The Experts below are selected from a list of 261 Experts worldwide ranked by ideXlab platform

Shibao Zheng - One of the best experts on this subject based on the ideXlab platform.

  • The Large-Scale Crowd Behavior Perception Based on Spatio-Temporal Viscous Fluid Field
    IEEE Transactions on Information Forensics and Security, 2013
    Co-Authors: Hang Su, Hua Yang, Shibao Zheng
    Abstract:

    Over the past decades, a wide attention has been paid to crowd control and management in the intelligent video surveillance area. Among the tasks for automatic surveillance video analysis, crowd motion modeling lays a crucial foundation for numerous subsequent analysis but encounters many unsolved challenges due to occlusions among pedestrians, complicated motion patterns in crowded scenarios, etc. Addressing the unsolved challenges, the authors propose a novel spatio-temporal Viscous Fluid field to model crowd motion patterns by exploring both appearance of crowd behaviors and interaction among pedestrians. Large-scale crowd events are hereby recognized based on characteristics of the Fluid field. First, a spatio-temporal variation matrix is proposed to measure the local fluctuation of video signals in both spatial and temporal domains. After that, eigenvalue analysis is applied on the matrix to extract the principal fluctuations resulting in an abstract Fluid field. Interaction force is then explored based on shear force in Viscous Fluid, incorporating with the fluctuations to characterize motion properties of a crowd. The authors then construct a codebook by clustering neighboring pixels with similar spatio-temporal features, and consequently, crowd behaviors are recognized using the latent Dirichlet allocation model. The convincing results obtained from the experiments on published datasets demonstrate that the proposed method obtains high-quality results for large-scale crowd behavior perception in terms of both robustness and effectiveness.

  • Crowd Event Perception Based on Spatio-temporal Viscous Fluid Field
    2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012
    Co-Authors: Hang Su, Hua Yang, Shibao Zheng
    Abstract:

    Over the past decades, a wide attention has been paid to crowd control and management in intelligent video surveillance area. In this paper, the authors propose a novel spatiotemporal Viscous Fluid field to recognize large-scale crowd event with respect to both appearance and driven factor of crowd behavior. Firstly, a spatiotemporal variation matrix is proposed to exploit motion property of a crowd. In particular, the paper exploits characteristics of the matrix with eigenvalue decomposition algorithm and constructs an abstract Fluid field to model the crowd motion pattern, which is denoted by spatiotemporal Fluid field. Secondly, the paper proposes a spatiotemporal force field to exploit the interaction force between the pedestrians. Furthermore, the Fluid and force field constructs a spatiotemporal Viscous Fluid field. Thirdly, after generating feature with bag of word model, the authors utilize latent Dirichlet allocation model to recognize crowd behavior. The experiments on PETS2009 and UMN datasets show that the proposed method has a better performance for large-scale crowd behavior perception in both robustness and effectiveness comparing with the conventional methods.

Hang Su - One of the best experts on this subject based on the ideXlab platform.

  • The Large-Scale Crowd Behavior Perception Based on Spatio-Temporal Viscous Fluid Field
    IEEE Transactions on Information Forensics and Security, 2013
    Co-Authors: Hang Su, Hua Yang, Shibao Zheng
    Abstract:

    Over the past decades, a wide attention has been paid to crowd control and management in the intelligent video surveillance area. Among the tasks for automatic surveillance video analysis, crowd motion modeling lays a crucial foundation for numerous subsequent analysis but encounters many unsolved challenges due to occlusions among pedestrians, complicated motion patterns in crowded scenarios, etc. Addressing the unsolved challenges, the authors propose a novel spatio-temporal Viscous Fluid field to model crowd motion patterns by exploring both appearance of crowd behaviors and interaction among pedestrians. Large-scale crowd events are hereby recognized based on characteristics of the Fluid field. First, a spatio-temporal variation matrix is proposed to measure the local fluctuation of video signals in both spatial and temporal domains. After that, eigenvalue analysis is applied on the matrix to extract the principal fluctuations resulting in an abstract Fluid field. Interaction force is then explored based on shear force in Viscous Fluid, incorporating with the fluctuations to characterize motion properties of a crowd. The authors then construct a codebook by clustering neighboring pixels with similar spatio-temporal features, and consequently, crowd behaviors are recognized using the latent Dirichlet allocation model. The convincing results obtained from the experiments on published datasets demonstrate that the proposed method obtains high-quality results for large-scale crowd behavior perception in terms of both robustness and effectiveness.

