Learning to Associate Image Features with CRF-Matching

机译：学习将图像功能与CRF匹配相关联

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

This paper presents a supervised learning algorithm for image feature matching. The algorithm is based on Conditional Random Fields which provides a mechanism for globally reason about the associations. The novelty of this work is twofold: (ⅰ) the use of Delaunay triangulation as the graph structure for a probabilistic network to reason about image feature association; (ⅱ) the combination of local and joint features to enforce consistency in a theoretically sound statistical learning procedure. Experimental results show that our approach outperforms RANSAC in our challenging datasets consisting of indoor and outdoor images, with significant occlusion, blurring, rotational and translational transformations.

机译：本文提出了一种用于图像特征匹配的监督学习算法。该算法基于条件随机字段，该条件随机字段提供了有关关联的全局原因的机制。这项工作的新颖性是双重的：（ⅰ）使用Delaunay三角剖分作为概率网络的图结构来推理图像特征关联；（ⅱ）在理论上合理的统计学习程序中结合局部和联合特征以增强一致性。实验结果表明，在包括室内和室外图像在内的具有挑战性的数据集中，我们的方法优于RANSAC，并具有明显的遮挡，模糊，旋转和平移变换。

著录项

来源
《International symposium on experimental robotics;ISER'11; 20080713-16;20080713-16; Athens(GR);Athens(GR)》|2008年|P.505-514|共10页
会议地点 Athens(GR);Athens(GR)
作者
Fabio Ramos; M. Waleed Kadous; Dieter Fox;
展开▼
作者单位

ARC Centre of Excellence for Autonomous Systems, Australian Centre for Field Robotics, The University of Sydney, Sydney, NSW 2006, Australia;

School of Computer Science and Engineering, University of New South Wales, Sydney NSW 2052, Australia;

Department;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类机器人技术;
关键词

相似文献

外文文献
中文文献
专利

1. Feature learning and change feature classification based on deep learning for ternary change detection in SAR images [J] . Gong Maoguo, Yang Hailun, Zhang Puzhao ISPRS Journal of Photogrammetry and Remote Sensing . 2017,第jula期

机译：基于深度学习的特征学习和变化特征分类用于SAR图像中的三重变化检测
2. Computer-aided diagnosis of congenital abnormalities of the kidney and urinary tract in children based on ultrasound imaging data by integrating texture image features and deep transfer learning image features [J] . Zheng Q., Furth S. L., Tasian G. E., Journal of pediatric urology . 2019,第1期

机译：计算机辅助诊断基于超声成像数据的儿童肾脏和泌尿道先天性异常通过集成纹理图像特征和深度转移学习图像特征
3. COMBINATION OF FEATURE ENGINEERING AND FEATURE LEARNING APPROACHES FOR CLASSIFICATION ON VISUAL COMPLEXITY IMAGES [J] . INDAH AGUSTIEN SIRADJUDDIN, AFNI SAKINAH, MOCHAMMAD KAUTSAR SOPHAN International Journal of Innovative Computing Information and Control . 2021,第3期

机译：特征工程和特征学习方法的组合在视觉复杂性图像上分类
4. Learning to Associate Image Features with CRF-Matching [C] . Fabio Ramos, M. Waleed Kadous, Dieter Fox International Symposium on Experimental Robotics . 2009

机译：学习将图像功能与CRF匹配相关联
5. Geometric Features Learning from 2D Images [D] . Zhu, Jing. 2020

机译：从2D图像学习几何特征
6. Lung nodule malignancy classification using only radiologist-quantified image features as inputs to statistical learning algorithms: probing the Lung Image Database Consortium dataset with two statistical learning methods [O] . Matthew C. Hancock, Jerry F. Magnan 2016

机译：仅使用放射科医生量化的图像特征作为统计学习算法的输入的肺结节恶性分类：使用两种统计学习方法探查肺图像数据库联盟数据集
7. Learning to Associate Image Features with CRF-Matching [O] . Fabio Ramos, M. Waleed Kadous, Dieter Fox 2009

机译：学习将图像功能与CRF匹配相关联

Learning to Associate Image Features with CRF-Matching

摘要

著录项

相似文献

相关主题

期刊订阅