TU Berlin

Communication Systems GroupProjects

Page Content

to Navigation

Ongoing Projects



Plenoptic Imaging aims at studying the phenomena of light field formation, propagation, sensing and perception along with the computational methods for extracting, processing and rendering the visual information. The PLENOPTIMA ultimate project goal is to establish new cross-sectorial, international, multi-university sustainable doctoral degree programmes in the area of plenoptic imaging and to train the first fifteen future researchers and creative professionals within these programmes for the benefit of a variety of application sectors. more to: PLENOPTIMA



The main goal of this project is to develop intelligent procedures for automatic people counting, people localization and motion analysis by means of video recordings from commercially available drones (SmartSense) and to integrate these into existing command and control systems of authorities and organizations with security tasks (BOS) in order to support their emergency forces in life-threatening situations in a simple and automated way (Rescue). more to: SmartSense&Rescue

Completed Projects



The aim of this project is to support security personnel at big events with remotely controlled drone-cameras monitoring the entire location, to automatically 3D reconstruct analyze the captured data and effectively visualize and highlight special events like violent behavior, emergence of panic, etc. In relationship to traditional installed cameras, drones allow a more flexible and comprehensive overview of the terrain, provide better analysis results and additionally reduce costs compared to the operation of helicopters. more to: SiGroViD



EU FP7 funded project LASIE - Large scale information exploitation of forensic data (01.05.2014 - 31.10.2017). The LASIE project aims to design and implement an open and expandable framework that will significantly increase the efficiency of current investigation practices, by providing an automated initial analysis of the vast amounts of heterogeneous forensic data that analysts have to cope with. The framework will be able to handle forensic data that have been acquired from a variety of different sources including CCTV surveillance content, confiscated desktops and hard disks, mobile devices, Internet, social networks, handwritten and calligraphic documents. more to: LASIE



QuaVideo - Video quality improvement based on long-term temporal trajectory filtering. Funded by BMBF (01.10.2013 - 30.11.2016). With the convergence of internet and digital television, low quality internet video is now frequently displayed on ultra high resolution, high quality displays. Typical examples include low resolution and poor quality Youtube video and older amateur family video displayed on 4K devices. Typical MPEG coding artifacts, like blocking and smearing, appear very annoying when displayed at high resolutions. Our challenge is the quality enhancement of legacy video to make content more appealing when viewed at large size displays. To this end we track motion information through hundreds of frames in the video scene to filter out noise and smearing artifacts. Our approach adapts to scene changes and varying content fully automatically and removes artifacts from hours of video. more to: QuaVideo

NOST - iFore


BMWi gefördertes Projekt NOST - iFore Crowd-geeignete Personenrückverfolgung (01.04.2015 - 30.09.2016). In dem Projekt "Intelligente Forensik/Personenrückverfolgung in Videoarchiven", Kurzbezeichnung "iFore", soll der Prototyp einer Hardware-Software-Lösung zur schnellen und effizienten Auswertung von Video-Aufzeichnungen in Fahrzeugen des ÖPNV erarbeitet werden. Dazu sollen markierte Personen automatisch durch ein Fahrzeug verfolgt und in weiteren Archivaufnahmen wieder gefunden werden können. more to: NOST - iFore



BMWi gefördertes Projekt PerimeterNetz (01.01.2015 - 31.12.2015). Ziel ist der Schutz von abgelegenen, ausgedehnten Objekten mit öffentlichen Zugang. Dabei soll das eingesetzte Wachpersonal durch eine im Projekt prototypenhaft zu realisierende automatische Szeneinterpretation alarmiert werden. Die Szeneinterpretation stützt sich im gewählten Ansatz auf eine dezentrale Sensorik. Jeder Sensorknoten ist dabei in der Lage mithilfe moderner Deep Learning Technologien Objekte mit hoher Genauigkeit zu erkennen. more to: PerimeterNetz



EU FP7 funded project VideoSense (2011-2015). VideoSense will integrate leading European research groups to create a long-term open integration of critical mass in the twin areas of Ethically-Guided, and, Privacy Preserving Video Analytics where the advent of new data intelligence technologies against the background of dynamic societal and citizen’s goals, norms, expectations, safety and security needs have all contributed to a complex interplay of influences which deserve in-depth study and solution seeking in order for the European society, citizen and industry to strike the optimal balance in resolution of the various challenges in this arena. more to: VideoSense