  • Crowd Event Perception Based on Spatio-temporal Viscous Fluid Field
    2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012
    Co-Authors: Hang Su, Hua Yang, Shibao Zheng
    Abstract:

    Over the past decades, a wide attention has been paid to crowd control and management in intelligent video surveillance area. In this paper, the authors propose a novel spatiotemporal Viscous Fluid field to recognize large-scale crowd event with respect to both appearance and driven factor of crowd behavior. Firstly, a spatiotemporal variation matrix is proposed to exploit motion property of a crowd. In particular, the paper exploits characteristics of the matrix with eigenvalue decomposition algorithm and constructs an abstract Fluid field to model the crowd motion pattern, which is denoted by spatiotemporal Fluid field. Secondly, the paper proposes a spatiotemporal force field to exploit the interaction force between the pedestrians. Furthermore, the Fluid and force field constructs a spatiotemporal Viscous Fluid field. Thirdly, after generating feature with bag of word model, the authors utilize latent Dirichlet allocation model to recognize crowd behavior. The experiments on PETS2009 and UMN datasets show that the proposed method has a better performance for large-scale crowd behavior perception in both robustness and effectiveness comparing with the conventional methods.

S. Nishijima - One of the best experts on this subject based on the ideXlab platform.

  • Development of a Superconducting High Gradient Magnetic Separator for a Highly Viscous Fluid
    IEEE Transactions on Applied Superconductivity, 2012
    Co-Authors: F. Mishima, S. Hayashi, Y. Akiyama, S. Nishijima
    Abstract:

    A magnetic separator which can remove martensitic transformed stainless steel particles from highly Viscous Fluid was developed. In the process of industrial products such as chemicals and foods, stainless steel wear debris are mixed from the movable parts of the manufacturing line into highly Viscous working Fluid. It is necessary to remove these impurities, because these can be the factor of the quality loss. Recently, the separation efficiency of the debris is decreasing drastically because the requirement of the viscosity of the working Fluid is increasing over 10 . It becomes more difficult to remove the debris with smaller than 25 micrometers. To solve the problem, superconducting high gradient magnetic separator was developed. We report the design guideline of the system based on the calculation and experiments to achieve high separation efficiency of the debris from the highly Viscous Fluid.

  • Study on High Gradient Magnetic Separation for Selective Removal of Impurity From Highly Viscous Fluid
    IEEE Transactions on Applied Superconductivity, 2011
    Co-Authors: S. Hayashi, F. Mishima, Y. Akiyama, S. Nishijima
    Abstract:

    There is an issue of contamination by metallic wear debris in the industrial plants processing highly Viscous Fluid. It is necessary to remove the ferromagnetic impurities such as metallic wear debris. In the case several kinds of ferromagnetic particles exist in the highly Viscous Fluid, it is required to remove the object material selectively. In this study, the selective separation from several kinds of ferromagnetic particles was examined by the high gradient magnetic separation (HGMS) experiment by using superconducting magnet and the particle trajectory simulation. We succeeded in separating the object particle at the flow velocity around 100 mm/s by the magnetic separation experiment. The possibility of the selective magnetic separation from several kinds of ferromagnetic particles was also confirmed by particle trajectory simulation.

