Joint deep Learning for pedestrian detection notes

1. Structure diagram

Introduction

Feature extraction, deformation handling, occlusion handling, and classification is four important components in Pedestri An detection. Existing methods Learn or design these components either individually or sequentially. The interaction among these are not yet well explored. This paper proposes, they should be jointly learned in order to maximize their strengths through cooperation. We formulate these four to 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 Classif Ication. With the "deep model", these components interact with each of 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 netwo Rks (CNN). With this layer, the various deformation handling approaches can be applied to our deep model.
• The features is 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 datasets, 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:

• Matlab Code (5 MB)
• Evaluation Code, detection results and annotations (200MB)
• Intemediate data required to run the code (about 5GB)

For users who cannot download from Google drive:

• Code and dataset on Baidu

The files is 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" and then you should has three folders "Root/cnn", "Root/data", "Root/model", "Root/nn", "R Oot/tmptoolbox "," Root/util ", and" Root/dbeval ". For "Root/data", there should is 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

• Frequently asked Question and Answer for the Code (KB)

Joint deep Learning for pedestrian detection notes