Topic
Distance transform
About: Distance transform is a research topic. Over the lifetime, 2886 publications have been published within this topic receiving 59481 citations.
Papers published on a yearly basis
Papers
More filters
••
TL;DR: The novel idea of replacing the pixel-wise class score maps of DCNNs with distance maps is orthogonal and complementary to other techniques employed by the state-of-the-art methods and could therefore be used to improve upon them.
Abstract: This paper addresses the challenge of learning spatial context for the semantic segmentation of high-resolution aerial images using Deep Convolutional Neural Networks (DCNNs). The proposed solution involves deriving a signed distance map for each semantic class from a ground truth label map and training a DCNN to predict this distance map instead of a score map for each class. Since the distance between a target pixel and its nearest object boundary measures how far the pixel penetrates an object, the distance maps encode spatial context, particularly spatial smoothness. Positive pixel values in the distance maps correspond to the correct class and negative values correspond to the incorrect class. A final label map is derived from the predicted distance maps by selecting the class with the maximum distance. Since neighboring pixels in the distance maps have similar values, the segmentation results are smoother than current approaches. The results are shown to be even better than performing post-processing using fully connected Conditional Random Fields (CRFs), a common approach to smoothing the segmentations produced DCNNs. Experimental results on the semantic labeling challenge dataset show the proposed approach outperforms most state-of-the-art methods. Our main contribution, though, is the novel idea of replacing the pixel-wise class score maps of DCNNs with distance maps. This is therefore orthogonal and complementary to other techniques employed by the state-of-the-art methods and could therefore be used to improve upon them.
43 citations
•
30 Sep 2002
TL;DR: In this article, a region growing method for identifying nodules in an anatomical volume segments a 3D image volume by controlled voxel growth from seed points, based on creation and use of a distance map for tracking the distance of vessel voxels from a predetermined location.
Abstract: A region-growing method for identifying nodules in an anatomical volume segments a 3-D image volume by controlled voxel growth from seed points. The process is based on creation and use of a distance map for tracking the distance of vessel voxels from a predetermined location. A volume map is created that identifies the largest sphere that can pass between a voxel and a predetermined location without touching a non-vessel voxel. The ratio between the distance map and the volume map is analyzed to find regions more likely to contain nodules, the features of which can be extracted or otherwise highlighted.
43 citations
••
01 Aug 1996TL;DR: A 3D deformable model that uses an adaptive mesh to increase computational efficiency and accuracy and employs a distance transform in order to overcome some of the problems caused by inaccurate initialisation is described.
Abstract: Deformable models are a powerful and popular tool for image segmentation, but in 3D imaging applications the high computational cost of fitting such models can be a problem. A further drawback is the need to select the initial size and position of a model in such a way that it is close to the desired solution. This task may require particular expertise on the part of the operator, and, furthermore, may be difficult to accomplish in three dimensions without the use of sophisticated visualisation techniques. This article describes a 3D deformable model that uses an adaptive mesh to increase computational efficiency and accuracy. The model employs a distance transform in order to overcome some of the problems caused by inaccurate initialisation. The performance of the model is illustrated by its application to the task of segmentation of 3D MR images of the human head and hand. A quantitative analysis of the performance is also provided using a synthetic test image.
43 citations
•
11 Sep 2006TL;DR: In this paper, the authors propose an image generation device that includes distance calculation means for calculating a distance between a space model and an imaging device arrangement object model which is a model such as a vehicle having a camera mounted, according to viewpoint conversion image data generated by viewpoint conversion means.
Abstract: The image generation device includes distance calculation means for calculating a distance between a space model and an imaging device arrangement object model which is a model such as a vehicle having a camera mounted, according to viewpoint conversion image data generated by viewpoint conversion means, captured image data representing captured image, a space model, or mapped space data. When displaying an image viewed from an arbitrary virtual viewpoint in the 3D space, the image display format is changed according to the distance calculated by the distance calculation means. When displaying a monitoring object such as a vicinity of a vehicle, a shop, a house or a city as an image viewed from an arbitrary virtual viewpoint in the 3D space, it is possible to display the monitoring object in such a manner that the relationship between the vehicle and the image of the monitoring object can be understood intuitionally.
43 citations
••
TL;DR: An automatic approach integrating multi-dimensional features into graph cut refinement is developed and validated and indicates that the method has ability to reach the desired boundary of liver and has potential value for clinical application.
Abstract: Liver segmentation is an essential procedure in computer-assisted surgery, radiotherapy, and volume measurement. It is still a challenging task to extract liver tissue from 3D CT images owing to nearby organs with similar intensities. In this paper, an automatic approach integrating multi-dimensional features into graph cut refinement is developed and validated. Multi-atlas segmentation is utilized to estimate the coarse shape of liver on the target image. The unsigned distance field based on initial shape is then calculated throughout the whole image, which aims at automatic graph construction during refinement procedure. Finally, multi-dimensional features and shape constraints are embedded into graph cut framework. The optimal liver region can be precisely detected with a minimal cost. The proposed technique is evaluated on 40 CT scans, obtained from two public databases Sliver07 and 3Dircadb1. The dataset Sliver07 is considered as the training set for parameter learning. On the dataset 3Dircadb1, the average of volume overlap is up to 94%. The experiment results indicate that the proposed method has ability to reach the desired boundary of liver and has potential value for clinical application.
43 citations