Inst. Technische Informatik und Mikroelektronik

207 Items

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

Sumbul, Gencer ; Demir, Begüm (2020-05-19)

Deep learning (DL) based methods have been found popular in the framework of remote sensing (RS) image scene classification. Most of the existing DL based methods assume that training images are annotated by single-labels, however RS images typically contain multiple classes and thus can simultaneously be associated with multi-labels. Despite the success of existing methods in describing the in...

Image-based tracking, quantification and exploration of cardiac dynamics

Tautz, Lennart (2020)

The heart is the central driver of blood circulation, which supplies the body with oxygen. Heart function is determined by a complex interaction between heart wall contraction, heart valves and respiration. Cardiac diseases and disease progression manifest often regionally and diversely across patients. Modern clinical imaging allows the acquisition of image data for the detailed assessment of...

BigEarthNet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding

Sumbul, Gencer ; Charfuelan, Marcela ; Demir, Begüm ; Markl, Volker (2019)

The BigEarthNet archive was constructed by the Remote Sensing Image Analysis (RSiM) Group and the Database Systems and Information Management (DIMA) Group at the Technische Universität Berlin (TU Berlin). This work is supported by the European Research Council under the ERC Starting Grant BigEarth and by the German Ministry for Education and Research as Berlin Big Data Center (BBDC). BigEart...

Exploring perception through the eyes

Wang, Xi (2020)

Everyday a huge amount of visual information enters the human brain through the eyes; meanwhile, a considerable amount of information is revealed by the eyes. The unique yet complex combination of the various roles of the eyes offer valuable opportunities to understand human perception, cognitive processing (e.g. visual search, recognition, and decision making), as well as mental states, and to...

60- and 122-GHz SiGe BiCMOS transceivers for FMCW radar applications

Öztürk, Efe (2020)

The continuous need for high-performance transceivers with demanding parameters for huge in-dustries targeting important radar applications are driving researchers to search for ways to im-prove the fabrication technologies, circuit topologies and system architectures. A considerable care should be exercised to achieve compact wideband chips at high frequencies with high output power and low po...

Accurate Energy and Performance Prediction for Frequency-Scaled GPU Kernels

Fan, Kaijie ; Cosenza, Biagio ; Juurlink, Ben (2020-04-27)

Energy optimization is an increasingly important aspect of today’s high-performance computing applications. In particular, dynamic voltage and frequency scaling (DVFS) has become a widely adopted solution to balance performance and energy consumption, and hardware vendors provide management libraries that allow the programmer to change both memory and core frequencies manually to minimize energ...

Sensor Artificial Intelligence and its Application to Space Systems - A White Paper

Börner, Anko ; Heinz-Wilhelm, Hübers ; Kao, Odej ; Schmidt, Florian ; Becker, Sören ; Denzler, Joachim ; Matolin, Daniel ; Haber, David ; Lucia, Sergio ; Samek, Wojciech ; Triebel, Rudolph ; Eichstädt, Sascha ; Biessmann, Felix ; Kruspe, Anna ; Jung, Peter ; Kok, Manon ; Gallego, Guillermo ; Berger, Ralf (2020-06)

Information and communication technologies have accompanied our everyday life for years. A steadily increasing number of computers, cameras, mobile devices, etc. generate more and more data, but at the same time we realize that the data can only partially be analyzed with classical approaches. The research and development of methods based on artificial intelligence (AI) made enormous progress i...

A Quantitative Study of Locality in GPU Caches

Lal, Sohan ; Juurlink, Ben (2020)

Traditionally, GPUs only had programmer-managed caches. The advent of hardware-managed caches accelerated the use of GPUs for general-purpose computing. However, as GPU caches are shared by thousands of threads, they are usually a victim of contention and can suffer from thrashing and high miss rate, in particular, for memory-divergent workloads. As data locality is crucial for performance, the...

Volcanic Hot-Spot Detection Using SENTINEL-2: A Comparison with MODIS−MIROVA Thermal Data Series

Massimetti, Francesco ; Coppola, Diego ; Laiolo, Marco ; Valade, Sébastien ; Cigolini, Corrado ; Ripepe, Maurizio (2020-03-03)

In the satellite thermal remote sensing, the new generation of sensors with high-spatial resolution SWIR data open the door to an improved constraining of thermal phenomena related to volcanic processes, with strong implications for monitoring applications. In this paper, we describe a new hot-spot detection algorithm developed for SENTINEL-2/MSI data that combines spectral indices on the SWIR ...

Active Acoustic Contact Sensing for Soft Pneumatic Actuators

Zöller, Gabriel ; Wall, Vincent ; Brock, Oliver (2020-02)

Supplementary data to our publication Zöller, Gabriel, Vincent Wall, and Oliver Brock. "Active Acoustic Contact Sensing for Soft Pneumatic Actuators." 2020 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2020.

