Showing papers on "Distance transform published in 2009"

Vehicle environment recognition system

Abstract: A vehicle environment recognition system includes stereo-image taking means for taking images of an environment around a subject vehicle and for outputting the images as a reference image and a comparative image, first stereo matching means for forming a first distance image on the basis of the reference image and the comparative image or on the basis of two images obtained by preprocessing the reference image and the comparative image, second stereo matching means for forming a second distance image on the basis of two images obtained by preprocessing the reference image and the comparative image in a different manner, detection means for detecting objects in the reference image on the basis of the first and second distance images, and selection means for selecting one of the results of detection based on the first and second distance images.

Online complete coverage path planning for mobile robots based on linked spiral paths using constrained inverse distance transform

Abstract: This paper presents a sensor-based online coverage path planning algorithm guaranteeing a complete coverage of unstructured planar environments by a mobile robot. The proposed complete coverage algorithm abstracts the environment as a union of robot-sized cells and then uses a spiral filling rule. It can be largely classified as an approximate cellular decomposition approach as defined by Choset. In this paper, we first propose a special map coordinate assignment scheme based on active wall-finding using the history of sensor readings, which can drastically reduce the number of turns on the generated coverage path. Next, we develop an efficient path planner to link the simple spiral paths using the constrained inverse distance transform that we introduced the first time. This planner selects the next target cell which is at the minimal path length away from the current cell among the remaining non-contiguous uncovered cells while at the same time, finding the path to this target to save both the memory and time which are important concern in embedded robotics. Experiments on both simulated and real cleaning robots demonstrate the practical efficiency and robustness of the proposed algorithm.

Automatically Determining the Number of Clusters in Unlabeled Data Sets

Abstract: Clustering is a popular tool for exploratory data analysis. One of the major problems in cluster analysis is the determination of the number of clusters in unlabeled data, which is a basic input for most clustering algorithms. In this paper we investigate a new method called DBE (dark block extraction) for automatically estimating the number of clusters in unlabeled data sets, which is based on an existing algorithm for visual assessment of cluster tendency (VAT) of a data set, using several common image and signal processing techniques. Basic steps include: 1) generating a VAT image of an input dissimilarity matrix; 2) performing image segmentation on the VAT image to obtain a binary image, followed by directional morphological filtering; 3) applying a distance transform to the filtered binary image and projecting the pixel values onto the main diagonal axis of the image to form a projection signal; 4) smoothing the projection signal, computing its first-order derivative, and then detecting major peaks and valleys in the resulting signal to decide the number of clusters. Our new DBE method is nearly "automatic", depending on just one easy-to-set parameter. Several numerical and real-world examples are presented to illustrate the effectiveness of DBE.

Learning semantic distance from community-tagged media collection

Abstract: This paper proposes a novel semantic-aware distance metric for images by mining multimedia data on the Internet, in particular, web images and their associated tags. As well known, a proper distance metric between images is a key ingredient in many realistic web image retrieval engines, as well many image understanding techniques. In this paper, we attempt to mine a novel distance metric from the web images by integrating their visual content as well as the associated user tags. Different from many existing distance metric learning algorithms which utilize the dissimilar or similar information between images pixels or features in signal level, the proposed scheme also takes the associated user-input tags into consideration. The visual content of images is also leveraged to respect an intuitive assumption that the visual similar images ought to have a smaller distance. A semi-definite programming is formulated to encode the above two aspects of criteria to learn the distance metric and we show such an optimization problem can be efficiently solved with a closed-form solution. We evaluate the proposed algorithm on two datasets. One is the benchmark Corel dataset and the other is a real-world dataset crawled from the image sharing website Flickr. By comparison with other existing distance learning algorithms, competitive results are obtained by the proposed algorithm in experiments.

