Histograms of Gaussian normal distribution for feature matching in clutter scenes
This addresses the problem of feature mismatches in cluttered scenes for applications like robotics or computer vision, but appears incremental as it builds on existing local reference frame methods.
The paper tackles 3D object recognition in cluttered scenes by proposing Histograms of Gaussian Normal Distribution (HGND) for feature matching, achieving a more reliable matching rate than state-of-the-art methods on datasets like Bologna and UWA.
3D feature descriptor provide information between corresponding models and scenes. 3D objection recognition in cluttered scenes, however, remains a largely unsolved problem. Practical applications impose several challenges which are not fully addressed by existing methods. Especially in cluttered scenes there are many feature mismatches between scenes and models. We therefore propose Histograms of Gaussian Normal Distribution (HGND) for extracting salient features on a local reference frame (LRF) that enables us to solve this problem. We propose a LRF on each local surface patches using the scatter matrix's eigenvectors. Then the HGND information of each salient point is calculated on the LRF, for which we use both the mesh and point data of the depth image. Experiments on 45 cluttered scenes of the Bologna Dataset and 50 cluttered scenes of the UWA Dataset are made to evaluate the robustness and descriptiveness of our HGND. Experiments carried out by us demonstrate that HGND obtains a more reliable matching rate than state-of-the-art approaches in cluttered situations.