Pair-wise Registration of 3D/Color Data Sets with ICP

Douadi, Lounis; Aldon, Marie-José; Crosnier, André

doi:10.1109/iros.2006.282551

Cited by 13 publications

(9 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to differing weights for each point, for an ALS solution, the horizontal uncertainty can be 2-5 times larger than the vertical uncertainty [31]. Therefore, based on the original Besl and McKay formulation, several ICP variants have been proposed, which include additional properties such as color [27], invariant geometric features [28], inter-point distance [29], the compatibility of normal, or surface normal [26] in the distance metric. In a review paper, Rusinkiewicz and Levoy [43] classified the proposed variants of the ICP algorithm as affecting one of six subtasks: 1) selection; 2) matching; 3) weighting; 4) outlier removal; 5) error metric; and 6) minimization.…”

Section: ) Transformationmentioning

confidence: 99%

Change Detection From Differential Airborne LiDAR Using a Weighted Anisotropic Iterative Closest Point Algorithm

Zhang

Glennie

Kusari

2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Differential light detection and ranging (LiDAR) from repeated surveys has recently emerged as an effective tool to measure the three-dimensional (3-D) change. Currently, the primary method for determining 3-D change from LiDAR is through the use of the iterative closest point (ICP) algorithm and its variants, with a simplistic assumption of a uniform accuracy for the entire LiDAR point cloud. This common practice ignores the localization anisotropy and results in local convergence and spurious error estimation. To rigorously determine spatial change, this paper introduces an anisotropic-weighted ICP (A-ICP) algorithm, and proposes to model the random error for every LiDAR observation in the differential point cloud, and use this as a priori weights in the ICP algorithm. The implementation is evaluated by qualitatively and quantitatively comparing the estimation performance on point clouds with synthetic fault ruptures between standard ICP and A-ICP algorithm. As a further enhancement, we also present a moving window technique to improve A-ICP. Practical application of the combined moving window A-ICP technique is evaluated by estimating post-earthquake slip for the 2010 El Mayor-Cucapah Earthquake (EMC) using pre-and postevent LiDAR. Based on the analysis, moving window A-ICP is able to better estimate the synthetic surface ruptures, and provides a smoother estimate of actual displacement for the EMC earthquake.Index Terms-Change detection, earthquake, iterative closest point (ICP), light detection and ranging (LiDAR), moving window

show abstract

Section: ) Transformationmentioning

confidence: 99%

Change Detection From Differential Airborne LiDAR Using a Weighted Anisotropic Iterative Closest Point Algorithm

Zhang

Glennie

Kusari

2015

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Druon et al [7] segment point clouds based on the hue component of the HSV color space, then perform ICP while requiring matching points to belong to the same color class. Douadi et al [6] incorporate both geometric and color information into the distance metric used by ICP. Huhle et al [14] register scans of 3D point data by extending the standard metric with color information using Gaussian mixture models in a color space.…”

Section: Related Workmentioning

confidence: 99%

Replacing Projective Data Association with Lucas-Kanade for KinectFusion

Peasley

Birchfield

2013

2013 IEEE International Conference on Robotics and Automation

View full text Add to dashboard Cite

Abstract-We propose to overcome a significant limitation of the KinectFusion algorithm, namely, its sole reliance upon geometric information to estimate camera pose. Our approach uses both geometric and color information in a direct manner that uses all the data in order to perform the association of data between two RGBD point clouds. Data association is performed by aligning the two color images associated with the two point clouds by estimating a projective warp using the Lucas-Kanade algorithm. This projective warp is then used to create a correspondence map between the two point clouds, which is then used as the data association for a point-to-plane error minimization. This approach to correspondence allows camera tracking to be maintained through areas of low geometric features. We show that our proposed LKDA data association technique enables accurate scene reconstruction in environments in which low geometric texture causes the existing approach to fail, while at the same time demonstrating that the new technique does not adversely affect results in environments in which the existing technique succeeds.

show abstract

“…The non-adaptive category mostly involves strategies for dense 3D reconstruction from RGB-D images. The coefficient λ is computed only once and it is used to align all the following frames which contain similar information, such as [9], [16], [17], [5], [13], [27], [6]. A real-time RGB-D SLAM using a non-adaptive scale factor is found in [23], [25], [24] where λ was also set empirically to reflect the relative difference in metrics used for color and depth costs.…”

Section: Introductionmentioning

confidence: 99%

A proof that fusing measurements using Point-to-hyperplane registration is invariant to relative scale

Muñoz¹,

Comport²

2016

2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)

View full text Add to dashboard Cite

The objective of this paper is to demonstrate that the metric error between different types of measurements can be jointly minimized without a scaling factor for the estimation processes if a Point-to-hyperplane approach is employed. This article is an extension of previous work based on the Point-tohyperplane approach in 4 dimensions applied to pose estimation, where the proposed method minimized a fused error (3D Euclidean points + Image intensities) and it was experimentally demonstrated that the method is invariant to the choice of scale factor. In this paper, the invariance to the scale factor will be mathematically demonstrated. By doing this, it will be shown how the proposed method can further improve the convergence domain in 4D (or higher dimensions) and speed up the alignment between augmented frames (color + depth) whilst maintaining the robust and accurate properties of hybrid approaches when different types of measurements are available.

show abstract

Pair-wise Registration of 3D/Color Data Sets with ICP

Cited by 13 publications

References 15 publications

Change Detection From Differential Airborne LiDAR Using a Weighted Anisotropic Iterative Closest Point Algorithm

Change Detection From Differential Airborne LiDAR Using a Weighted Anisotropic Iterative Closest Point Algorithm

Replacing Projective Data Association with Lucas-Kanade for KinectFusion

A proof that fusing measurements using Point-to-hyperplane registration is invariant to relative scale

Contact Info

Product

Resources

About