基于特定局部特征布局的视频运动目标挖掘

doi:10.3969/j.issn.1000-3428.2013.06.052

计算机工程 ›› 2013, Vol. 39 ›› Issue (6): 236-238,243.doi: 10.3969/j.issn.1000-3428.2013.06.052

基于特定局部特征布局的视频运动目标挖掘

马超^1,2，沈微¹，董景峰¹

(1. 东北林业大学工程技术学院，哈尔滨 150040；2. 哈尔滨工业大学计算机科学与技术学院，哈尔滨 150001)

收稿日期:2012-07-02 出版日期:2013-06-15 发布日期:2013-06-14
作者简介:马超(1979－)，男，讲师、博士研究生，主研方向：数据挖掘，数据可视化，物流信息技术；沈微、董景峰，讲师、博士
基金项目:
中央高校基本科研业务费专项基金资助项目“物联网中非结构化数据流的数据挖掘方法研究”(DL11BB21)；黑龙江省教育厅科学技术研究基金资助项目“智能供应链中非结构化数据流的数据挖掘算法研究”(12513014)

Video Moving Objects Mining Based on Distinctive Local Feature Configuration

MA Chao ^1,2, SHEN Wei ¹, DONG Jing-feng ¹

(1. College of Engineering and Technology, Northeast Forestry University, Harbin 150040, China; 2. School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, China)

Received:2012-07-02 Online:2013-06-15 Published:2013-06-14

摘要/Abstract

摘要： 针对局部特征描述子的高维特性以及视频中的复杂场景，提出一种利用频繁出现的特定局部特征空间布局对视频中运动目标进行挖掘的方法。在运动分割辅助下实现局部特征筛选，仅保留特定的运动相关特征，采用一种非参数维度约减方法建立精简描述子，并通过新的事务构建方式完成挖掘过程。标准数据集上的对比实验结果表明，该精简描述子在95%灵敏度情况下只有不到7%的假阳性率，整个挖掘方法相比同类方法具有更好的挖掘性能和可扩展性。

关键词: 局部特征, 特征布局, 视频挖掘, 特征筛选, 运动目标, 维度约减

Abstract: According to the requirements of coping with high dimensionality of local feature descriptors and clutter of video scenes, a new method of mining moving objects in videos using repetitive distinctive local feature configuration is proposed. Local features are filtered with motion segmentation aid, only the motion related descriptors are remained, and the condensed descriptors are constructed with a no parametric dimensionality reduction method. The final mining procedure is completed by a new transaction construction mechanism. Comparative test conducted on standard datasets demonstrates that the condensed descriptor gives 95% true positive at less than 7% false positive, and the whole mining method can exceed the mining performance and scalability of current state of the art techniques.

Key words: local feature, feature configuration, video mining, feature filtration, moving objects, dimension reduction

中图分类号:

TP311

马超, 沈微, 董景峰. 基于特定局部特征布局的视频运动目标挖掘[J]. 计算机工程, 2013, 39(6): 236-238,243.

MA Chao, CHEN Wei, DONG Jing-Feng. Video Moving Objects Mining Based on Distinctive Local Feature Configuration[J]. Computer Engineering, 2013, 39(6): 236-238,243.

参考文献

(上接第238页)