Connected Technologies


The goal of the sub-project „Interaktion und Sensoren“ (interaction and sensors) is to design usage scenarios for connected environments and to develop so called “generic” sensors and actuators. Prospective users from local neighborhoods will be involved in the scenario generation process. Prototypes with suitable sensors will be developed to demonstrate alternative forms of interaction. more to: Connected Technologies



The goal of the MOSAIC project has been to develop the MOSAIC Platform. The MOSAIC Platform involves multi-modal data intelligence capture and analytics including video and text collaterals etc. The distributed intelligence within the platform enables decision support for automated detection, recognition, geo-location and mapping, including intelligent decision support at various levels to enhance situation awareness, surveillance targeting and camera handover; these involve level one fusion, and situation understanding to enable decision support and impact analysis at level two and three of situation assessment. more to: Mosaic



OpenSEM, the open innovation platform for se-mantic media, is an EIT ICT Labs activity, started in 2011 with institutes from Germany, Finland, the Netherlands and France. OpenSEM builds on results achieved in the PetaMedia network of excellence and in some activities closely cooperates with PetaMedia. The consortium is open for new partners and various forms of cooperation with academic and commercial labs. OpenSEM helps participants translating research results to product and service innovation. OpenSEM is not just a project: It envisions long term cooperation of institutes and companies working on the cutting edge of semantic multimedia technology, thus establishing a virtual center of excellence on social media retrieval. more to: OpenSEM



PetaMedia is a Network of Excellence funded by the European Commission's Seventh Framework Programme. FP7 is a key tool to respond to Europe's needs in terms of jobs and competitiveness, and one of its goals is to maintain leadership in the global knowledge economy. The goal of the NoE PetaMedia is to bring together the research of four national networks in the Netherlands, Switzerland, UK and Germany in the area of multimedia content analysis (MCA) and social peer-to-peer networks and eventually to establish a European virtual centre of excellence. more to: PetaMedia



Projektpartner: •Bundespolizei, Potsdam •Deutsche Bahn AG, Berlin •Fraunhofer-Institut für Nachrichtentechnik, Heinrich-Hertz-Institut, Berlin •Funkwerk plettac electronic GmbH, Fürth •Gesellschaft zur Förderung angewandter Informatik, Berlin •Siemens Division Building Technologies, Karlsruhe •Technische Universität Berlin, Fachgebiet Nachrichtenübertragung, Berlin •VCS Video Communication Systems AG, BOSCH Group, Ottobrunn •Vis-à-pix GmbH, Potsdam Weitere Informationen: Projektbeschreibung Präsentation Abschlussberichte der Teilvorhaben more to: SinoVE

imcube media


imcube has an innovative technology and patented process for converting 2D video and film into stereoscopic 3D using the company‘s cubit software. imcube’s conversion process provides film makers, studios, and exhibitors with a new solution to 3D movie making and presentation. Exhibitors will have a flow of 3D product and theatre audiences will finally be able to enjoy both new and classic movie features in an entirely new reality elevated 3D cinematic experience. Our process is a high quality depth-restoration process with many automatic features that results in perfect and realistic 3D. Furthermore, movies converted to 3D via our process produce no eye fatigue for theatre audiences. The underlying software is developed with the cooperation of the Communication Systems Group of the Technische Universität Berlin. more to: imcube media



VISNET II builds on the success and achievements of the existing VISNET NoE to continue the progress towards achieving the NoE mission of creating a sustainable world force in Networked Audiovisual (AV) Media Technologies. VISNET II is a network of excellence that has strategic objectives revolving around the integration, research and dissemination activities of a network of excellence. Integration will be achieved both in each thematic area and across the 3 Themes defining the scope of research in VISNET II. more to: VISNET II



