Showing papers on "Distance transform published in 2005"

Motion estimation in a plurality of temporally successive digital images

Abstract: Method for computer-aided motion estimation in a plurality of temporally successive digital images. The method includes first partial motion estimating in a second digital image relative to a first digital image temporally preceding the second digital image; constructing a reference image structure from the first digital image and the second digital image based on the first partial motion estimation, the reference image structure containing at least features from the first digital image and/or the second digital image; second partial motion estimating in a third digital image, which temporally succeeds the second digital image, relative to the second digital image; third partial motion estimating with a comparison of features of the third digital image and of the features contained in the reference image structure; and determining motion in the third digital image relative to the first digital image based on the third partial motion estimation, the second partial motion estimation and the first partial motion estimation.

Method for point-of-interest attraction in digital images

Abstract: A method for point-of-interest attraction towards an object pixel in a digital image by first performing object segmentation resulting in a contour-based or a region-based representation of object pixels and background pixels of the image. Secondly a vector distance transform image is computed comprising a vector displacement of each background pixel towards the nearest of said object pixels and the nearest object pixel for a given background pixel is determined by adding the vector displacement to said background pixel. Finally the point-of-interest is attracted towards the determined nearest object pixel.

Adaptive estimation of normals and surface area for discrete 3-D objects: application to snow binary data from X-ray tomography

Abstract: Estimating the normal vector field on the boundary of discrete three-dimensional objects is essential for rendering and image measurement problems. Most of the existing algorithms do not provide an accurate determination of the normal vector field for shapes that present edges. Here, we propose a new and simple computational method in order to obtain accurate results on all types of shapes, whatever their local convexity degree. The presented method is based on the gradient vector field analysis of the object distance map. This vector field is adaptively filtered around each surface voxel using angle and symmetry criteria so that as many relevant contributions as possible are accounted for. This optimizes the smoothing of digitization effects while preserving relevant details of the processed numerical object. Thanks to the precise normal field obtained, a projection method can be proposed to immediately derive the surface area from a raw discrete object. An empirical justification of the validity of such an algorithm in the continuous limit is also provided. Some results on simulated data and snow images from X-ray tomography are presented, compared to the Marching Cubes and Convex Hull results, and discussed.

Registration of first and second image data of an object

Abstract: The invention relates to the registration of ultrasound image data of an object and of three-dimensional second image data of the object. It is proposed to support a manual registration by an automatic process. Reference information defining a reference location in the ultrasound image are used, wherein the reference location is located on a surface of the object or is located at a defined distance to the surface of the object when the ultrasound detector generates the ultrasound image data. At least one surface point on the surface of the object or at a defined distance to the surface is identified in the second image. The ultrasound image data and the second image data are aligned with respect to one registration direction using the reference information and using information concerning a location of the surface point in the second image.

A multiresolution manifold distance for invariant image similarity

Abstract: Accounting for spatial image transformations is a requirement for multimedia problems such as video classification and retrieval, face/object recognition or the creation of image mosaics from video sequences. We analyze a transformation invariant metric recently proposed in the machine learning literature to measure the distance between image manifolds - the tangent distance (TD) - and show that it is closely related to alignment techniques from the motion analysis literature. Exposing these relationships results in benefits for the two domains. On one hand, it allows leveraging on the knowledge acquired in the alignment literature to build better classifiers. On the other, it provides a new interpretation of alignment techniques as one component of a decomposition that has interesting properties for the classification of video. In particular, we embed the TD into a multiresolution framework that makes it significantly less prone to local minima. The new metric - multiresolution tangent distance (MRTD) - can be easily combined with robust estimation procedures, and exhibits significantly higher invariance to image transformations than the TD and the Euclidean distance (ED). For classification, this translates into significant improvements in face recognition accuracy. For video characterization, it leads to a decomposition of image dissimilarity into "differences due to camera motion" plus "differences due to scene activity" that is useful for classification. Experimental results on a movie database indicate that the distance could be used as a basis for the extraction of semantic primitives such as action and romance.

