Attention-Based Detection of Unknown Objects in a Situated Vision Framework

Abstract

We present an attention-based approach for the detection of unknown objects in a 3D environment. The ability to address individual objects in the environment without having previous knowledge about their properties or their identity is one important requirement of the Situated Vision theory. Based on saliency maps, our attention system determines the regions where objects are likely to be found; these are the proto-objects whose extent is refined by a 2D segmentation step. At the same time a 3D scene model is built from measurements of a depth camera. The detected objects are projected into the 3D scene, resulting in 3D object models which are incrementally updated. We show the validity of our approach in an RGB-D sequence recorded in an office environment.