What Shape Is Your Conjugate? A Survey of Computational Convex Analysis and Its Applications

Abstract: Computational convex analysis algorithms have been rediscovered several times in the past by researchers from different fields. To further communications between practitioners, we review the field of computational convex analysis, which focuses on the numerical computation of fundamental transforms arising from convex analysis. Current models use symbolic, numeric, and hybrid symbolic-numeric algorithms. Our objective is to disseminate widely the most efficient numerical algorithms useful for applications in image processing (computing the distance transform, the generalized distance transform, and mathematical morphology operators), partial differential equations (solving Hamilton-Jacobi equations and using differential equations numerical schemes to compute the convex envelope), max-plus algebra (computing the equivalent of the fast Fourier transform), multifractal analysis, etc. The fields of applications include, among others, computer vision, robot navigation, thermodynamics, electrical networks, medical imaging, and network communication.

Distance transform templates for object detection and pose estimation

Abstract: We propose a new approach for detecting low textured planar objects and estimating their 3D pose. Standard matching and pose estimation techniques often depend on texture and feature points. They fail when there is no or only little texture available. Edge-based approaches mostly can deal with these limitations but are slow in practice when they have to search for six degrees of freedom. We overcome these problems by introducing the distance transform templates, generated by applying the distance transform to standard edge based templates. We obtain robustness against perspective transformations by training a classifier for various template poses. In addition, spatial relations between multiple contours on the template are learnt and later used for outlier removal. At runtime, the classifier provides the identity and a rough 3D pose of the distance transform template, which is further refined by a modified template matching algorithm that is also based on the distance transform. We qualitatively and quantitatively evaluate our approach on synthetic and real-life examples and demonstrate robust real-time performance.

New Lane Model and Distance Transform for Lane Detection and Tracking

Abstract: Particle filtering of boundary points is a robust way to estimate lanes. This paper introduces a new lane model in correspondence to this particle filter-based approach, which is flexible to detect all kinds of lanes. A modified version of an Euclidean distance transform is applied to an edge map of a road image from a birds-eye view to provide information for boundary point detection. An efficient lane tracking method is also discussed. The use of this distance transform exploits useful information in lane detection situations, and greatly facilitates the initialization of the particle filter, as well as lane tracking. Finally, the paper validates the algorithm with experimental evidence for lane detection and tracking.

Method for simulating numerically controlled milling using adaptively sampled distance fields

Abstract: Provided is a method performed on a processor for simulating the milling of an object by moving a shape along a path intersecting the object. A composite adaptively sampled distance field (ADF) is generated to represent the object, where the composite ADF includes a set of cells. Each cell in the composite ADF includes a set of distance fields and a procedural reconstruction method for reconstructing the object within the cell. The shape is represented by a shape distance field. The path is represented by a parametric function. A swept volume distance field is defined in a continuous manner to represent a swept volume generated by moving the shape along the path according to a swept volume reconstruction method which reconstructs the swept volume distance field at a sample point. The composite ADF is edited to incorporate the swept volume distance field into the composite ADF to simulate the milling.

Adaptive watershed segmentation of binary particle image

Abstract: Oversegmentation is a tough problem in the morphological watershed segmentation of irregular-shaped binary particles, which is usually caused by spurious minima in the inverse distance transform. The position relationship between two objects is clear, according to the value of overlap parameter defined in the paper, and an adaptive algorithm is presented to depress oversegmentation by building the criterion to merge the spurious local minima. Some particle images are provided to validate the performance of the proposed method.

Visualizing time-varying features with TAC-based distance fields

Abstract: To analyze time-varying data sets, tracking features over time is often necessary to better understand the dynamic nature of the underlying physical process. Tracking 3D time-varying features, however, is non-trivial when the boundaries of the features cannot be easily defined. In this paper, we propose a new framework to visualize time-varying features and their motion without explicit feature segmentation and tracking. In our framework, a time-varying feature is described by a time series or Time Activity Curve (TAC). To compute the distance, or similarity, between a voxel's time series and the feature, we use the Dynamic Time Warping (DTW) distance metric. The purpose of DTW is to compare the shape similarity between two time series with an optimal warping of time so that the phase shift of the feature in time can be accounted for. After applying DTW to compare each voxel's time series with the feature, a time-invariant distance field can be computed. The amount of time warping required for each voxel to match the feature provides an estimate of the time when the feature is most likely to occur. Based on the TAC-based distance field, several visualization methods can be derived to highlight the position and motion of the feature. We present several case studies to demonstrate and compare the effectiveness of our framework.

