Over the last few decades, we have seen an increase in both quality and quantity of 3D data sets. These data sets primarily come in the form of discrete points that are projected onto the surface of the object (point clouds) and are often derived from either LIDAR data (in which case, the surface points are actively sensed) or stereoscopic pairs (in which case, the surface points are derived using two dimensional (2D) feature matching algorithms). As these data sets become larger and denser, they also become harder to sift through which demands methods for automatic object classification through computer vision processes. In this paper we revisit a method of recognizing objects from their surface features known as Tripod Operators.[1] More specifically, we explore how matching multiple features from an unknown object to a known shape allows us to determine the extent to which the objects are similar using the resultant Digital Elevation Model (DEM) or Surface Elevation Model (SEM) that results from manipulation of point clouds.. We apply this method to determine how to separate objects of various classes.
We address the problem of searching large amounts of 3D point set data for specific objects of interest, as characterized
by their surface shape. Motivating applications include the detection of ambush weapons from a convoy and the search
for objects of interest on the ground from an aircraft. Such data can occur in the form of relatively unstructured point
sets or range images, and can be derived from a variety of sensors. We study here the performance of Tripod Operators
(TOs) on synthetic range image data containing the shape of an oil drum; a cylinder with planar top. Tripod Operators
are an efficient method of extracting coordinate invariant shape information from surface shape representations using
discrete samples extracted in a specially constrained manner. They can be used in a variety of ways as components of a
system which performs detection, recognition and localization of objects based on their surface shape. We present
experimental results which characterize the approximate accuracy of detection of the test shape as a function of the
accuracy of the surface shape data. This is motivated by the need for an estimate of the required accuracy of 3D
surveillance data to enable detection of specific shapes.
We address the automatic detection of Ambush weapons such as rocket propelled grenades (RPGs) from range data
which might be derived from multiple camera stereo with textured illumination or by other means. We describe our
initial work in a new project involving the efficient acquisition of 3D scene data as well as discrete point invariant
techniques to perform real time search for threats to a convoy. The shapes of the jump boundaries in the scene are
exploited in this paper, rather than on-surface points, due to the large error typical of depth measurement at long range
and the relatively high resolution obtainable in the transverse direction. We describe examples of the generation of a
novel range-scaled chain code for detecting and matching jump boundaries.
KEYWORDS: Shape analysis, Artillery, Sensors, Data modeling, Object recognition, Data processing, Data conversion, Visualization, Distance measurement, Analytical research
We introduce an approach to the efficient recognition of families of surface shapes in range images. This builds upon
earlier work on Tripod Operators (TOs), a method for extracting small sets of N points from 3D surface data in a
canonical way such that coordinate independent shape descriptions can be efficiently generated and compared. Using
TOs, a specific surface shape generates a signature which is a manifold of dimension ≤ 3 in a feature space of dimension
d = N - 3. A runtime application of a TO on surface data generates a d-vector whose distance from the signature
manifold is closely related to the likelihood of a match. Ordnance identification is a motivating application.
In order to use TOs for recognizing objects from large sets of known shapes, and families of shapes, we introduce the
use of manifold learning to represent the signature manifolds with piecewise analytic descriptions instead of discrete
point sets. We consider the example of generalizing the signatures of several artillery shells which are qualitatively the
same in shape, but metrically different. This can yield a signature that is only slightly more complex than the originals,
but enables efficient recognition of a continuous family of shapes.