参考文献
[1] Ke Yan, Sukthankar R. PCA-SIFT: A More Distinctive Repre- sentation for Local Image Descriptors[C]//Proc. of IEEE Com- puter Society Conference on Computer Vision and Pattern Re- cognition. [S. l.]: IEEE Computer Society Press, 2004: 506-513.
[2] Burghouts G J, Geusebroek J M. Performance Evaluation of Local Colour Invariants[J]. Computer Vision and Image Understanding, 2009, 113(1): 48-62.
[3] Bay H, Ess A, Tuytelaars T, et al. Speeded-up Robust Features(SURF)[J]. Computer Vision and Image Under- standing, 2008, 110(3): 346-359.
[4] Quack T, Ferrari V, Leibe B. Efficient Mining of Frequent and Distinctive Feature Configurations[C]//Proc. of the 11th International Conference on Computer Vision. [S. l.]: IEEE Computer Society Press, 2007: 1-8.
[5] Morioka N, Satoh S. Building Compact Local Pairwise Code- book with Joint Feature Space Clustering[C]//Proc. of the 11th European Conference on Computer Vision. Berlin, Germany: Springer-Verlag, 2010: 692-705.
[6] Chen Hwann-Tzong, Chang Huangwei, Liu Tyng-Luh. Local Discriminant Embedding and Its Variants[C]//Proc. of IEEE Computer Society Conference on Computer Vision and Pat- tern Recognition. [S. l.]: IEEE Computer Society Press, 2005: 846-853.
[7] Ding Bolin, Lo D, Han Jiawei, et al. Efficient Mining of Closed Repetitive Gapped Subsequence from a Sequence Database[C]//Proc. of International Conference on Data Engineering. Shanghai, China: [s. n.], 2009.
[8] 张令杰, 徐维祥. 基于时态约束的关联规则挖掘算法[J]. 计算机工程, 2012, 38(5): 50-52.
[9] Ma Chao, Shen Wei. Clustering Navigation Patterns Using Closed Repetitive Gapped Subsequence[C]//Proc. of Inter- national Conference on Logistics Systems and Intelligent Management. Harbin, China: [s. n.], 2010.
[10] Sivic J, Zisserman A. Video Data Mining Using Configu- rations of Viewpoint Invariant Regions[C]//Proc. of IEEE Computer Society Conference on Computer Vision and Pat- tern Recognition. [S. l.]: IEEE Computer Society Press, 2004.
编辑顾逸斐

[1]	刘燕德, 曾体伟, 陈洞滨, 王观田. 基于区域相似信息的自适应运动目标检测算法[J]. 计算机工程, 2020, 46(3): 273-279.
[2]	张金凤, 石朝侠, 王燕清. 动态场景下基于视觉特征的SLAM方法[J]. 计算机工程, 2020, 46(10): 95-102.
[3]	谷凯凯,周东国,许晓路,蔡炜,周正钦,胡文山,黄华. 一种基于局部特征的PCNN电力故障区域提取方法[J]. 计算机工程, 2018, 44(7): 291-296.
[4]	宣晓,余勤. 加权截断p范数在运动目标检测中的应用[J]. 计算机工程, 2018, 44(6): 233-238,248.
[5]	施恩,李骞,顾大权,赵章明. 基于局部特征的卷积神经网络模型 [J]. 计算机工程, 2018, 44(2): 282-286.
[6]	刘小静,薛峰. 基于边缘对比差分算法的运动目标检测[J]. 计算机工程, 2018, 44(10): 246-251.
[7]	易生,梁华刚,茹锋. 基于多列深度3D卷积神经网络的手势识别[J]. 计算机工程, 2017, 43(8): 243-248.
[8]	段锁林,严翔,朱方,史兵. 基于改进混合高斯模型与六帧差分的目标检测算法[J]. 计算机工程, 2017, 43(7): 234-238.
[9]	王奎奎,玉振明. 基于DCT零系数与局部结构张量的局部模糊检测[J]. 计算机工程, 2017, 43(6): 207-211,218.
[10]	宋祺鹏,唐晶磊,辛菁. 基于生长模型的苗期大豆植株三维重建[J]. 计算机工程, 2017, 43(5): 275-280.
[11]	魏明俊,许道云,徐梦珂. 于均方差度量分块的自动加权稀疏表示算法[J]. 计算机工程, 2017, 43(5): 174-178,184.
[12]	房贻广,颜普,刘武,张骥,谭守标. 基于平稳小波变换和亮度序的局部特征描述子[J]. 计算机工程, 2017, 43(11): 272-276,280.
[13]	卢来,王军民,范锐. 基于自适应增强的图像二值描述子[J]. 计算机工程, 2016, 42(6): 230-234,240.
[14]	亚森·艾则孜,艾山·吾买尔. 运动目标检测中基于灰度特征模型的背景消除方法[J]. 计算机工程, 2015, 41(6): 240-246,257.
[15]	马超,沈微,董景峰. 复杂背景中一种特定运动目标检测与跟踪方法[J]. 计算机工程, 2015, 41(5): 219-223.

基于特定局部特征布局的视频运动目标挖掘

Video Moving Objects Mining Based on Distinctive Local Feature Configuration

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 10