Göm meny

Detection, Tracking and Recognition

Visual Tracking
The project investigates the contribution of color for the problem of visual tracking
COSPAL project (Completed Project)
In the COSPAL architecture we combine techniques from the field of artificial intelligence (AI) for symbolic reasoning and learning of artificial neural networks (ANN) for association of percepts and states in a bidirectional way. We establish feedback loops through the continuous and the symbolic parts of the system, which allow perception-action feedback at several levels in the system. After an initial bootstrapping phase, incremental learning techniques are used to train the system simultaneously at different levels, allowing adaptation and exploration. We expect the COSPAL architecture to allow the design of systems that show to a large extent autonomous behavior.
Embodied Visual Object Recognition
This project studies visual object recognition on robot platforms. Object recognition is an enabling competence for human-robot interaction in environments designed for people (e.g. homes, and offices). We do research on active learning for object model acquisition, active object recognition and visual search.
Moving Object Segmentation
This work is concerned with the development of fast online algorithms for autonomously segmenting moving objects from video
Object Pose Estimation Database
A database for evaluation of pose estimation accuracy.

Senast uppdaterad: 2015-05-21