Bera Aniket, Kim Sujeong, Manocha Dinesh
IEEE Comput Graph Appl. 2016 Nov-Dec;36(6):37-45. doi: 10.1109/MCG.2016.113.
The proposed interactive crowd-behavior learning algorithms can be used to analyze crowd videos for surveillance and training applications. The authors' formulation combines online tracking algorithms from computer vision, nonlinear pedestrian motion models from computer graphics, and machine learning techniques to automatically compute trajectory-level pedestrian behaviors for each agent in the video. These learned behaviors are used to automatically detect anomalous behaviors, perform motion segmentation, and generate realistic behaviors for virtual reality training applications.
所提出的交互式群体行为学习算法可用于分析群体视频，以用于监控和训练应用。作者的公式结合了计算机视觉中的在线跟踪算法、计算机图形学中的非线性行人运动模型以及机器学习技术，以自动计算视频中每个智能体的轨迹级行人行为。这些学习到的行为用于自动检测异常行为、进行运动分割，并为虚拟现实训练应用生成逼真的行为。
