›› 2016, Vol. 29 ›› Issue (9): 1-.

• 论文 •    下一篇

基于动态加权可变形部件模型的行人检测

高 华,邬春学,鲁 俊   

  1. (上海理工大学 光电信息与计算机工程学院,上海 200093)
  • 出版日期:2016-09-15 发布日期:2016-09-26
  • 作者简介:高华(1989-),女,硕士研究生。研究方向:数字图像处理。邬春学(1964-),男,博士,教授。研究方向:物联网与计算机控制技术。
  • 基金资助:

    国家自然科学基金资助项目(61202376);上海市教育基金会晨光计划项目(10CG49);
    上海市教委科研创新项目(13YZ075)

Pedestrian Detection Based on Deformable Part Model with Dynamic Weights Adjustment

GAO Hua, WU Chunxue, LU Jun   

  1. (School of Optical-Electronic and Computer Engineering, University of Shanghai for 
    Science and Technology, Shanghai 200093, China)
  • Online:2016-09-15 Published:2016-09-26

摘要:

近年来具有代表性的工作之一是Felzenszwalb等人提出的可变形部件模型。文中从可变形部件模型中存在的一些问题展开讨论,并提出了一种基于动态加权可变形部件模型的行人检测算法。在各个部件的检测中使用动态调整权值的方法获得更加准确的判断,从而识别处于复杂环境中的行人。实验结果表明,该方法能够有效识别复杂环境中传统DPM方法难以识别的行人。

关键词: 行人检测, 可变形部件模型, 动态加权

Abstract:

Pedestrian detection is an active research in computer vision. One of the representative works in pedestrian detection in recent years is the deformable part model (DPM). In this paper we discuss the disadvantages in DPM, and propose a new method based on the dynamic weight adjustment in DPM. The weight of the parts in DPM is adjusted dynamically to obtain more reliable results for identifying pedestrians in complex environments. Experiments show that this method can identify pedestrian more effective than the traditional DPM in complex environments.

Key words: pedestrian detection, deformable part model, dynamic weights adjustment

中图分类号: 

  • TP391.41