Comparing ICP Variants on Real-World Data Sets
نویسندگان
چکیده
Many modern sensors used for mapping produce 3D point clouds, which are typically registered together using the iterative closest point (icp) algorithm. Because icp has many variants whose performances depend on the environment and the sensor, hundreds of variations have been published. However, no comparison frameworks are available, leading to an arduous selection of an appropriate variant for particular experimental conditions. The first contribution of this paper consists of a protocol that allows for a comparison between icp variants, taking into account a broad range of inputs. The second contribution is an opensource icp library, which is fast enough to be usable in multiple real-world applications, while being modular This work was supported by the EU FP7 IP projects Natural Human-Robot Cooperation in Dynamic Environments (ICT247870) and myCopter (FP7-AAT-2010-RTD-1). F. Pomerleau was supported by a fellowship from the Fonds québécois de recherche sur la nature et les technologies (FQRNT). François Pomerleau Autonomous System Lab, ETH Zentrum CLA E26, Tannenstrasse 3, 8092 Zurich, Switzerland E-mail: [email protected] Francis Colas Autonomous System Lab, ETH Zentrum CLA E26, Tannenstrasse 3, 8092 Zurich, Switzerland E-mail: [email protected] Roland Siegwart Autonomous System Lab, ETH Zentrum CLA E14.2, Tannenstrasse 3, 8092 Zurich, Switzerland E-mail: [email protected] Stéphane Magnenat Autonomous System Lab, ETH Zentrum CLA E24, Tannenstrasse 3, 8092 Zurich, Switzerland E-mail: stephane at magnenat dot net enough to ease comparison of multiple solutions. This paper presents two examples of these field applications. The last contribution is the comparison of two baseline icp variants using data sets that cover a rich variety of environments. Besides demonstrating the need for improved icp methods for natural, unstructured and information-deprived environments, these baseline variants also provide a solid basis to which novel solutions could be compared. The combination of our protocol, software, and baseline results demonstrate convincingly how open-source software can push forward the research in mapping and navigation.
منابع مشابه
Comparing ICP variants on real-world data sets - Open-source library and experimental protocol
Many modern sensors used for mapping produce 3D point clouds, which are typically registered together using the iterative closest point (ICP) algorithm. Because ICP has many variants whose performances depend on the environment and the sensor, hundreds of variations have been published. However, no comparison frameworks are available, leading to an arduous selection of an appropriate variant fo...
متن کاملIncremental Structured ICP Algorithm
Variants of the ICP algorithm are widely used in many visionbased applications, such as visual odometry, structure from motion, 3D reconstruction, or object segmentation. Establishing correct correspondences between two sets of 3D points, generated by stereo vision, needs to take those uncertainties into account. We propose a novel variant of the traditional ICP algorithm for solving the mentio...
متن کاملPair-Wise Range Image Registration: A Study in Outlier Classification
In this paper, we present a robustness study on several popular techniques for performing fine registration of partially overlapping 2.5D range image pairs, with a focus on model building. In our first set of tests, we qualitatively evaluate the output of several iterative closest point (ICP) variants on real-world data. Our second set of tests expands to include additional ICP variants and an ...
متن کاملGeneralized-ICP
In this paper we combine the Iterative Closest Point (’ICP’) and ‘point-to-plane ICP‘ algorithms into a single probabilistic framework. We then use this framework to model locally planar surface structure from both scans instead of just the ”model” scan as is typically done with the point-to-plane method. This can be thought of as ‘plane-to-plane’. The new approach is tested with both simulated...
متن کاملPerformance Analysis of Nearest Neighbor Algorithms for ICP Registration of 3-D Point Sets
There are many nearest neighbor algorithms tailormade for ICP, but most of them require special input data like range images or triangle meshes. We focus on efficient nearest neighbor algorithms that do not impose this limitation, and thus can also be used with 3-D point sets generated by structure-frommotion techniques. We shortly present the evaluated algorithms and introduce the modification...
متن کامل