TITEL

Scene exploration and object inspection for mobile robots in indoor environments

SPREKER

Maja Rudinac, promovenda, TU Delft

ABSTRACT

In this presentation we will present a novel framework for scene exploration and object inspection for a low-cost mobile robot platform equipped with a single webcam. This framework can be especially useful for robots working in dynamic environments. The following modules were implemented and utilized: object localization, object database, object recognition and robot navigation. As a first step the scene is inspected and interesting objects are localized using our proposed method for saliency-based segmentation, after which recognition of the localized objects is performed. An object database is constructed by capturing several multiple views for each object.

For the recognition, we propose a fast and robust descriptor for multiple-view object recognition using a small number of training examples. In order to design a descriptor to be discriminative between many different object appearances, we base it on a combination of invariant color, edge and texture descriptors. We use a color descriptor based on a HSV histogram, as it is robust to size and position of the object, a gray-level cooccurrence matrix as texture descriptor and an edge histogram as shape descriptor. After extraction of feature vectors, we perform normalization on all feature vectors from the training database in order to increase the importance of the most dominant feature components and reduce the less dominant ones. If the object recognition module fails to find a good match from the database, the navigation module is activated and the robot follows a trajectory to acquire more information about the object by inspecting it from several viewpoints.

Results obtained by both simulation and real world experiments show that our framework is very suitable for robotic applications in indoor environments.

BIO

Maja Rudinac is a PhD student in the Biorobotics Lab at the Delft University of Technology. Her research interests cover a broad field of computer and robot vision as well as the applications of machine learning in robotics. The main idea of her thesis is the design of a robot vision system capable to detect and recognize specific objects and object classes in the indoor environment and learn their visual properties by interacting with them and inquiring a human supervisor. She is a member of the Esi project Falcon, which concentrates on a new generation of distribution centres and warehouses with a maximum degree of automation. Her part includes designing the vision and pattern recognition system for the automated picking and stacking of objects.

TAAL

Engels