SegMatch: Segment based place recognition in 3D point clouds
01 May 2017-pp 5266-5272
TL;DR: It is quantitatively demonstrated that SegMatch can achieve accurate localization at a frequency of 1Hz on the largest sequence of the KITTI odometry dataset, and shown how this algorithm can reliably detect and close loops in real-time, during online operation.
Abstract: Place recognition in 3D data is a challenging task that has been commonly approached by adapting image-based solutions. Methods based on local features suffer from ambiguity and from robustness to environment changes while methods based on global features are viewpoint dependent. We propose SegMatch, a reliable place recognition algorithm based on the matching of 3D segments. Segments provide a good compromise between local and global descriptions, incorporating their strengths while reducing their individual drawbacks. SegMatch does not rely on assumptions of ‘perfect segmentation’, or on the existence of ‘objects’ in the environment, which allows for reliable execution on large scale, unstructured environments. We quantitatively demonstrate that SegMatch can achieve accurate localization at a frequency of 1Hz on the largest sequence of the KITTI odometry dataset. We furthermore show how this algorithm can reliably detect and close loops in real-time, during online operation. In addition, the source code for the SegMatch algorithm is made publicly available1.
Citations
More filters
01 Oct 2018
TL;DR: A lightweight and ground-optimized lidar odometry and mapping method, LeGO-LOAM, for realtime six degree-of-freedom pose estimation with ground vehicles and integrated into a SLAM framework to eliminate the pose estimation error caused by drift is integrated.
Abstract: We propose a lightweight and ground-optimized lidar odometry and mapping method, LeGO-LOAM, for realtime six degree-of-freedom pose estimation with ground vehicles. LeGO-LOAM is lightweight, as it can achieve realtime pose estimation on a low-power embedded system. LeGO-LOAM is ground-optimized, as it leverages the presence of a ground plane in its segmentation and optimization steps. We first apply point cloud segmentation to filter out noise, and feature extraction to obtain distinctive planar and edge features. A two-step Levenberg-Marquardt optimization method then uses the planar and edge features to solve different components of the six degree-of-freedom transformation across consecutive scans. We compare the performance of LeGO-LOAM with a state-of-the-art method, LOAM, using datasets gathered from variable-terrain environments with ground vehicles, and show that LeGO-LOAM achieves similar or better accuracy with reduced computational expense. We also integrate LeGO-LOAM into a SLAM framework to eliminate the pose estimation error caused by drift, which is tested using the KITTI dataset.
960 citations
Cites methods from "SegMatch: Segment based place recog..."
...A segmentation-based registration algorithm is proposed in [18]....
[...]
TL;DR: This paper presents this extended version of RTAB‐Map and its use in comparing, both quantitatively and qualitatively, a large selection of popular real‐world datasets, outlining strengths, and limitations of visual and lidar SLAM configurations from a practical perspective for autonomous navigation applications.
513 citations
Cites methods from "SegMatch: Segment based place recog..."
...In these lidar‐based SLAM approaches, only SegMatch can be used for multisession or multirobot mapping (Dubé et al., 2017)....
[...]
04 Oct 2018
TL;DR: Scan Context is proposed, a non-histogram-based global descriptor from 3D Light Detection and Ranging (LiDAR) scans that makes loop-detection invariant to LiDAR viewpoint changes so that loops can be detected in places such as reverse revisit and corner.
Abstract: Compared to diverse feature detectors and descriptors used for visual scenes, describing a place using structural information is relatively less reported. Recent advances in simultaneous localization and mapping (SLAM) provides dense 3D maps of the environment and the localization is proposed by diverse sensors. Toward the global localization based on the structural information, we propose Scan Context, a non-histogram-based global descriptor from 3D Light Detection and Ranging (LiDAR) scans. Unlike previously reported methods, the proposed approach directly records a 3D structure of a visible space from a sensor and does not rely on a histogram or on prior training. In addition, this approach proposes the use of a similarity score to calculate the distance between two scan contexts and also a two-phase search algorithm to efficiently detect a loop. Scan context and its search algorithm make loop-detection invariant to LiDAR viewpoint changes so that loops can be detected in places such as reverse revisit and corner. Scan context performance has been evaluated via various benchmark datasets of 3D LiDAR scans, and the proposed method shows a sufficiently improved performance.
399 citations
Cites methods from "SegMatch: Segment based place recog..."
...Recently, SegMatch [23] introduced a segment-based matching algorithm....
[...]
26 Jun 2018
TL;DR: A novel, dense approach to laserbased mapping that operates on three-dimensional point clouds obtained from rotating laser sensors is proposed that is efficient and enables real-time capable registration and is able to detect loop closures and to perform map updates in an online fashion.
Abstract: Accurate and reliable localization and mapping is a fundamental building block for most autonomous robots. For this purpose, we propose a novel, dense approach to laserbased mapping that operates on three-dimensional point clouds obtained from rotating laser sensors. We construct a surfel-based map and estimate the changes in the robot’s pose by exploiting the projective data association between the current scan and a rendered model view from that surfel map. For detection and verification of a loop closure, we leverage the map representation to compose a virtual view of the map before a potential loop closure, which enables a more robust detection even with low overlap between the scan and the already mapped areas. Our approach is efficient and enables real-time capable registration. At the same time, it is able to detect loop closures and to perform map updates in an online fashion. Our experiments show that we are able to estimate globally consistent maps in large scale environments solely based on point cloud data.
353 citations
Cites background from "SegMatch: Segment based place recog..."
...[5] investigated an approach that matches segments extracted from a scan to find loop closures via segment-based features....