Method and apparatus for controlling convergence distance for observation of 3D image

Abstract: A method and an apparatus for controlling a convergence distance for observation of a 3-D image are provided. The apparatus includes an object image storage, a guide image storage, an image synthesizer, and a controller. The object image storage stores object image data generated by photographing 3-dimensionally an object positioned at an object image point. The guide image storage stores guide image data generated by sequentially moving back and forth of the object image point and photographing 3-dimensionally a guide object. The image synthesizer receives the object image data and the guide image data to generate a synthesized image. The controller controls to sequentially output the guide image data and if a photographing distance of the guide image data coincides with an object image point, controls to stop the outputting of the guide image data so that a convergence distance of an observer may coincide with the object image point.

Image obtaining apparatus

Abstract: The image obtaining apparatus realizes a function of detecting the distance, tilt, and/or attitude of an object, irrespective of the distance between the image obtaining apparatus and the object, while reducing the size and the cost of the apparatus. The apparatus includes: an image obtaining camera which obtains an image of an object; a light projecting unit which projects each spotlight parallel or approximately parallel to the optical axis of the image obtaining camera onto the object; a detecting unit which detects the distance between the image obtaining camera and the object based on the position of the spotlight, projected by the light projecting unit, on the object image obtained by the image obtaining camera.

Change Detection by Frequency Decomposition: Wave-Back

Abstract: We introduce a frequency decomposition based background generation and subtraction method that explicitly harnesses the scene dynamics to improve segmentation. This allows us to correctly interpret scenes that would confound appearance-based algorithms by having high-variance background in the presence of low-contrast targets, specifically when the background pixels are well modeled as cyclostationary random processes. In other words, we can distinguish near-periodic temporal patterns induced by real-world physics: the motion of plants driven by wind, the action of waves on a beach, and the appearance of rotating objects. To capture the cyclostionary behavior of each pixel, we compute the frequency coefficients of the temporal variation of pixel intensity in moving windows. We maintain a background model that is composed of frequency coefficients, and we compare the background model with the current set of coefficients to obtain a distance map. To eliminate trail effect, we fuse the distance maps. WIAMIS 2005

Generalized sweep templates for implicit modeling

Abstract: A technique is presented for generating implicit sweep objects that support direct specification and manipulation of the surface with no topological limitations on the 2D sweep template. The novelty of this method is that the underlying scalar field has global properties which are desirable for interactive implicit solid modeling, allowing multiple sweep objects to be composed. A simple method for converting distance fields to bounded fields is described, allowing implicit sweep templates to be generated from any set of closed 2D contours (including "holes"). To avoid blending issues arising from gradient discontinuities, a general distance field approximation technique is presented which preserves sharp creases on the contour but is otherwise C2 smooth. Flat endcaps are introduced into the 3D sweep formulation, which is implemented in the context of an interactive hierarchical implicit volume modeling tool.

Object based boundary refinement method

Abstract: An object based boundary refinement method for object segmentation in digital images receives an image and a single initial object region of interest and performs refinement zone definition using the initial object regions of interest to generate refinement zones output. A directional edge enhancement is performed using the input image and the refinement zones to generate directional enhanced region of interest output. A radial detection is performed using the input image the refinement zones and the directional enhanced region of interest to generate radial detection mask output. In addition, a final shaping is performed using the radial detection mask having single object region output. A directional edge enhancement method determining pixel specific edge contrast enhancement direction according to the object structure direction near the pixel consists receives an image and refinement zones and performs 1D horizontal distance transform and 1D vertical distance transform using the refinement zones to generate horizontal distance map and vertical distance map outputs. A neighboring direction determination is performed using the horizontal distance map and the vertical distance map to generate neighboring image output. In addition, a directional edge contrast calculation using the neighboring image and input image having directional enhanced region of interest output.

Real-time meshless deformation

Abstract: In this paper, we articulate a meshless computational paradigm for the effective modeling, accurate physical simulation, and real-time animation of point-sampled solid objects. Both the interior and the boundary geometry of our volumetric object representation only consist of points, further extending the powerful and popular method of point-sampled surfaces to the volumetric setting. We build the point-based physical model upon continuum mechanics, which affords to effectively model the dynamic elastic behavior of point-based volumetric objects. When only surface samples are provided, our prototype system first generates both interior volumetric points and a volumetric distance field with octree structure. The physics of these volumetric points in a solid interior are simulated using the Meshless Moving Least Squares (MLS) shape functions. In sharp contrast to the traditional finite element method (FEM), the meshless property of our new technique expedites the accurate representation and precise simulation of the underlying discrete model, without the need of domain meshing. In order to achieve real-time simulations, we utilize the warped modal analysis method that is locally linear in nature but globally warped to account for rotational deformation. The structural simplicity and real-time performance of our meshless simulation framework are ideal for interactive animation and game/movie production. Copyright # 2005 John Wiley & Sons, Ltd.

