A motion trajectory based video retrieval system using parallel adaptive self organizing maps

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005. Pub Date : 2005-12-27 DOI:10.1109/IJCNN.2005.1556153

Wei Qu, F. Bashir, D. Graupe, A. Khokhar, D. Schonfeld

引用次数: 20

Abstract

We present a novel motion trajectory based video retrieval system using LAMSTAR-based adaptive self organizing maps (PASOMs) in this paper. The trajectories are extracted from video by a robust tracker. To reduce the high dimension of motion trajectories, we first decompose each trajectory into sub-trajectories by using a maximum acceleration based approach. Each subtrajectory is then modeled and coded by two different methods, polynomial curving fitting and independent component analysis. To fuse the different features of subtrajectories for more efficient and flexible retrieval, we use PASOMs as the searching tool. Experimental results show the superior performance of the proposed approach for video retrieval comparing with prior approaches.

查看原文

微信好友朋友圈 QQ好友复制链接

本刊更多论文

基于并行自适应自组织映射的运动轨迹视频检索系统

本文提出了一种基于lamstar的自适应自组织映射(PASOMs)的运动轨迹视频检索系统。通过鲁棒跟踪器从视频中提取轨迹。为了降低运动轨迹的高维，我们首先使用基于最大加速度的方法将每个轨迹分解为子轨迹。然后通过多项式曲线拟合和独立分量分析两种不同的方法对每个子轨迹进行建模和编码。为了融合子轨迹的不同特征，提高检索的效率和灵活性，我们使用PASOMs作为搜索工具。实验结果表明，该方法在视频检索中具有较好的性能。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文去求助

来源期刊

Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005.

自引率

0.00%

发文量

期刊最新文献

Conference topics An analysis of underfitting in MLP networks Modular network SOM (mnSOM): from vector space to function space A motion trajectory based video retrieval system using parallel adaptive self organizing maps Neural network model for time series prediction by reinforcement learning