Joint Deep Learning for Pedestrian Detection笔记

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

时间： 2024-10-15 15:46:03

Joint Deep Learning for Pedestrian Detection笔记的相关文章

行人检测(Pedestrian Detection)资源整理

一.论文 综述类的文章: [1] D. Geronimo, and A. M.Lopez. Vision-based Pedestrian Protection Systems for Intelligent Vehicles, BOOK, 2014. [2] P.Dollar, C. Wojek,B. Schiele, et al. Pedestrian detection: an evaluation of the state of the art [J].IEEE Transactions

论文笔记之：Pedestrian Detection aided by Deep Learning Semantic Tasks

Pedestrian Detection aided by Deep Learning Semantic Tasks CVPR 2015 本文考虑将语义任务(即:行人属性和场景属性)和行人检测相结合,以语义信息协助进行行人检测.先来看一下大致的检测结果(TA-CNN为本文检测结果): 可以看出,由于有了属性信息的协助,其行人检测的精确度有了较大的提升.具体网络架构如下图所示:

论文笔记之：From Facial Parts Responses to Face Detection: A Deep Learning Approach

From Facial Parts Responses to Face Detection: A Deep Learning Approach ICCV 2015

Deep Learning Face Representation by Joint Identification-Verification

Deep Learning Face Representation by Joint Identification-Verification 转载请注明:http://blog.csdn.net/stdcoutzyx/article/details/41497545 这篇文章是论文Deep Learning Face Representation by Joint Identification-Verification的笔记. 1. Main Contribution 这篇论文使用deep le

深度学习论文阅读笔记--Deep Learning Face Representation from Predicting 10,000 Classes

来自:CVPR 2014   作者:Yi Sun ,Xiaogang Wang,Xiaoao Tang 题目:Deep Learning Face Representation from Predicting 10,000 Classes 主要内容:通过深度学习来进行图像高级特征表示(DeepID),进而进行人脸的分类. 优点:在人脸验证上面做,可以很好的扩展到其他的应用,并且夸数据库有效性:在数据库中的类别越多时,其泛化能力越强,特征比较少,不像其他特征好几K甚至上M,好的泛化能力+不过拟合于

Deep Learning Face Representation from Predicting 10,000 Classes论文笔记

Deep Learning Face Representation from Predicting 10,000 Classes论文笔记(2015.03.24) 一.基本思路 作者利用卷积神经网络(Convolutional Neural Network,CNN)对大量样本进行训练,提取Deep hidden identity feature(DeepID)特征,然后利用这些特征进行人脸验证(Face Verification).在LFW(Labeled Faces in the Wild)库上

Progress and Prospect of target detection technology based on deep learning

Viola-Jones face detector One of the more successful examples of object detection in the whole computer field is the Viola-Jones face detector that appeared around 2000,which makes it a more mature technique compared to the object detection.The basic

Deep Learning（深度学习）学习笔记整理系列七

Deep Learning(深度学习)学习笔记整理系列 声明: 1)该Deep Learning的学习系列是整理自网上很大牛和机器学习专家所无私奉献的资料的.具体引用的资料请看参考文献.具体的版本声明也参考原文献. 2)本文仅供学术交流,非商用.所以每一部分具体的参考资料并没有详细对应.如果某部分不小心侵犯了大家的利益,还望海涵,并联系博主删除. 3)本人才疏学浅,整理总结的时候难免出错,还望各位前辈不吝指正,谢谢. 4)阅读本文需要机器学习.计算机视觉.神经网络等等基础(如果没有也没关系了,没

Deep Learning（深度学习）学习笔记整理系列之（五）

Deep Learning(深度学习)学习笔记整理系列 [email protected] http://blog.csdn.net/zouxy09 作者:Zouxy version 1.0 2013-04-08 声明: 1)该Deep Learning的学习系列是整理自网上很大牛和机器学习专家所无私奉献的资料的.具体引用的资料请看参考文献.具体的版本声明也参考原文献. 2)本文仅供学术交流,非商用.所以每一部分具体的参考资料并没有详细对应.如果某部分不小心侵犯了大家的利益,还望海涵,并联系博主