direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Software

This page lists software developed and maintained at RSiM. All the codes are publicly available for private use and research only.

Metric-Learning-Based Deep Hashing Network for Content-Based Retrieval of Remote Sensing Images

This repository contains the code of our metric-learning based hashing network, which learns: 1) a semantic-based metric space for effective feature representation; and 2) compact binary hash codes for fast archive search. Our network considers an interplay of multiple loss functions that allows to jointly learn a metric based semantic space facilitating similar images to be clustered together in that target space and at the same time producing compact final activations that lose negligible information when binarized.

Repository: 

Accompanying Paper:

Contact Person: Subhankar Roy

S2-cGAN: Self-Supervised Adversarial Representation Learning for Binary Change Detection in Multispectral Images

This repository contains the code of the paper S2-cGAN: Self-Supervised Adversarial Representation Learning for Binary Change Detection in Multispectral Images. The model has been trained and tested on Wordview 2 Dataset for Binary Change Detection. The model is implemented in PyTorch. 

Repositories: 

Accompanying Paper:

Contact Persons: Jose Luis Holgado Alvarez, Dr. Mahdyar Ravanbakhsh

A Deep Multi-Attention Driven Approach for Multi-Label Remote Sensing Image Classification

This repository includes the code for our multi-attention driven multi-label scene classification approach. This approach is based on three main steps. The first step describes the complex spatial and spectral content of image local areas by a K-Branch CNN that includes spatial resolution specific CNN branches. The second step initially characterizes the importance scores of different local areas of each image and then defines a global descriptor for each image based on these scores. This is achieved by a multi-attention strategy that utilizes the bidirectional long short-term memory networks. The final step achieves the classification of RS image scenes with multi-labels. 

Contact Person: Gencer Sumbul

parallelCollGS: Parallel Download from Sentinel Collaborative Ground Segments

This repository provides the python toolchain (parallelCollGS) for parallel queries to download Sentinel 1, 2, and 3 products from a varying number of collaborative ground segments. This toolchain abstracts sentinelsat Python API client to support parallelized mirror access, and thus provides simultaneous access to both high-speed and high-coverage mirrors while reusing the workflow of the non-parallelized client. While keeping as much of the original client’s workflow intact as possible, a fault-tolerant mechanism is included in parallelCollGS for accessing multiple mirrors in parallel. In addition, parallelCollGS uses a scheduling strategy for concurrent downloads to ensure optimal utilization of the available bandwidth. The toolchain provides convenient access to Hadoop Distributed File System (HDFS) via the Apache Hadoop stack based interface for the convenient upload of obtained products.

BigEarthNet Deep Learning Models

This repository contains: i) code to use the BigEarthNet archive with the original CORINE Land Cover (CLC) Level-3 class nomenclature for deep learning applications; and ii) model weights for deep learning models that have been pre-trained on BigEarthNet for scene classification. The code to use the pre-trained deep learning models, to train new models, and to evaluate pre-trained models is implemented based on both TensorFlow and PyTorch. 

BigEarthNet-19 Deep Learning Models

This repository contains: i) code to use the BigEarthNet archive with the BigEarthNet-19 class nomenclature for deep learning applications; and ii) model weights for deep learning models that have been pre-trained on BigEarthNet with the BigEarthNet-19 class nomenclature for scene classification. The BigEarthNet-19 class nomenclature was defined by interpreting and arranging the CORINE Land Cover (CLC) Level-3 nomenclature based on the properties of Sentinel-2 images. The code to use the pre-trained deep learning models, to train new models, and to evaluate pre-trained models is implemented based on TensorFlow. 

BigEarthNet Tools

This repository contains tools for processing the BigEarthNet Sentinel-2 Benchmark Archive. The repository includes three main tools: i) to read the Sentinel-2 image patches in the BigEarthNet; ii) to eliminate the BigEarthNet patches with high density snow/shadow/cloud; and iii) to extract names and download links of the Sentinel-2 Level-1C tiles that were used to create the image patches in the BigEarthNet. The tools are implemented as Python scripts. 

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Head of Chair

Prof. Dr. Begüm Demir
 Phone: +49 30 314 23771
Room E-N 627

Administration

Minh Tai Le
Room E-N 628
Phone +49 30 314 21418

Office Hours:
Monday to Friday
10:00 - 12:00