Refine
Year of publication
- 2016 (17) (remove)
Document Type
- Conference Proceeding (9)
- Part of a Book (4)
- Article (3)
- Patent (1)
Has Fulltext
- no (17) (remove)
Keywords
- Virtual (TV) Studio (2)
- Functions of music (1)
- Gesture recognition (1)
- Habilitation (1)
- Interaction (1)
- Kinect (1)
- Learning (1)
- Lehre (1)
- Multimodal database (1)
- Myo (1)
Department/institution
- Fachbereich - Medien (17) (remove)
Bei einem Verfahren zum Erzeugen eines Trainingsbilds, welches ein zu erkennendes Objekt in einer natürlichen Objektumgebung zeigt, wird das Trainingsbild als synthetisches Bild durch Kombination eines von einer Kamera aufgenommenen Basisbilds und eines Template-Bilds erzeugt, indem mittels eines Shift-Map-Algorithmus ein Strukturmerkmal aus dem Basisbild entfernt und durch ein dem Template-Bild entnommenes Strukturmerkmal ersetzt wird.
In order to improve the interactivity between users and computers, recent technologies focus on incorporating gesture recognition into interactive systems. The aim of this article is to evaluate the effectiveness of using a Myo control armband and the Kinect 2 for recognition of gestures in order to interact with virtual objects in a weather report scenario. The Myo armband has an inertial measurement unit and is able to read electrical activity produced by skeletal muscles, which can be recognized as gestures, which are trained by machine learning. A Kinect sensor was used to build up a dataset which contains motion recordings of 8 different gestures and was also build up by a gesture training machine learning algorithm. Both input methods, the Kinect 2 and the Myo armband, were evaluated with the same interaction patterns in a user study, which allows a direct comparison and reveals benefits and limits of each technique.
Live video broadcasting requires a multitude of professional expertise to enable multi-camera productions. Robotic systems allow the automation of common and repeated tracking shots. However, predefined camera shots do not allow quick adjustments when required due to unpredictable events. We introduce a modular automated robotic camera control and video switch system, based on fundamental cinematographic rules. The actors' positions are provided by a markerless tracking system. In addition, sound levels of actors' lavalier microphones are used to analyse the current scene. An expert system determines appropriate camera angles and decides when to switch from one camera to another. A test production was conducted to observe the developed prototype in a live broadcast scenario and served as a video-demonstration for an evaluation.
Based on experience in teaching programming, we developed the integrated development environment (IDE) 5Code especially to support beginners. As a first step, a simple, understandable formula was developed how to advance from the problem to the program in 5 operative steps:
read it → get it → think it → note it → code it.
In order to reduce the cognitive load of the learners effectively, 5Code was designed such that all 5 steps are permanently presented, accessible and executable. Thus, learners are provided with the entire programming context from presentation of the task via own notes and annotations to the code area. Learners can mark and annotate any part of the given task’s text; these annotations can be edited as notes with own comments. Furthermore, the notes can be dragged into the code area, where they are shown as comments in the coding language. Any modifications in the comments are synchronized between notes and code. 5Code is implemented as a web-application. It is used in university introductory courses on object oriented programming.