检索结果-内蒙古大学图书馆

object classification in 3d baggage security computed tomography imagery using visual codebooks

PATTERN RECOGNITION 2015年第8期48卷 2489-2499页

作者： Flitton, Greg Mouton, Andre Breckon, Toby P. Cranfield Univ Sch Engn Cranfield MK43 0AL Beds England Univ Durham Sch Engn & Comp Sci Durham DH1 3HP England

We investigate the performance of a Bag of (Visual) Words (BoW) object classification model as an approach for automated threat object detection within 3d Computed Tomography (CT) imagery from a baggage security context. This poses a novel and unique challenge for rigid object classification within complex and cluttered volumetric imagery. Within this context it extends the BoW model to 3d transmission imagery (X-ray CT) from its conventional application in 2d reflectance (photographic) imagery. We explore combinations of four 3d feature descriptors (density Histogram (dH), density Gradient Histogram (dGH), Scale Invariant Feature Transform (SIFT) and Rotation Invariant Feature Transform (RIFT)), three codebook assignment methodologies (hard, kernel and uncertainty) and seven codebook sizes. Optimal performance is achieved using the dH and dGH descriptors in conjunction with an uncertainty assignment methodology. Successful detection rates in excess of 97% for handguns and 89% for bottles and false-positive rates of approximately 2-3% are achieved. We demonstrate that the underlying imaging modality and the irrelevance of illumination and scale invariance within the transmission imagery context considered here result in the favourable performance of simpler density histogram descriptors (dH, dGH) over 3d extensions of the well-established SIFT and RIFT feature descriptor approaches. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： 3d object classification Bag of (Visual) Words 3d descriptors SIFT RIFT Baggage-CT

来源：评论

学校读者我要写书评

暂无评论

GENERATION FOR UNSUPERVISEd dOMAIN AdAPTATION: A GAN-BASEd APPROACH FOR object classification WITH 3d POINT CLOUd dATA 47

GENERATION FOR UNSUPERVISED DOMAIN ADAPTATION: A GAN-BASED A...

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Huang, Junxuan Yuan, Junsong Qiao, Chunming Univ Buffalo Dept Comp Sci & Engn Buffalo NY 14260 USA

ISBN: (纸本)9781665405409

Recent deep networks have achieved good performance on a variety of 3d points classification tasks. However, these models often face challenges in "wild tasks" where there are considerable differences between the labeled training/source data collected by one Lidar and unseen test/target data collected by a different Lidar. Unsupervised domain adaptation (UdA) seeks to overcome such a problem without target domain labels. Instead of aligning features between source data and target data, we propose a method that uses a Generative Adversarial Network (GAN) to generate synthetic data from the source domain so that the output is close to the target domain. Experiments show that our approach performs better than state-of-the-art UdA methods in three popular 3d object/scene datasets (i.e., ModelNet, ShapeNet and ScanNet) for cross-domain 3d object classification.

关键词： 3d object classification GAN Unsupervised domain adaptation

来源：评论

学校读者我要写书评

暂无评论

InSphereNet: A Concise Representation and classification Method for 3d object 26th

InSphereNet: A Concise Representation and Classification Met...

引用

26th International Conference on MultiMedia Modeling (MMM)

作者： Cao, Hui du, Haikuan Zhang, Siyu Cai, Shen Donghua Univ Sch Comp Sci & Technol Shanghai Peoples R China

ISBN: (纸本)9783030377342;9783030377335

In this paper, we present an InSphereNet method for the problem of 3d object classification. Unlike previous methods that use points, voxels, or multi-view images as inputs of deep neural network (dNN), the proposed method constructs a class of more representative features named infilling spheres from signed distance field (SdF). Because of the admirable spatial representation of infilling spheres, we can not only utilize very fewer number of spheres to accomplish classification task, but also design a lightweight InSphereNet with less layers and parameters than previous methods. Experiments on ModelNet40 show that the proposed method leads to superior performance than PointNet in accuracy. In particular, if there are only a few dozen sphere inputs or about 100000 dNN parameters, the accuracy of our method remains at a very high level.

关键词： 3d object classification Signed distance field deep learning Infilling sphere

来源：评论

学校读者我要写书评

暂无评论

Multi-View Saliency Guided deep Neural Network for 3-d object Retrieval and classification

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2020年第6期22卷 1496-1506页

作者： Zhou, He-Yu Liu, An-An Nie, Wei-Zhi Nie, Jie Tianjin Univ Sch Elect & Informat Engn Tianjin 300072 Peoples R China Ocean Univ China Coll Informat Sci & Engn Qingdao 266100 Peoples R China

In this paper, we propose the multi-view saliency guided deep neural network (MVSG-dNN) for 3d object retrieval and classification. This method mainly consists of three key modules. First, the module of model projection rendering is employed to capture the multiple views of one 3d object. Second, the module of visual context learning applies the basic Convolutional Neural Networks for visual feature extraction of individual views and then employs the saliency LSTM to adaptively select the representative views based on multi-view context. Finally, with these information, the module of multi-view representation learning can generate the compile 3d object descriptors with the designed classification LSTM for 3d object retrieval and classification. The proposed MVSG-dNN has two main contributions: 1) It can jointly realize the selection of representative views and the similarity measure by fully exploiting multi-view context;2) It can discover the discriminative structure of multi-view sequence without constraints of specific camera settings. Consequently, it can support flexible 3d object retrieval and classification for real applications by avoiding the required camera settings. Extensive comparison experiments on ModelNet10, ModelNet40, and ShapeNetCore55 demonstrate the superiority of MVSG-dNN against the state-of-art methods.

