检索结果-内蒙古大学图书馆

1.2 Watt classification of 3d Voxel Based Point-clouds using a CNN on a Neural Compute Stick

NEUROCOMPUTING 2020年 393卷 165-174页

作者： Xu, Xiaofan Caulfield, Sam Amaro, Joao Falcao, Gabriel Moloney, david Intel Ireland Ltd Movidius Div Leixlip Kildare Ireland Univ Coimbra Inst Telecomunicacoes Dept Elect & Comp Engn Coimbra Portugal

With the recent surge in popularity of Convolutional Neural Networks (CNNs), motivated by their significant performance in many classification and related tasks, a new challenge now needs to be addressed: how to accommodate CNNs in mobile devices, such as drones, smartphones, and similar low-power devices? In order to tackle this challenge we exploit the Vision Processing Unit (VPU) that combines dedicated CNN hardware blocks and very low power requirement. The lack of readily available training data and memory requirements are two of the factors hindering the training and accuracy performance of 3d CNNs. In this paper, we propose a method for generating synthetic 3d point-clouds from realistic CAd scene models to enrich the training process for volumetric CNNs. Furthermore, an efficient 3d volumetric object representation Volumetric Accelerator format (VOLA) is employed. VOLA is a sexaquaternary (power-of-four subdivision) tree-based representation which allows for significant memory saving for volumetric data. Multiple CNN models were trained and pruning techniques for the weights were applied to the trained 3d Volumetric Network in order to remove almost 70% of the parameters and outperform the existing state-of-the-art networks. The top performing and efficient model was ported to the Movidius (TM) Neural Compute Stick (NCS). After deployment on the NCS, it takes 11 ms (similar to 90 frames per second) to perform inference on each input volume, with a reported power requirement of 1.2W, which leads to 75.75 inferences per second per Watt. (C) 2019 Elsevier B.V. All rights reserved.

关键词： 3d Convolutional Neural Network 3d object classification Embedded systems Low-power

来源：评论

学校读者我要写书评

暂无评论

Robust classification of 3d objects using discrete orthogonal moments and deep neural networks

引用

MULTIMEdIA TOOLS ANd APPLICATIONS 2020年第27-28期79卷 18883-18907页

作者： Lakhili, Zouhir El Alami, Abdelmajid Mesbah, Abderrahim Berrahou, Aissam Qjidaa, Hassan Sidi Mohamed Ben Abdellah Univ CED ST Ctr Doctoral Studies Sci & Technol LESSI Lab Fac Sci Dhar el Mahraz Fes Morocco Sidi Mohamed Ben Abdellah Univ Dept Phys Fes Morocco Mohammed V Univ Rabat Morocco

In this paper, we propose a new model based on 3d discrete orthogonal moments and deep neural networks (dNN) to improve the classification accuracy of 3d objects under geometric transformations and noise. However, the utilization of moment invariants presents some drawbacks: They can't describe the object efficiently, and their computation process is time consuming. discrete orthogonal moments have the property to extract pertinent features from an image even in lower orders and are robust to noise. The main goal of this work is to investigate the robustness of the proposed model to geometric transformations like translation, scale and rotation and noisy conditions. The experiment simulations are conducted on datasets formed by applying some geometric transformations and noise on selected objects from McGill database. The obtained results indicate that the proposed model achieves high performance classification rates, robust to geometric transformations and noise degradation than other methods based on moment invariants.

关键词： 3d discrete orthogonal moments 3d object classification Geometric transformations Noisy conditions deep neural networks

来源：评论

学校读者我要写书评

暂无评论

WGNet: Wider graph convolution networks for 3d point cloud classification with local dilated connecting and context-aware

引用

INTERNATIONAL JOURNAL OF APPLIEd EARTH OBSERVATION ANd GEOINFORMATION 2022年 110卷

作者： Chen, Yiping Luo, Zhipeng Li, Wen Lin, Haojia Nurunnabi, Abdul Lin, Yaojin Wang, Cheng Zhang, Xiao-Ping Li, Jonathan Sun Yat sen Univ Sch Geospatial Engn & Sci Zhuhai 519082 Peoples R China Xiamen Univ Sch Informat Fujian Key Lab Sensing & Comp Smart Cities Xiamen Peoples R China Univ Luxembourg Inst Civil & Environm Engn Dept Geodesy & Geospatial Engn Esch Sur Alzette Luxembourg Minnan Normal Univ Sch Comp Sci & Engn Zhangzhou Peoples R China Ryerson Univ Dept Elect Comp & Biomed Engn Toronto ON Canada Univ Waterloo Dept Geog & Environm Management Waterloo ON Canada Univ Waterloo Dept Syst Design Engn Waterloo ON Canada

