Robust Object Detection at Regions of Interest with an Application in Ball Recognition

Sara Mitri, Simone Frintrop,
Kai Pervölz, Hartmut Surmann Fraunhofer Institute for Autonomous Intelligent Systems (AIS)
Schloss Birlinghoven,
D-53754 Sankt Augustin, Germany
simone.frintrop at ais.fraunhofer.de
- Andreas Nüchter University of Osnabrück
Institute for Computer Science
Knowledge-Based Systems Research Group
Albrechtstraße 28
D-49069 Osnabrück, Germany

Abstract:

In this paper, we present a new combination of a biologically inspired attention system (VOCUS - Visual Object detection with a CompUtational attention System) with a robust object detection method. As an application, we built a reliable system for ball recognition in the RoboCup context. Firstly, VOCUS finds regions of interest generating a hypothesis for possible locations of the ball. Secondly, a fast classifier verifies the hypothesis by detecting balls at regions of interest. The combination of both approaches makes the system highly robust and eliminates false detections. Furthermore, the system is quickly adaptable to balls in different scenarios: The complex classifier is universally applicable to balls in every context and the attention system improves the performance by learning scenario-specific features quickly from only a few training examples.