icVision: A modular vision system for cognitive robotics research

Abstract

We present an easy-to-use, modular framework for performing computer vision related tasks in support of cognitive robotics research on the iCub humanoid robot. The system performs object recognition and localization of objects in 3D space. One of the main design goals is to allow rapid prototyping and testing of vision software on the iCub and reduce development time by removing redundant and repetitive processes. The framework is implemented in C++, and uses YARP and HTTP for connectivity and OpenCV for the underlying image processing.