Showing papers on "Line segment published in 2003"

Estimating 3D hand pose from a cluttered image

Abstract: A method is proposed that can generate a ranked list of plausible three-dimensional hand configurations that best match an input image. Hand pose estimation is formulated as an image database indexing problem, where the closest matches for an input hand image are retrieved from a large database of synthetic hand images. In contrast to previous approaches, the system can function in the presence of clutter, thanks to two novel clutter-tolerant indexing methods. First, a computationally efficient approximation of the image-to-model chamfer distance is obtained by embedding binary edge images into a high-dimensional Euclidean space. Second, a general-purpose, probabilistic line matching method identifies those line segment correspondences between model and input images that are the least likely to have occurred by chance. The performance of this clutter tolerant approach is demonstrated in quantitative experiments with hundreds of real hand images.

Weighted line fitting algorithms for mobile robot map building and efficient data representation

Abstract: This paper presents an algorithm to find the line-based map that best fits sets of two-dimensional range scan data. To construct the map, we first provide an accurate means to fit a line segment to a set of uncertain points via maximum likelihood formalism. This scheme weights each point's influence on the fit according to its uncertainty, which is derived from sensor noise models. We also provide closed-form formulas for the covariance of the line fit, along with methods to transform line coordinates and covariances across robot poses. A Chi-squared based criterion for "knitting" together sufficiently similar lines can be used to merge lines directly (as we demonstrate) or as part of the framework for a line-based SLAM implementation. Experiments using a Sick LMS-200 laser scanner and a Nomad 200 mobile robot illustrate the effectiveness of the algorithm.

Near-optimal detection of geometric objects by fast multiscale methods

Abstract: We construct detectors for "geometric" objects in noisy data. Examples include a detector for presence of a line segment of unknown length, position, and orientation in two-dimensional image data with additive white Gaussian noise. We focus on the following two issues. i) The optimal detection threshold-i.e., the signal strength below which no method of detection can be successful for large dataset size n. ii) The optimal computational complexity of a near-optimal detector, i.e., the complexity required to detect signals slightly exceeding the detection threshold. We describe a general approach to such problems which covers several classes of geometrically defined signals; for example, with one-dimensional data, signals having elevated mean on an interval, and, in d-dimensional data, signals with elevated mean on a rectangle, a ball, or an ellipsoid. In all these problems, we show that a naive or straightforward approach leads to detector thresholds and algorithms which are asymptotically far away from optimal. At the same time, a multiscale geometric analysis of these classes of objects allows us to derive asymptotically optimal detection thresholds and fast algorithms for near-optimal detectors.

Matching planar maps

Abstract: The subject of this paper are algorithms for measuring the similarity of patterns of line segments in the plane, a standard problem in, e.g. computer vision, geographic information systems, etc. More precisely, we will define feasible distance measures that reflect how close a given pattern H is to some part of a larger pattern G. These distance measures are generalizations of the well known Frechet distance for curves. We will first give an efficient algorithm for the case that H is a polygonal curve and G is a geometric graph. Then, slightly relaxing the definition of distance measure we will give an algorithm for the general case where both, H and G, are geometric graphs.

Methods and systems for downloading and viewing maps

Abstract: Embodiments of the present invention comprise a method for transmitting map data, a method for displaying map data, a system for processing and displaying map data, and a method for rendering line segments on a pixel display. A preferred method for transmitting map data comprises receiving, layering [220], and simplifying map data and transmitting some of the simplified data [240]. A preferred method for displaying map data comprises receiving compressed map data [250], decompressing the received data [3], and rendering the decompressed data [3] on a display device. A preferred system for processing and displaying map data comprises a map database [110], a map generation sub-system, a map rendering sub-system, and a display device. A preferred method for rendering line segments on a pixel display comprises, for a line segment from a first endpoint to a second endpoint, rounding off the slope of the line segment and calculating pixel locations based on that rounded off slope.

Computing the Hausdorff Distance of Geometric Patterns and Shapes

Abstract: A very natural distance measure for comparing shapes and patterns is the Hausdorff distance. In this article we develop algorithms for computing the Hausdorff distance in a very general case in which geometric objects are represented by finite collections of k-dimensional simplices in d-dimensional space. The algorithms are polynomial in the size of the input,a ssuming d is a constant. In addition,w e present more efficient algorithms for special cases like sets of points,or line segments,or triangulated surfaces in three dimensions.

