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:

• 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

FAQ

• Frequently Asked Question and Answer for the code (13 KB)