Graph convolution networks (GCNs) have been proven powerful in describing unstructured data. Currently, most of existing GCNs aim on more accuracy by constructing deeper models. However, these methods show limited benefits, and they often suffer from the common drawbacks brought by deep networks, such as large model size, high memory consumption and slow training speed. In this paper, different from these methods, we widen GCNs to improve the descriptiveness by expanding the width of input to avoid the above drawbacks. Specifically, we present a wider GCNs based model, WGNet, for 3d point cloud classification. A local dilated connecting (LdC) module is designed to obtain the adjacency matrix, while a context information aware (CIA) module is proposed to generate initial node representation. These two modules provide a way to transform 3d point cloud into graph structure with larger receptive field and rich initial node features. These two properties widen the channels of input and provide more rich information to describe the samples precisely. Besides, we provide analysis to formulate the above idea as the sample precision description. Then, we adopt ChebyNet as our basic network, and present a skip-connection-based GCNs to improve efficiency of feature reuse. WGNet was evaluated on two datasets. One was acquired by a mobile laser scanning system under the real road environments, while the other was the well-known public artificial dataset, ModelNet40. Experimental results show that WGNet achieves better performance than the state-of-the-art in terms of descriptiveness, efficiency and robustness. Ablation studies also demonstrate the effectiveness of our designed LdC and CIA modules.

关键词： 3d point cloud Graph convolution networks 3d object classification dilated connecting Context information aware

来源：评论

学校读者我要写书评

暂无评论

SVP-Classifier: Single-View Point Cloud data Classifier with Multi-view Hallucination 21st

SVP-Classifier: Single-View Point Cloud Data Classifier with...

引用

21st International Conference on Image Analysis and Processing (ICIAP)

作者： Mohammadi, Seyed Saber Wang, Yiming Taiana, Matteo Morerio, Pietro del Bue, Alessio Univ Genoa Dept Marine Elect Elect & Telecommun Engn Genoa Italy Italian Inst Technol Pattern Anal & Comp Vis PAVIS Genoa Italy Fdn Bruno Kessler Deep Visual Learning DVL Trento Italy

ISBN: (纸本)9783031064302;9783031064296

We address single-view 3d shape classification with partial Point Cloud data (PCd) inputs. Conventional PCd classifiers achieve the best performance when trained and evaluated with complete 3d object scans. However, they all experience a performance drop when trained and evaluated on partial single-view PCd. We propose a Single-View PCd Classifier (SVP-Classifier), which first hallucinates the features of other viewpoints covering the unseen part of the object with a Conditional Variational Auto-Encoder (CVAE). It then aggregates the hallucinated multi-view features with a multi-level Graph Convolutional Network (GCN) to form a global shape representation that helps to improve the single-view PCd classification performance. With experiments on the single-view PCds generated from ModelNet40 and ScanobjectNN, we prove that the proposed SVP-Classifier outperforms the best single-view PCd-based methods, after they have been retrained on single-view PCds, thus reducing the gap between single-view methods and methods that employ complete PCds. Code and datasets are available: https://***/IIT-PAVIS/SVP-Classifier.

关键词： Multi-view feature hallucination 3d object classification Partial point cloud

来源：评论

学校读者我要写书评

暂无评论

object classification IN POINT CLOUd VIA CONdITIONAL AdVERSARIAL dOMAIN AdAPTATION FOR FOREST INVENTORY

OBJECT CLASSIFICATION IN POINT CLOUD VIA CONDITIONAL ADVERSA...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Li, Lingkai Luo, Huan Fan, Wenhui Wang, Cheng Guo, Wenzhong Li, Jonathan Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China Xiamen Univ Sch Informat Fujian Key Lab Sensing & Comp Smart City Xiamen Peoples R China Univ Waterloo Dept Geog & Environm Management Waterloo ON Canada

ISBN: (数字)9781665427920

ISBN: (纸本)9781665427920

Recently, laser scanning system is widely used to accurately predict forest inventory attributes. In this work, we propose an efficient framework including Feature Extractor Module and Conditional Adversarial Module for object classification in 3d heterogeneous point clouds. The Feature Extractor Module can aggregate features of objects in point clouds. For domain adaptation task, the Conditional Adversarial Module is proposed to minimize the discrepancy of source and target domains. Since there is no common evaluation benchmark for object classification in 3d point cloud, we build a benchmark of six tasks from three 3d objects datasets. Evaluations on six tasks with four categories have demonstrated the effectiveness of our proposed framework of object classification. The framework can be applied potentially in forest management.

