scholarly journals Learning part-based spatial models for laser-vision-based room categorization

2017 ◽  
Vol 36 (4) ◽  
pp. 379-402 ◽  
Author(s):  
Peter Uršič ◽  
Aleš Leonardis ◽  
Danijel Skočaj ◽  
Matej Kristan
Keyword(s):  
Spatial Model ◽  
Spatial Models ◽  
Range Data ◽  
Large Dataset ◽  
New Approach ◽  
Laser Range ◽  
Learning Technique ◽  
Laser Vision ◽  
Domestic Environments ◽  
Discriminative Dictionary Learning

Room categorization, that is, recognizing the functionality of a never before seen room, is a crucial capability for a household mobile robot. We present a new approach for room categorization that is based on two-dimensional laser range data. The method is based on a novel spatial model consisting of mid-level parts that are built on top of a low-level part-based representation. The approach is then fused with a vision-based method for room categorization, which is also based on a spatial model consisting of mid-level visual parts. In addition, we propose a new discriminative dictionary learning technique that is applied for part-dictionary selection in both laser-based and vision-based modalities. Finally, we present a comparative analysis between laser-based, vision-based, and laser-vision-fusion-based approaches in a uniform part-based framework, which is evaluated on a large dataset with several categories of rooms from domestic environments.

Evaluation of Safe Landing Area Determination Algorithms for Autonomous Rotorcraft Using Site Benchmarking

2013 ◽  
Vol 58 (3) ◽  
pp. 1-13 ◽  
Author(s):  
Marc D. Takahashi ◽  
Avi Abershitz ◽  
Rafael Rubinets ◽  
Matthew S. Whalley
Keyword(s):  
Landing Site ◽  
Flight Test ◽  
Test Method ◽  
Range Data ◽  
New Approach ◽  
Laser Range ◽  
Landing Zone ◽  
Rotorcraft Uav ◽  
High Level ◽  
Area Determination

An important element of rotorcraft UAV operations is safe landing area determination (SLAD), which is the ability to select desirable landing or load placement areas at unprepared sites. Effectively and reliably accomplishing this task would greatly enhance high-level autonomous capabilities in many operations such as search and rescue and resupply. This paper presents the results of quantitatively evaluating two SLAD algorithms using a new test method that incorporates a detailed survey of the test sites. These survey sites act as benchmarks against which the SLAD methods are compared. One SLAD algorithm is a new approach that uses laser range data to detect a set of potential landing points and uses fuzzy logic to rank them based on surface roughness, size, and terrain slope metrics. The second algorithm uses laser range data to optimize a performance index, based on sliding window statistics of surface slope and roughness over the landing zone, to select potential landing points. Flight-test data were collected at six sites ranging from simple to complex with multiple runs at each site. Both methods are evaluated based on their true-positive and false-positive rates and the consistency of their landing site selection.

Introduction

2018 ◽  
Author(s):  
Justin Buchler
Keyword(s):  
Spatial Model ◽  
Spatial Models ◽  
Spatial Theory ◽  
Roll Call ◽  
Policy Space ◽  
Policy Decisions ◽  
Roll Call Voting ◽  
Legislative Session ◽  
History Of ◽  
Conventional Models

Spatial theory is divided between models of elections and models of roll call voting, neither of which alone can explain congressional polarization. This chapter discusses the history of spatial theory, why it is important to link the two strands of spatial models, and the value of reversing the order of conventional models. Conventional models place an election before policy decisions are made. This chapter proposes a unified spatial model of Congress in which the conventional order is reversed. First, there is a legislative session, then an election in which voters respond retrospectively, not to the locations candidates claim to hold, but to the bundles of roll call votes that incumbents cast to incrementally adopt their locations in the policy space. Such a model is best suited to explaining three puzzles: why do legislators adopt extreme positions, how do they win, and what role do parties play in the process?

On filtering and compressing lageos laser range data

1983 ◽  
Vol 57 (1-4) ◽  
pp. 121-130 ◽  
Author(s):  
E. G. Masters ◽  
A. Stolz ◽  
B. Hirsch
Keyword(s):  
Range Data ◽  
Laser Range

scholarly journals The pencil of the 4th and 3rd order surfaces obtained as a harmonic equivalent of the pencil of quadrics through a 4th order space curve of the 1st category

2012 ◽  
Vol 10 (2) ◽  
pp. 193-207 ◽  
Author(s):  
Gordana Djukanovic ◽  
Marija Obradovic
Keyword(s):  
Cross Sections ◽  
Spatial Model ◽  
Spatial Models ◽  
Space Curve ◽  
Parabolic Cylinder ◽  
Triaxial Ellipsoid ◽  
Architectural Practice ◽  
Ordered Space ◽  
Pass Through ◽  
Frontal Projection