General Spatial Curve Joint for Rail Guided Vehicles: Kinematics and Dynamics

Abstract: In the framework of multibody dynamics for rail-guided vehicleapplications, a new kinematic constraint is proposed, whichenforces that a point of a body follows a reference path while thebody maintains a prescribed orientation relative to a Frenet frameassociated to the spatial track curve. Depending on the specificapplication, the tracks of rail-guided vehicle are described byanalytical line segments or by parametric curves. For railway andlight track vehicles, the nominal geometry of the track isgenerally done by putting together straight and circular tracksegments, interconnected by transition track segments that ensurethe continuity of the first and second derivatives of the railwayin the transition points. For other applications, the definitionof the track is done using parametric curves that interpolate agiven number of control points. In both cases, the completecharacterization of the tracks also requires the definition of thecant angle variation, which is done with respect to the osculatingplane associated to the curve. The track models for multibodyanalysis must be in the form of parameterized curves, where thenominal geometry is obtained as a function of a parameterassociated to the curve length. The descriptions adopted hereensure, not only that the type of continuity of the original trackdefinition is maintained, but also that no unwanted deviationsfrom the nominal track geometry are observed, which can beperceived in the dynamic analysis as track perturbations. In thiswork different types of track geometric descriptions arediscussed. The application of cubic splines, to interpolate a setof points used to describe the track geometry, leads to undesiredoscillations in the model. The parameterization of analyticalsegments of straight, circular and cubic polynomial track segmentsdoes not introduce such oscillations on the track geometry but itis rather complex for the description of railways with largeslopes or with vertical curves. Splines with tension minimize theundesired oscillations of the interpolated curve that describesthe railway track nominal geometry, but the curve segmentparameters are not proportional to the length of the track. It isproposed here that the nominal geometry of the track is describedby a discreet number of points, which are organized in a tabularmanner as function of a parameter that is the length of the trackmeasured from its origin to a given point. For each entry, thetable also includes the vectors defining the Frenet frames and thederivatives required by the track constraint. The multibody codeinterpolates such table to obtain all required geometriccharacteristics of the track. With applications to a rollercoaster, the suitability of this description is discussed in termsof the choice of original parametric curves used to construct thetable, the size of the length parameter step adopted for the tableand the efficiency of the computer implementation of theformulation.

Radar device for a vehicle

Abstract: A radar device mounted to a vehicle includes a camera for obtaining images including the road surface in front of or behind the vehicle on which it is mounted, a sensor having for obtaining at least positional information on a target object of detection such as another vehicle in front or behind and a control unit for correcting the direction of the center axis of the sensor based on the image obtained by the camera. The control unit detects a line segment along a lane in which the vehicle is traveling, detects a vector indicative of the direction on a road-fixed coordinate system of the obtained line segment, and controls correction of horizontal and vertical directions of the center axis of the sensor so as to coincide with the direction of the detected vector.

Reshaping freehand drawn lines and shapes in an electronic document

Abstract: The invention improves the appearance of freehand drawn lines and shapes in an electronic document by first recognizing freehand drawn lines and shapes and generating a line made up of sequential straight line segments for the freehand drawn line when the line does not form a closed line and generating a multiple straight-line-segment shape when the line forms a closed line. If a multiple segment shape is being reshaped, a basic shape is selected from reference ideal shapes as the basic shape of the multiple segment shape. The basic shape is adjusted to provide a specific shape as an improved shape for the freehand drawn shape. The recognition of the freehand drawn lines and shapes is accomplished by comparing source segments of a source freehand drawn line to a straight line and substituting a straight line segment for a source segment if the deviation between the source segment and the straight line is below a predetermined value. Sequential source segments of a source freehand drawn line are evaluated to determine if they are an angle segment. A segment pair of sequential source line segments are defined as an angle segment having two straight line segments intersecting at a common end point if both source segments of the segment pair are within a predetermined deviation value from a straight line. The straight line segments and angle segments are combined to form a multiple segment line if the line does not close on itself and a multiple segment shape if the line does close on itself.

