Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly dist...Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly distributed features because dense features occupy excessive weight.Herein,a new human visual attention mechanism for point-and-line stereo visual odometry,which is called point-line-weight-mechanism visual odometry(PLWM-VO),is proposed to describe scene features in a global and balanced manner.A weight-adaptive model based on region partition and region growth is generated for the human visual attention mechanism,where sufficient attention is assigned to position-distinctive objects(sparse features in the environment).Furthermore,the sum of absolute differences algorithm is used to improve the accuracy of initialization for line features.Compared with the state-of-the-art method(ORB-VO),PLWM-VO show a 36.79%reduction in the absolute trajectory error on the Kitti and Euroc datasets.Although the time consumption of PLWM-VO is higher than that of ORB-VO,online test results indicate that PLWM-VO satisfies the real-time demand.The proposed algorithm not only significantly promotes the environmental adaptability of visual odometry,but also quantitatively demonstrates the superiority of the human visual attention mechanism.展开更多
Intrinsic image decomposition is an important and long-standing computer vision problem.Given an input image,recovering the physical scene properties is ill-posed.Several physically motivated priors have been used to ...Intrinsic image decomposition is an important and long-standing computer vision problem.Given an input image,recovering the physical scene properties is ill-posed.Several physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image decomposition.This work takes advantage of deep learning,and shows that it can solve this challenging computer vision problem with high efficiency.The focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input image.To achieve this goal,we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding space.We define feature distribution divergence to efficiently separate the feature vectors of different intrinsic components.The feature distributions are also constrained to fit the real ones through a feature distribution consistency.In addition,a data refinement approach is provided to remove data inconsistency from the Sintel dataset,making it more suitable for intrinsic image decomposition.Our method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent frames.Experimental results indicate that our proposed network structure can outperform the existing state-of-the-art.展开更多
In the field of supercritical wing design, various principles and rules have been summarized through theoretical and experimental analyses. Compared with black-box relationships between geometry parameters and perform...In the field of supercritical wing design, various principles and rules have been summarized through theoretical and experimental analyses. Compared with black-box relationships between geometry parameters and performances, quantitative physical laws about pressure distributions and performances are clearer and more beneficial to designers. With the advancement of computational fluid dynamics and computational intelligence, discovering new rules through statistical analysis on computers has become increasingly attractive and affordable. This paper proposes a novel sampling method for the statistical study on pressure distribution features and performances, so that new physical laws can be revealed. It utilizes an adaptive sampling algorithm, of which the criteria are developed based on Kullback–Leibler divergence and Euclidean distance.In this paper, the proposed method is employed to generate airfoil samples to study the relationships between the supercritical pressure distribution features and the drag divergence Mach number as well as the drag creep characteristic. Compared with conventional sampling methods, the proposed method can efficiently distribute samples in the pressure distribution feature space rather than directly sampling airfoil geometry parameters. The corresponding geometry parameters are searched and found under constraints, so that supercritical airfoil samples that are well distributed in the pressure distribution space are obtained. These samples allow statistical studies to obtain more reliable and universal aerodynamic rules that can be applied to supercritical airfoil designs.展开更多
Real-world networks,such as social networks,cryptocurrency networks,and e-commerce networks,always have occurrence time of interactions between nodes.Such networks are typically modeled as temporal graphs.Mining cohes...Real-world networks,such as social networks,cryptocurrency networks,and e-commerce networks,always have occurrence time of interactions between nodes.Such networks are typically modeled as temporal graphs.Mining cohesive subgraphs from temporal graphs is practical and essential in numerous data mining applications,since mining cohesive subgraphs gets insights into the time-varying nature of temporal graphs.However,existing studies on mining cohesive subgraphs,such as Densest-Exact and k-truss,are mainly tailored for static graphs(whose edges have no temporal information).Therefore,those cohesive subgraph models cannot indicate both the temporal and the structural characteristics of subgraphs.To this end,we explore the model of cohesive temporal subgraphs by