Aggregation analysis of surveillance trajectory based on motion similarity

作者：Liang Hao Zhe^*; Huang Kui Hua; Li Guo Hui; Zhang Jun

来源：Journal of National University of Defense Technology, 2011, 33(5): 103-109.

• Aggregation model
• Feature estimation
• Hierarchical trajectory
• Inflection points
• Kernel Density Estimation
• Motion features
• Motion region
• Motion similarity
• Multi-modal
• Potential structure
• Semantic content
• Temporal pattern
• Trajectory-based
• Visual surveillance

For surveillance trajectory, a potential semantic content discovering method based on motion features was investigated. In the phase of feature estimation, precise and smooth multi-modal distribution of direction was obtained by combining inflection points of trajectory curve with the kernel density estimation. Then sequential and concurrent temporal patterns of trajectory sub-class were modeled by Hidden Markov Model. With motion feature distribution, a hierarchical trajectory aggregation model based on motion similarity was proposed. Experimental results show that the model can be used to discover potential structure of trajectory set which reflect the motion region information of surveillance scene.

• 出版日期2011