  • Development of High Gradient Magnetic Separation System for a Highly Viscous Fluid
    IEEE Transactions on Applied Superconductivity, 2010
    Co-Authors: S. Hayashi, F. Mishima, Y. Akiyama, S. Nishijima
    Abstract:

    It is necessary to remove the metallic wear debris originating from pipe of manufacturing line in industrial plant processing highly Viscous Fluid such as foods or industrial products. In this study, we developed a high gradient magnetic separation (HGMS) system which consists of superconducting magnet and magnetic filters to remove the metallic wear debris. The particle trajectory simulation and the magnetic separation experiment were conducted with polyvinyl alcohol (PVA) as a model material of which viscosity coefficient was 1 Pa · s. As a result, maximum separation efficiency over 80% was achieved by optimization of experimental conditions such as mesh number, flow velocity and the number of filters.

  • a superconducting magnetic separation system of ferromagnetic fine particles from a Viscous Fluid
    Physica C-superconductivity and Its Applications, 2007
    Co-Authors: F. Mishima, Shinichi Takeda, M Fukushima, S. Nishijima
    Abstract:

    Abstract A superconducting magnetic separation system has been developed to remove fine particles of martensitic transformed stainless steel (diameter: 1–10 μm) from a Viscous Fluid. The magnetic filters were set in the superconducting magnet with large spaces between filters. The separation efficiency increased with the magnetic field due to the magnetic force to the particles being in the radial direction. The design concept of an HGMS is proposed. The separation efficiency was examined by changing the flow rate and magnetic field. The experimental results are used for the design of the system.

Hua Yang - One of the best experts on this subject based on the ideXlab platform.

  • The Large-Scale Crowd Behavior Perception Based on Spatio-Temporal Viscous Fluid Field
    IEEE Transactions on Information Forensics and Security, 2013
    Co-Authors: Hang Su, Hua Yang, Shibao Zheng
    Abstract:

    Over the past decades, a wide attention has been paid to crowd control and management in the intelligent video surveillance area. Among the tasks for automatic surveillance video analysis, crowd motion modeling lays a crucial foundation for numerous subsequent analysis but encounters many unsolved challenges due to occlusions among pedestrians, complicated motion patterns in crowded scenarios, etc. Addressing the unsolved challenges, the authors propose a novel spatio-temporal Viscous Fluid field to model crowd motion patterns by exploring both appearance of crowd behaviors and interaction among pedestrians. Large-scale crowd events are hereby recognized based on characteristics of the Fluid field. First, a spatio-temporal variation matrix is proposed to measure the local fluctuation of video signals in both spatial and temporal domains. After that, eigenvalue analysis is applied on the matrix to extract the principal fluctuations resulting in an abstract Fluid field. Interaction force is then explored based on shear force in Viscous Fluid, incorporating with the fluctuations to characterize motion properties of a crowd. The authors then construct a codebook by clustering neighboring pixels with similar spatio-temporal features, and consequently, crowd behaviors are recognized using the latent Dirichlet allocation model. The convincing results obtained from the experiments on published datasets demonstrate that the proposed method obtains high-quality results for large-scale crowd behavior perception in terms of both robustness and effectiveness.

  • Crowd Event Perception Based on Spatio-temporal Viscous Fluid Field
    2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012
    Co-Authors: Hang Su, Hua Yang, Shibao Zheng
    Abstract:

    Over the past decades, a wide attention has been paid to crowd control and management in intelligent video surveillance area. In this paper, the authors propose a novel spatiotemporal Viscous Fluid field to recognize large-scale crowd event with respect to both appearance and driven factor of crowd behavior. Firstly, a spatiotemporal variation matrix is proposed to exploit motion property of a crowd. In particular, the paper exploits characteristics of the matrix with eigenvalue decomposition algorithm and constructs an abstract Fluid field to model the crowd motion pattern, which is denoted by spatiotemporal Fluid field. Secondly, the paper proposes a spatiotemporal force field to exploit the interaction force between the pedestrians. Furthermore, the Fluid and force field constructs a spatiotemporal Viscous Fluid field. Thirdly, after generating feature with bag of word model, the authors utilize latent Dirichlet allocation model to recognize crowd behavior. The experiments on PETS2009 and UMN datasets show that the proposed method has a better performance for large-scale crowd behavior perception in both robustness and effectiveness comparing with the conventional methods.