Enhancing images in scattering media utilizing stereovision and polarization

Abstract: Consider photography in scattering media. One goal is to enhance the images and compensate for scattering effects. A second goal is to estimate a distance map of the scene. A prior method exists to achieve these goals. It is based on acquiring two images from a fixed position, using a single camera mounted with a polarizer at different settings. However, the shortcomings of this polarization-based method comprise having to acquire these images sequentially, reduced light level, and inapplicability at low backscatter degree of polarization. In this paper, a new technique is described to alleviate these issues by integrating polarization and stereo cues. More precisely, the earlier single-camera method is extended to a pair of cameras displaced by a finite baseline. Each camera utilizes polarizers at different settings. Stereo disparity and polarization analysis are fused to construct de-scattered left and right views. The binocular stereo cues provide additional geometric constraints for distance computation. Moreover, the proposed technique acquires the two raw images simultaneously. Thus it can be applied to dynamic scenes. Underwater experiments are presented.

Low-Level Image Processing for Lane Detection and Tracking

Abstract: Lane detection and tracking is a significant component of vision-based driver assistance systems (DAS). Low-level image processing is the first step in such a component. This paper suggests three useful techniques for low-level image processing in lane detection situations: bird’s-eye view mapping, a specialized edge detection method, and the distance transform. The first two techniques have been widely used in DAS, while the distance transform is a method newly exploited in DAS, that can provide useful information in lane detection situations. This paper recalls two methods to generate a bird’s-eye image from the original input image, it also compares edge detectors. A modified version of the Euclidean distance transform called real orientation distance transform (RODT) is proposed. Finally, the paper discusses experiments on lane detection and tracking using these technologies.

Disparity map refinement and 3D surface smoothing via Directed Anisotropic Diffusion

Abstract: We propose a new binocular stereo algorithm and 3D reconstruction method from multiple disparity images. First, we present an accurate binocular stereo algorithm. In our algorithm, we use neither color segmentation nor plane fitting methods, which are common techniques among many algorithms nominated in the Middlebury ranking. These methods assume that the 3D world consists of a collection of planes and that each segment of a disparity map obeys a plane equation. We exclude these assumptions and introduce a Directed Anisotropic Diffusion technique for refining a disparity map. Second, we show a method to fill some holes in a distance map and smooth the reconstructed 3D surfaces by using another type of Anisotropic Diffusion technique. The evaluation results on the Middlebury datasets show that our stereo algorithm is competitive with other algorithms that adopt plane fitting methods. We present an experiment that shows the high accuracy of a reconstructed 3D model using our method, and the effectiveness and practicality of our proposed method in a real environment.

Efficient C-space and cost function updates in 3D for unmanned aerial vehicles

Abstract: When operating in partially-known environments, autonomous vehicles must constantly update their maps and plans based on new sensor information. Much focus has been placed on developing efficient incremental planning algorithms that are able to efficiently replan when the map and associated cost function changes. However, much less attention has been placed on efficiently updating the cost function used by these planners, which can represent a significant portion of the time spent replanning. In this paper, we present the Limited Incremental Distance Transform algorithm, which can be used to efficiently update the cost function used for planning when changes in the environment are observed. Using this algorithm it is possible to plan paths in a completely incremental way starting from a list of changed obstacle classifications. We present results comparing the algorithm to the Euclidean distance transform and a mask-based incremental distance transform algorithm. Computation time is reduced by an order of magnitude for a UAV application. We also provide example results from an autonomous micro aerial vehicle with on-board sensing and computing.

Bayesian robot localization using spatial object contexts

Abstract: We propose a semantic representation and Bayesian model for robot localization using spatial relations among objects that can be created by a single consumer-grade camera and odometry. We first suggest a semantic representation to be shared by human and robot. This representation consists of perceived objects and their spatial relationships, and a qualitatively defined odometry-based metric distance. We refer to this as a topological-semantic distance map. To support our semantic representation, we develop a Bayesian model for localization that enables the location of a robot to be estimated sufficiently well to navigate in an indoor environment. Extensive localization experiments in an indoor environment show that our Bayesian localization technique using a topological-semantic distance map is valid in the sense that localization accuracy improves whenever objects and their spatial relationships are detected and instantiated.

