1、结构图

Introduction

Feature extraction, deformation handling, occlusion handling, and classification are four important components in pedestrian detection. Existing methods learn or design these components either individually or sequentially. The interaction among these components is not yet well explored. This paper proposes that they should be jointly learned in order to maximize their strengths through cooperation. We formulate these four components into a joint deep learning framework and propose a new deep network architecture

Contribution Highlights

  • A unified deep model for jointly learning feature extraction, a part deformation model, an occlusion model and classification. With the deep model, these components interact with each other in the learning process, which allows each component to maximize its strength when cooperating with others .
  • We enrich the operation in deep models by incorporating the deformation layer into the convolutional neural networks (CNN). With this layer, various deformation handling approaches can be applied to our deep model.
  • The features are learned from pixels through interaction with deformation and occlusion handling models . Such interaction helps to learn more discriminative features.

Citation

If you use our codes or dataset, please cite the following papers:

  • W. Ouyang and X. Wang. Joint Deep Learning for Pedestrian Detection. In ICCV, 2013. PDF

Code (Matlab code on Wnidows OS)

Code and dataset on Google Drive:

For users who cannot download from Google Drive:

The files are on the GoogleDocs and Baidu. To Run the code, please read the following readme file:

  • Readme
  • 1. Put all of the documents into the same folder and decompress them using the command "extract to here". Suppose the root folder is "root", then you should have three folders "root/CNN", "root/data", "root/model", "root/NN", "root/tmptoolbox", "root/util", and "root/dbEval". For "root/data", there should be 4 folders: "root/data/CaltechTest", "root/data/CaltechTrain", "root/data/ETH", and "root/data/INRIATrain".
  • 2. Run the "cnnexamples.m" or "testing.m." in the folder "root/CNN" to obtain the results.

FAQ

最新文章

  1. React Native 开发之 (07) 常用组件-View
  2. java高薪之路__002_异常处理
  3. 用C#开发的双色球走势图(二)
  4. 修改数据库中group_concat的返回结果的长度限制
  5. Java intern()方法
  6. Java 将容器 Map中的内容保存到数组
  7. iconfont在线链接使用方法（转）
  8. MySQL主从 常见的错误及解决方案
  9. LNK2022: 元数据操作失败(8013118D): 重复类型(FactoryContext)中的布局信息不一致: (0x02000230)
  10. RabbitMQ下的生产消费者模式与订阅发布模式
  11. C++变量存储类别和内存四区
  12. [51CTO]新说MySQL事务隔离级别！
  13. [DevExpress使用随笔]之预览repx报表（转）
  14. PHP框架CI（codeigniter）的使用笔记
  15. iOS 11开发教程（一）
  16. Java第五次实验报告
  17. 第13章 学习shell script
  18. scala windows 安装
  19. 优雅的处理你的Java异常
  20. 配置Linux的SSH双重认证

热门文章

  1. 探索C++的秘密之详解extern "C",这就是为什么很多.lib被我们正确调用确总是无法解析的。
  2. HTML 链接<a>标签
  3. Android开发--Layout元素
  4. uva 1660 & poj 1966(点连通度）
  5. cookie的使用
  6. 【59测试】【树】【dp】
  7. JavaScript本地对象 内置对象 宿主对象
  8. 例子：Alarm Clock with voice Commands Sample
  9. Android开源框架：Universal-Image-Loader解析（一）
  10. 关于VS中文件属性的解释