An analysis of solving the electromagnetic scattering by buried objects using vectorwave function expansion is presented.For expanding the boundary conditions both on the planarair-earth interface and on the spherical...An analysis of solving the electromagnetic scattering by buried objects using vectorwave function expansion is presented.For expanding the boundary conditions both on the planarair-earth interface and on the spherical surface,the conversion relations between the cylindricaland spherical vector wave functions are derived.Hence the vector wave function expansion isconveniently applied to solve this complex boundary-value problem.For the excitation of the in-cident plane wave and the dipole above the earth,the scatterlng patterns of the buried conductingand dielectric spheres are presented and discussed.展开更多
Road boundary detection is essential for autonomous vehicle localization and decision-making,especially under GPS signal loss and lane discontinuities.For road boundary detection in structural environments,obstacle oc...Road boundary detection is essential for autonomous vehicle localization and decision-making,especially under GPS signal loss and lane discontinuities.For road boundary detection in structural environments,obstacle occlusions and large road curvature are two significant challenges.However,an effective and fast solution for these problems has remained elusive.To solve these problems,a speed and accuracy tradeoff method for LiDAR-based road boundary detection in structured environments is proposed.The proposed method consists of three main stages:1)a multi-feature based method is applied to extract feature points;2)a road-segmentation-line-based method is proposed for classifying left and right feature points;3)an iterative Gaussian Process Regression(GPR)is employed for filtering out false points and extracting boundary points.To demonstrate the effectiveness of the proposed method,KITTI datasets is used for comprehensive experiments,and the performance of our approach is tested under different road conditions.Comprehensive experiments show the roadsegmentation-line-based method can classify left,and right feature points on structured curved roads,and the proposed iterative Gaussian Process Regression can extract road boundary points on varied road shapes and traffic conditions.Meanwhile,the proposed road boundary detection method can achieve real-time performance with an average of 70.5 ms per frame.展开更多
This paper provides a brief introduction to the methods for generating fuzzy categorical maps from remotely sensed images (in graphical and digital forms).This is followed by a description of the slicing process for d...This paper provides a brief introduction to the methods for generating fuzzy categorical maps from remotely sensed images (in graphical and digital forms).This is followed by a description of the slicing process for deriving fuzzy boundaries from fuzzy categorical maps,which can be based on the maximum fuzzy membership values,confusion index,or measure of entropy.Results from an empirical test preformed in an Edinburgh suburb show that fuzzy boundaries of land cover can be derived from aerial photographs and satellite images by using the three criteria with small differences,and that slicing based on the maximum fuzzy membership values is the easiest and most straightforward solution.This,in turn,implies the suitability of maintaining both a crisp classification and its underlying certainty map for deriving fuzzy boundaries at different thresholds,which is a flexible and compact management of categorical map data and their uncertainty.展开更多
Monocular depth estimation is the basic task in computer vision.Its accuracy has tremendous improvement in the decade with the development of deep learning.However,the blurry boundary in the depth map is a serious pro...Monocular depth estimation is the basic task in computer vision.Its accuracy has tremendous improvement in the decade with the development of deep learning.However,the blurry boundary in the depth map is a serious problem.Researchers find that the blurry boundary is mainly caused by two factors.First,the low-level features,containing boundary and structure information,may be lost in deep networks during the convolution process.Second,themodel ignores the errors introduced by the boundary area due to the few portions of the boundary area in the whole area,during the backpropagation.Focusing on the factors mentioned above.Two countermeasures are proposed to mitigate the boundary blur problem.Firstly,we design a scene understanding module and scale transformmodule to build a lightweight fuse feature pyramid,which can deal with low-level feature loss effectively.Secondly,we propose a boundary-aware depth loss function to pay attention to the effects of the boundary’s depth value.Extensive experiments show that our method can predict the depth maps with clearer boundaries,and the performance of the depth accuracy based on NYU-Depth V2,SUN RGB-D,and iBims-1 are competitive.展开更多
