This course focuses on a recent trend in Artificial Intelligence for Remote Sensing called "AI4RS" and covers or touches topics such as image classification, object detection, semantic segmentation, change detection, and security for remote sensing in possible areas from local to global scales .
In a mixture of theoretical and hands-on sessions, students will be able to gain a deeper understanding of Machine Learning and Deep Learning and their background as well as apply new concepts and approaches to a variety of practical applications of remote sensing image processing such as data fusion, land-cover, and land-use mapping, urban dynamics monitoring, natural hazard assessment, and vehicle\aircraft detection, using RGB, multispectral, and hyperspectral data.
As part of this course, both depth and extent of skills will be developed within a full workflow from data loader implementation (eg, customized scripts for data reading), data pre-processing (eg, normalization), environment preparation (eg, machine learning libraries), model training (eg, hyperparameter settings), testing and accuracy assessment of predictions.
The main topics include the following:
- machine\deep learning foundations for remote sensing
- remote sensing image classification
- remote sensing image object detection
- remote sensing image semantic segmentation
- Remote sensing image change detection
- Remote sensing image anomaly detection
- Kursverantwortliche/r: Pedram Ghamisi