic segmentation method based on a deep fully convolutional network and a conditional random field. Parameter Learning and Image Semantic Segmentation. This application introduces dilated convolution and spatial pyramid pooling modules into the deep fully convolutional network, and further corrects the label prediction map output by the deep fully convolutional network using a conditional random field. The dilated convolution expands the receptive field while ensuring the feature map The resolution remains unchanged, and the spatial pyramid pooling module extracts regional context features of different scales from the convolutional local feature map, providing the relationship between different objects and the relationship between objects and regional features of different scales for label prediction. The fully connected conditional random field is based on The pixel labels are further optimized by the feature similarity of pixel intensity and location, resulting in semantic segmentation maps with high resolution, precise boundaries, and good spatial continuity.

Description

technical field [0001] The invention relates to the technical field of image understanding, in particular to an image semantic segmentation method based on a deep full convolution network and a conditional random field. Background technique [0002] Image semantic segmentation is to label image pixels according to their semantics to form different segmentation regions. Semantic segmentation is the cornerstone technology of image understanding, and it plays a pivotal role in street view recognition and understanding of automatic driving systems, judgment of UAV landing sites, and lesion recognition and positioning of medical images. [0003] The emergence of deep learning technology has significantly improved the performance of image semantic segmentation compared with traditional methods. Supervised learning on large datasets using deep convolutional neural networks is currently the mainstream method for image semantic segmentation. Input the image to be segmented, use con...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the problems existing in the existing methods, the present invention provides an image semantic segmentation method based on a deep full convolutional network and a conditional random field. The method introduces dilated convolution and spatial pyramid pooling modules into the deep full convolutional network, and The label prediction map output by the deep full convolutional network is further corrected using conditional random fields; the expansion convolution expands the receptive field while ensuring that the resolution of the feature map remains unchanged; the spatial pyramid pooling module extracts regional contexts of different scales from the convolutional local feature map Features, which provide the relationship between different objects and the connection between objects and regional features of different scales for label prediction; the fully connected conditional random field further optimizes the pixel label according to the feature similarity of pixel intensity and position, thereby generating high-resolution, boundary Precise and spatially continuous semantic segmentation map

Images