Robust Reconstruction of Building Models from Three-Dimensional Line Segments

Abstract: tor has to estimate the location of hidden corners from the conThis paper presents a novel method for semi-automatically jugate images. This procedure is tedious and inefficient and constructing building models from photogrammetric 3D line has a limited accuracy, especially for connected buildings in segments of buildings, i.e., their roof edges. The method, which densely built-up areas. we call “Split-Merge-Shape” (SMS), can treat both complete Weidner (1997), Haala and Brenner (1998), and Brenner line segments as well as incomplete line segments due to image (2000) proposed the use of digital surface models (DSMS )t o reocclusions. The proposed method is comprised of five major construct 3D building models. The DSM data can be generated parts: (1) the creation of the Region of Interest (ROI) and pre- automatically using stereo-pairs, or can be obtained from airprocessing, (2) splitting the model by using the 3D line seg- borne laser scanning (Lohr, 1996). The problem is that precise ments to construct a combination of roof primitives, (3) merging buildingboundaries cannotbewell defineddue tothesegmenconnected roof primitives to complete the boundary of each tation of DSMS. Therefore, other complementary data, such as building, (4) shaping each building rooftop by connected ground plans of the building outlines, are necessary to assure coplanar analysis and coplanar fitting, and (5) quality assur- the reconstruction. This limits the practicability of the ance. The experimental results indicate that the proposed approach. method can soundly rebuild the topology from the 3D line In order to increase efficiency, Fischer et al. (1998) and segments and reconstruct building models with up to a 98

Uncertainty of Line Segments Extracted from Static SICK PLS Laser Scans

Abstract: Data fusion using Kalman filters requires reasonably good error models. Our intention to fuse line segments, corners and edges obtained from a laser scanner and from advanced sonars provided the motivation on the investigation of Sick PLS laser scanner range measurement reliability, and line segment estimation precision. We present an approach for fitting lines straight in the lasers polar coordinate system, which enables a simple estimation of line parameter covariance. We also develop systematic error models for line parameter estimation. Finally we measure our systematic and random error models experimentally, and show, that systematic errors can be larger than random ones.

Disk drive printed circuit board with component-dedicated alignment line indicators including inner and outer line segments

Abstract: A printed circuit board on which multiple component-dedicated alignment line indicators including parallel lines may be used to facilitate the evaluation and segregation process during the production of printed circuit board assemblies based on the alignment characteristics of mounted disk drive electrical components with respect to these parallel lines. Each electrical component defines a perimeter with edges defining a first and second lateral distances and corners defining a diagonal distance. The alignment line indicators include first and second inner line segments spaced apart a first inner spacing at least the first lateral distance and less than the diagonal distance. The alignment line indicators include third and fourth inner line segments spaced apart at least the second lateral distance and less than the diagonal distance. The alignment line indicators include first and second outer line segments spaced apart more than the first inner spacing and less than the diagonal distance.

Image processing method, image processing apparatus, computer program product and computer memory product

Abstract: A plurality of images are read in, two line segments which need be inherently parallel with each other in each of the images are designated, and a planar projective transform matrix is obtained from coordinates of end points of the line segments for parallelizing the line segments, thereby executing height normalization. Subsequently, totally four sets of corresponding points are obtained among three sequential images at regions where adjacent two images are overlapped, and matrix elements of planar projective transform matrix is obtained from the obtained corresponding points to calculate an stitch coefficient. Image stitching is executed by using the stitch coefficient. In stitching a plurality of images for stitching, it is possible to accurately stitch the images after the height is normalized among the images.

Digital altimetric map drawing method and device

Abstract: A digital map is created by a method comprising a step of dividing a basic drawing created by the UTM projection into thus created squares with predetermined intervals, further dividing the squares into small squares (4) by interpolating data lacking between squares and discontinuous data in each square, a step of creating digital data while relating the x, y coordinates of the small squares (4) to the altitudes obtained by survey, connecting the small squares (4) at the same altitude through straight lines one by one to draw a first altimetric map (5) where contour lines (6) are composed of line segment sequences, and a step of drawing a second altimetric map (7) where contour lines (6) are formed of curves smoother than the contour lines (6) formed of the line segment sequences by mathematically smoothing the contour lines (6) of the first altimetric map (5). Thus, a digital altimetric map where contour lines (6) are expressed by smooth curves can be drawn in a short time.

Line segment distribution of sketches for Persian signature recognition

Abstract: A novel fast method for line segment extraction based on chain code representation of thinned sketches (or edge maps) is presented and exploited for Persian signature recognition. The method has a parallel nature and can be employed on parallel machines. It breaks the macro chains into several micro chains after applying shifting, smoothing and differentiating. The micro chains are then approximated by straight line segments. Length and position distributions of the extracted line segments are used to make a compact feature vector for Iranian cursive signature. The feature vector is invariant under affine transforms and can be used effectively in paperless office projects. Experimental results show fast response and accurate recognition/retrieval rate.

Sweepline the music

Abstract: The problem of matching sets of points or sets of horizontal line segments in plane under translations is considered. For finding the exact occurrences of a point set of size m within another point set of size n we give an algorithm with running time O(mn), and for finding partial occurrences an algorithm with running time O(mnlogm). To find the largest overlap between two line segment patterns we develop an algorithm with running time O(mnlog(mn)). All algorithms are based on a simple sweepline traversal of one of the patterns in the lexicographic order. The motivation for the problems studied comes from music retrieval and analysis.

