The Experts below are selected from a list of 48087 Experts worldwide ranked by ideXlab platform

P R Kumar - One of the best experts on this subject based on the ideXlab platform.

Mark Campbell - One of the best experts on this subject based on the ideXlab platform.

  • pedestrian motion model using non parametric trajectory clustering and Discrete Transition points
    International Conference on Robotics and Automation, 2019
    Co-Authors: Yutao Han, Rina Tse, Mark Campbell
    Abstract:

    This letter presents a pedestrian motion model that includes both low level trajectory patterns, and high level Discrete Transitions. The inclusion of both levels creates a more general predictive model, allowing for more meaningful prediction and reasoning about pedestrian trajectories, as compared to the current state of the art. The model uses an iterative clustering algorithm with Dirichlet Process Gaussian Processes to cluster trajectories into continuous motion patterns and hypothesis testing to identify Discrete Transitions in the data called Transition points . The model iteratively splits full trajectories into sub-trajectory clusters based on Transition points, where pedestrians make Discrete decisions. State Transition probabilities are then learned over the Transition points and trajectory clusters. The model is for online prediction of motions, and detection of anomalous trajectories. The proposed model is validated on the Duke Multi-Target, Multi-Camera Tracking Project (Duke MTMC) dataset to demonstrate identification of low level trajectory clusters and high level Transitions, and the ability to predict pedestrian motion and detect anomalies online with high accuracy.

  • Pedestrian Motion Model Using Non-Parametric Trajectory Clustering and Discrete Transition Points
    IEEE Robotics and Automation Letters, 2019
    Co-Authors: Yutao Han, Rina Tse, Mark Campbell
    Abstract:

    This paper presents a pedestrian motion model that includes both low level trajectory patterns, and high level Discrete Transitions. The inclusion of both levels creates a more general predictive model, allowing for more meaningful prediction and reasoning about pedestrian trajectories, as compared to the current state of the art. The model uses an iterative clustering algorithm with (1) Dirichlet Process Gaussian Processes to cluster trajectories into continuous motion patterns and (2) hypothesis testing to identify Discrete Transitions in the data called Transition points. The model iteratively splits full trajectories into sub-trajectory clusters based on Transition points, where pedestrians make Discrete decisions. State Transition probabilities are then learned over the Transition points and trajectory clusters. The model is for online prediction of motions, and detection of anomalous trajectories. The proposed model is validated on the Duke MTMC dataset to demonstrate identification of low level trajectory clusters and high level Transitions, and the ability to predict pedestrian motion and detect anomalies online with high accuracy.

Kyoungdae Kim - One of the best experts on this subject based on the ideXlab platform.

Chengbin Chu - One of the best experts on this subject based on the ideXlab platform.

  • Modeling and Conflict Detection of Crude Oil Operations for Refinery Process Based on Controlled Colored Timed Petri Net
    IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews), 2007
    Co-Authors: Naiqi Wu, Liping Bai, Chengbin Chu
    Abstract:

    Recently, there has been a great interest in the modeling and analysis of process industry, and various models are proposed for different uses. It is meaningful to have a model to serve as an analytical aid tool in short-term scheduling for oil refinery process. However, in oil refinery process, there are special constraints and requirements, and the existing models cannot be applied directly. Thus, as an application in this paper, we extend the hybrid Petri net to model the crude-oil operations in oil refinery process. This Petri net is called controlled colored timed Petri net (CCTPN). In this model, a token carries both Discrete and continuous properties. A token in a Discrete place shows its Discrete properties, while the continuous properties are captured when it is in a continuous place. A Discrete Transition treats a token just as a Discrete one, and a continuous Transition deals with it as a continuous one. In this way, we integrate the Discrete and continuous processes together in the CCTPN. Based on the CCTPN, liveness for CCTPN is defined, and with the liveness definition we show how to detect conflicts in scheduling the system by using this model.

Yutao Han - One of the best experts on this subject based on the ideXlab platform.

  • pedestrian motion model using non parametric trajectory clustering and Discrete Transition points
    International Conference on Robotics and Automation, 2019
    Co-Authors: Yutao Han, Rina Tse, Mark Campbell
    Abstract:

    This letter presents a pedestrian motion model that includes both low level trajectory patterns, and high level Discrete Transitions. The inclusion of both levels creates a more general predictive model, allowing for more meaningful prediction and reasoning about pedestrian trajectories, as compared to the current state of the art. The model uses an iterative clustering algorithm with Dirichlet Process Gaussian Processes to cluster trajectories into continuous motion patterns and hypothesis testing to identify Discrete Transitions in the data called Transition points . The model iteratively splits full trajectories into sub-trajectory clusters based on Transition points, where pedestrians make Discrete decisions. State Transition probabilities are then learned over the Transition points and trajectory clusters. The model is for online prediction of motions, and detection of anomalous trajectories. The proposed model is validated on the Duke Multi-Target, Multi-Camera Tracking Project (Duke MTMC) dataset to demonstrate identification of low level trajectory clusters and high level Transitions, and the ability to predict pedestrian motion and detect anomalies online with high accuracy.

  • Pedestrian Motion Model Using Non-Parametric Trajectory Clustering and Discrete Transition Points
    IEEE Robotics and Automation Letters, 2019
    Co-Authors: Yutao Han, Rina Tse, Mark Campbell
    Abstract:

    This paper presents a pedestrian motion model that includes both low level trajectory patterns, and high level Discrete Transitions. The inclusion of both levels creates a more general predictive model, allowing for more meaningful prediction and reasoning about pedestrian trajectories, as compared to the current state of the art. The model uses an iterative clustering algorithm with (1) Dirichlet Process Gaussian Processes to cluster trajectories into continuous motion patterns and (2) hypothesis testing to identify Discrete Transitions in the data called Transition points. The model iteratively splits full trajectories into sub-trajectory clusters based on Transition points, where pedestrians make Discrete decisions. State Transition probabilities are then learned over the Transition points and trajectory clusters. The model is for online prediction of motions, and detection of anomalous trajectories. The proposed model is validated on the Duke MTMC dataset to demonstrate identification of low level trajectory clusters and high level Transitions, and the ability to predict pedestrian motion and detect anomalies online with high accuracy.