This paper shows the process of inverting the 4th ordered space curve of the first category with a self-intersecting point (with two planes of symmetry) and determining its harmonic equivalent. There are harmonic equivalents for five groups of surfaces obtained through the 4th order space curve of the 1st category. Mapping was done through a system of circular cross-sections. Both classical and relativistic geometry interpretations are presented. We also designed spatial models - a spatial model of the pencil of quadrics and a spatial model of the pencil of equivalent quadrics. Besides the boundary surfaces, one surface of the 3rd order, which is an equivalent to a triaxial ellipsoid, passes through this pencil of surface of the 4th order. The center of inversion is located on the contour of the ellipsoid. The parabolic cylinder is mapped into its equivalent, by mapping the contour parabola of the cylinder, in the frontal projection, in relation to the center and the sphere of inversion into a contour curve of the 4th order surface. The generating lines of the parabolic cylinder, which are in a projecting position and pass through the antipode, are mapped into circles (also in a projecting position) whose diameters are from the center of inversion to the contour line. The application of the 4th order surfaces in architectural practice is also presented.

scholarly journals The tourism space of Barlinek in the context of spatial models

Turyzm ◽  
2018 ◽  
Vol 28 (2) ◽  
pp. 31-40
Author(s):  
Bartłomiej Łuć
Keyword(s):  
Spatial Model ◽  
Swot Analysis ◽  
Spatial Models ◽  
Tourism Development ◽  
Field Studies ◽  
Tourism Attractions

This article describes the tourism space of Barlinek in the context of a spatial model. On the basis of field studies and analyses of tourism attractions and elements of tourism development, the author has compared and adapted the models developed by S. Liszewski (1995) and B. Włodarczyk (2011). Moreover the author has developed an extended SWOT analysis of Barlinek’s tourism space.

scholarly journals Introducing the Viewpoint in the Resource Description using Machine Learning

2021 ◽  
Author(s):  
Ouahiba Djama
Keyword(s):  
Machine Learning ◽  
Experimental Study ◽  
Search Engines ◽  
Machine Learning Technique ◽  
New Approach ◽  
Learning Technique ◽  
Resource Description

Search engines allow providing the user with data and information according to their interests and specialty. Thus, it is necessary to exploit descriptions of the resources, which take into consideration viewpoints. Generally, the resource descriptions are available in RDF (e.g., DBPedia of Wikipedia content). However, these descriptions do not take into consideration viewpoints. In this paper, we propose a new approach, which allows converting a classic RDF resource description to a resource description that takes into consideration viewpoints. To detect viewpoints in the document, a machine learning technique will be exploited on an instanced ontology. This latter allows representing the viewpoint in a given domain. An experimental study shows that the conversion of the classic RDF resource description to a resource description that takes into consideration viewpoints, allows giving very relevant responses to the user’s requests.

Variable Focus Three-Dimensional Laser Digitizing System

1995 ◽  
Author(s):  
David G. Alciatore ◽  
Ronald M. Pasquini
Keyword(s):  
Focal Length ◽  
Single Point ◽  
Three Dimensional ◽  
Range Data ◽  
State University ◽  
Focus Laser ◽  
New Approach ◽  
Colorado State University ◽  
Significant Step ◽  
Variable Focus

Abstract This paper describes a new three-dimensional scanning technology which is being developed at Colorado State University. Unlike other laser-based scanners which use active or passive triangulation to obtain surface range data, the new variable focus laser digitizing system (VFLDS) uses the principles of optical focal length to measure surface range data. This system should represent a significant step forward in speed and simplicity over current laser-based single point digitizing systems while retaining all of their advantages. The goal of the initial research presented here is to produce preliminary results which will prove the viability of this new approach.

Position Registration of Scanning Lasers for Experimental Spatial Dynamics Modeling

1994 ◽  
Author(s):  
David E. Montgomery ◽  
Robert L. West
Keyword(s):  
Spatial Dynamics ◽  
Spatial Models ◽  
Laser Doppler Vibrometer ◽  
Sample Surface ◽  
Surface Shape ◽  
Surface Velocity ◽  
Multiple Point ◽  
Range Data ◽  
Dynamics Modeling ◽  
Velocity Measurements

Abstract Experimental spatial dynamics modeling involves using scanning lasers to sample surface shape and dynamic response of structures in order to verify structural dynamics design intent. Formation of accurate spatial models from laser-based measurements requires that laser position and orientation be registered relative to a fixed coordinate system. A three point direct registration procedure is defined for shape modeling using laser range and mirror deflection angles. Surface velocity measurements with a portable laser Doppler vibrometer (LDV) also require registration, but range information is unavailable. A multiple point indirect registration algorithm for the LDV is described that involves minimizing three nonlinear equations. A simulated laser rangefinder (LRF) was developed for demonstrating three point direct registration. The 3-D geometry of a compressor housing was modeled by combining range data from multiple laser positions. The multiple point indirect registration was applied to 3-D velocity response field reconstruction of a composite plate from velocity measurements scanned at three separate positions.

Sign in / Sign up

Export Citation Format

Share Document