Shrouded flexible packages

Abstract: A shrouded flexible package is provided with an improved continuous laser score line. The score line has end portions adjacent the side seals of the package, which are located above fastener tracks which are enclosed by a shroud portion of the package. The score line contains downwardly and inwardly converging segments joined to a medial score line segment extending along side and generally below the fastener tracks. The score line is preferably formed with a laser energy source.

Constructing a dem from grid-based data by computing intermediate contours

Abstract: We present a technique for creating a digital elevation model (DEM) from grid-based contour data. The method computes new, intermediate contours in between existing isolines. These are found by finding the shortest line segment that connects points on two neighboring contours with differing elevations. The midpoint of the line segment becomes a point on the intermediate contour. The contours are completed by connecting individual points. The new contours are then used as data for successive iterations, until an initial surface is formed. Peaks are computed by Hermite splines that follow the slope trend. Gaussian smoothing is applied to the entire surface or only to newly computed elevations, yielding an approximated or interpolated surface, respectively. The DEMs are tested with quantitative methods, and are shown to compare favorably to well established algorithms.

Automated weld location system for vehicles

Abstract: An automatically weld locating system locates welds on a subassembly including first and second components. First and second finite element analysis models of the first and second components are retrieved. Edges of the first component are located. An outline of the first component is translated in a direction that is normal to its edge in its plane within a predetermined edge distance. A line segment of the first component is retrieved. Welds are created on the line segment with a predetermined maximum spacing and with a predetermined weld tolerance. The retrieving, determining and creating steps are repeated for additional line segments of the first component. The line segments of the second component are also processed. Welds that are within a predetermined minimum spacing are deleted.

Fast line extraction from digital images using line segments

Abstract: This paper presents a fast line extraction method using the line segments found in digital images. A digital line can be decomposed into line segments, which consist of continuous edge pixels, in four directions. The directions of the line segments are varied and limited by the relationship between the line segments and the slopes of analog lines. The proposed method attains high speed and accuracy by tracking each line segment in the same direction which comes from the relationship. Experimental results are included to show that the proposed method can achieve high accuracy with a large reduction in the computation time and has robustness in the presence of noise. © 2003 Wiley Periodicals, Inc. Syst Comp Jpn, 34(10): 76–89, 2003; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10124

Scan matching based on CLS relationships

Abstract: Position estimation based on scan matching is a type of popular approaches for mobile robot localization in indoor office-like environments. Global scan matching and local scan matching are two basic position estimation problems. Global scan matching is subject to global localization for mobile robot and local scan matching is used to deal with tracking mobile robot position over time. Global localization based on scan matching is represented in this paper. A global map is built to represent whole environment feature and a local map is built to represent current range scan. Global map and local map consist of a lot of line segments. Complete line segment that represents a complete environment object is singled out and used to match between local map and global map. Line segments are sorted counterclockwise in two maps. This type of ordinal map improves the searching efficiency of matching and localization algorithm is timesaving. In addition, matching between current range scan and global map is based on relative position relationships of line segments in local and global map. Global localization based on relative position relationship avoids frequent coordinates transformation and lowers computational cost. All these techniques have been implemented on our mobile robot ATRVII equipped with 2D laser range scanner SICK.

Fault location algorithms for super high voltage power transmission lines

Abstract: This paper presents a new approach for calculation of fault location on high voltage transmission lines. The proposed fault location algorithm utilizes statistical information about the equivalent impedances of the system at the unmonitored end of the transmission line. Knowledge about the distribution laws of these values or their numerical characteristics, which are more accessible for practical use, results in more accurate fault location for lines with grounded neutral, especially in case of distant short circuit through the large transient resistance. The proposed algorithm is based on modelling of the faulted line and the method of Monte-Carlo. The utilized line model with distributed parameters is described by two-port network theory equations. The algorithm automatically eliminates the effect of line shunt capacitance and calculates not only the expected value of the distance to the fault, but also another important additional characteristic for the fault location, namely, the length of the line segment, where short circuit may have occurred. Furthermore, the possibility to reduce the costs on the inspection of transmission line faulted segment and fault point location is described in the paper.

Discrete Morphology with Line Structuring Elements

Abstract: Discrete morphological operations with line segments are notoriously hard to implement. In this paper we study different possible implementations of the line structuring element, compare them, and examine their rotation and translation invariance in the continuous domain. That is, we are interested in obtaining a morphological operator that is invariant to rotations and translations of the image before sampling.