Remote sensing image road segmentation method based on convolutional neural network weak supervised learning

Abstract

The invention relates to a remote sensing image road segmentation method based on convolutional neural network weak supervised learning. Sparse supervision information provided by road center line data is utilized, semantic features are propagated from a road center line to unmarked pixels through a context-aware label propagation algorithm, and a deep learning framework is combined to train convolutional neural network learning of a double-branch encoding-decoding structure to predict road surface data from a remote sensing image. The method has the advantages that the robustness is high, themethod can adapt to road surface segmentation of remote sensing images of different scales, continuous iteration and continuous optimization can be achieved, a road surface extraction result close tothe manual drawing level can be achieved only under weak label supervision, dependence on a large amount of training data of manual labeling is avoided, the labeling cost is greatly reduced, the method is an important step in automatic extraction of road research from remote sensing images, and has high application value in the aspects of resource exploration and planning, surveying and mapping,regional development and the like.

Description

technical field [0001] The invention relates to a weakly supervised segmentation method for extracting road surfaces from remote sensing images by using a convolutional neural network. Only under the supervision of weak labels provided by road centerline data, the road surface extraction results close to the level of manual drawing can be realized without Relying on the road label labeled pixel by pixel can greatly reduce the cost of labeling and has high application value. It is an important step in the research of automatic road extraction from remote sensing images. Background technique [0002] Remote sensing technology is an important part of modern information technology, the main technical means of collecting geographic information and its dynamic change data, and the basic method of scientific research in earth science, surveying, mapping and surveying and other disciplines. As a basic task in the field of remote sensing data processing and analysis, road extraction ...

AI Technical Summary

Problems solved by technology

However, due to the complexity of remote sensing images, there are few studies that directly apply weakly supervised learning techniques to road segmentation in remote sensing images.

Existing weakly supervised learning technologies mostly use alternate optimization schemes, which increase the amount of calculation and take a long time, and the extracted road edges are irregular, which is not conducive to actual production applications

Therefore, the task of segmenting roads from remote sensing images using weakly supervised learning techniques is both important and challenging.

Images