Carl Henshaw, Keith Akins, N. Glenn Creamer, Matthew Faria, Cris Flagg, Matthew Hayden, Liam Healy, Brian Hrolenok, Jeffrey Johnson, Kimberly Lyons, Frank Pipitone, Fred Tasker
SUMO, the Spacecraft for the Universal Modification of Orbits, is a DARPA-sponsored spacecraft designed to provide orbital repositioning services to geosynchronous satellites. Such services may be needed to facilitate changing the geostationary slot of a satellite, to allow a satellite to be used until the propellant is expended instead of reserving propellant for a retirement burn, or to rescue a satellite stranded in geosynchronous transfer orbit due to a launch failure. Notably, SUMO is being designed to be compatible with the current geosynchronous satellite catalog, which implies that it does not require the customer spacecraft to have special docking fixtures, optical guides, or cooperative communications or pose sensors. In addition, the final approach and grapple will be performed autonomously. SUMO is being designed and built by the Naval Center for Space Technology, a division of the U.S. Naval Research Laboratory in Washington, DC. The nature of the SUMO concept mission leads to significant challenges in onboard spacecraft autonomy. Also, because research and development in machine vision, trajectory planning, and automation algorithms for SUMO is being pursued in parallel with flight software development, there are considerable challenges in prototyping and testing algorithms in situ and in transitioning these algorithms from laboratory form into software suitable for flight. This paper discusses these challenges, outlining the current SUMO design from the standpoint of flight algorithms and software. In particular, the design of the SUMO phase 1 laboratory demonstration software is described in detail. The proposed flight-like software architecture is also described.
KEYWORDS: Space operations, Robotics, Machine vision, Satellites, Sensors, Control systems, Analytical research, Aerospace engineering, Space robots, Algorithm development
SUMO, or Spacecraft for the Universal Modification of Orbits, is a risk reduction program for an advanced servicing spacecraft sponsored by the Defense Advanced Research Projects Agency and executed by the Naval Center for Space Technology at the Naval Research Laboratory in Washington, DC. The purpose of the program is to demonstrate the integration of machine vision, robotics, mechanisms, and autonomous control algorithms to accomplish autonomous rendezvous and grapple of a variety of interfaces traceable to future spacecraft servicing operations. The laboratory demonstration is being implemented in NRL’s Proximity Operations Test Facility, which provides precise six degree of freedom motion control for both the servicer and customer spacecraft platforms. This paper will describe the conceptual design of the SUMO advanced servicing spacecraft, a concept for a near term low-cost flight demonstration, as well as plans and status for the laboratory demonstration. In addition, component requirements for the various spacecraft subsystems will be discussed.
Results are described of an ongoing project whose goal is to provide advanced Computer Vision for small low flying autonomous aircraft. The work consists of two parts; range-based vision for object recognition and pose estimation, and monocular vision for navigation and collision avoidance. A wide variety of range imaging methods were considered for the former, and it was found that a promising approach is multi-ocular stereo with a pseudo-random texture projected with a xenon flash. This provides high range resolution despite motion, and can be small and light. The resulting range images, taken at a few meters range, would support the use of Tripod Operators, an efficient and general method for recognizing and localizing surface shapes in 6 DOF. This would provide the ability to recognize immediately upon encounter many kinds of targets. The monocular navigation system is based on finding corresponding features in successive images, and deducing from these the relative pose of the aircraft. Two methods are under development, based on horizon registration and point correspondences, respectively. The first can serve as a preprocessor for the second. This approach aims to continuously and accurately estimate the net motion of the vehicle.
A new method is described for obtaining accurate range images at high sped in a low-cost instrument. A prototype has been built and tested, and a patent application submitted. The method resembles grid-coding in that a camera and a stripe projector are directed at a scene, but the projector is different. It consists of a thin light source on the axis of a turntable, and a binary mask conforming to a cylinder coaxial with this. The mask has alternate black and clear stripes parallel to the axis. It forms a DeBruijn sequence, i.e., a sequence in which all possible sub- sequences of given length occur. No lens is used, deliberately smoothing the resulting illumination. In operation, the turntable rotates, and six consecutive images are taken at uniform intervals. A given pixel records six consecutive samples of a scene point. This six-vector, when normalized to unity to accommodate reflectance variations, is unique to the place in the sequence form which it came. Thus we can compute the position in 3-space of the surface point at which the pixel is looking. Observed accuracy is .1 millimeter at 30 centimeters range.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.