K-Space is a network of leading research teams from academia and industry conducting integrative research and dissemination activities in semantic inference for automatic and semi-automatic annotation and retrieval of multimedia content. K-Space exploits the complementary expertise of project partners, enables resource optimization and fosters innovative research in the field. The aim of K-Space research is to narrow the gap between low-level content descriptions that can be computed automatically by a machine and the richness and subjectivity of semantics in high-level human interpretations of audiovisual media: The Semantic Gap. more to: K-Space

3DTV: Integrated Three-Dimensional Television - Capture, Transmission, and Display


A consortium of 19 entities, led by Bilkent University, has been working on planning and conducting a 48-month project on 3DTV. The Network of Excellence (NoE) is funded by EC and started on 1 September 2004. The primary goal of the team is to deal with all aspects of the 3DTV in an integrated manner. The team believes that the timing is perfect in terms of technological environment and consumer attitude and needs. The primary objective of this project is to align European researchers with diverse experience and activity in distinct, yet complementary, areas so that an effective network for achieving full scale 3D video capabilities integrated seemlessly to a more general information technology base (like internet) is established and kept functional for a long time. more to: 3DTV: Integrated Three-Dimensional Television - Capture, Transmission, and Display


Project goal: Combating vandalism in public transportation systems through wireless networked sensors, video and surveillance systems. more to: MO-SENSNETS

MPEG-4 Audio Lossless Coding (ALS)

Der MPEG-4 ALS Standard gehört zur Familie der MPEG-4 Audiocodierstandards, die von der ISO (www.iso.org) herausgegeben werden. Im Gegensatz zu verlustbehafteten Verfahren wie MP3 und AAC, die lediglich die subjektiv empfundene Qualität zu erhalten versuchen, erlaubt die verlustlose Codierung jedoch eine exakte Wiederherstellung jedes einzelnen Bits der ursprüglichen Audiodaten. Das grundlegende Verfahren von MPEG-4 ALS wurde am Fachgebiet Nachrichtenübertragung der Technischen Universität Berlin entwickelt. Die erste Version des MPEG-4 ALS Standards wurde 2006 veröffentlicht, und die aktuelle Beschreibung ist inzwischen Teil der 4. Edition (2009) des übergreifenden MPEG-4 Audiostandards (ISO/IEC 14496-3:2009). Eine neue Version (RM23) der MPEG-4 ALS Referenzsoftware und des Codecs ist jetzt verfügbar. Mehr dazu hier (in English)... MPEG-4 ALS wird mittlerweile von FFmpeg, MPlayer, VLC Media Player und weiteren Anwendungen unterstützt. Mehr dazu hier (in Englisch)... more to: MPEG-4 Audio Lossless Coding (ALS)

Multiple-Description-Codierung von Sprachsignalen

Verzögerungen oder Störungen einer Multimediaübertragung über Kommunikationsnetze wie z. B. das Internet führen zu Paketverlusten, d. h. kurzzeitigen Unterbrechungen, die sich insbesondere bei niederratigen Sprachsignalen unangenehm bemerkbar machen. Bei einer Übertragung an viele Empfänger - Multicast oder Broadcast - unterliegen diese sehr unterschiedlichen, oft auch schwankenden Bandbreiten und Verlusten, denen hauptsächlich durch empfängerseitige Maßnahmen individuell begegnet werden muss. Eine zunehmende Paketverlustrate, der ein Empfänger unterliegt, sollte dabei nur zu einer allmählichen Verminderung der Sprachsignalqualität führen und so auch unter ungünstigen Bedingungen noch eine akzeptable Decodierung ermöglichen. Gleichzeitig sollen andere Empfänger, die das codierte Sprachsignal gerade ohne Verluste empfangen, weiterhin die höchstmögliche Signalqualität liefern. more to: Multiple-Description-Codierung von Sprachsignalen

Verlustlose Mehrkanal-Audiocodierung / MPEG-4 ALS

Lossless audio coding enables the compression of digital audio data without any loss in quality due to a perfect reconstruction of the original signal. Principal applications are transmission and archiving systems, in particular for professional use in broadcasting and sound engineering. The objective of the project is to extend former studies on lossless audio coding by developing methods for joint coding of stereo and multichannel signals. While conventional algorithms only remove intra-channel correlations, it is worthwhile to make use of inter-channel correlations as well. Therefore, a main goal of the project is the development of a efficient lossless multichannel codec. more to: Verlustlose Mehrkanal-Audiocodierung / MPEG-4 ALS

