Full convolutional neural network cultivated land extraction method and system based on multi-scale fusion

Abstract

The invention discloses a full convolutional neural network cultivated land extraction method and system based on multi-scale fusion, and the method comprises the steps of carrying out the unsupervised segmentation of a high-resolution remote sensing image based on an unsupervised multi-scale segmentation mode, carrying out the image processing of a plurality of obtained vector units, and obtaining a training sample data set; building a multi-scale fusion full convolutional neural network, using the training sample data set to train the multi-scale fusion full convolutional neural network, where the multi-scale fusion full convolutional neural network adopts four-scale feature network structures which are connected in parallel, and a feature output layer is added into a neighborhood feature fusion module; and inputting a cultivated land image to be extracted into the trained multi-scale fused full convolutional neural network for prediction, generating a category grid image, and obtaining a final cultivated land vector pattern spot through an image post-processing algorithm. According to the method, relatively regular and homogeneous cultivated land parcel vectors can be stably extracted from a high-resolution image.

Description

technical field [0001] The invention relates to the technical field of optical remote sensing, in particular to a method and system for extracting cultivated land based on a full convolutional neural network based on multi-scale fusion. Background technique [0002] The quantity and quality of cultivated land is the key to ensure the sustainable development of agriculture in our country. The significance of identifying and classifying cultivated land through remote sensing images is not limited to monitoring and protecting cultivated land. The analysis of cultivated land on remote sensing images of different time periods can make statistics and estimates on the growth, distribution and even yield of crops in my country. Traditional remote sensing cultivated land extraction mostly relies on low- to medium-resolution multispectral images, and extracts the distribution range of cultivated land mainly through the spectral differences between the spectral characteristics of crop...

AI Technical Summary

Problems solved by technology

Some scholars have proposed a method based on image segmentation to obtain complete and regular plots, but due to the existence of under-segmentation and over-segmentation, it is difficult to obtain high accuracy

At present, the acquisition of high-precision cultivated land plot products mainly relies on manual interpretation and computer-aided mapping, which is time-consuming and labor-intensive

Images