Video Based Moving Object Tracking by Particle Filter

Abstract: Usually, the video based object tracking deal with non-stationary image stream that changes over time. Robust and Real time moving object tracking is a problematic issue in computer vision research area. Most of the existing algorithms are able to track only in predefined and well controlled environment. Some cases, they don’t consider non-linearity problem. In our paper, we develop such a system which considers color information, distance transform (DT) based shape information and also nonlinearity. Particle filtering has been proven very successful for non-gaussian and non-linear estimation problems. We examine the difficulties of video based tracking and step by step we analyze these issues. In our first approach, we develop the color based particle filter tracker that relies on the deterministic search of window, whose color content matches a reference histogram model. A simple HSV histogram-based color model is used to develop this observation system. Secondly, we describe a new approach for moving object tracking with particle filter by shape information. The shape similarity between a template and estimated regions in the video scene is measured by their normalized cross-correlation of distance transformed images. Our observation system of particle filter is based on shape from distance transformed edge features. Template is created instantly by selecting any object from the video scene by a rectangle. Finally, in this paper we illustrate how our system is improved by using both these two cues with non linearity.

An improved template matching method for object detection

Abstract: This paper presents an improved template matching method that combines both spatial and orientation information in a simple and effective way The spatial information is obtained through a generalized distance transform (GDT) that weights the distance transform more on the strong edge pixels and the orientation information is represented as an orientation map (OM) which is calculated from local gradient We applied the proposed method to detect humans, cars, and maple leaves from images The experimental results have shown that the proposed method outperforms the existing template matching methods and is robust against cluttered background.

Distance Solutions for Medial Axis Transform

Abstract: A method towards robust and efficient medial axis transform (MAT) of arbitrary domains using distance solutions is presented. The distance field, d, is calculated by solving the hyperbolic-natured Eikonal (or Level Set) equation. The solution is obtained on Cartesian grids. Both the fast-marching method and fast-sweeping method are used to calculate d. Medial axis point clouds are then extracted based on the distance solution via a simple criteria: the Laplacian or the Hessian determinant of d. These point clouds in 2D-pixel and 3D-voxel space are further thinned to curves and surfaces through binary image thinning algorithms. This results in an overall hybrid approach. As an alternative to other methods, the current d −MAT procedure bypasses difficulties that are usually encountered by pure geometric methods (e.g. the Voronoi approach), especially in 3D, and provides better accuracy than pure thinning methods. It is also shown that the d −MAT approach provides the potential to sculpt/control the MAT form for specialized solution purposes. Various examples are given to demonstrate the current approach.

On a Method of Paired Representation: Enhancement and Decomposition by Series Direction Images

Abstract: In the paired representation, a two-dimensional (2-D) image is represented uniquely by a complete set of 1-D signals, so-called splitting-signals, that carry the spectral information of the image at frequency-points of specific subsets that divide the whole domain of frequencies Image processing can thus be reduced to processing of splitting-signals and such process requires a modification of only a few spectral components of the image, for each signal For instance, the ?-rooting method of image enhancement can be fulfilled through processing one or a few splitting-signals Such process can even be accomplished without computing the 2-D Fourier transforms of the original and enhanced images To show that, we present an effective formula for inverse 2-D N×N-point paired transform, where N is a power of 2 The representation of the image and 2-D DFT by paired splitting-signals leads to the new concepts of direction and series images, that define the resolution and periodic structures of the image components, which can be packed in the form of the "resolution map" of the size of the image Simple method of image enhancement by series images is described

