Port ore heap segmentation and reserve calculation method based on improved UNet network

Abstract

The invention discloses a port ore heap segmentation and reserve calculation method based on an improved UNet network, and belongs to the field of optical remote sensing image processing and deep learning. The method comprises the steps of 1 making a port ore heap semantic segmentation data set based on a high-resolution optical remote sensing image; 2 improving a UNet network algorithm: optimizing a downsampling process of the UNet network by using a hole convolution layer; 3, training the ore heap segmentation data set by using an improved UNet network; 4 performing image semantic segmentation on the image test data containing the ore heap by using the trained network; and 5 carrying out reserve estimation on the segmented ore heap by using an ore heap volume estimation method. The method can accurately identify the ore heap in a port heaping area and estimate the reserves of the ore heap, and has a guiding effect in the fields of financial futures and the like.

Description

technical field [0001] The invention relates to a port ore pile segmentation and reserve calculation method based on an improved UNet network, which belongs to the field of optical remote sensing image processing and deep learning. Background technique [0002] Image semantic segmentation is an important field in computer vision. Image semantic segmentation can identify objects at the pixel level and predict the category of each pixel in the image. The port ore stacking area is a specific area where the ore to be transported is stacked in the port. The ore stacks in the same ore stacking area are arranged in an orderly manner, but because the ore stack will gradually increase or decrease with continuous transportation, the shape is irregular, and many ores are related to bare The color of the ground is relatively close, which makes it difficult for traditional computer vision methods to detect the edge of ore in remote sensing images. The deep learning image semantic segmen...

AI Technical Summary

Problems solved by technology

The port ore stacking area is a specific area where the ore to be transported is stacked in the port. The ore stacks in the same ore stacking area are arranged in an orderly manner, but because the ore stack will gradually increase or decrease with continuous transportation, the shape is irregular, and many ores are related to bare The color of the ground is relatively close, which makes it difficult for traditional computer vision methods to detect the edge of ore in remote sensing images

Images