关键词： Three-dimensional displays Solid modeling Visualization Cameras Feature extraction Computational modeling Shape 3d object retrieval 3d object classification multi-view learning saliency analysis

来源：评论

学校读者我要写书评

暂无评论

Exploring Local and Global Consistent Correlation on Hypergraph for Rotation Invariant Point Cloud Analysis

引用

IEEE TRANSACTIONS ON MULTIMEdIA 2025年 27卷 186-197页

作者： dai, Yue Ying, Shihui Gao, Yue Tsinghua Univ Sch Software BNRist KLISS Beijing 100084 Peoples R China Shanghai Univ Shanghai Inst Appl Math & Mech Shanghai 1200072 Peoples R China

Rotation invariant point cloud analysis is essential for many real-world applications where objects can appear in arbitrary orientations. Traditional local rotation-invariant methods rely on lossy region descriptors, limiting the global comprehension of 3d objects. Conversely, global features derived from pose alignment can capture complementary information. To leverage both local and global consistency for enhanced accuracy, we propose the Global-Local-Consistent Hypergraph Cross-Attention Network (GLC-HCAN). This framework includes the Global Consistent Feature (GCF) representation branch, the Local Consistent Feature (LCF) representation branch, and the Hypergraph Cross-Attention (HyperCA) network to model complex correlations through the global-local-consistent hypergraph representation learning. Specifically, the GCF branch employs a multi-pose grouping and aggregation strategy based on PCA for improved global comprehension. Simultaneously, the LCF branch uses local farthest reference point features to enhance local region descriptions. To capture high-order and complex global-local correlations, we construct hypergraphs that integrate both features, mutually enhancing and fusing the representations. The inductive HyperCA module leverages attention techniques to better utilize these high-order relations for comprehensive understanding. Consequently, GLC-HCAN offers an effective and robust rotation-invariant point cloud analysis network, suitable for object classification and shape retrieval tasks in SO(3). Experimental results on both synthetic and scanned point cloud datasets demonstrate that GLC-HCAN outperforms state-of-the-art methods.

关键词： Point cloud compression Correlation Three-dimensional displays Principal component analysis Representation learning Feature extraction Shape deep learning Transformers Topology Point cloud rotation invariance 3d object classification shape retrieval hypergraph cross-attention

来源：评论

学校读者我要写书评

暂无评论

Progressive conditional GAN-based augmentation for 3d object recognition

引用

NEUROCOMPUTING 2021年 460卷 20-30页

作者： Muzahid, A. A. M. Wanggen, Wan Sohel, Ferdous Bennamoun, Mohammed Hou, Li Ullah, Hidayat Shanghai Univ Sch Commun & Informat Engn Shanghai 200444 Peoples R China Shanghai Univ Inst Smart City Shanghai 200444 Peoples R China Murdoch Univ Informat Technol Ctr Crop & Food Innovat Murdoch WA 6150 Australia Univ Western Australia Dept Comp Sci & Software Engn Perth WA 6009 Australia Huangshan Univ Sch Informat Engn Huangshan 245041 Peoples R China

We consider the 3d object recognition problem from the perspective of the lack of labelled data. In this paper, we propose a novel progressive conditional generative adversarial network (PC-GAN) for 3d object recognition by conditioning the input with progressive learning strategies. PC-GAN is a powerful adversarial model whose generator automatically produces realistic 3d objects with annotations, and the discriminator distinguishes them from the training distribution and recognizes their categories. We train the discriminative classifier simultaneously with the generator to predict the class label by embedding a SoftMax classifier. Progressive learning uses input samples from lower to higher resolutions to increase the generator performance gradually and produce informative objects for a certain class of objects. The key idea of adopting progressing learning is to mitigate overshoots issues of the discriminator and increase variations in the generated objects by learning progressively. This strategy helps the generator to produce more realistic synthetic objects and improve the active classification performance of the discriminator. Our proposed PC-GAN is trained for object classification in a supervised manner and the performance is evaluated on two public datasets. Experimental results demonstrate that our adversarial PCGAN outperforms the existing volumetric discriminative classifiers in term of classification accuracy. (c) 2021 Elsevier B.V. All rights reserved.