[...]
08 Sep 2018
TL;DR: The 3DFeat-Net is proposed which learns both 3D feature detector and descriptor for point cloud matching using weak supervision and obtains state-of-the-art performance on these gravity-aligned datasets.
Abstract: In this paper, we propose the 3DFeat-Net which learns both 3D feature detector and descriptor for point cloud matching using weak supervision Unlike many existing works, we do not require manual annotation of matching point clusters Instead, we leverage on alignment and attention mechanisms to learn feature correspondences from GPS/INS tagged 3D point clouds without explicitly specifying them We create training and benchmark outdoor Lidar datasets, and experiments show that 3DFeat-Net obtains state-of-the-art performance on these gravity-aligned datasets
237 citations
References
More filters
[...]
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
79,257 citations
"SegMatch: Segment based place recog..." refers methods in this paper
...Random forests offer classification performance similar to the AdaBoost algorithm but are less sensitive to noise in the output label (such as a mis-labeled candidates) since they do not concentrate their efforts on misclassified candidates [24]....
[...]
TL;DR: New results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form that provide the basis for an automatic system that can solve the Location Determination Problem under difficult viewing.
Abstract: A new paradigm, Random Sample Consensus (RANSAC), for fitting a model to experimental data is introduced. RANSAC is capable of interpreting/smoothing data containing a significant percentage of gross errors, and is thus ideally suited for applications in automated image analysis where interpretation is based on the data provided by error-prone feature detectors. A major portion of this paper describes the application of RANSAC to the Location Determination Problem (LDP): Given an image depicting a set of landmarks with known locations, determine that point in space from which the image was obtained. In response to a RANSAC requirement, new results are derived on the minimum number of landmarks needed to obtain a solution, and algorithms are presented for computing these minimum-landmark solutions in closed form. These results provide the basis for an automatic system that can solve the LDP under difficult viewing
23,396 citations
"SegMatch: Segment based place recog..." refers methods in this paper
...The candidate matches are fed to a geometric-verification test using random sample consensus (RANSAC) [25]....
[...]
16 Jun 2012
TL;DR: The autonomous driving platform is used to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection, revealing that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world.
Abstract: Today, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advantage of our autonomous driving platform to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection. Our recording platform is equipped with four high resolution video cameras, a Velodyne laser scanner and a state-of-the-art localization system. Our benchmarks comprise 389 stereo and optical flow image pairs, stereo visual odometry sequences of 39.2 km length, and more than 200k 3D object annotations captured in cluttered scenarios (up to 15 cars and 30 pedestrians are visible per image). Results from state-of-the-art algorithms reveal that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world. Our goal is to reduce this bias by providing challenging benchmarks with novel difficulties to the computer vision community. Our benchmarks are available online at: www.cvlibs.net/datasets/kitti
11,283 citations
"SegMatch: Segment based place recog..." refers methods in this paper
...The proposed segment based algorithm is evaluated using the KITTI odometry dataset [26]....
[...]
09 May 2011
TL;DR: PCL (Point Cloud Library) is presented, an advanced and extensive approach to the subject of 3D perception that contains state-of-the art algorithms for: filtering, feature estimation, surface reconstruction, registration, model fitting and segmentation.
Abstract: With the advent of new, low-cost 3D sensing hardware such as the Kinect, and continued efforts in advanced point cloud processing, 3D perception gains more and more importance in robotics, as well as other fields. In this paper we present one of our most recent initiatives in the areas of point cloud perception: PCL (Point Cloud Library - http://pointclouds.org). PCL presents an advanced and extensive approach to the subject of 3D perception, and it's meant to provide support for all the common 3D building blocks that applications need. The library contains state-of-the art algorithms for: filtering, feature estimation, surface reconstruction, registration, model fitting and segmentation. PCL is supported by an international community of robotics and perception researchers. We provide a brief walkthrough of PCL including its algorithmic capabilities and implementation strategies.
4,501 citations
"SegMatch: Segment based place recog..." refers methods in this paper
...Keypoints are selected in the target and source clouds using the Harris 3D keypoint extractor of the PCL library [27]....
[...]
12 May 2009
TL;DR: This paper modifications their mathematical expressions and performs a rigorous analysis on their robustness and complexity for the problem of 3D registration for overlapping point cloud views, and proposes an algorithm for the online computation of FPFH features for realtime applications.
Abstract: In our recent work [1], [2], we proposed Point Feature Histograms (PFH) as robust multi-dimensional features which describe the local geometry around a point p for 3D point cloud datasets. In this paper, we modify their mathematical expressions and perform a rigorous analysis on their robustness and complexity for the problem of 3D registration for overlapping point cloud views. More concretely, we present several optimizations that reduce their computation times drastically by either caching previously computed values or by revising their theoretical formulations. The latter results in a new type of local features, called Fast Point Feature Histograms (FPFH), which retain most of the discriminative power of the PFH. Moreover, we propose an algorithm for the online computation of FPFH features for realtime applications. To validate our results we demonstrate their efficiency for 3D registration and propose a new sample consensus based method for bringing two datasets into the convergence basin of a local non-linear optimizer: SAC-IA (SAmple Consensus Initial Alignment).
3,138 citations
"SegMatch: Segment based place recog..." refers methods in this paper
...This includes features such as Fast Point Feature Histogram (FPFH) [7] which will also be employed later in this work....
[...]
...Each keypoint is described using the fast point feature histogram (FPFH) with a radius of 0.4 meters [7]....
[...]
...This includes features such as fast point feature histogram (FPFH) [7] which will also be employed later in this work....
[...]