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: Experimental results showed that the method aligned the images robustly even in cases where conventional methods failed to find optimal locations, and the accuracy of the method was comparable to that of the NMI-based registration method.
16 citations
••
13 Apr 2005TL;DR: This article presents an efficient propagation algorithm based on a best-first pixel queue for computing the Distance Transform on Curved Space (DTOCS), applicable also for other geodesic distance transforms.
Abstract: Geodesic distance transforms are usually computed with sequential mask operations, which may have to be iterated several times to get a globally optimal distance map. This article presents an efficient propagation algorithm based on a best-first pixel queue for computing the Distance Transform on Curved Space (DTOCS), applicable also for other geodesic distance transforms. It eliminates repetitions of local distance calculations, and performs in near-linear time.
16 citations
•
08 Apr 2004
TL;DR: In this article, the authors proposed a method for detecting a mobile unit by generating a background distance map, indicating the distance information from the laser radar 10 in a detection area to an object in the background, even under the conditions where the environment in the monitoring area fluctuates and the condition where the reference plane for detecting the mobile unit cannot be set to be a plane.
Abstract: PROBLEM TO BE SOLVED: To provide an apparatus and a method for detecting a mobile unit allowing to detect a mobile unit stably, even under the condition where the environment in the monitoring area fluctuates and the condition where the reference plane for detecting the mobile unit cannot be set to be a plane. SOLUTION: A background distance generation section 21, on the basis of measurement results of a laser radar 10, generates a background distance map, indicating the distance information from the laser radar 10 in a detection area to an object in the background. A mobile unit detecting section 23 detects a mobile unit in the detection area from the difference between the distance information of the background distance map stored in a background distance map memory 22, in advance, and the measurement results of the laser radar 10. COPYRIGHT: (C)2006,JPO&NCIPI
16 citations
•
TL;DR: Dense RepPoints as discussed by the authors uses a large set of points to describe an object at multiple levels, including both box level and pixel level, using a distance transform sampling method combined with set-to-set supervision.
Abstract: We present a new object representation, called Dense RepPoints, that utilizes a large set of points to describe an object at multiple levels, including both box level and pixel level. Techniques are proposed to efficiently process these dense points, maintaining near-constant complexity with increasing point numbers. Dense RepPoints is shown to represent and learn object segments well, with the use of a novel distance transform sampling method combined with set-to-set supervision. The distance transform sampling combines the strengths of contour and grid representations, leading to performance that surpasses counterparts based on contours or grids. Code is available at \url{this https URL}.
16 citations
••
10 Dec 2002TL;DR: A medial surface representation of agrey-level volume image is computed by combining distance information with grey-level information and the structure of the surface skeleton is simplified by removing some peripheral surfaces, so obtaining the desired medialsurface representation.
Abstract: A medial surface representation of a grey-level volume image is computed. The foreground is reduced to a subset topologically equivalent to the initial foreground and mainly consisting of surfaces centred within regions having locally higher intensities, here, regarded as more informative. This result is obtained by combining distance information with grey-level information. A surface skeleton is first computed, where excessive shortening is prevented by a regularity condition defined on the distance transform. The structure of the surface skeleton is then simplified by removing some peripheral surfaces, so obtaining the desired medial surface representation.
16 citations