Auflistung nach Autor:in "Brunnett, Guido"
1 - 5 von 5
Treffer pro Seite
Sortieroptionen
- TextdokumentEvaluation of CNN-based algorithms for human pose analysis of persons in red carpet scenarios(INFORMATIK 2017, 2017) Kowerko, Danny; Richter, Daniel; Heinzig, Manuel; Kahl, Stefan; Helmert, Stefan; Brunnett, GuidoWe evaluate two CNN-based algorithms for keypoint-based human pose analysis on two image test sets containing red carpet scenarios, one taken under controlled conditions in a TV studio environment and another more heterogeneous data set taken from FlickR without any restriction but to contain a red carpet. We focus on the pose of persons standing directly on the red carpet. A web application is presented allowing collaborative work to confirm or modify already pre-localised body keypoints given from the method presented in [Ca17]. These annotations helped to quickly define ground truth for the subsequent evaluation of several hundreds of persons standing on a red carpet. An own evaluation formalism is presented that adopts to the size of the respective keypoints. The TV studio data set includes coarsely defined body and head poses. Using the angular information, we are able to quantitatively define the optimum head pose angle range and limitations of facial keypoint determination.
- TextdokumentFast and accurate creation of annotated head pose image test beds as prerequisite for training neural networks(INFORMATIK 2017, 2017) Kowerko, Danny; Manthey, Robert; Heinz, Marcel; Kronfeld, Thomas; Brunnett, GuidoIn this paper we present an experimental setup consisting of 36 cameras on 4 height levels covering more than half space around a centrally sitting person. The synchronous image release allows to build a 3D model of the human torso in this position. Using this so-called body scanner we recorded 36 different positions giving in total 1296 images in several minutes obtaining tens to hundreds of different pitch-roll-yaw head pose combinations with very high precision of less than +-5. From annotation of 7 facial keypoints (ears, eyes, nose, corners of the mouth) in the 36 calculated 3D models of a human head/upper body, we automatically get 1296 x 7 2D facial landmark points saving a factor 36 in annotation time. The projection of the 3D model to the camera provides a foreground/background separation mask of the person in each image usable for data set augmentation e.g. by inserting different backgrounds (required for training convolutional neural networks, CNNs). Moreover, we utilize our 3D model in combination with textures to create realistic images of the pitch-roll-yaw range not assessed in experiments. This interpolation is ad hoc applicable to a subset of 10 central out of 36 total camera views where fine-grained interpolation of head poses is possible. Using interpolation and background masks for background exchange enables us to augment the data set easily by a factor of 1000 or more knowing precisely pitch, roll, yaw and the 7 annotated facial keypoints in each image.
- KonferenzbeitragGrundlagen für das Retrieval rotationssymmetrischer Gefäße(Workshop Audiovisuelle Medien WAM 2009, 2009) Wagner, Stefan; Hörr, Christian; Brunner, David; Brunnett, GuidoIn der wissenschaftlichen Erforschung archäologischer Sachverhalte spielt die präzise Dokumentation der Fundstücke eine äußerst wichtige Rolle. Einer rapide steigenden Anzahl von Fundstücken ist allerdings mit den traditionellen Methoden der Archäologie kaum noch Herr zu werden. Moderne Retrievalsysteme stellen dabei eine Möglichkeit dar, Funddaten über einen längeren Zeitraum systematisch zu speichern und bieten dem Nutzer gleichzeitig passende Werkzeuge für die Abfrage derselben. Im vorliegenden Beitrag wird der Entwurf eines solches Systems für rotationssymmetrische Keramikgefäße vorgestellt und einzelne Aspekte näher beleuchtet. Insbesondere die automatische Extraktion und Analyse spezifischer Eigenschaften der Gefäße sind dabei wichtig. Sie werden hauptsächlich aus der Analyse der Profillinie gewonnen, deren wichtigste Voraussetzung die Ausrichtung des Gefäßes an seiner Rotationsachse darstellt.
- WorkshopbeitragA Novel Approach to Real-Time Rendering of Large-Scale Terrains Employing Uniform Distance-Dependent Level of Detail and Chunked Clipmaps(GI VR / AR Workshop, 2023) Kühnert, Kurt; Uhlmann, Tom; Brunnett, Guido
- WorkshopbeitragProcedural Generation and Realtime Rendering of Waterbodies on Height-Map based Terrains(GI VR / AR Workshop, 2023) Wolf, Richard; Uhlmann, Tom; Brunnett, Guido