期刊文献+
共找到3篇文章
< 1 >
每页显示 20 50 100
CurveNet:Curvature-Based Multitask Learning Deep Networks for 3D Object Recognition 被引量:2
1
作者 A.A.M.Muzahid Wanggen Wan +2 位作者 Ferdous Sohel Lianyao Wu Li Hou 《IEEE/CAA Journal of Automatica Sinica》 SCIE EI CSCD 2021年第6期1177-1187,共11页
In computer vision fields,3D object recognition is one of the most important tasks for many real-world applications.Three-dimensional convolutional neural networks(CNNs)have demonstrated their advantages in 3D object ... In computer vision fields,3D object recognition is one of the most important tasks for many real-world applications.Three-dimensional convolutional neural networks(CNNs)have demonstrated their advantages in 3D object recognition.In this paper,we propose to use the principal curvature directions of 3D objects(using a CAD model)to represent the geometric features as inputs for the 3D CNN.Our framework,namely CurveNet,learns perceptually relevant salient features and predicts object class labels.Curvature directions incorporate complex surface information of a 3D object,which helps our framework to produce more precise and discriminative features for object recognition.Multitask learning is inspired by sharing features between two related tasks,where we consider pose classification as an auxiliary task to enable our CurveNet to better generalize object label classification.Experimental results show that our proposed framework using curvature vectors performs better than voxels as an input for 3D object classification.We further improved the performance of CurveNet by combining two networks with both curvature direction and voxels of a 3D object as the inputs.A Cross-Stitch module was adopted to learn effective shared features across multiple representations.We evaluated our methods using three publicly available datasets and achieved competitive performance in the 3D object recognition task. 展开更多
关键词 3d shape analysis convolutional neural network DNNs object classification volumetric CNN
下载PDF
Aggregate Point Cloud Geometric Features for Processing
2
作者 Yinghao Li Renbo Xia +4 位作者 Jibin Zhao Yueling Chen Liming Tao Hangbo Zou Tao Zhang 《Computer Modeling in Engineering & Sciences》 SCIE EI 2023年第7期555-571,共17页
As 3D acquisition technology develops and 3D sensors become increasingly affordable,large quantities of 3D point cloud data are emerging.How to effectively learn and extract the geometric features from these point clo... As 3D acquisition technology develops and 3D sensors become increasingly affordable,large quantities of 3D point cloud data are emerging.How to effectively learn and extract the geometric features from these point clouds has become an urgent problem to be solved.The point cloud geometric information is hidden in disordered,unstructured points,making point cloud analysis a very challenging problem.To address this problem,we propose a novel network framework,called Tree Graph Network(TGNet),which can sample,group,and aggregate local geometric features.Specifically,we construct a Tree Graph by explicit rules,which consists of curves extending in all directions in point cloud feature space,and then aggregate the features of the graph through a cross-attention mechanism.In this way,we incorporate more point cloud geometric structure information into the representation of local geometric features,which makes our network perform better.Our model performs well on several basic point clouds processing tasks such as classification,segmentation,and normal estimation,demonstrating the effectiveness and superiority of our network.Furthermore,we provide ablation experiments and visualizations to better understand our network. 展开更多
关键词 Deep learning point-based models point cloud analysis 3d shape analysis point cloud processing
下载PDF
Missing and murdered indigenous women and girls in Canada:a new population affinity assessment technique to aid in identification using 3D technology
3
作者 Elisabeth Cuerrier-Richer 《Forensic Sciences Research》 CSCD 2022年第3期427-439,共13页
As of 2015,204 cases of missing and murdered Indigenous women and girls(MMIWG)remained unsolved in Canada,making it a major concern for Canadian Indigenous communities,who are still pressing for the resolution of thes... As of 2015,204 cases of missing and murdered Indigenous women and girls(MMIWG)remained unsolved in Canada,making it a major concern for Canadian Indigenous communities,who are still pressing for the resolution of these cases.In forensic anthropology,the assessment of population affinity can be useful to help identify victims.Population affinity,previously referred to as ancestry,is evaluated based on morphological analyses,which examine the size and shape of skeletal features,and metric analyses,which utilise skeletal measurements.However,morphological analyses strongly depend on an anthropologist’s experience with human variation,which makes the analyses particularly challenging to reproduce and standardise.The purpose of this study is to improve the rigour of morphological analyses by using 3D technology to quantify relevant cranial nonmetric population affinity traits.As there is currently little morphological data available for the Canadian Indigenous population,this research aims to develop a new technique that could aid in the identification of MMIWG.The study comprised a total of 87 adult female crania,including 24 of Canadian Inuit origin,50 of European descent and 13 of African descent.The samples were imaged using photogrammetry,then analysed using a 3D shape analysis in 3DS Max.Results show that this method is satisfactory in correctly evaluating population affinity with an accuracy of 87.36%(jackknifed:80.46%)and an average repeatability of 97%.Unfortunately,the small Canadian Indigenous sample size impacted the applicability of the results and further research will be required before the technique can be used to aid in the identification of MMIWG in Canada. 展开更多
关键词 Forensic sciences forensic anthropology population affinity assessment Canadian Indigenous morphological analyses cranial traits 3d shape analysis
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部