基于核Fisher判别分析视频运动目标的分类

刘丽红; 曾志高; 彭程; 杨凡稳; 周丹; 姚慧丹

基于核Fisher判别分析视频运动目标的分类

引用本文：刘丽红，曾志高，彭程，杨凡稳，周丹,姚慧丹.基于核Fisher判别分析视频运动目标的分类[J].计算技术与自动化,2015,(2):87-91

摘要点击次数: 1267

全文下载次数: 55

作者	单位
刘丽红，曾志高，彭程，杨凡稳，周丹,姚慧丹	（1．湖南工业大学计算机与通信学院智能所, 湖南株洲412007；2. 华北电力大学能源动力与机械工程学院，北京102206)

中文摘要:针对线性判别分析只能提取线性特征而不能描述非线性特征的缺点，采用将核函数和Fisher判别分析方法的可分性结合起来的核Fisher判别分析的方法对视频中的运动目标进行自动分类，运动目标包含人、汽车和宠物三类。该方法取得了较好的分类效果，且在查全率、查准率和F1 -Measure获得了满意的性能。

中文关键词:线性判别分析特征提取核Fisher判别分析运动目标分类视频

Classification of Moving Targets in Video Based on the Kernel Fisher Discriminant Analysis

Abstract:In order to overcome the shorts of linear discriminant analysis, which can only extract linear features and can not describe nonlinear characteristics, the Kernel Fisher Discriminant Analysis algorithm, which combines the kernel learning and the separation of linear discriminant analysis, was adopted to automatically classify the moving objects in video. The objects include three categories: people, cars and pets. The method has obtained satisfying performance both in this system and in the recall, precision and F1-score.

keywords:linear discriminant analysis feature extraction kernel Fisher discriminant analysis moving object classification video

查看全文 查看/发表评论 下载pdf阅读器