Most of the existing deep learning-based methods for 3D hand and human pose estimation
from a single depth map are based on a common framework that takes a 2D depth map and …

Acquiring the accurate three-dimensional (3-D) position of a target person around a robot
provides valuable information that is applicable to a wide range of robotic tasks, especially …

Human action recognition in 3D sequences is one of the most challenging and active areas
of research in the computer vision domain. However designing automatic systems that are …

In this paper, we optimize the placement of a camera in simulation in order to achieve a high
success rate for a pose estimation problem. This is achieved by simulating 2D images from a …

Coupled with machine learning, the use of signal processing techniques for big data
analysis, Internet of things, smart cities, security, and bio-informatics applications has …

Zusammenfassung Mit Chatbot, Augmented Reality (AR) und Künstlicher Intelligenz (KI)
durch die Industrie-Ausbildung: Mit dem augmentierten Lern-Tisch KoBeLU können Azubis …

Motion capture is the process of capturing and representing human motion in a form that is
suitable for further processing. Typically, human motion capture data is represented as a …

Abstract Kontextadaptive Dienste ermitteln auf Basis von Sensordaten die aktuelle Situation
des Nutzers. Dabei zählt neben Zeit, Identität und Aktivität vor allem der Aufenthaltsort zu …