三支决策将不确定样本划分至边界域进行延迟决策,但需基于损失函数确定阈值,以划分边界域,然而,损失函数通常需要先验知识,具有一定的主观性,因此对边界域划分能力不足。针对这种问题,构建一种多目标三支决策边界域求解方法,从而更好地...三支决策将不确定样本划分至边界域进行延迟决策,但需基于损失函数确定阈值,以划分边界域,然而,损失函数通常需要先验知识,具有一定的主观性,因此对边界域划分能力不足。针对这种问题,构建一种多目标三支决策边界域求解方法,从而更好地划分边界域,提升分类性能。采用贝叶斯规则获取样本的条件概率;设定3个目标,包括降低边界域的不确定性、缩小边界域的大小以及减小整个决策区域的错误分类率,通过融入熵权法的TOPSIS(technique for order preference by similarity to an ideal solution)方法求取最优阈值,该方法采用熵权法计算这3个目标所占的权重,得到最优阈值,获得边界域,进行延迟决策;结合不同分类器对边界域进行分类。通过UCI数据集进行对比实验,根据分类准确率和F1值,表明该方法学习到的阈值能合理地划分边界域,建立的模型能取得更好的分类性能。展开更多
Collaborative work on increasingly complex hydroclimatic investigations often crosses disciplinary boundaries. Elements of scientific inquiry, such as data or the results of analyses can become objectified, or capable...Collaborative work on increasingly complex hydroclimatic investigations often crosses disciplinary boundaries. Elements of scientific inquiry, such as data or the results of analyses can become objectified, or capable of being adopted and/or adapted by users from multiple disciplinary realms. These objects often provide a bridge for collaborative endeavors, or are used as tools by individuals pursuing multi-disciplinary work. Boundary object terminology was first formalized and applied by social scientists. However, few examples of the application of this useful framework are found in the hydrologic literature. The construct is applied here to identify and discuss how common researcb products and processes are used both internally and externally through providing examples from a project examining the historical and paleo proxy-based hydroclimatology of a headwaters region of Mongolia. The boundary object concept is valuable to consider when conducting and critiquing basic research, collaborating across multiple disciplinary teams as when studying climate change issues, as an individual researcher working in a cross boundary sense using methods from differing disciplines to answer questions, and/or when one group adapts the work of another to their own research problems or interpretive needs, as occurred with selected products of this project.展开更多
基金This work is supported by the National Natural Science Foundation of China
文摘An analysis of solving the electromagnetic scattering by buried objects using vectorwave function expansion is presented.For expanding the boundary conditions both on the planarair-earth interface and on the spherical surface,the conversion relations between the cylindricaland spherical vector wave functions are derived.Hence the vector wave function expansion isconveniently applied to solve this complex boundary-value problem.For the excitation of the in-cident plane wave and the dipole above the earth,the scatterlng patterns of the buried conductingand dielectric spheres are presented and discussed.
基金This work was supported by the Research on Construction and Simulation Technology of Hardware in Loop Testing Scenario for Self-Driving Electric Vehicle in China(2018YFB0105103J).
文摘Road boundary detection is essential for autonomous vehicle localization and decision-making,especially under GPS signal loss and lane discontinuities.For road boundary detection in structural environments,obstacle occlusions and large road curvature are two significant challenges.However,an effective and fast solution for these problems has remained elusive.To solve these problems,a speed and accuracy tradeoff method for LiDAR-based road boundary detection in structured environments is proposed.The proposed method consists of three main stages:1)a multi-feature based method is applied to extract feature points;2)a road-segmentation-line-based method is proposed for classifying left and right feature points;3)an iterative Gaussian Process Regression(GPR)is employed for filtering out false points and extracting boundary points.To demonstrate the effectiveness of the proposed method,KITTI datasets is used for comprehensive experiments,and the performance of our approach is tested under different road conditions.Comprehensive experiments show the roadsegmentation-line-based method can classify left,and right feature points on structured curved roads,and the proposed iterative Gaussian Process Regression can extract road boundary points on varied road shapes and traffic conditions.Meanwhile,the proposed road boundary detection method can achieve real-time performance with an average of 70.5 ms per frame.
