A Concise Guide to Feature Histograms with Applications to LIDAR-Based Spacecraft Relative Navigation

Rhodes, Andrew; Christian, John A.; Evans, Thomas

doi:10.1007/s40295-016-0108-y

Cited by 16 publications

(28 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, mature techniques now exist for both recognizing and aligning objects in an observed 3D point-cloud with known 3D models of those same objects. A variety of 3D feature descriptors exist [14,15,16] for applications spanning home entertainment [6], precision agriculture [17], industrial and home robotics [18], space exploration [7,19,16],…”

Section: Sensor Development and Supportmentioning

confidence: 99%

“…Recent literature contains a variety of approaches for performing spacecraft RelNav using 3D point-clouds [22,25,26,27,19,28,29,30,16]. Most methods use the Iterative Closest Point (ICP) algorithm [31] or variant thereof [32,33,34,35] to align the sensed point-cloud with a known model.…”

Section: Uncorrelated Pose Estimates In Navigation Filtersmentioning

confidence: 99%

“…Consequently, the method and accuracy of ICP initialization for both initial acquisition and frame-to-frame tracking is of importance. Literature contains a variety of proposals for ICP initialization using methods such as polygonal aspect hashing [38], principal component analysis [39], template matching [28,29], and feature histograms [25,19,30,40,16].…”

Section: Uncorrelated Pose Estimates In Navigation Filtersmentioning

confidence: 99%

“…Methods of independent pose estimation from point-clouds may also encounter -and therefore must be robust to -situations of clutter, occlusions, or missing data. Examples using uncorrelated measurements has been shown using a popular feature descriptor OUR-CVFH with real-time performance [30,16].…”

Section: Uncorrelated Pose Estimates In Navigation Filtersmentioning

confidence: 99%

“…Instead of using a feature histogram, CS3 uses the time history of the scale-invariant LoG values as a function of scale for the feature descriptor. The scale-invariant LoG curve is calculated as [16]. For this dissertation, notation and terminology has been updated to maintain consistency and clarity of this document.…”

Section: Thriftmentioning

confidence: 99%

See 4 more Smart Citations

Utilization of Scale in Keypoint Detection and Feature Description

Rhodes¹

View full text Add to dashboard Cite

Ubiquitous availability of inexpensive three dimensional (3D) sensors has led to an abundance of keypoint detection and feature description techniques for point-clouds. While some recent methods utilize color along with geometric information, most only implicitly discuss-if not completely disregard-the information provided by scale. Scale is an inherent characteristic of any keypoint or feature that describes its physical size or region of support. Exploiting information provided by scale facilitates the processes of keypoint detection and feature description. A 3D scale-space, extended from robust and popular 2D methods, is constructed to diffuse a signal on triangulated meshes. Methods of scale-parameter estimation and a novel neighborhood definition are presented that improve the methods' robustness to noise and arbitrary mesh connectivity. Keypoint repeatability experiments show that a novel definition of the Laplace-Beltrami operator (LBO) leads to the most accurate scale-space. A point-cloud feature descriptor, popular in the robotics community and recently proposed for spacecraft relative navigation (RelNav), is modified to explicitly utilize scale in the description and matching processes. The Scaled Oriented Unique Clustered Viewpoint Feature Histogram (SOUR-CVFH) uses a cluster's scale to expedite the histogram matching procedure and increase pose estimation accuracy. SOUR-CVFH is demonstrated in experiments of (1) object recognition in both isolated and cluttered scenes and (2) simulated RelNav of a spacecraft to a asteroid.

show abstract

Section: Sensor Development and Supportmentioning

confidence: 99%

Section: Uncorrelated Pose Estimates In Navigation Filtersmentioning

confidence: 99%

Section: Uncorrelated Pose Estimates In Navigation Filtersmentioning

confidence: 99%

Section: Uncorrelated Pose Estimates In Navigation Filtersmentioning

confidence: 99%

Section: Thriftmentioning

confidence: 99%

See 3 more Smart Citations

Utilization of Scale in Keypoint Detection and Feature Description

Rhodes¹

View full text Add to dashboard Cite

show abstract

Evaluating 3D local descriptors and recursive filtering schemes for LIDAR‐based uncooperative relative space navigation

Kechagias‐Stamatis

Aouf

Dubanchet³

2019

Journal of Field Robotics

View full text Add to dashboard Cite

We propose a Light Detection and Ranging (LIDAR) based relative navigation scheme that is appropriate for uncooperative relative space navigation applications. Our technique combines the encoding power of the 3D local descriptors that are matched exploiting a correspondence grouping scheme, with the robust rigid transformation estimation capability of the proposed adaptive recursive filtering techniques. Trials evaluate several current state-of-the-art 3D local descriptors and recursive filtering techniques on a number of both real and simulated scenarios that involve various space objects including satellites and asteroids. Results demonstrate that the proposed architecture affords a 50% odometry accuracy improvement over current solutions, while also affording a low computational burden. From our trials we conclude that HoD-S combined with the adaptive αβ filtering poses the most appealing combination for the majority of the scenarios evaluated, as it combines high quality odometry with a low processing burden.

show abstract

Accurate Pose Tracking for Uncooperative Targets via Data Fusion of Laser Scanner and Optical Camera

Zhang

Wang

et al. 2022

J Astronaut Sci

View full text Add to dashboard Cite

A Concise Guide to Feature Histograms with Applications to LIDAR-Based Spacecraft Relative Navigation

Cited by 16 publications

References 34 publications

Utilization of Scale in Keypoint Detection and Feature Description

Utilization of Scale in Keypoint Detection and Feature Description

Evaluating 3D local descriptors and recursive filtering schemes for LIDAR‐based uncooperative relative space navigation

Accurate Pose Tracking for Uncooperative Targets via Data Fusion of Laser Scanner and Optical Camera

Contact Info

Product

Resources

About