Abstract:
Proposed an improved approach to the segmentation of multispectral images using Convolutional Neural Networks (CNN). The original algorithm
was described earlier. It took into account some errors that could arise during the
processing of SNA images using a sliding window. The proposed modification
uses the NDVI and NDWI indices, which have a high correlation coefficient with
real objects present in the images, also images pyramids were used.
Key words and phrases:multispectral imaging, Earth remote sensing, convolutional neural networks, segmentation, image pyramid.