检索结果-内蒙古大学图书馆

Generative vs. discriminative deep Belief Netwok for 3d object categorization 12

Generative vs. Discriminative Deep Belief Netwok for 3D Obje...

12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP)

作者： Zrira, Nabila Hannat, Mohamed Bouyakhf, El Houssine Khan, Haris Ahmad Mohammed V Univ Rabat Fac Sci LIMIARF Lab Rabat Morocco Univ Bourgogne Franche Comte CNRS UMR 6306 Le2iArts & Metiers Dijon France Norwegian Univ Sci & Technol NTNU Gjovik Norway

ISBN: (纸本)9789897582264

object categorization has been an important task of computer vision research in recent years. In this paper, we propose a new approach for representing and learning 3d object categories. First, We extract the Viewpoint Feature Histogram (VFH) descriptor from point clouds and then we learn the resulting features using deep learning architectures. We evaluate the performance of both generative and discriminative deep belief network architectures (GdBN/ddBN) for object categorization task. GdBN trains a sequence of Restricted Boltzmann Machines (RBMs) while ddBN uses a new deep architecture based on RBMs and the joint density model. Our results show the power of discriminative model for object categorization and outperform state-of-the-art approaches when tested on the Washington RGBd dataset.

关键词： 3d object categorization Point Clouds Viewpoint Feature Histogram (VFH) ddBN GdBN RBM Joint density Model Bback-propagation

来源：评论

学校读者我要写书评

暂无评论

Extracting Essential Local object Characteristics for 3d object categorization

Extracting Essential Local Object Characteristics for 3D Obj...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems

作者： Marianna Madry Heydar Maboudi Afkham Carl Henrik Ek Stefan Carlsson danica Kragic Centre for Autonomous Systems and the Computer Vision and Active Perception Lab CSC KTH Royal Institute of Technology Stockholm Sweden.

ISBN: (纸本)9781467363563

Most object classes share a considerable amount of local appearance and often only a small number of features are discriminative. The traditional approach to represent an object is based on a summarization of the local characteristics by counting the number of feature occurrences. In this paper we propose the use of a recently developed technique for summarizations that, rather than looking into the quantity of features, encodes their quality to learn a description of an object. Our approach is based on extracting and aggregating only the essential characteristics of an object class for a task. We show how the proposed method significantly improves on previous work in 3d object categorization. We discuss the benefits of the method in other scenarios such as robot grasping. We provide extensive quantitative and qualitative experiments comparing our approach to the state of the art to justify the described approach.

关键词： 3d object categorization traditional approach represent

来源：评论

学校读者我要写书评

暂无评论

The bag of words approach for retrieval and categorization of 3d objects

引用

VISUAL COMPUTER 2010年第10期26卷 1257-1268页

作者： Toldo, Roberto Castellani, Umberto Fusiello, Andrea Univ Verona Dipartimento Informat I-37134 Verona Italy

In this paper, we propose a novel framework for 3d object retrieval and categorization. The object is modeled in terms of its subparts as an histogram of 3d visual word occurrences. We introduce an effective method for hierarchical 3d object segmentation driven by the minima rule that combines spectral clustering-for the selection of seed-regions-with region growing based on fast marching. descriptors attached to the regions allow the definition of the visual words. After coding of each object according to the Bag-of-Words paradigm, retrieval can be performed by matching with a suitable kernel, or categorization by learning a Support Vector Machine. Several examples on the Aim@Shape watertight dataset and on the Tosca dataset demonstrate the versatility of the proposed method in working with either 3d objects with articulated shape changes or partially occluded or compound objects. Results are encouraging as shown by the comparison with other methods for each of the analyzed scenarios.

关键词： 3d object retrieval 3d object categorization 3d segmentation

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Point Cloud categorization for Rigid and Non-Rigid 3d objects 11

Evaluation of Point Cloud Categorization for Rigid and Non-R...

引用

11th Indian Conference on Computer Vision, Graphics and Image Processing (ICVGIP)

作者： Setty, Shankar Hegde, Sindhu B. Satyappanavar, Supriya Mudenagudi, Uma KLE Technol Univ Hubballi Karnataka India

ISBN: (纸本)9781450366151

In this paper, we address the problem of 3d object categorization for point cloud data. With the availability of inexpensive scanning devices and powerful computational resources, there is a rapid growth of point cloud data. This necessitates efficient classification techniques which form the basis for analysis and processing of 3d point cloud data. In order to address the classification problem, we propose a 3d object categorization framework for both rigid and non-rigid objects. Initially, the proposed approach extracts the feature descriptors using improved wave kernel signature by approximating Laplace-Beltrami operator on point cloud data for non-rigid objects. For rigid objects, our approach uses the geometric features, namely, metric tensor and Christoffel symbols by modifying the geodesic distance computation. These feature descriptors are then represented using bag-of-features and improved Fisher vector encoding techniques. Finally, the support vector machine classifies the 3d objects into predefined set of classes. We also provide an exhaustive performance evaluation of the proposed 3d object categorization framework on state-of-the-art datasets, namely, SHREC'10, SHREC'11, SHREC'12, SHREC'15 and Princeton Shape Benchmark. The evaluation results reveal that the proposed approach outperforms the existing object categorization methods for both rigid and non-rigid 3d objects.

