A Region-Growing Segmentation Algorithm for GPUs

Happ P.N.; Feitosa R.Q.; Bentes C.; Farias R.

首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >A Region-Growing Segmentation Algorithm for GPUs

【24h】

A Region-Growing Segmentation Algorithm for GPUs

机译：GPU的区域增长分割算法

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

This letter proposes a parallel version for graphics processing units (GPU) of a region-growing image segmentation algorithm widely used by the geographic object-based image analysis (GEOBIA) community. Initially, all image pixels are considered as seeds or primitive segments. Fine-grained parallel threads assigned to individual pixels merge adjacent segments iteratively always ensuring to minimize the overall heterogeneity increase. Besides spectral features the merging criterion considers morphological features that can be efficiently computed in the underlying GPU architecture. Two alternatives using different merging criteria are proposed and tested. An experimental analysis upon five different test images has shown that the parallel algorithm may run up to 19 times faster than its sequential counterpart.

机译：这封信为基于地理对象的图像分析（GEOBIA）社区广泛使用的区域增长图像分割算法的图形处理单元（GPU）提出了并行版本。最初，所有图像像素都被视为种子或原始段。分配给各个像素的细粒度并行线程会迭代地合并相邻段，从而始终确保将整体异质性增加降至最低。除频谱特征外，合并标准还考虑可以在基础GPU架构中有效计算的形态特征。提出并测试了使用不同合并标准的两种选择。对五张不同的测试图像进行的实验分析表明，并行算法的运行速度比顺序算法快19倍。

著录项

来源
《IEEE Geoscience and Remote Sensing Letters》 |2013年第6期|1-1|共1页
作者
Happ P.N.; Feitosa R.Q.; Bentes C.; Farias R.;
展开▼
作者单位

Department of Electrical Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, Brazil|c|;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Image segmentation; graphics processing unit (GPU); parallel processing;

机译：图像分割;图形处理单元（GPU）;并行处理;

相似文献

外文文献
中文文献
专利

1. Parameter selection for region-growing image segmentation algorithms using spatial autocorrelation [J] . G. M. ESPINDOLA, G. CAMARA, I. A. REIS, International journal of remote sensing . 2006,第12a14期

机译：使用空间自相关的区域增长图像分割算法的参数选择
2. Accelerating compute-intensive image segmentation algorithms using GPUs [J] . Shehab Mohammed, Al-Ayyoub Mahmoud, Jararweh Yaser, Journal of supercomputing . 2017,第5期

机译：使用GPU加速计算密集型图像分割算法
3. A Smart Region-Growing Algorithm for Single-Neuron Segmentation From Confocal and 2-Photon Datasets [J] . Alejandro Luis Callara, Chiara Magliaro, Arti Ahluwalia, Frontiers in Neuroinformatics . 2020,第4期

机译：来自共聚焦和2-光子数据集的单神经元分段的智能区域越来越多的算法
4. An improved region-growing algorithm for mammographic mass segmentation [C] . Ying Cao, Xin Hao, Shunren Xia International symposium on multispectral image processing and pattern recognition;MIPPR 2009 . 2009

机译：乳腺X线摄影分割的改进区域增长算法
5. Blocked Algorithms for Neural Networks: Design and Implementation on GPUs [D] . Tillet, Philippe. 2020

机译：神经网络的阻止算法：GPU上的设计与实现
6. A Smart Region-Growing Algorithm for Single-Neuron Segmentation From Confocal and 2-Photon Datasets [O] . Alejandro Luis Callara, Chiara Magliaro, Arti Ahluwalia, 2020

机译：从共焦和2光子数据集进行单神经元分割的智能区域增长算法
7. A Smart Region-Growing Algorithm for Single-Neuron Segmentation From Confocal and 2-Photon Datasets [O] . Alejandro Luis Callara, Chiara Magliaro, Arti Ahluwalia, 2020

机译：来自共聚焦和2-光子数据集的单神经元分段的智能区域越来越多的算法
8. Incorporating Edge Information into Best Merge Region-Growing Segmentation. [R] . Tilton, J. C., Pasolli, E. 2014

机译：将边缘信息纳入最佳合并区域 - 增长分割。

A Region-Growing Segmentation Algorithm for GPUs

摘要

著录项

相似文献

相关主题

期刊订阅