Locally solving linear systems for geometry processing

Herholz, Philipp (2020)

Geometry processing algorithms commonly need to solve linear systems involv- ing discrete Laplacians. In many cases this constitutes a central building block of the algorithm and dominates runtime. Usually highly optimized libraries are em- ployed to solve these systems, however, they are built to solve very general linear systems. I argue that it is possible to create more efficient algorithms...

Performance Counters based Power Modeling of Mobile GPUs using Deep Learning

Mammeri, Nadjib ; Neu, Markus ; Lal, Sohan ; Juurlink, Ben (2019-07-15)

GPUs have recently become important computational units on mobile devices, resulting in heterogeneous devices that can run a variety of parallel processing applications. While developing and optimizing such applications, estimating power consumption is of immense importance as energy efficiency has become the key design constraint to optimize for on these platforms. In this work, we apply deep ...

An Efficient Lightweight Framework for Porting Vision Algorithms on Embedded SoCs

Ashish, Apurv ; Lal, Sohan ; Juurlink, Ben (2019-09-10)

The recent advances in the field of embedded hardware and computer vision have made autonomous vehicles a tangible reality. The primary requirement of such an autonomous vehicle is an intelligent system that can process sensor inputs such as camera or lidar to have a perception of the surroundings. The vision algorithms are the core of a camera-based Advanced Driver Assistance Systems (ADAS). H...

A Weighted SVM-Based Approach to Tree Species Classification at Individual Tree Crown Level Using LiDAR Data

Nguyen, Hoang Minh ; Demir, Begüm ; Dalponte, Michele (2019-12-09)

Tree species classification at individual tree crowns (ITCs) level, using remote-sensing data, requires the availability of a sufficient number of reliable reference samples (i.e., training samples) to be used in the learning phase of the classifier. The classification performance of the tree species is mainly affected by two main issues: (i) an imbalanced distribution of the tree species class...

The mean point of vergence is biased under projection

Wang, Xi ; Holmqvist, Kenneth ; Alexa, Marc (2019-09-09)

The point of interest in three-dimensional space in eye tracking is often computed based on intersecting the lines of sight with geometry, or finding the point closest to the two lines of sight. We first start by theoretical analysis with synthetic simulations. We show that the mean point of vergence is generally biased for centrally symmetric errors and that the bias depends on the horizontal ...

Deep Metric and Hash-Code Learning for Content-Based Retrieval of Remote Sensing Images

Roy, Subhankar ; Sangineto, Enver ; Demir, Begüm ; Sebe, Nicu (2018-11-05)

The growing volume of Remote Sensing (RS) image archives demands for feature learning techniques and hashing functions which can: (1) accurately represent the semantics in the RS images; and (2) have quasi real-time performance during retrieval. This paper aims to address both challenges at the same time, by learning a semantic-based metric space for content based RS image retrieval while simul...

Advanced Local Binary Patterns for Remote Sensing Image Retrieval

Tekeste, Issayas ; Demir, Begüm (2018-11-05)

The standard Local Binary Pattern (LBP) is considered among the most computationally efficient remote sensing (RS) image descriptors in the framework of large-scale content based RS image retrieval (CBIR). However, it has limited discrimination capability for characterizing high dimensional RS images with complex semantic content. There are several LBP variants introduced in computer vision tha...

Retrieving Images with Generated Textual Descriptions

Hoxha, Genc ; Melgani, Farid ; Demir, Begüm (2019-11-14)

This paper presents a novel remote sensing (RS) image retrieval system that is defined based on generation and exploitation of textual descriptions that model the content of RS images. The proposed RS image retrieval system is composed of three main steps. The first one generates textual descriptions of the content of the RS images combining a convolutional neural network (CNN) and a recurrent ...

A Novel Multi-Attention Driven System for Multi-Label Remote Sensing Image Classification

Sumbul, Gencer ; Demir, Begüm (2019-11-14)

This paper presents a novel multi-attention driven system that jointly exploits Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) in the context of multi-label remote sensing (RS) image classification. The proposed system consists of four main modules. The first module aims to extract preliminary local descriptors of RS image bands that can be associated to different spatial...

Bigearthnet: A Large-Scale Benchmark Archive for Remote Sensing Image Understanding

Sumbul, Gencer ; Charfuelan, Marcela ; Demir, Begüm ; Markl, Volker (2019-11-14)

This paper presents the BigEarthNet that is a new large-scale multi-label Sentinel-2 benchmark archive. The BigEarthNet consists of 590, 326 Sentinel-2 image patches, each of which is a section of i) 120 × 120 pixels for 10m bands; ii) 60×60 pixels for 20m bands; and iii) 20×20 pixels for 60m bands. Unlike most of the existing archives, each image patch is annotated by multiple land-cover class...