Object segmentation in cluttered and visually complex environments

Object segmentation is essential for systems that acquire object models online for robotic grasping. However, it remains a major technical challenge in visually complex and uncontrolled environments. Segmentation algorithms that rely on image features alone can perform poorly under certain lighting conditions, or if the object and the background have similar appearance. In parallel, known object segmentation algorithms that rely exclusively on three dimensional (3D) geometric data are derived under strong assumptions about the geometry of the scene. A promising approach to performing object segmentation is to use a combination of appearance and 3D features. In this paper, an object segmentation algorithm is presented that combines multiple appearance and geometric cues. The segmentation is formulated as a binary labeling problem. The Conditional Random Fields (CRF) framework is used to model the conditional probability of the labeling given the appearance and geometric data. The maximum a posteriori estimation of the labeling is obtained by minimizing the energy function corresponding to the CRF using graph cuts. A simple and efficient method for initializing the proposed algorithm is also presented. Experimental results have demonstrated the effectiveness of the proposed algorithm.