Part-based object detection into a hierarchy of image segmentations combining color and topology

Object detection is one of the key components in computer vision systems. Current research on this topic has shifted from holistic approaches to representations of individual object parts linked by structural information. Along this line of research, this paper presents a novel part-based approach for automatic object detection using 2D images. The approach encodes the visual structures of the object to be detected and the image by a 2D combinatorial map and a combinatorial pyramid, respectively. Within this framework, we propose to perform the searching of the object as an error-tolerant submap isomorphism that will be conducted at the different layers of the pyramid. The approach has been applied to the detection of visual landmarks for mobile robotics self-localization. Experimental results show the good performance and robustness of the approach in the presence of partial occlusions, uneven illumination and 3-dimensional rotations.

► An algorithm for error-tolerant submap isomorphism is proposed.
► The scene is represented at different levels of abstraction as a combinatorial pyramid.
► Top-down filtering is applied to restrict the searching of the template inside the pyramid.
► Object topology determines the arcs of the maps associated to the template and scene.
► Map arcs are attributed with photometric features.