Arbitrary viewpoint image synthesizing device

Abstract: PROBLEM TO BE SOLVED: To provide an arbitrary viewpoint image synthesizing device which generates an image in which an image capturing direction and an eye direction match by subjecting images captured by a plurality of cameras in different image capturing directions to synthesis processing. SOLUTION: An image from each camera 2A, 2B and 2C is coordinate-transformed by coordinate transformation parts 21, 22 and 23 based on a parameter stored in a camera parameter storage part 26. The transformed image is transferred to a distance estimation part 24 and an image synthesis part 25. The distance estimation part 24 evaluates those three images by block matching for each two image as one set. The image synthesis part 25 composites the images of virtual camera viewpoints by extracting and attaching a corresponding pixel color from the coordinate transformed image to the created distance image of an object. COPYRIGHT: (C)2011,JPO&INPIT

Thickness analysis and reconstruction of trabecular bone and bone substitute microstructure based on fuzzy distance map using both ridge and thinning skeletonization

Abstract: The accurate geometric analysis of microstructured biological porous media is crucial for an understanding of the geometric changes that result from diseases such as osteoporosis and for the design of bone substitutes for the treatment of cancer patients. This paper presents a methodological development designed to improve the description of the average pore size and thickness of a micro structure's biological media. Specifically, the paper introduces a new skeletonization method based on a ridge skeleton combined with fuzzy distance transform (FDT), which has recently been used in the literature and has shown some advantages compared to the traditional distance transform. The new skeletonization method is applied to trabecular bone excised from healthy and osteoporotic vertebrae, as well as to bone substitutes with small and large pores. These samples are scanned by a micro-computed tomography scanner. The new skeletonization method has been implemented successfully, and an exact algorithm for implementation and reconstruction has been developed. The results show that, compared to widely used thinning methods, the new FDT ridge skeleton generates measurements that are more representative of the microstructure of the examined media. It is concluded that the new method can find the ridges of the FDT and produce topologically accurate skeletons, leading to accurate measurement and reconstruction of the microstructured porous media.

System and method for colon unfolding via skeletal subspace deformation

Abstract: A system and method for colon unfolding via skeletal subspace deformation comprises: performing a centerline computation on a segmented image for deriving a centerline thereof; computing a distance map utilizing said centerline and said segmented image to derive said distance map; generating a polyhedral model of the lumen of said colon; and utilizing said polyhedral model, said distance map, and said centerline for performing a straightening operation on said centerline.

Clutter Noise Removal in Binary Document Images

Abstract: The paper presents a clutter detection and removal algorithm for complex document images. The distance transform based approach is independent of clutter's position, size, shape and connectivity with text. Features are based on a residual image obtained by analysis of the distance transform and clutter elements, if present, are identified with an SVM classifier. Removal is restrictive, so text attached to the clutter is not deleted in the process. The method was tested on a collection of degraded and noisy, machine-printed and handwritten Arabic and English text documents. Results show pixel-level accuracies of 97.5% and 95% for clutter detection and removal respectively. This approach was also extended with a noise detection and removal model for documents having a mix of clutter and salt-n-pepper noise.

Reliable sweeps

Abstract: We present a simple algorithm to generate a topology-preserving, error-bounded approximation of the outer boundary of the volume swept by a polyhedron along a parametric trajectory. Our approach uses a volumetric method that generates an adaptive volumetric grid, computes signed distance on the grid points, and extracts an isosurface from the distance field. In order to guarantee geometric and topological bounds, we present a novel sampling and front propagation algorithm for adaptive grid generation. We highlight the performance of our algorithm on many complex benchmarks that arise in geometric and solid modeling, motion planning and CNC milling applications. To the best of our knowledge, this is the first practical algorithm that can generate swept volume approximations with geometric and topological guarantees on complex polyhedral models swept along any parametric trajectory.

Method for reconstructing a distance field of a swept volume at a sample point

Abstract: A method performed on a processor reconstructs a distance field of an object at a sample point, where the object is a swept volume generated by moving a shape along a path. The shape is represented by a shape distance field. The path is represented by a parametric function. Distance data at the sample points is determined, where the distance data characterizes the distance field of the object at the sample point. An optimal set of parameters defining an optimal placement of the shape along the path is determined in a continuous manner. The shape distance field is transformed to the optimal placement to produce a transformed shape distance field. The distance data is determined at the sample point from the transformed shape distance field to reconstruct the distance field at the sample point.