Skip to content

Latest commit

 

History

History
47 lines (34 loc) · 1.18 KB

Readme.md

File metadata and controls

47 lines (34 loc) · 1.18 KB

PWSCup 2019 - Team 11 : Unknown IPA

This repesotory contains all script to do preprocessing, anonymisation an attackinf trajectories dataset from PWSCup contest

Installation

Use the package manager pip to install requirements of this repo.

pip install -r requirements.txt

Note that traj_dist package must be installed here

Usage

  1. Download PWSCup data from the team Google Drive account 1(bis). You can also download testing data here

  2. Preprocessing of the data with preprocessing.py

preprocessing.py -i <your_trajectory_input_file> -o <name_of_directory_for_output> -r <information_region_file>
  1. Runing benchmark (you need both original and reference files). An example using the testings files
python distance_benchmark.py \
    -o ../data/testing_data/output_org_osaka \
    -r ../data/testing_data/output_ref_osaka

Re-identification

cd data/reid_preliminary_phase/
./prepro.sh /PubData
./prepro.sh /RefData_000-021
cd src/
./attack.sh ../data/reid_preliminary_phase/prepro