3D Model-based Still Image Object Categorization

机译：基于3D模型的静止图像对象分类

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 proposes a novel recognition scheme algorithm for semantic labeling of 2D object present in still images. The principle consists of matching unknown 2D objects with categorized 3D models in order to infer the semantics of the 3D object to the image. We tested our new recognition framework by using the MPEG-7 and Princeton 3D model databases in order to label unknown images randomly selected from the web. Results obtained show promising performances, with recognition rate up to 84%, which opens interesting perspectives in terms of semantic metadata extraction from still images/videos.

机译：针对静止图像中存在的二维物体的语义标记问题，提出了一种新颖的识别方案算法。该原理包括将未知的2D对象与分类的3D模型进行匹配，以便将3D对象的语义推论到图像上。我们通过使用MPEG-7和Princeton 3D模型数据库测试了我们的新识别框架，以便标记从网络中随机选择的未知图像。获得的结果显示出令人鼓舞的性能，识别率高达84％，这为从静止图像/视频中提取语义元数据开辟了有趣的视角。

著录项

来源
《Mathematics of data/image pattern coding, compression, and encryption with applications XIII》|2011年|p.81360C.1-81360C.10|共10页
会议地点 San Diego CA(US)
作者
Raluca-Diana Petre; Titus Zaharia;
展开▼
作者单位

Institut TELECOM TELECOM SudParis, ARTEMIS Department UMR CNRS 8145 MAP5 9 rue Charles Fourier, 91011 Evry Cedex, France;

Institut TELECOM TELECOM SudParis, ARTEMIS Department UMR CNRS 8145 MAP5 9 rue Charles Fourier, 91011 Evry Cedex, France;

展开▼
会议组织
原文格式 PDF
正文语种 eng
中图分类图像信号处理;
关键词
indexing and retrieval; object classification; 2D and 3D shape descriptors;

机译：索引和检索；对象分类； 2D和3D形状描述符;

相似文献

外文文献
中文文献
专利

1. 3D Model-Based Semantic Categorization of Still Image 2D Objects [J] . Raluca-Diana Petre, Titus Zaharia International journal of multimedia data engineering & management . 2011,第4期

机译：基于3D模型的静态图像2D对象的语义分类
2. 3D object articulation and motion estimation in model-based stereoscopic videoconference image sequence analysis and coding [J] . Tzovaras Dimitrios, Strintzis Michael G, Kompatsiaris Ioannis Signal Processing. Image Communication: A Publication of the the European Association for Signal Processing . 1999,第10期

机译：基于模型的立体视频会议图像序列分析和编码中的3D对象表达和运动估计
3. Volumetric object reconstruction using the 3D-MRF model-based segmentation [magnetic resonance imaging] [J] . Soo Mi Choi, Jae Eun Lee IEEE Transactions on Medical Imaging . 1997,第6期

机译：使用基于3D-MRF模型的分割[磁共振成像]重建体积物体
4. MPI parallel implementation of 3D object categorization using spin-images [C] . Eleliemy A., Hegazy D., Elkilani Wail S. International Computer Engineering Conference . 2014

机译：使用自旋图像的MPI并行实现3D对象分类
5. 3D Object Detection, Instance Segmentation and Classification from 3D Range and 2D Color Images [D] . Shen, Xiaoke. 2021

机译：3D对象检测，实例分段和3D范围和2D彩色图像的分类
6. NEUROIMAGING EVIDENCE FOR OBJECT MODEL VERIFICATION THEORY: ROLE OF PREFRONTAL CONTROL IN VISUAL OBJECT CATEGORIZATION [O] . Giorgio Ganis, Haline E. Schendan, Stephen M. Kosslyn -1

机译：对象模型验证理论的神经影像学证据：前控制在视觉对象分类中的作用
7. 3D Object Categorization Using Spin-Images with MPI Parallel Implementation [O] . D. Hegazy, A. Hamdy, W. Elkilany 2014

机译：3D对象分类使用带有MPI并行实现的自旋图像

3D Model-based Still Image Object Categorization

摘要

著录项

相似文献

相关主题

期刊订阅