关键词： 3d object categorization Point Cloud data Metric Tensor Christoffel Symbols IWKS IFV Bag-of-Features

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation of 3d car parts using UAV-based images

引用

COMPUTERS & GRAPHICS-UK 2022年 107卷 93-103页

作者： Jurado-Rodriguez, david Jurado, Juan M. Pauda, Luis Neto, Alexandre Munoz-Salinas, Rafael Sousa, Joaquim J. Univ Cordoba Dept Comp Sci & Numer Anal Cordoba Spain Seabery R&D Doctor Emilio Haya Prats 13 Huelva 21005 Spain Univ Granada Dept Software Engn Granada Spain Univ Tras Os Montes & Alto Douro Ctr Res & Technol Agroenvironm & Biol Sci Vila Real Portugal Univ Tras Os Montes & Alto Douro Sch Sci & Technol Vila Real Portugal INESC Technol & Sci INESC TEC C BER Porto Portugal INESC Technol & Sci INESC TEC CRIIS Porto Portugal

Environment understanding in real-world scenarios has gained an increased interest in research and industry. The advances in data capture and processing allow a high-detailed reconstruction from a set of multi-view images by generating meshes and point clouds. Likewise, deep learning architectures along with the broad availability of image datasets bring new opportunities for the segmentation of 3d models into several classes. Among the areas that can benefit from 3d semantic segmentation is the automotive industry. However, there is a lack of labeled 3d models that can be useful for training and use as ground truth in deep learning-based methods. In this work, we propose an automatic procedure for the generation and semantic segmentation of 3d cars that were obtained from the photogrammetric processing of UAV-based imagery. Therefore, sixteen car parts are identified in the point cloud. To this end, a convolutional neural network based on the U-Net architecture combined with an Inception V3 encoder was trained in a publicly available dataset of car parts. Then, the trained model is applied to the UAV-based images and these are mapped on the photogrammetric point clouds. According to the preliminary image-based segmentation, an optimization method is developed to get a full labeled point cloud, taking advantage of the geometric and spatial features of the 3d model. The results demonstrate the method's capabilities for the semantic segmentation of car models. Moreover, the proposed methodology has the potential to be extended or adapted to other applications that benefit from 3d segmented models.

关键词： 3d modeling Image mapping 3d object categorization deep learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Point Cloud categorization for Rigid and Non-Rigid 3d objects 18

Evaluation of Point Cloud Categorization for Rigid and Non-R...

引用

Proceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing

作者： Shankar Setty Sindhu B. Hegde Supriya Satyappanavar Uma Mudenagudi K. L. E. Technological University Hubballi Karnataka India

ISBN: (纸本)9781450366151

关键词： 3d object categorization

来源：评论

学校读者我要写书评

暂无评论

object categorization from Range Images using a Hierarchical Compositional Representation 22

Object Categorization from Range Images using a Hierarchical...

引用

22nd International Conference on Pattern Recognition (ICPR)

作者： Kramarev, Vladislav Zurek, Sebastian Wyatt, Jeremy L. Leonardis, Ales Univ Birmingham Sch Comp Sci Birmingham B15 2TT W Midlands England

ISBN: (纸本)9781479952083

This paper proposes a novel hierarchical compositional representation of 3d shape that can accommodate a large number of object categories and enables efficient learning and inference. The hierarchy starts with simple pre-defined parts on the first layer, after which subsequent layers are learned recursively by taking the most statistically significant compositions of parts from the previous layer. Our representation is able to scale because of its very economical use of memory and because subparts of the representation are shared. We apply our representation to 3d multi-class object categorization. object categories are represented by histograms of compositional parts, which are then used as inputs to an SVM classifier. We present results for two datasets, Aim@Shape [1] and the Washington RGB-d object dataset [2], and demonstrate the competitive performance of our method.

关键词： 3d object representation 3d object categorization compositional hierarchy classification

来源：评论

学校读者我要写书评

暂无评论

dFT-Net: deep Feature Transformation Based Network for object categorization and Part Segmentation in 3-dimensional Point Clouds

引用

SENSORS 2022年第7期22卷 2512页

作者： Sheikh, Mehak Asghar, Muhammad Adeel Bibi, Ruqia Malik, Muhammad Noman Shorfuzzaman, Mohammad Mehmood, Raja Majid Kim, Sun-Hee Natl Univ Modern Languages Dept Comp Sci NUML Rawalpindi 46000 Pakistan Natl Univ Modern Languages Dept Software Engn NUML Rawalpindi 46000 Pakistan Taif Univ Coll Comp & Informat Technol Dept Comp Sci POB 11099 At Taif 21944 Saudi Arabia Xiamen Univ Malaysia Sch Elect & Comp Engn Informat & Commun Technol Dept Sepang 43900 Malaysia Korea Univ Dept Brain & Cognit Engn Seoul 02841 South Korea

Unlike 2-dimensional (2d) images, direct 3-dimensional (3d) point cloud processing using deep neural network architectures is challenging, mainly due to the lack of explicit neighbor relationships. Many researchers attempt to remedy this by performing an additional voxelization preprocessing step. However, this adds additional computational overhead and introduces quantization error issues, limiting an accurate estimate of the underlying structure of objects that appear in the scene. To this end, in this article, we propose a deep network that can directly consume raw unstructured point clouds to perform object classification and part segmentation. In particular, a deep Feature Transformation Network (dFT-Net) has been proposed, consisting of a cascading combination of edge convolutions and a feature transformation layer that captures the local geometric features by preserving neighborhood relationships among the points. The proposed network builds a graph in which the edges are dynamically and independently calculated on each layer. To achieve object classification and part segmentation, we ensure point order invariance while conducting network training simultaneously-the evaluation of the proposed network has been carried out on two standard benchmark datasets for object classification and part segmentation. The results were comparable to or better than existing state-of-the-art methodologies. The overall score obtained using the proposed dFT-Net is significantly improved compared to the state-of-the-art methods with the ModelNet40 dataset for object categorization.

关键词： point cloud deep neural network 3d object categorization classification part segmentation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：