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
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
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
基金This paper was partially supported by a project of the Shanghai Science and Technology Committee(18510760300)Anhui Natural Science Foundation(1908085MF178)Anhui Excellent Young Talents Support Program Project(gxyqZD2019069).
文摘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.
基金supported by the National Natural Science Foundation of China (Grant Nos.91948203,52075532).
文摘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.
基金supported by the Social Sciences and Humanities Research Council of Canada(SSHRC).
文摘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.