Built independently by an author, for readers. Read the story and support ChapterPal
ChapterPal Logo
Log inSign up

keyword

Air Change dataset

The Air Change dataset is a publicly available remote sensing benchmark used to train and evaluate computer vision and machine learning algorithms for change detection in aerial imagery. It consists of multi-temporal pairs of coregistered optical aerial photographs captured over the same geographical regions across substantial time intervals spanning several years. Along with the aligned image pairs, the dataset provides manually annotated pixel-level binary ground truth masks that distinguish meaningful land-use and structural changes, such as new building construction, groundwork, tree planting, and agricultural modifications, from non-relevant variations caused by differences in lighting, seasons, or viewpoints.

1 item

Fully Convolutional Siamese Networks for Change Detection

Fully Convolutional Siamese Networks for Change Detection

Rodrigo Caye Daudt, Bertrand Le Saux, Alexandre Boulch

OrganizationsDTISInstitut polytechnique de ParisONERATélécom ParisUniversité Paris-Saclay

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