文摘This paper provides a brief introduction to the methods for generating fuzzy categorical maps from remotely sensed images (in graphical and digital forms).This is followed by a description of the slicing process for deriving fuzzy boundaries from fuzzy categorical maps,which can be based on the maximum fuzzy membership values,confusion index,or measure of entropy.Results from an empirical test preformed in an Edinburgh suburb show that fuzzy boundaries of land cover can be derived from aerial photographs and satellite images by using the three criteria with small differences,and that slicing based on the maximum fuzzy membership values is the easiest and most straightforward solution.This,in turn,implies the suitability of maintaining both a crisp classification and its underlying certainty map for deriving fuzzy boundaries at different thresholds,which is a flexible and compact management of categorical map data and their uncertainty.
基金supported in part by School Research Projects of Wuyi University (No.5041700175).
文摘Monocular depth estimation is the basic task in computer vision.Its accuracy has tremendous improvement in the decade with the development of deep learning.However,the blurry boundary in the depth map is a serious problem.Researchers find that the blurry boundary is mainly caused by two factors.First,the low-level features,containing boundary and structure information,may be lost in deep networks during the convolution process.Second,themodel ignores the errors introduced by the boundary area due to the few portions of the boundary area in the whole area,during the backpropagation.Focusing on the factors mentioned above.Two countermeasures are proposed to mitigate the boundary blur problem.Firstly,we design a scene understanding module and scale transformmodule to build a lightweight fuse feature pyramid,which can deal with low-level feature loss effectively.Secondly,we propose a boundary-aware depth loss function to pay attention to the effects of the boundary’s depth value.Extensive experiments show that our method can predict the depth maps with clearer boundaries,and the performance of the depth accuracy based on NYU-Depth V2,SUN RGB-D,and iBims-1 are competitive.
文摘三支决策将不确定样本划分至边界域进行延迟决策,但需基于损失函数确定阈值,以划分边界域,然而,损失函数通常需要先验知识,具有一定的主观性,因此对边界域划分能力不足。针对这种问题,构建一种多目标三支决策边界域求解方法,从而更好地划分边界域,提升分类性能。采用贝叶斯规则获取样本的条件概率;设定3个目标,包括降低边界域的不确定性、缩小边界域的大小以及减小整个决策区域的错误分类率,通过融入熵权法的TOPSIS(technique for order preference by similarity to an ideal solution)方法求取最优阈值,该方法采用熵权法计算这3个目标所占的权重,得到最优阈值,获得边界域,进行延迟决策;结合不同分类器对边界域进行分类。通过UCI数据集进行对比实验,根据分类准确率和F1值,表明该方法学习到的阈值能合理地划分边界域,建立的模型能取得更好的分类性能。
文摘Collaborative work on increasingly complex hydroclimatic investigations often crosses disciplinary boundaries. Elements of scientific inquiry, such as data or the results of analyses can become objectified, or capable of being adopted and/or adapted by users from multiple disciplinary realms. These objects often provide a bridge for collaborative endeavors, or are used as tools by individuals pursuing multi-disciplinary work. Boundary object terminology was first formalized and applied by social scientists. However, few examples of the application of this useful framework are found in the hydrologic literature. The construct is applied here to identify and discuss how common researcb products and processes are used both internally and externally through providing examples from a project examining the historical and paleo proxy-based hydroclimatology of a headwaters region of Mongolia. The boundary object concept is valuable to consider when conducting and critiquing basic research, collaborating across multiple disciplinary teams as when studying climate change issues, as an individual researcher working in a cross boundary sense using methods from differing disciplines to answer questions, and/or when one group adapts the work of another to their own research problems or interpretive needs, as occurred with selected products of this project.