关键词： Forest inventory Point cloud 3d object classification domain adaptation

来源：评论

学校读者我要写书评

暂无评论

Spherical Transformer: Adapting Spherical Signal to Convolutional Networks 5th

Spherical Transformer: Adapting Spherical Signal to Convolut...

引用

5th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Liu, Yuqi Wang, Yin du, Haikuan Cai, Shen Tongji Univ Sch Elect & Informat Engn Shanghai Peoples R China Donghua Univ Visual & Geometr Percept Lab Shanghai Peoples R China

ISBN: (纸本)9783031189128;9783031189135

Convolutional neural networks (CNNs) have been widely used in various vision tasks, e.g. image classification, semantic segmentation, etc. Unfortunately, standard 2d CNNs are not well suited for spherical signals such as panorama images or spherical projections, as the sphere is an unstructured grid. In this paper, we present Spherical Transformer which can transform spherical signals into vectors that can be directly processed by standard CNNs such that many well-designed CNNs architectures can be reused across tasks and datasets by pretraining. To this end, the proposed method first uses local structured sampling methods such as HEALPix to construct a transformer grid by using the information of spherical points and its adjacent points, and then transforms the spherical signals to the vectors through the grid. By building the Spherical Transformer module, we can use multiple CNN architectures directly. We evaluate our approach on the tasks of spherical MNIST recognition, 3d object classification and omnidirectional image semantic segmentation. For 3d object classification, we further propose a rendering-based projection method to improve the performance and a rotational-equivariant model to improve the anti-rotation ability. Experimental results on three tasks show that our approach achieves superior performance over state-of-the-art methods.

关键词： Spherical transformer 3d object classification Omnidirectional image semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Review of multi-view 3d object recognition methods based on deep learning

引用

dISPLAYS 2021年 69卷 102053-102053页

作者： Qi, Shaohua Ning, Xin Yang, Guowei Zhang, Liping Long, Peng Cai, Weiwei Li, Weijun Chinese Acad Sci Inst Semicond Beijing 100083 Peoples R China Qingdao Univ Coll Elect Informat Qingdao 266071 Peoples R China Wave Grp Cognit Comp Technol Joint Lab Beijing 102208 Peoples R China Cent South Univ Forestry & Technol Sch Logist & Transportat Changsha 410004 Peoples R China Univ Chinese Acad Sci Ctr Mat Sci & Optoelect Engn Beijing 100049 Peoples R China Univ Chinese Acad Sci Sch Microelect Beijing 100049 Peoples R China

Three-dimensional (3d) object recognition is widely used in automated driving, medical image analysis, virtual/ augmented reality, artificial intelligence robots, and other areas. deep learning is increasingly being used to solve 3d vision problems. Multi-view 3d object recognition based on the deep learning technique has become one of the rigorously researched topics because it can directly use the pretrained and successful advanced classification network as the backbone network, and views from multiple viewpoints can complement each other's detailed features of the object. However, some challenges still exist in this area. Recently, many methods have been proposed to solve the problems pertaining to this research topic. This paper presents a comprehensive review and classification of the latest developments in the deep learning methods for multi-view 3d object recognition. It also summarizes the results of these methods on a few mainstream datasets, provides an insightful summary, and puts forward enlightening future research directions.

