1. REMOTE SENSING IMAGE REGRESSION FOR HETEROGENEOUS CHANGE DETECTION
- Author
-
Luigi Tommaso Luppino, Stian Normann Anfinsen, Gabriele Moser, and Filippo Maria Bianchi
- Subjects
FOS: Computer and information sciences ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,0211 other engineering and technologies ,02 engineering and technology ,Mønstergjenkjenning / Pattern Recognition ,symbols.namesake ,VDP::Mathematics and natural scienses: 400::Information and communication science: 420 ,0202 electrical engineering, electronic engineering, information engineering ,Gaussian process ,021101 geological & geomatics engineering ,Remote sensing ,Domain adaptation ,Maskinlæring / Machine learning ,Hyperparameter ,Bildebehandling / Image processing ,Pixel ,Change detection ,Heterogeneous image sources ,Regression ,Human-Computer Interaction ,Signal Processing ,Random forest ,Support vector machine ,VDP::Matematikk og naturvitenskap: 400::Informasjons- og kommunikasjonsvitenskap: 420 ,Kunstig intelligens / Artificial intelligence ,Transformation (function) ,symbols ,Kernel regression ,020201 artificial intelligence & image processing - Abstract
Change detection in heterogeneous multitemporal satellite images is an emerging topic in remote sensing. In this paper we propose a framework, based on image regression, to perform change detection in heterogeneous multitemporal satellite images, which has become a main topic in remote sensing. Our method learns a transformation to map the first image to the domain of the other image, and vice versa. Four regression methods are selected to carry out the transformation: Gaussian processes, support vector machines, random forests, and a recently proposed kernel regression method called homogeneous pixel transformation. To evaluate not only potentials and limitations of our framework, but also the pros and cons of each regression method, we perform experiments on two data sets. The results indicates that random forests achieve good performance, are fast and robust to hyperparameters, whereas the homogeneous pixel transformation method can achieve better accuracy at the cost of a higher complexity., Accepted to Machine Learning for Signal Processing 2018
- Published
- 2018
- Full Text
- View/download PDF