incorporating both the evolving and the structural characteristics of temporal subgraphs.Unfortunately,the volume of time intervals in a temporal network is quadratic.As a result,the time complexity of mining temporal cohesive subgraphs is high.To efficiently address the problem,we first mine the temporal density distribution of temporal graphs.Guided by the distribution,we can safely prune many unqualified time intervals with the linear time cost.Then,the remaining time intervals where cohesive temporal subgraphs fall in are examined using the greedy search.The results of the experiments on nine real-world temporal graphs indicate that our model outperforms state-of-the-art solutions in efficiency and quality.Specifically,our model only takes less than two minutes on a million-vertex DBLP and has the highest overall average ranking in EDB and TC metrics.展开更多
In order to improve the accuracy of damage region division and eliminate the interference of damage adjacent region,the airframe damage region division method based on the structure tensor dynamic operator is proposed...In order to improve the accuracy of damage region division and eliminate the interference of damage adjacent region,the airframe damage region division method based on the structure tensor dynamic operator is proposed in this paper.The structure tensor feature space is established to represent the local features of damage images.It makes different damage images have the same feature distribution,and transform varied damage region division into consistent process of feature space division.On this basis,the structure tensor dynamic operator generation method is designed.It integrates with bacteria foraging optimization algorithm improved by defining double fitness function and chemotaxis rules,in order to calculate the parameters of dynamic operator generation method and realize the structure tensor feature space division.And then the airframe damage region division is realized.The experimental results on different airframe structure damage images show that compared with traditional threshold division method,the proposed method can improve the division quality.The interference of damage adjacent region is eliminated.The information loss caused by over-segmentation is avoided.And it is efficient in operation,and consistent in process.It also has the applicability to different types of structural damage.展开更多
基金Supported by Tianjin Municipal Natural Science Foundation of China(Grant No.19JCJQJC61600)Hebei Provincial Natural Science Foundation of China(Grant Nos.F2020202051,F2020202053).
文摘Visual odometry is critical in visual simultaneous localization and mapping for robot navigation.However,the pose estimation performance of most current visual odometry algorithms degrades in scenes with unevenly distributed features because dense features occupy excessive weight.Herein,a new human visual attention mechanism for point-and-line stereo visual odometry,which is called point-line-weight-mechanism visual odometry(PLWM-VO),is proposed to describe scene features in a global and balanced manner.A weight-adaptive model based on region partition and region growth is generated for the human visual attention mechanism,where sufficient attention is assigned to position-distinctive objects(sparse features in the environment).Furthermore,the sum of absolute differences algorithm is used to improve the accuracy of initialization for line features.Compared with the state-of-the-art method(ORB-VO),PLWM-VO show a 36.79%reduction in the absolute trajectory error on the Kitti and Euroc datasets.Although the time consumption of PLWM-VO is higher than that of ORB-VO,online test results indicate that PLWM-VO satisfies the real-time demand.The proposed algorithm not only significantly promotes the environmental adaptability of visual odometry,but also quantitatively demonstrates the superiority of the human visual attention mechanism.
基金supported by the Special Funds for Creative Research(Grant No.2022C61540)the National Natural Science Foundation of China(NSFC,Grant Nos.61972012 and 61732016).
文摘Intrinsic image decomposition is an important and long-standing computer vision problem.Given an input image,recovering the physical scene properties is ill-posed.Several physically motivated priors have been used to restrict the solution space of the optimization problem for intrinsic image decomposition.This work takes advantage of deep learning,and shows that it can solve this challenging computer vision problem with high efficiency.The focus lies in the feature encoding phase to extract discriminative features for different intrinsic layers from an input image.To achieve this goal,we explore the distinctive characteristics of different intrinsic components in the high-dimensional feature embedding space.We define feature distribution divergence to efficiently separate the feature vectors of different intrinsic components.The feature distributions are also constrained to fit the real ones through a feature distribution consistency.In addition,a data refinement approach is provided to remove data inconsistency from the Sintel dataset,making it more suitable for intrinsic image decomposition.Our method is also extended to intrinsic video decomposition based on pixel-wise correspondences between adjacent frames.Experimental results indicate that our proposed network structure can outperform the existing state-of-the-art.
