Joint Deep Learning for Pedestrian Detection


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.


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)

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

    Share This Page

    © 2013 Multimedia Laboratory

    The Chinese University of Hong Kong 香港中文大学

    Site Credits