关键词： Multi-view deep Learning 3d object classification 3d object Retrieval

来源：评论

学校读者我要写书评

暂无评论

Multi-Class classification and Multi-Output Regression of Three-dimensional objects Using Artificial Intelligence Applied to digital Holographic Information

引用

SENSORS 2023年第3期23卷 1095-1095页

作者： Mahesh, R. N. Uma Nelleri, Anith Vellore Inst Technol VIT Sch Elect Engn Chennai 600127 Tamilnadu India

digital holographically sensed 3d data processing, which is useful for AI-based vision, is demonstrated. Three prominent methods of learning from datasets such as sensed holograms, computationally retrieved intensity and phase from holograms forming concatenated intensity-phase (whole information) images, and phase-only images (depth information) were utilized for the proposed multi-class classification and multi-output regression tasks of the chosen 3d objects in supervised learning. Each dataset comprised 2268 images obtained from the chosen eighteen 3d objects. The efficacy of our approaches was validated on experimentally generated digital holographic data then further quantified and compared using specific evaluation matrices. The machine learning classifiers had better AUC values for different classes on the holograms and whole information datasets compared to the CNN, whereas the CNN had a better performance on the phase-only image dataset compared to these classifiers. The MLP regressor was found to have a stable prediction in the test and validation sets with a fixed EV regression score of 0.00 compared to the CNN, the other regressors for holograms, and the phase-only image datasets, whereas the RF regressor showed a better performance in the validation set for the whole information dataset with a fixed EV regression score of 0.01 compared to the CNN and other regressors.

关键词： 3d information sensing 3d vision convolutional neural network (CNN) digital holography machine learning artificial intelligence (AI) supervised learning 3d object classification 3d object regression

来源：评论

学校读者我要写书评

暂无评论

Weight-Edge Convolution Neural Network for Point Clouds Learning

引用

Wuhan University Journal of Natural Sciences 2021年第2期26卷 137-146页

作者： QIU Xiong ZHANG Juan ZHU Wumingrui ZHANG Shuqi KONG Lihong College of Electronic and Electrical Engineering Shanghai University of Engineering ScienceShanghai 201620China

As a kind of flexible three-dimensional geometric data, point clouds can accomplish many challenging tasks so long as the rich information in the geometric topology architecture can be deeply analyzed. On account of that point cloud data is sparse, disordered and rotation-invariant, the success of convolutional neural network in 2 d image cannot be directly reproduced on point cloud. In this paper, we propose WECNN, namely, Weight-Edge Convolution Neural Network, which has an excellent ability to utilize local structural features. As the core of WECNN, a novel convolution operator called WEConv tries to capture structural features by constructing a fixed number of directed graphs and extracting the edge information of the graph to further analyze the local regions of point cloud. Moreover, a weight function is designed for different tasks to assign weights to the edges, so that feature extractions on the edges can be more fine-grained and robust. WECNN gets overall accuracy of 93.8% and mean class accuracy of 91.6% on Model Net40 dataset. At the same time, it gets a mean Io U of 85.5% on Shape Net Part dataset. Results of extensive experiments show that our WECNN outperforms other classification and segmentation approaches on challenging benchmarks.

关键词： point cloud 3d object classification part segmentation graph convolution

来源：评论

学校读者我要写书评

暂无评论

RESIdUAL ENHANCEd MULTI-HYPERGRAPH NEURAL NETWORK

RESIDUAL ENHANCED MULTI-HYPERGRAPH NEURAL NETWORK

引用

IEEE International Conference on Image Processing (ICIP)

作者： Huang, Jing Huang, Xiaolin Yang, Jie Shanghai Jiao Tong Univ Dept Automat Shanghai Peoples R China

ISBN: (纸本)9781665441155

Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various researching fields. Meanwhile, HyperGraph Neural Network (HGNN) is currently the de-facto method for hypergraph representation learning. However, HGNN aims at single hypergraph learning and uses a pre-concatenation approach when confronting multi-modal datasets, which leads to sub-optimal exploitation of the inter-correlations of multi-modal hypergraphs. HGNN also suffers the over-smoothing issue, that is, its performance drops significantly when layers are stacked up. To resolve these issues, we propose the Residual enhanced Multi-Hypergraph Neural Network, which can not only fuse multi-modal information from each hypergraph effectively, but also circumvent the over-smoothing issue associated with HGNN. We conduct experiments on two 3d benchmarks, the NTU and the ModelNet40 datasets, and compare against multiple state-of-the-art methods. Experimental results demonstrate that both the residual hypergraph convolutions and the multi-fusion architecture can improve the performance of the base model and the combined model achieves a new state-of-the-art. Code is available at https://***/OneForward/ResMHGNN.

关键词： Hypergraph learning multi-hypergraph learning deep hypergraph neural network multimodal fusion 3d object classification

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：