基金supported by the National Natural Science Foundation of China(Nos.91852108 and 11872230)。
文摘In the field of supercritical wing design, various principles and rules have been summarized through theoretical and experimental analyses. Compared with black-box relationships between geometry parameters and performances, quantitative physical laws about pressure distributions and performances are clearer and more beneficial to designers. With the advancement of computational fluid dynamics and computational intelligence, discovering new rules through statistical analysis on computers has become increasingly attractive and affordable. This paper proposes a novel sampling method for the statistical study on pressure distribution features and performances, so that new physical laws can be revealed. It utilizes an adaptive sampling algorithm, of which the criteria are developed based on Kullback–Leibler divergence and Euclidean distance.In this paper, the proposed method is employed to generate airfoil samples to study the relationships between the supercritical pressure distribution features and the drag divergence Mach number as well as the drag creep characteristic. Compared with conventional sampling methods, the proposed method can efficiently distribute samples in the pressure distribution feature space rather than directly sampling airfoil geometry parameters. The corresponding geometry parameters are searched and found under constraints, so that supercritical airfoil samples that are well distributed in the pressure distribution space are obtained. These samples allow statistical studies to obtain more reliable and universal aerodynamic rules that can be applied to supercritical airfoil designs.
基金The work was supported by the National Key Research and Development Program of China under Grant No.2018YFB1402802the National Natural Science Foundation of China under Grant Nos.61932004 and 62072205.
文摘Real-world networks,such as social networks,cryptocurrency networks,and e-commerce networks,always have occurrence time of interactions between nodes.Such networks are typically modeled as temporal graphs.Mining cohesive subgraphs from temporal graphs is practical and essential in numerous data mining applications,since mining cohesive subgraphs gets insights into the time-varying nature of temporal graphs.However,existing studies on mining cohesive subgraphs,such as Densest-Exact and k-truss,are mainly tailored for static graphs(whose edges have no temporal information).Therefore,those cohesive subgraph models cannot indicate both the temporal and the structural characteristics of subgraphs.To this end,we explore the model of cohesive temporal subgraphs by incorporating both the evolving and the structural characteristics of temporal subgraphs.Unfortunately,the volume of time intervals in a temporal network is quadratic.As a result,the time complexity of mining temporal cohesive subgraphs is high.To efficiently address the problem,we first mine the temporal density distribution of temporal graphs.Guided by the distribution,we can safely prune many unqualified time intervals with the linear time cost.Then,the remaining time intervals where cohesive temporal subgraphs fall in are examined using the greedy search.The results of the experiments on nine real-world temporal graphs indicate that our model outperforms state-of-the-art solutions in efficiency and quality.Specifically,our model only takes less than two minutes on a million-vertex DBLP and has the highest overall average ranking in EDB and TC metrics.
基金the Aviation Science Foundation of China(No.20151067003)。
文摘In order to improve the accuracy of damage region division and eliminate the interference of damage adjacent region,the airframe damage region division method based on the structure tensor dynamic operator is proposed in this paper.The structure tensor feature space is established to represent the local features of damage images.It makes different damage images have the same feature distribution,and transform varied damage region division into consistent process of feature space division.On this basis,the structure tensor dynamic operator generation method is designed.It integrates with bacteria foraging optimization algorithm improved by defining double fitness function and chemotaxis rules,in order to calculate the parameters of dynamic operator generation method and realize the structure tensor feature space division.And then the airframe damage region division is realized.The experimental results on different airframe structure damage images show that compared with traditional threshold division method,the proposed method can improve the division quality.The interference of damage adjacent region is eliminated.The information loss caused by over-segmentation is avoided.And it is efficient in operation,and consistent in process.It also has the applicability to different types of structural damage.
