Distance transform

About: Distance transform is a research topic. Over the lifetime, 2886 publications have been published within this topic receiving 59481 citations.

An ISO-surfaces based local deformation handling framework of lung tissues

Abstract: Handling the deformations of the lung tissues in successive chest computed tomography (CT) scans of a patient is a vital step in any computer-aided diagnostic (CAD) system for lung cancer diagnosis. In this paper, we propose a new nonrigid registration methodology for the segmented lung region from CT data that involves two steps. The first step globally aligns the target-to-reference CT scans using an affine transformation based on ascent maximization of the estimated mutual information of the calculated distance map using the fast marching level sets method inside the segmented lung for both the target and reference objects. The second step is the local alignment of the target lung object in order to correct for intricate relative deformations due to breathing and heart beats. The local deformations are handled based on displacing each voxel of the target over evolving closed equi-spaced surfaces (iso-surfaces) to closely match the reference object. In order to displace the voxel on the iso-surfaces of the target lung object, the initial voxel-to-voxel match between target and reference lung objects is estimated by solving the 3D Laplace equation between each two corresponding iso-surfaces on the reference and target objects. Finally, the estimation of voxel-to-voxel match is refined through iterative energy minimization using a generalized Gauss-Markov random field (GGMRF) model. Qualitative and quantitative results demonstrate the promise of the proposed nonrigid registration framework.

Skeletonizing the distance transform on the hexagonal grid

Abstract: An efficient skeletonizing algorithm is presented for the hexagonal grid. The skeleton has unit width, except at crossings and in regions of the shape having even width. Otherwise the skeleton has all the properties generally required for correct skeletons. It includes all local maxima, so complete recovery of the original shape is obtained by using the reverse distance transformation. The algorithm uses only local operations. Thus it can be performed both on sequential and parallel computers. In the sequential case described only three passes through the image are necessary, two to compute the distance transform and one for the identification of skeletal pixels. >

Three-dimensional object representation and invariant recognition using continuous distance transform neural networks

Abstract: 3D object recognition under partial object viewing is a difficult pattern recognition task. In this paper, we introduce a neural-network solution that is robust to partial viewing of objects and noise corruption. This method directly utilizes the acquired 3D data and requires no feature extraction. The object is first parametrically represented by a continuous distance transform neural network (CDTNN) trained by the surface points of the exemplar object. The CDTNN maps any 3D coordinate into a value that corresponds to the distance between the point and the nearest surface point of the object. Therefore, a mismatch between the exemplar object and an unknown object can be easily computed. When encountered with deformed objects, this mismatch information can be backpropagated through the CDTNN to iteratively determine the deformation in terms of affine transform. Application to 3D heart contour delineation and invariant recognition of 3D rigid-body objects is presented.

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.