F. Mishima - One of the best experts on this subject based on the ideXlab platform.

  • Development of a Superconducting High Gradient Magnetic Separator for a Highly Viscous Fluid
    IEEE Transactions on Applied Superconductivity, 2012
    Co-Authors: F. Mishima, S. Hayashi, Y. Akiyama, S. Nishijima
    Abstract:

    A magnetic separator which can remove martensitic transformed stainless steel particles from highly Viscous Fluid was developed. In the process of industrial products such as chemicals and foods, stainless steel wear debris are mixed from the movable parts of the manufacturing line into highly Viscous working Fluid. It is necessary to remove these impurities, because these can be the factor of the quality loss. Recently, the separation efficiency of the debris is decreasing drastically because the requirement of the viscosity of the working Fluid is increasing over 10 . It becomes more difficult to remove the debris with smaller than 25 micrometers. To solve the problem, superconducting high gradient magnetic separator was developed. We report the design guideline of the system based on the calculation and experiments to achieve high separation efficiency of the debris from the highly Viscous Fluid.

  • Study on High Gradient Magnetic Separation for Selective Removal of Impurity From Highly Viscous Fluid
    IEEE Transactions on Applied Superconductivity, 2011
    Co-Authors: S. Hayashi, F. Mishima, Y. Akiyama, S. Nishijima
    Abstract:

    There is an issue of contamination by metallic wear debris in the industrial plants processing highly Viscous Fluid. It is necessary to remove the ferromagnetic impurities such as metallic wear debris. In the case several kinds of ferromagnetic particles exist in the highly Viscous Fluid, it is required to remove the object material selectively. In this study, the selective separation from several kinds of ferromagnetic particles was examined by the high gradient magnetic separation (HGMS) experiment by using superconducting magnet and the particle trajectory simulation. We succeeded in separating the object particle at the flow velocity around 100 mm/s by the magnetic separation experiment. The possibility of the selective magnetic separation from several kinds of ferromagnetic particles was also confirmed by particle trajectory simulation.

  • Development of High Gradient Magnetic Separation System for a Highly Viscous Fluid
    IEEE Transactions on Applied Superconductivity, 2010
    Co-Authors: S. Hayashi, F. Mishima, Y. Akiyama, S. Nishijima
    Abstract:

    It is necessary to remove the metallic wear debris originating from pipe of manufacturing line in industrial plant processing highly Viscous Fluid such as foods or industrial products. In this study, we developed a high gradient magnetic separation (HGMS) system which consists of superconducting magnet and magnetic filters to remove the metallic wear debris. The particle trajectory simulation and the magnetic separation experiment were conducted with polyvinyl alcohol (PVA) as a model material of which viscosity coefficient was 1 Pa · s. As a result, maximum separation efficiency over 80% was achieved by optimization of experimental conditions such as mesh number, flow velocity and the number of filters.

  • a superconducting magnetic separation system of ferromagnetic fine particles from a Viscous Fluid
    Physica C-superconductivity and Its Applications, 2007
    Co-Authors: F. Mishima, Shinichi Takeda, M Fukushima, S. Nishijima
    Abstract:

    Abstract A superconducting magnetic separation system has been developed to remove fine particles of martensitic transformed stainless steel (diameter: 1–10 μm) from a Viscous Fluid. The magnetic filters were set in the superconducting magnet with large spaces between filters. The separation efficiency increased with the magnetic field due to the magnetic force to the particles being in the radial direction. The design concept of an HGMS is proposed. The separation efficiency was examined by changing the flow rate and magnetic field. The experimental results are used for the design of the system.