Object Boundary Identification using Two-phase Incremental Clustering

Abstract

Abstract In order to perform the required task, understanding its environment is important for a service robot employed in indoor and outdoor environments. Learning the environment can be done using characteristic features of the environment such as the set of objects present there. Object identification and environment mapping is done using on board sensing devices like ultrasonic sensors, Lidars, and cameras. In this paper, we have employed a novel two-phase incremental clustering based approach to map object boundaries. Tracing of points on object boundaries has been done by exploring the environment in multiple paths using inexpensive ultrasonic sensors. The proposed two-phase algorithm performs much faster compared to the standard hierarchical agglomerative clustering algorithm. Effectiveness of the proposed algorithm is analyzed using a data set created with the help of a simulated environment. Analysis of the results obtained confirms that our approach is capable of capturing object boundaries that can be used as features to identify robotic environments.