A robust 3D unique descriptor for 3D object detection

Abstract

3D object recognition techniques based on local surface features are widely used for robust recognition. This paper proposes a 3D object recognition technique named 3DU using local features computed based on the uniqueness of keypoints. The technique first transforms 3D keypoints into another 3D space using Local Reference Frame. This transformation helps to find a list of probable matched keypoints of a query keypoint. Further, the proposed uniqueness-based descriptor rejects false matches to obtain the best match from the list. The proposed technique is validated by experiments on the Bologna dataset and achieved 100% recognition rate. In real-time scenarios, scenes obtained by an RGBD camera primarily consist of point density variation, cluttered surfaces, and occlusions. Most of the 3D descriptors have not been validated on such scenes in literature. We have analyzed 3DU and top-rated techniques on three RGBD datasets (dataset proposed in this paper, Challenge and Willow datasets). The results obtained by experiments on the proposed dataset show that the top-rated techniques have failed to handle RGBD data and 3DU has outperformed all compared techniques. The inferior performance of all techniques on complex datasets such as Challenge and Willow has elicited a need to develop robust training-free recognition techniques. The proposed dataset and code of the proposed technique 3DU are openly available in Mendeley (anonymously). http://dx.doi.org/10.17632/rfvzy9jn5v.1.