Feature Transformation and SVM Based Hierarchical Pedestrian Detection with a Monocular Moving Camera

TIAN Guang; QI Fei-hu

您当前的位置：

首页 >

文章列表页 >

Feature Transformation and SVM Based Hierarchical Pedestrian Detection with a Monocular Moving Camera

更新时间：2025-07-16

- Feature Transformation and SVM Based Hierarchical Pedestrian Detection with a Monocular Moving Camera
- Acta Electronica Sinica Vol. 36, Issue 5, Pages: 1024-1028(2008)
- 作者机构：
  
  上海交通大学计算机科学与工程系,上海,200240
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP391
- Published：2008
- 稿件说明：
移动端阅览
TIAN Guang, QI Fei-hu. Feature Transformation and SVM Based Hierarchical Pedestrian Detection with a Monocular Moving Camera[J]. Acta Electronica Sinica, 2008, 36(5): 1024-1028.
DOI：

TIAN Guang, QI Fei-hu. Feature Transformation and SVM Based Hierarchical Pedestrian Detection with a Monocular Moving Camera[J]. Acta Electronica Sinica, 2008, 36(5): 1024-1028. DOI：

摘要

本文提出了一种应用于单目移动摄像机的基于特征变换和支持向量机(Support Vector Machine

简称SVM)的coarse-to-fine行人检测方法.首先

用查找表(Look-Up Table

简称LUT) Gentle AdaBoost Cascade训练一个粗级的行人检测器.接着把粗级的行人检测器的每一段分别作为一个特征

并用能通过粗级行人检测器的正负样本来训练基于SVM的精密级行人检测器.最后

采用基于颜色和空间信息的时序分析方法进一步提高行人检测率和降低误报率.从实验结果可以看出我们算法的高效性.

Abstract

In this paper

we propose a coarse-to-fine pedestrian detection based on feature transformation and SVM with a monocular moving camera.In this method

a coarse pedestrian detector is learnt by Look-Up Table (LUT) Gentle AdaBoost cascade.Then each stage classifier in coarse detector is taken as a feature

and a fine pedestrian detector based on those features is learnt with SVM from those training data which pass through the coarse pedestrian detector.The detection results by this detector are refined by temporal analysis using the color and spatial information of each detection results to improved pedestrian detection rate and decrease the false alarm rate.Experimental results show our method high performance.

关键词

Keywords

references

Views

1166

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Method Research on Vehicular Infrared Pedestrian Detection Based on Local Features

Multi-Pose Pedestrian Detection Based on Posterior HOG Feature

A Survey on Pedestrian Detection

Pedestrian Detection Combined with Single and Couple Pedestrian DPM Models in Traffic Scene

A Method for Pedestrian Detection by Combining Textual and Visual Information

Related Author

ZHUANG Jia-jun

LIU Qiong

WANG Guo-hua

ZHAO Hong

YUAN Huai

CHAI Li-ying

YU Bing

DUAN Cheng-wei

Related Institution

School of Software Engineering, South China University of Technology

Research Academy, Northeastern University

Fujian Key Laboratory of the Brain-like Intelligent Systems (Xiamen University)

School of ScienceJimei UniversityXiamenFujian 361021China

Department of Computer Engineering and ScienceYuan-Ze UniversityTaiwanChina

⁰