项目

一般

简介

Human Detection

本课题研究图像/视频中的人识别。

技术介绍:

HOG技术

SVM技术

软件应用与安装:

OPENCV

VS2008

MATLAB 2009b/2010b

前期理论研究

2011.8

Histogram of Template for Pedestrian Detection

Accurate Human Detection by Appearance and Motion

Research on Robust Local Feature Extraction Method for Human Detection

2011.8 后续

Histograms of Oriented Gradients for Human Detection

Fast Human Detection Using a Cascade of Histograms of Oriented Gradients

Human Detection Using Oriented Histograms of Flow and Appearance

Support Vector Machines for Histogram-Based Image Classification

2012.3:

efficient HOG human detection

Robust Motion Detection using Histogram of Oriented Gradients for Illumination Variations

Extended Histogram of Gradients with Asymmetric Principal Component and Discriminant Analyses for Human Detection

AdaBoost Learning for Fabric Defect Detection Based on HOG and SVM

A Pedestrian Detection Method Based on SVM Classifier and Optimized Histograms of Oriented Gradients Feature

human detection based on integral histograms of oriented gradients and svm

human detection based on pc-svm

流程图:

HOG

HOT

SVM总结

针对性问题讨论:

直方图与SVM的关系

SVM中点的代表物及xi与yi的定义

SVM中比较方法的深入理解

代码:

HOG代码

SVM代码

论文相关:

论文

数据分析

Reference

论文: Human Detection

统计.xls (37.5 KB) 潘 宇腾, 2012-04-19 17:28

project_name_0.3.doc (1.04 MB) 潘 宇腾, 2012-05-31 17:29