Motion Pattern Discovery from the Moving Object Trajectory

摘要：

This paper is concerned with motion pattern discovery from the moving object trajectory. The motion trajectory is arbitrarily sampled as a sequence of spatial coordinates over time. Upon the requirements of wavelet transformations, some linearly interpolations of sampled data are made first. After a wavelet transformation of the moving object trajectory, the wavelet coefficients are thresholded particularly for identifying speed-changing positions and motion trends of the object. Importantly, the relations between wavelet transformation coefficients and motion characteristics have been elaborated. Some experimental results have shown that the multi-resolution analysis of wavelets is helpful to discover some motion patterns (speed- changing positions, motion trends or simplified trajectories) from the moving object trajectory.

关键词： wavelets motion trajectory data mining

作者: Hong Shu Jun Pang Cuihong Qi

作者单位: National Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan, China

会议类型: 国际会议

会议名称: The Second International Symposium on Intelligence Computation and Applications(ISICA 2007)(第二届智能计算及其应用国际会议)

会议地点: 武汉

会议语种:英文

在线出版日期: 2007-09-21（万方平台首次上网日期，不代表论文的发表时间）