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.

A Comparative Study of Deep Learning Loss Functions for Multi-Label Remote Sensing Image Classification

This repository contains the code for our comparative study on deep learning loss functions in the context of multi-label remote sensing image classification. In this study, seven different deep learning loss functions have been compared in terms of their: 1) overall accuracy; 2) class imbalance awareness (for which the number of samples associated to each class significantly varies); 3) convexibility and differentiability; and 4) learning efficiency. The code is written based on TensorFlow.

Repository: 

Accompanying Paper: 

Contact Person: Gencer Sumbul

SD-RSIC: Summarization Driven Deep Remote Sensing Image Captioning

This repository contains the code for our Summarization Driven Remote Sensing Image Captioning (SD-RSIC) approach. The SD-RSIC approach consists of three main steps. The first step obtains the standard image captions by jointly exploiting convolutional neural networks (CNNs) with long short-term memory (LSTM) networks. The second step, unlike the existing RS image captioning methods, summarizes the ground-truth captions of each training image into a single caption by exploiting sequence to sequence neural networks and eliminates the redundancy present in the training set. The third step automatically defines the adaptive weights associated to each RS image to combine the standard captions with the summarized captions based on the semantic content of the image. This is achieved by a novel adaptive weighting strategy defined in the context of LSTM networks. The code is written based on TensorFlow.

Repository: 

Accompanying Paper: 

Contact Person: Gencer Sumbul

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.

Deep Learning Models for BigEarthNet-S2 with 43 Classes

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. 

Deep Learning Models for BigEarthNet-S2 with 19 Classes

This repository contains code to use the BigEarthNet Sentinel-2 (denoted as BigEarthNet-S2) archive with the nomenclature of 19 classes for deep learning applications. The nomenclature of 19 classes 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. 

Deep Learning Models for BigEarthNet-MM with 19 Classes

This repository contains code to use the multi-modal BigEarthNet (BigEarthNet-MM) archive with the nomenclature of 19 classes for deep learning applications. The nomenclature of 19 classes was defined by interpreting and arranging the CORINE Land Cover (CLC) Level-3 nomenclature based on the properties of Sentinel-2 images. The tools are implemented as Python scripts. 

BigEarthNet-S2, BigEarthNet-S1 and BigEarthNet-MM Tools

This repositories contain tools for processing the BigEarthNet Sentinel-1 (BigEarthNet-S1), BigEarthNet Sentinel-2 (BigEarthNet-S2) and  BigEarthNet Multi Modal (BigEarthNet-MM) Benchmark Archives. 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 Le
Room EN 628
Phone +49 30 314 21418

Office Hours:
Tuesday and Thursday