Tree structure based 2D to 3D registration

Abstract: A system and method for tree structure based two-dimensional to three-dimensional registration are provided for receiving three-dimensional (3D) data indicative of vessels, segmenting the 3D data with a vessel tree, simulating two-dimensional (2D) data responsive to the segmented 3D data to form a simulated 2D image, receiving 2D data indicative of vessels, segmenting the received 2D data with a vessel tree, finding a distance transform of the segmented 2D data to form a 2D distance map image, considering a set of poses as state vectors with the corresponding probability computed using the similarity measure computation, re-sampling the pose vector to find a set of most probable poses and considering them as hypothesized poses, recomputing the projection and re-evaluating the probability of the hypothesized poses and updating the state vector until the optimal pose is found.

Determining scene distance in digital camera images

Abstract: A method for producing a distance map of scene distance values for a digital image captured by a digital camera includes capturing a first digital image of a scene under a first illumination condition, wherein the first digital image includes a plurality of pixels and the scene includes a plurality of scene objects located at different distances from the digital camera, capturing a second digital image of the scene under a second illumination condition that is different from the first illumination condition, and using the first and second digital images to produce a distance map having a plurality of scene distance values, wherein each scene distance value relates to the distance between the digital camera and the corresponding scene object.

Multisensor fusion for volumetric reconstruction of large outdoor areas

Abstract: This paper presents techniques for the merging of 3D data coming from different sensors, such as ground and aerial laser range scans. The 3D models created are reconstructed to give a photo-realistic scene enabling interactive virtual walkthroughs, measurements and scene change analysis. The reconstructed model is based on a weighted integration of all available data based on sensor-specific parameters such as noise level, accuracy, inclination and reflectivity of the target, spatial distribution of points. The geometry is robustly reconstructed with a volumetric approach. Once registered and weighed, all data is re-sampled in a multi-resolution distance field using out-of-core techniques. The final mesh is extracted by contouring the iso-surface with a feature preserving dual contouring algorithm. The paper shows results of the above technique applied to Verona (Italy) city centre.

Euclidean Skeletons of 3D Data Sets in Linear Time by the Integer Medial Axis Transform

Abstract: A general algorithm for computing Euclidean skeletons of 3D data sets in linear time is presented. These skeletons are defined in terms of a new concept, called the integer medial axis (IMA) transform. The algorithm is based upon the computation of 3D feature transforms, using a modification of an algorithm for Euclidean distance transforms. The skeletonization algorithm has a time complexity which is linear in the amount of voxels, and can be easily parallelized. The relation of the IMA skeleton to the usual definition in terms of centers of maximal disks is discussed.

Automatic Detection of the Optic Disc, Fovea and Vacular Arch in Digital Color Photographs of the Retina.

Abstract: We present a novel method that determines whether a macula centered retinal image is from the left or right eye and automatically detects the optic disc, the fovea and the vascular arch by inferring the location of a set of landmarks placed on these structures. The algorithm relies on a specific energy function that combines global and local cues. The global cues are derived from vascular atlases of the vessel orientation and thickness on the retina as well as a vascular distance map. A fourth component models the local appearance around each of the landmarks in the model and is able to estimate the distance between a position in the image and the target position of a landmark. For the minimization of the energy function a combination of optimization methods is used. We compare the results of several different system setups and combinations of energy function components with the performance of a second human observer. The best performing system localizes the OD in 91% of all cases, the fovea in 94% of all cases and correctly positions 74% of all vessel landmarks. The results show that a combination of global and local energy function components is required to obtain optimal results.

Distance Measurement Using a Single Camera with a Rotating Mirror

Abstract: A new distance measurement method with the use of a single camera and a rotating mirror is presented. A camera in front of a rotating mirror acquires a sequence of reflected images, from which distance information is extracted. The distance measurement is based on the idea that the corresponding pixel of an object point at a longer distance moves at a higher speed in a sequence of images in this type of system setting. Distance measurement based on such pixel movement is investigated. Like many other image-based techniques, this presented technique requires matching corresponding points in two images. To alleviate such difficulty, two kinds of techniques of image tracking through the sequence of images and the utilization of multiple sets of image frames are described. Precision improvement is possible and is one attractive merit. The presented approach with a rotating mirror is especially suitable for such multiple measurements. The imprecision caused by the physical limit could be improved through making several measurements and taking an average. In this paper, mathematics necessary for implementing the technique is derived and presented. Also, the error sensitivities of related parameters are analyzed. Experimental results using the real camera-mirror setup are reported.