关键词： 3d object classification GAN deep learning Volumetric CNN

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

View-point Invariant 3d classification for Mobile Robots Using a Convolutional Neural Network

引用

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION ANd SYSTEMS 2018年第6期16卷 2888-2895页

作者： Moon, Jiyoun Kim, Hanjun Lee, Beomhee Seoul Natl Univ Dept Elect Engn Automat & Syst Res Inst Seoul South Korea

3d object classification is an important component in semantic scene understanding for mobile robots. However, many current systems do not consider the practical issues such as object representation from different viewing positions of mobile robots. A novel 3d object representation is introduced using cylindrical occupancy grid and 3d convolutional neural network with row-wise max pooling layer. due to the rotationally invariant characteristics of this method, robots can successfully classify 3d objects regardless of starting positions of object modelling. Experimental results on publicly available benchmark dataset show the significantly improved performance compared with other conventional algorithms.

关键词： 3d object classification cylindrical CNN mobile robots view-point invariant

来源：评论

学校读者我要写书评

暂无评论

Rigid and non-rigid 3d shape classification based on 3d Hahn moments neural networks model

引用

MULTIMEdIA TOOLS ANd APPLICATIONS 2022年第26期81卷 38067-38090页

作者： Lakhili, Zouhir El Alami, Abdelmajid Mesbah, Abderrahim Berrahou, Aissam Qjidaa, Hassan Sidi Mohamed Ben Abdellah Univ Fes Morocco Mohammed V Univ Rabat Morocco

With the rapid development of 3d technology, 3d object classification has recently become a popular research topic in computer graphics and pattern recognition. Analyzing the shape of 3d models has become a common concern for researchers. A crucial technique for analyzing these 3d shapes is to capture features from 3d models that can sufficiently distinguish their shapes. While the 3d discrete orthogonal moments are powerful for the analysis and representation of 3d objects. It was proved that they have a better feature representation capability than the continuous orthogonal moments. This paper presents a new model for 3d shape classification named 3d Hahn moments neural networks (3dHMNNs) to improve the classification accuracy and decrease the computational complexity of 3d pattern recognition process. The proposed model is derived by introducing 3d Hahn moments as an input layer in neural network, largely utilized in various applications related to the pattern recognition. In fact, the advantages of image moments, especially discrete orthogonal moments have the property to extract relevant features from an object in lower orders and their robustness against image noise. Along with the efficiency of the neural networks, we can construct the proposed robust model. The main purpose of this work is to investigate the classification capabilities of the proposed model on rigid and non-rigid 3d shape datasets. The experiment simulations are conducted on the Articulated of McGill Princeton Shape Benchmark (PSB), SHREC'2011, ModelNet10 and ModelNet40 databases to assess the effectiveness of our proposed model. Two structures of the proposed model are constructed as noted 3dHMNNs(6 layers) and 3dHMNNs(7 layers). The obtained results indicate that the proposed model provide a reasonable performance in terms of classification accuracy by achieving 90.96% on ModelNet10, 83.87% on ModelNet40, 97.66% on SHREC'2011 and over 90.16% on Articulated McGill outperforming other existi

关键词： 3d object classification 3d Hahn moments neural networks 3d discrete Hahn moments Rigid 3d dataset Non-rigid 3d dataset Noisy conditions Complexity

来源：评论

学校读者我要写书评

暂无评论

Fast and Accurate Computation of 3d Charlier Moment Invariants for 3d Image classification

引用

CIRCUITS SYSTEMS ANd SIGNAL PROCESSING 2021年第12期40卷 6193-6223页

作者： Yamni, M. daoui, A. El Ogri, O. Karmouni, H. Sayyouri, M. Qjidaa, H. Maaroufi, M. Alami, B. Univ Sidi Mohamed Ben Abdellah Fac Sci Dhar El Mahrez Lab Elect Signals & Syst Informat LESSI CED STSTIC Fes Morocco Sidi Mohamed Ben Abdellah Univ Natl Sch Appl Sci Engn Syst & Applicat Lab BP 72My Abdallah Ave Km 5 Imouzzer Rd Fes Morocco Sidi Mohamed Ben Abdellah Univ Fac Med & Pharm Clin Neurosci Lab Fes Morocco Univ Hosp Fez Dept Radiol & Clin Imaging Fes Morocco Sidi Mohamed Ben Abdellah Univ Dept Biophys & Clin MRI Methods Km 2-200Sidi Hrazem RdBP 893 Fes 30000 Morocco

The problem of 3d digital object invariability is encountered in image processing, especially in pattern classification/recognition. The 3d object should be correctly recognized regardless of its particular position and orientation in the scene. This paper proposes a new method to extract 3d Charlier moment invariants to translation and scaling (3dCMITS). These descriptors are extracted directly from discrete orthogonal Charlier polynomials without using 3d geometric moment invariants. This method is fast and does not require any numerical approximation compared to the indirect method based on 3d geometric moment invariants. The results show the proposed method's effectiveness in terms of speed with an improvement exceeding 99,97%. For validation purposes and as an illustration of the interest of 3dCMITS, this paper offers a classification system for 3d objects based on the proposed 3dCMITS and Support Vector Machine (SVM) classifier. The obtained results are verified with K-Nearest Neighbor (KNN) classifier and other existing works in the literature.

关键词： 3d Charlier moment invariants 3d Charlier moments Charlier polynomials Translation-scale invariance 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：