keyword
multispectral images
Multispectral images are digital images that capture optical data at specific, discrete wavelength bands across the electromagnetic spectrum. While standard color photographs record only the three primary visible bands of red, green, and blue, multispectral images typically capture between three and fifteen distinct spectral channels that often extend beyond human vision into near-infrared, shortwave infrared, and thermal infrared regions. By recording how materials reflect or emit radiation at these targeted wavelengths, multispectral imagery reveals physical and chemical properties that are otherwise imperceptible, making it a foundational tool in satellite remote sensing, environmental monitoring, agricultural assessment, and automated image analysis.
2 items
Fully Convolutional Siamese Networks for Change Detection
Rodrigo Caye Daudt, Bertrand Le Saux, Alexandre Boulch
Why you should read this
Proposes fully convolutional Siamese architectures for remote sensing change detection that train from scratch on coregistered image pairs to deliver superior accuracy at over 500 times the speed of previous methods.
This paper presents three fully convolutional neural network architectures which perform change detection using a pair of coregistered images. Most notably, we propose two Siamese extensions of fully convolutional networks which use heuristics about the current problem to achieve the best results in our tests on two open change detection datasets, using both RGB and multispectral images. We show that our system is able to learn from scratch using annotated change detection images. Our architectures achieve better performance than previously proposed methods, while being at least 500 times faster than related systems. This work is a step towards efficient processing of data from large scale Earth observation systems such as Copernicus or Landsat.
Added
2026-09-24
Seeded Region Growing
Rolf Adams, L. Bischof
Why you should read this
Proposes seeded region growing, a parameter-free segmentation algorithm that rapidly partitions images by iteratively assimilating adjacent pixels based on statistical similarity to seed-initialized regions.
We present here a new algorithm for segmentation of intensity images which is robust, rapid, and free of tuning parameters. The method, however, requires the input of a number of seeds, either individual pixels or regions, which will control the formation of regions into which the image will be segmented. In this correspondence, we present the algorithm, discuss briefly its properties, and suggest two ways in which it can be employed, namely, by using manual seed selection or by automated procedures.
Added
2026-09-11