Geometry synthesis by example

Abstract: In this paper we present a method for geometry synthesis by example, inspired by techniques from texture synthesis. Given an example of input geometry, we synthesize new output geometry that is perceived similar to the input geometry, but at the same time differs in its local appearance. We assume the input geometry satisfies the constraints of a Markov Random Field model, and represent the input geometry by a hierarchical distance field. This allows us to perform fast matching between a target distance field that is partially synthesized, and the input distance field. Once the target distance field is completed, we copy the original corresponding geometry elements to the synthesized result. We show that automatically generating geometry by example can be achieved within reasonable computing times, and is able to produce convincing results.

Differential fly-throughs (DFT): a general framework for computing flight paths

Abstract: In this paper, we propose a new variational framework based on distance transform and gradient vector flow, to compute flight paths through tubular and non-tubular structures, for virtual endoscopy. The proposed framework propagates two wave fronts of different speeds from a point source voxel, which belongs to the medial curves of the anatomical structure. The first wave traverses the 3D structure with a moderate speed that is a function of the distance field to extract its topology, while the second wave propagates with a higher speed that is a function of the magnitude of the gradient vector flow to extract the flight paths. The motion of the fronts are governed by a nonlinear partial equation, whose solution is computed efficiently using the higher accuracy fast marching level set method (HAFMM). The framework is robust, fully automatic, and computes flight paths that are centered, connected, thin, and less sensitive to boundary noise. We have validated the robustness of the proposed method both quantitatively and qualitatively against synthetic and clinical datasets.

A method to detect victims in search and rescue operations using template matching

Abstract: We present an approach to vision-based person detection in robotic applications that uses template matching. We detect people using templates of the human silhouette. In our approach, we detect borders on each image, then apply a distance transform, and then match templates at different scales. Our system integrates silhouette, corners (point of interest) and skin presence in order to obtain more robust results in the detection of victims in search and rescue operations. Further, we describe the automatic generation of templates from a set of photographs of the object of interest.

Method for estimating an aircraft distance taking into account air navigation constraints

Abstract: in order to estimate a distance, the inventive method uses a distance transform by propagation taking into consideration only paths which are accessible for the aircraft taking into account the vertical flight profile thereof and respecting the air traffic control. The propagated distance is associated with a propagated altitude (Ap) which follows each point of the vertical flight profile of the aircraft, is greater than the altitudes of said points and respects the air traffic control restrictions at said points. The result is attainable by subjecting the propagation to requirements of the vertical flight profile of the aircraft, the obstacles of the land elevation points and the air traffic control restrictions.

Image mapping method and image mapping program

Abstract: An image mapping method comprising the steps of acquiring a captured image as well as positional information of an image object in the captured image and positional information of an image taking position, reading map data containing the position of the image object from a recording medium that stores map data and displaying an electronic map based on the map data on a display device, displaying an indicator that shows the image taking direction of the image object on the electronic map based on the positional information of the image object in the captured image and the positional information of the image taking position, and displaying a marker that shows the position of the image object on the electronic map and disposing on the electronic map a scaled-down image of the captured image that is associated with the indicator showing the image taking direction that was shown on the electronic map.

Fast alignment of 3D geometrical models and 2D color images using 2D distance maps

Abstract: This paper presents a fast pose estimation algorithm of a 3D free form object in 2D images using 2D distance maps. One of the popular techniques of the pose estimation of 3D object in 2D image is the point-based method such as the ICP algorithm. However, the calculation cost for determining point correspondences is expensive. To overcome this problem, the proposed method utilizes a distance map on the 2D image plane, which is constructed quite rapidly by the fast marching method. For pose estimation of the object, contour lines of the 2D image and the projection of the 3D object are aligned using the distance map iteratively by the robust m-estimator. Some experimental results with simulated models and actual images of the endoscopic operation are successfully carried out.