Skip to content
Code to reproduce 'Deep Learning for Decentralized Parking Lot Occupancy Detection' paper.
Branch: master
Clone or download
Type Name Latest commit message Commit time
Failed to load latest commit information.
pyffe @ be98c54 updated pyffe submodule Apr 23, 2019
.gitmodules added pyffe submodule Jan 26, 2018 Create Jan 26, 2018 added main experiments Jan 26, 2018 added main experiments Jan 26, 2018

Deep Learning for Decentralized Parking Lot Occupancy Detection

This repo contains code to reproduce the experiments presented in Deep Learning for Decentralized Parking Lot Occupancy Detection.

Visit the project website for more info and resources (dataset, pre-trained models).


  • Caffe with Python interface (PyCaffe)

Steps to reproduce experiments

  1. Clone this repo together with its submodules:

    git clone --recursive
  2. Download the datasets using the following links and extract them somewhere.

    Dataset Link Size
    CNRPark 36.6 MB
    CNR-EXT 449.5 MB
    PKLot visit PKLot webpage 4.6 GB
  3. Get the dataset splits and extract them in the repo folder

    # Listfile containing dataset splits
  4. Add a files inside each folder in splits/ to tell pyffe where the images are. The content of the files should be like this (adjust the root_dir attribute to the absolute path of the extracted datasets):

    config = dict(root_folder = '/path/to/dataset/dir/')

    This path will be prepended to each line in the list files defining the various splits.

  5. Train and evaluate all the models by running:


    Modify to select the experiments you want to reproduce. Run if you want to train and evaluate our architecture on the PKLot splits only.


  title={Deep learning for decentralized parking lot occupancy detection},
  author={Amato, Giuseppe and Carrara, Fabio and Falchi, Fabrizio and Gennaro, Claudio and Meghini, Carlo and Vairo, Claudio},
  journal={Expert Systems with Applications},
You can’t perform that action at this time.