Source Separation from Stereo Musical Mixtures

Identifying and extracting the individual sound sources that are present in a mixture can be of extreme value for a wide range of semantic analysis applications (such as transcription, classification and denoising), as well as a powerful application by itself (unmixing). Motivated by the increasing potential of on-line music distribution services, we center our research on the separation of the instruments out of a musical mixture. We also emphasize on the stereo case, which is still the most common audio format. The goal of the project is to study the implications and requirements of such a separation, and to develop a system capable of identifying the number of instruments present in a mixture, to locate them spatially, and to resynthesize the separated sources. An important part of the research will be to study the combination of underdetermined Blind Source Separation (BSS) methods, such as sparsity- or ICA-related algorithms, with psychoacoustic-related methods, such as Computational Auditory Scene Analysis (CASA). more to: Source Separation from Stereo Musical Mixtures

MPEG-7-based Audio Annotation for the Archival of Digital Video

MPEG-7 is a standardisation initiative of the Motion Pictures Expert Group (MPEG) that, instead of focusing on coding like MPEG-1, MPEG-2 and MPEG-4, is meant to be an standardization of the way to describe multimedia content (see also: MPEG-7 Link list). This project is actually part of a larger one, called MPEG-7-based Archival of Digital Video. Its objective is the achievement of a complete audio-visual database management platform, allowing to segment, index and retrieve audio-visual data, based on MPEG-7 "descriptors" and tools. more to: MPEG-7-based Audio Annotation for the Archival of Digital Video

GraVis - Graphenbasierte Deskriptoren zur Beschreibung von Personen in Videos

Dieses Projektvorhaben hat die Weiterentwicklung und Verbesserung von automatischen Verfahren zur Lokalisierung und Beschreibung von Personen in Video-Bilddaten zum Gegenstand. Die drei Grundelemente von Personen, nämlich Gesicht, Körper und Bekleidung sollen durch einen hierarchischen Deskriptor geschlossen beschrieben werden. Dabei sollen Merkmale aus einem Merkmalsvorrat adaptiv ausgewählt und durch ein übergeordnetes Konzept methodisch homogen integriert werden. Auf der Ebene der Merkmalsklassifikation und Statistik sind nicht-lineare Methoden in großem Umfang vorgesehen. Dieses Forschungsvorhaben will an der methodischen Grundlagenbildung des Sektors "Looking at People" oder "Sensing People" mitwirken, der sowohl von wissenschaftlicher als auch von großer technologisch-wirtschaftlicher Relevanz ist. more to: GraVis - Graphenbasierte Deskriptoren zur Beschreibung von Personen in Videos

Sensing People - Intelligente Kameras und Sensoren

Sensing People bedeutet die Beschreibung und Auswertung von Personendaten in digitalen Bild- und Audioquellen im Hinblick auf Aufenthaltsort, Tätigkeit, Zustand, Sprechaktivität, Identität und sonstiger personeller Gesichtspunkte. Ziel des Forschungsprojektes ist die Entwicklung von Konzepten und Lösungen für universell einsetzbare intelligente Kameras und Sensoren, die Sensing-People-Funktionalitäten integrieren und in eine Vielzahl von Bereichen eingesetzt werden können. Dazu gehören beispielsweise Multimedia-Anwendungen, Haushaltselektronik und Industrieapplikationen. Aus Sensorsignalen sollen für möglichst viele potentielle Anwendungen personengebundene more to: Sensing People - Intelligente Kameras und Sensoren

Query by Humming

Query by Humming (QBH) is a method for searching in a multimedia database system containing meta data descriptions of songs. The database can be searched by hummed queries, this means that a user can hum a melody into a microphone which is connected to the computer hosting the system. The QBH system searches the database for songs which are similar to the input query and presents the result to the user as a list of matching songs. A QBH system is a typical application using the standard MPEG-7. more to: Query by Humming


Quick Access

Schnellnavigation zur Seite über Nummerneingabe