Repository files navigation

Created by Denis Tomè, Federico Monti, Luca Baroffio and Luca Bondi.

DeepPed is a state-of-the-art pedestrian detector that extends R-CNN work done by Girshick et al. combining region proposals with rich features computed by a convolutional neural network. This method achieves 19.90% log-average-miss-rate on the Caltech Pedestrian Dataset.

DeepPed is described in anarXiv tech report and will appear in Elsevier Journal of Signal Processing.

If you find R-CNN useful in your research, please consider citing:

@article{tome2015Deep,    author = {Tomè, Denis and Monti, Federico and Baroffio, Luca and Bondi, Luca and Tagliasacchi, Marco and Tubaro, Stefano},    title = {Deep convolutional neural networks for pedestrian detection},    journal = {arXiv preprint arXiv:1510.03608},    year = {2015}}

}

DeepPed is released under the Simplified BSD License (refer to theLICENSE file for details).

0. Prerequisites
1. MATLAB (tested with 2015a on 64-bit Linux)
2. Caffe'sprerequisites
3. Install Caffe and R-CNN
4. DownloadCaffe (version described in R-CNN instructions)
5. Download R-CNN and follow theinstructions
6. Install DeepPed
7. Change into the R-CNN source code directory:cd rcnn
8. Get the DeepPed source code by cloning the repository:git clone https://github.com/DenisTome/DeepPed.git
9. Get the Piotr's Image & Video Matlab Toolbox by cloning the repository:git clone https://github.com/pdollar/toolbox.git
10. From theR-CNN folder, run the model fetch script:./DeepPed/fetch_models.sh.
11. Open thestartup.m matlab file, adding the two commandsaddpath(genpath('DeepPed')); andaddpath(genpath('toolbox')); at the end of the file.

1. Change to where you installed R-CNN:cd rcnn.
2. Start MATLABmatlab.

• Important: if you don't see the messageR-CNN startup done when MATLAB starts, then you probably didn't start MATLAB inrcnn directory.

3. Run the demo:>> deepPed_demo