.png){kind=icon}
返回
Fast Convolutional Distance Transform
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2019.2910466.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We propose convolutional distance transform-efficient implementations of distance transform. Specifically, we leverage approximate minimum functions to rewrite the distance transform in terms of convolution operators. Thanks to the fast Fourier transform, the proposed convolutional distance transforms have O(N log N) complexity, where N is the total number of pixels. The proposed acceleration technique is distance metric agnostic. In the special case that the distance function is a p-norm, the distance transform can be further reduced to separable convolution filters; and for Euclidean norm, we achieve O( N) using constant-time Gaussian filtering.
Keyword:
Convolution
distance transform
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
Cytogenetics of Four Species of Genus <i>Berberis</i> L. (Berberidaceae Juss.) from the Western Himalayas西喜马拉雅地区<i>Berberis</i> L.属四种植物的细胞遗传学研究（小檗科Juss.）.png)
CYTOLOGIA
OAAI
CYTOLOGIAIF0
OAAI分享收藏Three-dimensional Euclidean distance transformation and its application to shortest path planning三维欧氏距离变换及其在最短路径规划中的应用PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏
查看更多内容